Merge branch 'slf/perf-improvements1' into tmp/merge-delme

... and allow direct start by machi_sup for EUnit tests.

.gitignore

@@ -2,20 +2,32 @@ prototype/chain-manager/patch.*
 .eqc-info
 .eunit
 deps
-*.plt
+dev
 erl_crash.dump
+eqc
 .concrete/DEV_MODE
 .rebar
 edoc
 
+# Dialyzer stuff
+.dialyzer-last-run.txt
+.ebin.native
+.local_dialyzer_plt
+dialyzer_unhandled_warnings
+dialyzer_warnings
+*.plt
+
 # PB artifacts for Erlang
 include/machi_pb.hrl
 
 # Release packaging
 rel/machi
+rel/vars/dev*vars.config
 
 # Misc Scott cruft
 *.patch
 current_counterexample.eqc
 foo*
+RUNLOG*
 typescript*
+*.swp

.travis.yml

@@ -4,3 +4,4 @@ notifications:
 script: "priv/test-for-gh-pr.sh"
 otp_release:
   - 17.5
+## No, Dialyzer is too different between 17 & 18:  - 18.1

FAQ.md

@@ -11,14 +11,14 @@
 
 + [1 Questions about Machi in general](#n1)
     + [1.1 What is Machi?](#n1.1)
-    + [1.2 What is a Machi "cluster of clusters"?](#n1.2)
+    + [1.2 What is a Machi chain?](#n1.2)
-        + [1.2.1 This "cluster of clusters" idea needs a better name, don't you agree?](#n1.2.1)
+    + [1.3 What is a Machi cluster?](#n1.3)
-    + [1.3 What is Machi like when operating in "eventually consistent"/"AP mode"?](#n1.3)
+    + [1.4 What is Machi like when operating in "eventually consistent" mode?](#n1.4)
-    + [1.4 What is Machi like when operating in "strongly consistent"/"CP mode"?](#n1.4)
+    + [1.5 What is Machi like when operating in "strongly consistent" mode?](#n1.5)
-    + [1.5 What does Machi's API look like?](#n1.5)
+    + [1.6 What does Machi's API look like?](#n1.6)
-    + [1.6 What licensing terms are used by Machi?](#n1.6)
+    + [1.7 What licensing terms are used by Machi?](#n1.7)
-    + [1.7 Where can I find the Machi source code and documentation?  Can I contribute?](#n1.7)
+    + [1.8 Where can I find the Machi source code and documentation?  Can I contribute?](#n1.8)
-    + [1.8 What is Machi's expected release schedule, packaging, and operating system/OS distribution support?](#n1.8)
+    + [1.9 What is Machi's expected release schedule, packaging, and operating system/OS distribution support?](#n1.9)
 + [2 Questions about Machi relative to {{something else}}](#n2)
     + [2.1 How is Machi better than Hadoop?](#n2.1)
     + [2.2 How does Machi differ from HadoopFS/HDFS?](#n2.2)
@@ -28,13 +28,15 @@
 + [3 Machi's specifics](#n3)
     + [3.1 What technique is used to replicate Machi's files?  Can other techniques be used?](#n3.1)
     + [3.2 Does Machi have a reliance on a coordination service such as ZooKeeper or etcd?](#n3.2)
-    + [3.3 Is it true that there's an allegory written to describe humming consensus?](#n3.3)
+    + [3.3 Are there any presentations available about Humming Consensus](#n3.3)
-    + [3.4 How is Machi tested?](#n3.4)
+    + [3.4 Is it true that there's an allegory written to describe Humming Consensus?](#n3.4)
-    + [3.5 Does Machi require shared disk storage? e.g. iSCSI, NBD (Network Block Device), Fibre Channel disks](#n3.5)
+    + [3.5 How is Machi tested?](#n3.5)
-    + [3.6 Does Machi require or assume that servers with large numbers of disks must use RAID-0/1/5/6/10/50/60 to create a single block device?](#n3.6)
+    + [3.6 Does Machi require shared disk storage? e.g. iSCSI, NBD (Network Block Device), Fibre Channel disks](#n3.6)
-    + [3.7 What language(s) is Machi written in?](#n3.7)
+    + [3.7 Does Machi require or assume that servers with large numbers of disks must use RAID-0/1/5/6/10/50/60 to create a single block device?](#n3.7)
-    + [3.8 Does Machi use the Erlang/OTP network distribution system (aka "disterl")?](#n3.8)
+    + [3.8 What language(s) is Machi written in?](#n3.8)
-    + [3.9 Can I use HTTP to write/read stuff into/from Machi?](#n3.9)
+    + [3.9 Can Machi run on Windows?  Can Machi run on 32-bit platforms?](#n3.9)
+    + [3.10 Does Machi use the Erlang/OTP network distribution system (aka "disterl")?](#n3.10)
+    + [3.11 Can I use HTTP to write/read stuff into/from Machi?](#n3.11)
 
 <!-- ENDOUTLINE -->
 
@@ -44,13 +46,13 @@
 <a name="n1.1">
 ### 1.1.  What is Machi?
 
-Very briefly, Machi is a very simple append-only file store.
+Very briefly, Machi is a very simple append-only blob/file store.
 
 Machi is
 "dumber" than many other file stores (i.e., lacking many features
-found in other file stores) such as HadoopFS or simple NFS or CIFS file
+found in other file stores) such as HadoopFS or a simple NFS or CIFS file
 server.
-However, Machi is a distributed file store, which makes it different
+However, Machi is a distributed blob/file store, which makes it different
 (and, in some ways, more complicated) than a simple NFS or CIFS file
 server.
 
@@ -82,45 +84,39 @@ For a much longer answer, please see the
 [Machi high level design doc](https://github.com/basho/machi/tree/master/doc/high-level-machi.pdf).
 
 <a name="n1.2">
-### 1.2.  What is a Machi "cluster of clusters"?
+### 1.2.  What is a Machi chain?
 
-Machi's design is based on using small, well-understood and provable
+A Machi chain is a small number of machines that maintain a common set
-(mathematically) techniques to maintain multiple file copies without
+of replicated files.  A typical chain is of length 2 or 3.  For
-data loss or data corruption.  At its lowest level, Machi contains no
+critical data that must be available despite several simultaneous
-support for distribution/partitioning/sharding of files across many
+server failures, a chain length of 6 or 7 might be used.
-servers.  A typical, fully-functional Machi cluster will likely be two
-or three machines.
 
-However, Machi is designed to be an excellent building block for
+<a name="n1.3">
-building larger systems.  A deployment of Machi "cluster of clusters"
+### 1.3.  What is a Machi cluster?
-will use the "random slicing" technique for partitioning files across
-multiple Machi clusters that, as individuals, are unaware of the
-larger cluster-of-clusters scheme.
 
-The cluster-of-clusters management service will be fully decentralized
+A Machi cluster is a collection of Machi chains that
+partitions/shards/distributes files (based on file name) across the
+collection of chains.  Machi uses the "random slicing" algorithm (a
+variation of consistent hashing) to define the mapping of file name to
+chain name.
+
+The cluster management service will be fully decentralized
 and run as a separate software service installed on each Machi
 cluster.  This manager will appear to the local Machi server as simply
-another Machi file client.  The cluster-of-clusters managers will take
+another Machi file client.  The cluster managers will take
 care of file migration as the cluster grows and shrinks in capacity
 and in response to day-to-day changes in workload.
 
-Though the cluster-of-clusters manager has not yet been implemented,
+Though the cluster manager has not yet been implemented,
 its design is fully decentralized and capable of operating despite
-multiple partial failure of its member clusters.  We expect this
+multiple partial failure of its member chains.  We expect this
 design to scale easily to at least one thousand servers.
 
 Please see the
 [Machi source repository's 'doc' directory for more details](https://github.com/basho/machi/tree/master/doc/).
 
-<a name="n1.2.1">
+<a name="n1.4">
-#### 1.2.1.  This "cluster of clusters" idea needs a better name, don't you agree?
+### 1.4.  What is Machi like when operating in "eventually consistent" mode?
-
-Yes.  Please help us: we are bad at naming things.
-For proof that naming things is hard, see
-[http://martinfowler.com/bliki/TwoHardThings.html](http://martinfowler.com/bliki/TwoHardThings.html)
-
-<a name="n1.3">
-### 1.3.  What is Machi like when operating in "eventually consistent"/"AP mode"?
 
 Machi's operating mode dictates how a Machi cluster will react to
 network partitions.  A network partition may be caused by:
@@ -130,37 +126,30 @@ network partitions.  A network partition may be caused by:
 * An extreme server software "hang" or "pause", e.g. caused by OS
   scheduling problems such as a failing/stuttering disk device.
 
-"AP mode" refers to the "A" and "P" properties of the "CAP
+The consistency semantics of file operations while in eventual
-conjecture", meaning that the cluster will be "Available" and
+consistency mode during and after network partitions are:
-"Partition tolerant".
-
-The consistency semantics of file operations while in "AP mode" are
-eventually consistent during and after network partitions:
 
 * File write operations are permitted by any client on the "same side"
   of the network partition.
 * File read operations are successful for any file contents where the
   client & server are on the "same side" of the network partition.
+    * File read operations will probably fail for any file contents where the
+      client & server are on "different sides" of the network partition.
 * After the network partition(s) is resolved, files are merged
   together from "all sides" of the partition(s).
     * Unique files are copied in their entirety.
     * Byte ranges within the same file are merged.  This is possible
-      due to Machi's restrictions on file naming (files names are
+      due to Machi's restrictions on file naming and file offset
-      alwoys assigned by Machi servers) and file offset assignments
+      assignment.  Both file names and file offsets are always chosen
-      (byte offsets are also always chosen by Machi servers according
+      by Machi servers according to rules which guarantee safe
-      to rules which guarantee safe mergeability.).
+      mergeability.  Server-assigned names are a characteristic of a
+      "blob store".
 
-<a name="n1.4">
+<a name="n1.5">
-### 1.4.  What is Machi like when operating in "strongly consistent"/"CP mode"?
+### 1.5.  What is Machi like when operating in "strongly consistent" mode?
 
-Machi's operating mode dictates how a Machi cluster will react to
+The consistency semantics of file operations while in strongly
-network partitions.
+consistency mode during and after network partitions are:
-"CP mode" refers to the "C" and "P" properties of the "CAP
-conjecture", meaning that the cluster will be "Consistent" and
-"Partition tolerant".
-
-The consistency semantics of file operations while in "CP mode" are
-strongly consistent during and after network partitions:
 
 * File write operations are permitted by any client on the "same side"
   of the network partition if and only if a quorum majority of Machi servers
@@ -175,19 +164,19 @@ strongly consistent during and after network partitions:
 
 Machi's design can provide the illusion of quorum minority write
 availability if the cluster is configured to operate with "witness
-servers".  (This feaure is not implemented yet, as of June 2015.)
+servers".  (This feaure partially implemented, as of December 2015.)
 See Section 11 of
 [Machi chain manager high level design doc](https://github.com/basho/machi/tree/master/doc/high-level-chain-mgr.pdf)
 for more details.
 
-<a name="n1.5">
+<a name="n1.6">
-### 1.5.  What does Machi's API look like?
+### 1.6.  What does Machi's API look like?
 
 The Machi API only contains a handful of API operations.  The function
-arguments shown below use Erlang-style type annotations.
+arguments shown below (in simplifed form) use Erlang-style type annotations.
 
-    append_chunk(Prefix:binary(), Chunk:binary()).
+    append_chunk(Prefix:binary(), Chunk:binary(), CheckSum:binary()).
-    append_chunk_extra(Prefix:binary(), Chunk:binary(), ExtraSpace:non_neg_integer()).
+    append_chunk_extra(Prefix:binary(), Chunk:binary(), CheckSum:binary(), ExtraSpace:non_neg_integer()).
     read_chunk(File:binary(), Offset:non_neg_integer(), Size:non_neg_integer()).
     
     checksum_list(File:binary()).
@@ -205,17 +194,22 @@ Internally, there is a more complex protocol used by individual
 cluster members to manage file contents and to repair damaged/missing
 files.  See Figure 3 in
 [Machi high level design doc](https://github.com/basho/machi/tree/master/doc/high-level-machi.pdf)
-for more details.
+for more description.
 
-<a name="n1.6">
+The definitions of both the "high level" external protocol and "low
-### 1.6.  What licensing terms are used by Machi?
+level" internal protocol are in a
+[Protocol Buffers](https://developers.google.com/protocol-buffers/docs/overview)
+definition at [./src/machi.proto](./src/machi.proto).
+
+<a name="n1.7">
+### 1.7.  What licensing terms are used by Machi?
 
 All Machi source code and documentation is licensed by
 [Basho Technologies, Inc.](http://www.basho.com/)
 under the [Apache Public License version 2](https://github.com/basho/machi/tree/master/LICENSE).
 
-<a name="n1.7">
+<a name="n1.8">
-### 1.7.  Where can I find the Machi source code and documentation?  Can I contribute?
+### 1.8.  Where can I find the Machi source code and documentation?  Can I contribute?
 
 All Machi source code and documentation can be found at GitHub:
 [https://github.com/basho/machi](https://github.com/basho/machi).
@@ -229,11 +223,11 @@ ideas for improvement, please see our contributing & collaboration
 guidelines at
 [https://github.com/basho/machi/blob/master/CONTRIBUTING.md](https://github.com/basho/machi/blob/master/CONTRIBUTING.md).
 
-<a name="n1.8">
+<a name="n1.9">
-### 1.8.  What is Machi's expected release schedule, packaging, and operating system/OS distribution support?
+### 1.9.  What is Machi's expected release schedule, packaging, and operating system/OS distribution support?
 
-Basho expects that Machi's first release will take place near the end
+Basho expects that Machi's first major product release will take place
-of calendar year 2015.
+during the 2nd quarter of 2016.
 
 Basho's official support for operating systems (e.g. Linux, FreeBSD),
 operating system packaging (e.g. CentOS rpm/yum package management,
@@ -308,15 +302,15 @@ file's writable phase).
 
 <tr>
 <td> Does not have any file distribution/partitioning/sharding across
-Machi clusters: in a single Machi cluster, all files are replicated by
+Machi chains: in a single Machi chain, all files are replicated by
-all servers in the cluster.  The "cluster of clusters" concept is used
+all servers in the chain.  The "random slicing" technique is used
 to distribute/partition/shard files across multiple Machi clusters.
 <td> File distribution/partitioning/sharding is performed
 automatically by the HDFS "name node".
 
 <tr>
-<td> Machi requires no central "name node" for single cluster use.
+<td> Machi requires no central "name node" for single chain use or
-Machi requires no central "name node" for "cluster of clusters" use
+for multi-chain cluster use.
 <td> Requires a single "namenode" server to maintain file system contents
 and file content mapping.  (May be deployed with a "secondary
 namenode" to reduce unavailability when the primary namenode fails.)
@@ -482,8 +476,8 @@ difficult to adapt to Machi's design goals:
 * Both protocols use quorum majority consensus, which requires a
   minimum of *2F + 1* working servers to tolerate *F* failures.  For
   example, to tolerate 2 server failures, quorum majority protocols
-  require a minium of 5 servers.  To tolerate the same number of
+  require a minimum of 5 servers.  To tolerate the same number of
-  failures, Chain replication requires only 3 servers.
+  failures, Chain Replication requires a minimum of only 3 servers.
 * Machi's use of "humming consensus" to manage internal server
   metadata state would also (probably) require conversion to Paxos or
   Raft.  (Or "outsourced" to a service such as ZooKeeper.)
@@ -500,7 +494,17 @@ Humming consensus is described in the
 [Machi chain manager high level design doc](https://github.com/basho/machi/tree/master/doc/high-level-chain-mgr.pdf).
 
 <a name="n3.3">
-### 3.3.  Is it true that there's an allegory written to describe humming consensus?
+### 3.3.  Are there any presentations available about Humming Consensus
+
+Scott recently (November 2015) gave a presentation at the
+[RICON 2015 conference](http://ricon.io) about one of the techniques
+used by Machi; "Managing Chain Replication Metadata with
+Humming Consensus" is available online now.
+* [slides (PDF format)](http://ricon.io/speakers/slides/Scott_Fritchie_Ricon_2015.pdf)
+* [video](https://www.youtube.com/watch?v=yR5kHL1bu1Q)
+
+<a name="n3.4">
+### 3.4.  Is it true that there's an allegory written to describe Humming Consensus?
 
 Yes.  In homage to Leslie Lamport's original paper about the Paxos
 protocol, "The Part-time Parliamant", there is an allegorical story
@@ -511,8 +515,8 @@ The full story, full of wonder and mystery, is called
 There is also a
 [short followup blog posting](http://www.snookles.com/slf-blog/2015/03/20/on-humming-consensus-an-allegory-part-2/).
 
-<a name="n3.4">
+<a name="n3.5">
-### 3.4.  How is Machi tested?
+### 3.5.  How is Machi tested?
 
 While not formally proven yet, Machi's implementation of Chain
 Replication and of humming consensus have been extensively tested with
@@ -537,16 +541,20 @@ change several times during any single test case) and a random series
 of cluster operations, an event trace of all cluster activity is used
 to verify that no safety-critical rules have been violated.
 
-<a name="n3.5">
+All test code is available in the [./test](./test) subdirectory.
-### 3.5.  Does Machi require shared disk storage? e.g. iSCSI, NBD (Network Block Device), Fibre Channel disks
+Modules that use QuickCheck will use a file suffix of `_eqc`, for
+example, [./test/machi_ap_repair_eqc.erl](./test/machi_ap_repair_eqc.erl).
+
+<a name="n3.6">
+### 3.6.  Does Machi require shared disk storage? e.g. iSCSI, NBD (Network Block Device), Fibre Channel disks
 
 No, Machi's design assumes that each Machi server is a fully
 independent hardware and assumes only standard local disks (Winchester
 and/or SSD style) with local-only interfaces (e.g. SATA, SCSI, PCI) in
 each machine.
 
-<a name="n3.6">
+<a name="n3.7">
-### 3.6.  Does Machi require or assume that servers with large numbers of disks must use RAID-0/1/5/6/10/50/60 to create a single block device?
+### 3.7.  Does Machi require or assume that servers with large numbers of disks must use RAID-0/1/5/6/10/50/60 to create a single block device?
 
 No.  When used with servers with multiple disks, the intent is to
 deploy multiple Machi servers per machine: one Machi server per disk.
@@ -564,10 +572,13 @@ deploy multiple Machi servers per machine: one Machi server per disk.
   placement relative to 12 servers is smaller than a placement problem
   of managing 264 seprate disks (if each of 12 servers has 22 disks).
 
-<a name="n3.7">
+<a name="n3.8">
-### 3.7.  What language(s) is Machi written in?
+### 3.8.  What language(s) is Machi written in?
 
-So far, Machi is written in 100% Erlang.
+So far, Machi is written in Erlang, mostly.  Machi uses at least one
+library, [ELevelDB](https://github.com/basho/eleveldb), that is
+implemented both in C++ and in Erlang, using Erlang NIFs (Native
+Interface Functions) to allow Erlang code to call C++ functions.
 
 In the event that we encounter a performance problem that cannot be
 solved within the Erlang/OTP runtime environment, all of Machi's
@@ -576,8 +587,16 @@ in C, Java, or other "gotta go fast fast FAST!!"  programming
 language.  We expect that the Chain Replication manager and other
 critical "control plane" software will remain in Erlang.
 
-<a name="n3.8">
+<a name="n3.9">
-### 3.8.  Does Machi use the Erlang/OTP network distribution system (aka "disterl")?
+### 3.9.  Can Machi run on Windows?  Can Machi run on 32-bit platforms?
+
+The ELevelDB NIF does not compile or run correctly on Erlang/OTP
+Windows platforms, nor does it compile correctly on 32-bit platforms.
+Machi should support all 64-bit UNIX-like platforms that are supported
+by Erlang/OTP and ELevelDB.
+
+<a name="n3.10">
+### 3.10.  Does Machi use the Erlang/OTP network distribution system (aka "disterl")?
 
 No, Machi doesn't use Erlang/OTP's built-in distributed message
 passing system.  The code would be *much* simpler if we did use
@@ -588,19 +607,16 @@ bit-twiddling magicSPEED ... without also having to find a replacement
 for disterl.  (Or without having to re-invent disterl's features in
 another language.)
 
-<a name="artisanal-protocol">
+All wire protocols used by Machi are defined & implemented using
-In the first drafts of the Machi code, the inter-node communication
+[Protocol Buffers](https://developers.google.com/protocol-buffers/docs/overview).
-uses a hand-crafted, artisanal, mostly ASCII protocol as part of a
+The definition file can be found at [./src/machi.proto](./src/machi.proto).
-"demo day" quick & dirty prototype.  Work is underway (summer of 2015)
-to replace that protocol gradually with a well-structured,
-well-documented protocol based on Protocol Buffers data serialization.
 
-<a name="n3.9">
+<a name="n3.11">
-### 3.9.  Can I use HTTP to write/read stuff into/from Machi?
+### 3.11.  Can I use HTTP to write/read stuff into/from Machi?
 
-Yes, sort of.  For as long as the legacy of
+Short answer: No, not yet.
-Machi's first internal protocol & code still
+
-survives, it's possible to use a
+Longer answer: No, but it was possible as a hack, many months ago, see 
 [primitive/hack'y HTTP interface that is described in this source code commit log](https://github.com/basho/machi/commit/6cebf397232cba8e63c5c9a0a8c02ba391b20fef).
 Please note that commit `6cebf397232cba8e63c5c9a0a8c02ba391b20fef` is
 required to try using this feature: the code has since bit-rotted and

Makefile

@@ -8,8 +8,9 @@ ifeq ($(REBAR),)
 REBAR = $(BASE_DIR)/rebar
 endif
 OVERLAY_VARS    ?=
+EUNIT_OPTS       = -v
 
-.PHONY: rel deps package pkgclean edoc
+.PHONY: rel stagedevrel deps package pkgclean edoc
 
 all: deps compile
 
@@ -34,11 +35,6 @@ deps:
 clean:
 	$(REBAR) -r clean
 
-test: deps compile eunit
-
-eunit:
-	$(REBAR) -v skip_deps=true eunit
-
 edoc: edoc-clean
 	$(REBAR) skip_deps=true doc
 
@@ -50,28 +46,6 @@ pulse: compile
 	#env USE_PULSE=1 $(REBAR) skip_deps=true clean compile
 	#env USE_PULSE=1 $(REBAR) skip_deps=true -D PULSE eunit -v
 
-APPS = kernel stdlib sasl erts ssl compiler eunit crypto
-PLT = $(HOME)/.machi_dialyzer_plt
-
-build_plt: deps compile
-	dialyzer --build_plt --output_plt $(PLT) --apps $(APPS) deps/*/ebin
-
-DIALYZER_DEP_APPS = ebin/machi_pb.beam deps/protobuffs/ebin
-DIALYZER_FLAGS = -Wno_return -Wrace_conditions -Wunderspecs
-
-dialyzer: deps compile
-	dialyzer $(DIALYZER_FLAGS) --plt $(PLT) ebin $(DIALYZER_DEP_APPS) | \
-            egrep -v -f ./filter-dialyzer-dep-warnings
-
-dialyzer-test: deps compile
-	echo Force rebar to recompile .eunit dir w/o running tests > /dev/null
-	rebar skip_deps=true eunit suite=lamport_clock
-	dialyzer $(DIALYZER_FLAGS) --plt $(PLT) .eunit $(DIALYZER_DEP_APPS) | \
-            egrep -v -f ./filter-dialyzer-dep-warnings
-
-clean_plt:
-	rm $(PLT)
-
 ##
 ## Release targets
 ##
@@ -82,3 +56,39 @@ relclean:
 
 stage : rel
 	$(foreach dep,$(wildcard deps/*), rm -rf rel/$(REPO)/lib/$(shell basename $(dep))* && ln -sf $(abspath $(dep)) rel/$(REPO)/lib;)
+
+##
+## Developer targets
+##
+##  devN - Make a dev build for node N
+##  stagedevN - Make a stage dev build for node N (symlink libraries)
+##  devrel - Make a dev build for 1..$DEVNODES
+##  stagedevrel Make a stagedev build for 1..$DEVNODES
+##
+##  Example, make a 68 node devrel cluster
+##    make stagedevrel DEVNODES=68
+
+.PHONY : stagedevrel devrel
+DEVNODES ?= 3
+
+# 'seq' is not available on all *BSD, so using an alternate in awk
+SEQ = $(shell awk 'BEGIN { for (i = 1; i < '$(DEVNODES)'; i++) printf("%i ", i); print i ;exit(0);}')
+
+$(eval stagedevrel : $(foreach n,$(SEQ),stagedev$(n)))
+$(eval devrel : $(foreach n,$(SEQ),dev$(n)))
+
+dev% : all
+	mkdir -p dev
+	rel/gen_dev $@ rel/vars/dev_vars.config.src rel/vars/$@_vars.config
+	(cd rel && ../rebar generate target_dir=../dev/$@ overlay_vars=vars/$@_vars.config)
+
+stagedev% : dev%
+	  $(foreach dep,$(wildcard deps/*), rm -rf dev/$^/lib/$(shell basename $(dep))* && ln -sf $(abspath $(dep)) dev/$^/lib;)
+
+devclean: clean
+	rm -rf dev
+
+DIALYZER_APPS = kernel stdlib sasl erts ssl compiler eunit crypto public_key syntax_tools
+PLT = $(HOME)/.machi_dialyzer_plt
+
+include tools.mk

README.md

@@ -1,61 +1,136 @@
-# Machi
+# Machi: a distributed, decentralized blob/large file store
 
   [Travis-CI](http://travis-ci.org/basho/machi) :: ![Travis-CI](https://secure.travis-ci.org/basho/machi.png)
 
-Our goal is a robust & reliable, distributed, highly available(*),
+Outline
-large file store based upon write-once registers, append-only files,
-Chain Replication, and client-server style architecture.  All members
-of the cluster store all of the files.  Distributed load
-balancing/sharding of files is __outside__ of the scope of this
-system.  However, it is a high priority that this system be able to
-integrate easily into systems that do provide distributed load
-balancing, e.g., Riak Core.  Although strong consistency is a major
-feature of Chain Replication, first use cases will focus mainly on
-eventual consistency features --- strong consistency design will be
-discussed in a separate design document (read more below).
 
-The ability for Machi to maintain strong consistency will make it
+1. [Why another blob/file store?](#sec1)
-attractive as a toolkit for building things like CORFU and Tango as
+2. [Where to learn more about Machi](#sec2)
-well as better-known open source software such as Kafka's file
+3. [Development status summary](#sec3)
-replication.  (See the bibliography of the [Machi high level design
+4. [Contributing to Machi's development](#sec4)
-doc](./doc/high-level-machi.pdf) for further references.)
 
-(*) Capable of operating in "AP mode" or "CP mode" relative to the
+<a name="sec1">
-  CAP Theorem.
+## 1. Why another blob/file store?
 
-## Status: mid-June 2015: work is underway
+Our goal is a robust & reliable, distributed, highly available, large
+file and blob store.  Such stores already exist, both in the open source world
+and in the commercial world.  Why reinvent the wheel?  We believe
+there are three reasons, ordered by decreasing rarity.
 
-The two major design documents for Machi are now ready or nearly ready
+1. We want end-to-end checksums for all file data, from the initial
-for internal Basho and external party review.  Please see the
+   file writer to every file reader, anywhere, all the time.
-[doc](./doc) directory's [README](./doc) for details
+2. We need flexibility to trade consistency for availability:
+   e.g. weak consistency in exchange for being available in cases
+   of partial system failure.
+3. We want to manage file replicas in a way that's provably correct
+   and also easy to test.
 
-* Machi high level design
+Criteria #3 is difficult to find in the open source world but perhaps
-* Machi chain self-management design
+not impossible.
 
-The work of implementing first draft of Machi is now underway.  The
+If we have app use cases where availability is more important than
-code from the [prototype/demo-day-hack](prototype/demo-day-hack/) directory is
+consistency, then systems that meet criteria #2 are also rare.
-being used as the initial scaffolding.
+Most file stores provide only strong consistency and therefore
+have unavoidable, unavailable behavior when parts of the system
+fail.
+What if we want a file store that is always available to write new
+file data and attempts best-effort file reads?
 
-* The chain manager is ready for "AP mode" use in eventual
+If we really do care about data loss and/or data corruption, then we
-  consistency use cases.
+really want both #3 and #1.  Unfortunately, systems that meet
+criteria #1 are _very rare_.  (Nonexistant?)
+Why?  This is 2015.  We have decades of research that shows
+that computer hardware can (and
+indeed does) corrupt data at nearly every level of the modern
+client/server application stack.  Systems with end-to-end data
+corruption detection should be ubiquitous today.  Alas, they are not.
 
-* All Machi client/server protocols are based on
+Machi is an effort to change the deplorable state of the world, one
-  [Protocol Buffers](https://developers.google.com/protocol-buffers/docs/overview).
+Erlang function at a time.
-    * The current specification for Machi's protocols can be found at
-      [https://github.com/basho/machi/blob/master/src/machi.proto](https://github.com/basho/machi/blob/master/src/machi.proto).
-    * The Machi PB protocol is not yet stable.  Expect change!
-    * The Erlang language client implementation of the high-level
-      protocol flavor is very brittle (e.g., very little error
-      handling yet).
-    * The Erlang language client implementation of the low-level
-      protocol flavor are still a work-in-progress ... but they are
-      more robust than the high-level library's implementation.
 
-If you'd like to work on a protocol such as Thrift, UBF,
+<a name="sec2">
-msgpack over UDP, or some other protocol, let us know by
+## 2. Where to learn more about Machi
-[opening an issue](./issues/new) to discuss it.
 
-## Contributing to Machi: source code, documentation, etc.
+The two major design documents for Machi are now mostly stable.
+Please see the [doc](./doc) directory's [README](./doc) for details.
+
+We also have a
+[Frequently Asked Questions (FAQ) list](./FAQ.md).
+
+Scott recently (November 2015) gave a presentation at the
+[RICON 2015 conference](http://ricon.io) about one of the techniques
+used by Machi; "Managing Chain Replication Metadata with
+Humming Consensus" is available online now.
+* [slides (PDF format)](http://ricon.io/speakers/slides/Scott_Fritchie_Ricon_2015.pdf)
+* [video](https://www.youtube.com/watch?v=yR5kHL1bu1Q)
+
+See later in this document for how to run the Humming Consensus demos,
+including the network partition simulator.
+
+<a name="sec3">
+## 3. Development status summary
+
+Mid-March 2016: The Machi development team has been downsized in
+recent months, and the pace of development has slowed.  Here is a
+summary of the status of Machi's major components.
+
+* Humming Consensus and the chain manager
+  * No new safety bugs have been found by model-checking tests.
+  * A new document,
+    [Hands-on experiments with Machi and Humming Consensus](doc/humming-consensus-demo.md)
+    is now available.  It is a tutorial for setting up a 3 virtual
+    machine Machi cluster and how to demonstrate the chain manager's
+    reactions to server stops & starts, crashes & restarts, and pauses
+    (simulated by `SIGSTOP` and `SIGCONT`).
+  * The chain manager can still make suboptimal-but-safe choices for
+    chain transitions when a server hangs/pauses temporarily.
+    * Recent chain manager changes have made the instability window
+      much shorter when the slow/paused server resumes execution.
+    * Scott believes that a modest change to the chain manager's
+      calculation of a new projection can reduce flapping in this (and
+      many other cases) less likely.  Currently, the new local
+      projection is calculated using only local state (i.e., the chain
+      manager's internal state + the fitness server's state).
+      However, if the "latest" projection read from the public
+      projection stores were also input to the new projection
+      calculation function, then many obviously bad projections can be
+      avoided without needing rounds of Humming Consensus to
+      demonstrate that a bad projection is bad.
+
+* FLU/data server process
+  * All known correctness bugs have been fixed.
+  * Performance has not yet been measured.  Performance measurement
+    and enhancements are scheduled to start in the middle of March 2016.
+    (This will include a much-needed update to the `basho_bench` driver.)
+
+* Access protocols and client libraries
+  * The protocol used by both external clients and internally (instead
+    of using Erlang's native message passing mechanisms) is based on
+    Protocol Buffers.
+    * (Machi PB protocol specification: ./src/machi.proto)[./src/machi.proto]
+    * At the moment, the PB specification contains two protocols.
+      Sometime in the near future, the spec will be split to separate
+      the external client API (the "high" protocol) from the internal
+      communication API (the "low" protocol).
+
+* Recent conference talks about Machi
+  * Erlang Factory San Francisco 2016
+    [the slides and video recording](http://www.erlang-factory.com/sfbay2016/scott-lystig-fritchie)
+    will be available a few weeks after the conference ends on March
+    11, 2016.
+  * Ricon 2015
+    * [The slides](http://ricon.io/archive/2015/slides/Scott_Fritchie_Ricon_2015.pdf)
+    * and the [video recording](https://www.youtube.com/watch?v=yR5kHL1bu1Q&index=13&list=PL9Jh2HsAWHxIc7Tt2M6xez_TOP21GBH6M)
+    are now available.
+    * If you would like to run the Humming Consensus code (with or without
+    the network partition simulator) as described in the RICON 2015
+    presentation, please see the
+    [Humming Consensus demo doc](./doc/humming_consensus_demo.md).
+
+<a name="sec4">
+## 4. Contributing to Machi's development
+
+### 4.1 License
 
 Basho Technologies, Inc. as committed to licensing all work for Machi
 under the
@@ -71,57 +146,29 @@ We invite all contributors to review the
 [CONTRIBUTING.md](./CONTRIBUTING.md) document for guidelines for
 working with the Basho development team.
 
-## A brief survey of this directories in this repository
+### 4.2 Development environment requirements
-
-* A list of Frequently Asked Questions, a.k.a.
-  [the Machi FAQ](./FAQ.md).
-
-* The [doc](./doc/) directory: home for major documents about Machi:
-  high level design documents as well as exploration of features still
-  under design & review within Basho.
-
-* The `ebin` directory: used for compiled application code
-
-* The `include`, `src`, and `test` directories: contain the header
-  files, source files, and test code for Machi, respectively.
-
-* The [prototype](./prototype/) directory: contains proof of concept
-  code, scaffolding libraries, and other exploratory code.  Curious
-  readers should see the [prototype/README.md](./prototype/README.md)
-  file for more explanation of the small sub-projects found here.
-
-## Development environment requirements
 
 All development to date has been done with Erlang/OTP version 17 on OS
 X.  The only known limitations for using R16 are minor type
 specification difference between R16 and 17, but we strongly suggest
 continuing development using version 17.
 
-We also assume that you have the standard UNIX/Linux developers
+We also assume that you have the standard UNIX/Linux developer
-tool chain for C and C++ applications.  Specifically, we assume `make`
+tool chain for C and C++ applications.  Also, we assume
-is available.  The utility used to compile the Machi source code,
+that Git and GNU Make are available.
+The utility used to compile the Machi source code,
 `rebar`, is pre-compiled and included in the repo.
+For more details, please see the
+[Machi development environment prerequisites doc](./doc/dev-prerequisites.md).
 
-There are no known OS limits at this time: any platform that supports
+Machi has a dependency on the
-Erlang/OTP should be sufficient for Machi.  This may change over time
+[ELevelDB](https://github.com/basho/eleveldb) library.  ELevelDB only
-(e.g., adding NIFs which can make full portability to Windows OTP
+supports UNIX/Linux OSes and 64-bit versions of Erlang/OTP only; we
-environments difficult), but it hasn't happened yet.
+apologize to Windows-based and 32-bit-based Erlang developers for this
+restriction.
 
-## Contributions 
+### 4.3 New protocols and features
-
-Basho encourages contributions to Riak from the community. Here’s how
-to get started.
-
-* Fork the appropriate sub-projects that are affected by your change. 
-* Create a topic branch for your change and checkout that branch.
-     git checkout -b some-topic-branch
-* Make your changes and run the test suite if one is provided. (see below)
-* Commit your changes and push them to your fork.
-* Open pull-requests for the appropriate projects.
-* Contributors will review your pull request, suggest changes, and merge it when it’s ready and/or offer feedback.
-* To report a bug or issue, please open a new issue against this repository.
-
--The Machi team at Basho, 
-[Scott Lystig Fritchie](mailto:scott@basho.com), technical lead, and
-[Matt Brender](mailto:mbrender@basho.com), your developer advocate.
 
+If you'd like to work on a protocol such as Thrift, UBF,
+msgpack over UDP, or some other protocol, let us know by
+[opening an issue to discuss it](./issues/new).

dialyzer.ignore-warnings

@@ -0,0 +1,15 @@
+### The auto-generated code of machi_pb.beam has some complaints, not fixed yet.
+machi_pb.erl:0:
+##################################################
+########  Specific types     #####################
+##################################################
+Unknown types:
+  basho_bench_config:get/2
+  machi_partition_simulator:get/1
+  hamcrest:matchspec/0
+##################################################
+########  Specific messages  #####################
+##################################################
+machi_chain_manager1.erl:2473: The created fun has no local return
+machi_chain_manager1.erl:2184: The pattern <_P1, P2, Else = {'expected_author2', UPI1_tail, _}> can never match the type <#projection_v1{epoch_number::'undefined' | non_neg_integer(),epoch_csum::'undefined' | binary(),author_server::atom(),chain_name::atom(),all_members::'undefined' | [atom()],witnesses::[atom()],creation_time::'undefined' | {non_neg_integer(),non_neg_integer(),non_neg_integer()},mode::'ap_mode' | 'cp_mode',upi::'undefined' | [atom()],repairing::'undefined' | [atom()],down::'undefined' | [atom()],dbg::'undefined' | [any()],dbg2::'undefined' | [any()],members_dict::'undefined' | [{_,_}]},#projection_v1{epoch_number::'undefined' | non_neg_integer(),epoch_csum::binary(),author_server::atom(),chain_name::atom(),all_members::'undefined' | [atom()],witnesses::[atom()],creation_time::'undefined' | {non_neg_integer(),non_neg_integer(),non_neg_integer()},mode::'ap_mode' | 'cp_mode',upi::'undefined' | [atom()],repairing::'undefined' | [atom()],down::'undefined' | [atom()],dbg::'undefined' | [any()],dbg2::'undefined' | [any()],members_dict::'undefined' | [{_,_}]},'true'>
+machi_chain_manager1.erl:2233: The pattern <_P1 = {'projection_v1', _, _, _, _, _, _, _, 'cp_mode', UPI1, Repairing1, _, _, _, _}, _P2 = {'projection_v1', _, _, _, _, _, _, _, 'cp_mode', UPI2, Repairing2, _, _, _, _}, Else = {'epoch_not_si', EpochX, 'not_gt', EpochY}> can never match the type <#projection_v1{epoch_number::'undefined' | non_neg_integer(),epoch_csum::'undefined' | binary(),author_server::atom(),chain_name::atom(),all_members::'undefined' | [atom()],witnesses::[atom()],creation_time::'undefined' | {non_neg_integer(),non_neg_integer(),non_neg_integer()},mode::'ap_mode' | 'cp_mode',upi::'undefined' | [atom()],repairing::'undefined' | [atom()],down::'undefined' | [atom()],dbg::'undefined' | [any()],dbg2::'undefined' | [any()],members_dict::'undefined' | [{_,_}]},#projection_v1{epoch_number::'undefined' | non_neg_integer(),epoch_csum::binary(),author_server::atom(),chain_name::atom(),all_members::'undefined' | [atom()],witnesses::[atom()],creation_time::'undefined' | {non_neg_integer(),non_neg_integer(),non_neg_integer()},mode::'ap_mode' | 'cp_mode',upi::'undefined' | [atom()],repairing::'undefined' | [atom()],down::'undefined' | [atom()],dbg::'undefined' | [any()],dbg2::'undefined' | [any()],members_dict::'undefined' | [{_,_}]},'true'>

doc/README.md

@@ -6,20 +6,6 @@ Erlang documentation, please use this link:
 
 ## Documents in this directory
 
-### chain-self-management-sketch.org
-
-[chain-self-management-sketch.org](chain-self-management-sketch.org)
-is a mostly-deprecated draft of
-an introduction to the
-self-management algorithm proposed for Machi.  Most material has been
-moved to the [high-level-chain-mgr.pdf](high-level-chain-mgr.pdf) document.
-
-### cluster-of-clusters (directory)
-
-This directory contains the sketch of the "cluster of clusters" design
-strawman for partitioning/distributing/sharding files across a large
-number of independent Machi clusters.
-
 ### high-level-machi.pdf
 
 [high-level-machi.pdf](high-level-machi.pdf)
@@ -50,9 +36,9 @@ introduction to the Humming Consensus algorithm.  Its abstract:
 > of file updates to all replica servers in a Machi cluster.  Chain
 > Replication is a variation of primary/backup replication where the
 > order of updates between the primary server and each of the backup
-> servers is strictly ordered into a single ``chain''.  Management of
+> servers is strictly ordered into a single "chain".  Management of
-> Chain Replication's metadata, e.g., ``What is the current order of
+> Chain Replication's metadata, e.g., "What is the current order of
-> servers in the chain?'', remains an open research problem.  The
+> servers in the chain?", remains an open research problem.  The
 > current state of the art for Chain Replication metadata management
 > relies on an external oracle (e.g., ZooKeeper) or the Elastic
 > Replication algorithm.
@@ -60,7 +46,7 @@ introduction to the Humming Consensus algorithm.  Its abstract:
 > This document describes the Machi chain manager, the component
 > responsible for managing Chain Replication metadata state.  The chain
 > manager uses a new technique, based on a variation of CORFU, called
-> ``humming consensus''.
+> "humming consensus".
 > Humming consensus does not require active participation by all or even
 > a majority of participants to make decisions.  Machi's chain manager
 > bases its logic on humming consensus to make decisions about how to
@@ -71,3 +57,18 @@ introduction to the Humming Consensus algorithm.  Its abstract:
 > decision during that epoch.  When a differing decision is discovered,
 > new time epochs are proposed in which a new consensus is reached and
 > disseminated to all available participants.
+
+### chain-self-management-sketch.org
+
+[chain-self-management-sketch.org](chain-self-management-sketch.org)
+is a mostly-deprecated draft of
+an introduction to the
+self-management algorithm proposed for Machi.  Most material has been
+moved to the [high-level-chain-mgr.pdf](high-level-chain-mgr.pdf) document.
+
+### cluster (directory)
+
+This directory contains the sketch of the cluster design
+strawman for partitioning/distributing/sharding files across a large
+number of independent Machi chains.
+

doc/cluster-of-clusters/name-game-sketch.org

@@ -1,435 +0,0 @@
--*- mode: org; -*-
-#+TITLE: Machi cluster-of-clusters "name game" sketch
-#+AUTHOR: Scott
-#+STARTUP: lognotedone hidestars indent showall inlineimages
-#+SEQ_TODO: TODO WORKING WAITING DONE
-#+COMMENT: M-x visual-line-mode
-#+COMMENT: Also, disable auto-fill-mode
-
-* 1. "Name Games" with random-slicing style consistent hashing
-
-Our goal: to distribute lots of files very evenly across a cluster of
-Machi clusters (hereafter called a "cluster of clusters" or "CoC").
-
-* 2. Assumptions
-
-** Basic familiarity with Machi high level design and Machi's "projection"
-
-The [[https://github.com/basho/machi/blob/master/doc/high-level-machi.pdf][Machi high level design document]] contains all of the basic
-background assumed by the rest of this document.
-
-** Familiarity with the Machi cluster-of-clusters/CoC concept
-
-This isn't yet well-defined (April 2015).  However, it's clear from
-the [[https://github.com/basho/machi/blob/master/doc/high-level-machi.pdf][Machi high level design document]] that Machi alone does not support
-any kind of file partitioning/distribution/sharding across multiple
-small Machi clusters.  There must be another layer above a Machi cluster to
-provide such partitioning services.
-
-The name "cluster of clusters" orignated within Basho to avoid
-conflicting use of the word "cluster".  A Machi cluster is usually
-synonymous with a single Chain Replication chain and a single set of
-machines (e.g. 2-5 machines).  However, in the not-so-far future, we
-expect much more complicated patterns of Chain Replication to be used
-in real-world deployments.
-
-"Cluster of clusters" is clunky and long, but we haven't found a good
-substitute yet.  If you have a good suggestion, please contact us!
-~^_^~
-
-Using the [[https://github.com/basho/machi/tree/master/prototype/demo-day-hack][cluster-of-clusters quick-and-dirty prototype]] as an
-architecture sketch, let's now assume that we have ~N~ independent Machi
-clusters.  We wish to provide partitioned/distributed file storage
-across all ~N~ clusters.  We call the entire collection of ~N~ Machi
-clusters a "cluster of clusters", or abbreviated "CoC".
-
-** Continue CoC prototype's assumption: a Machi cluster is unaware of CoC
-
-Let's continue with an assumption that an individual Machi cluster
-inside of the cluster-of-clusters is completely unaware of the
-cluster-of-clusters layer.
-
-We may need to break this assumption sometime in the future?  It isn't
-quite clear yet, sorry.
-
-** Analogy: "neighborhood : city :: Machi : cluster-of-clusters"
-
-Analogy: The word "machi" in Japanese means small town or
-neighborhood.  As the Tokyo Metropolitan Area is built from many
-machis and smaller cities, therefore a big, partitioned file store can
-be built out of many small Machi clusters.
-
-** The reader is familiar with the random slicing technique
-
-I'd done something very-very-nearly-identical for the Hibari database
-6 years ago.  But the Hibari technique was based on stuff I did at
-Sendmail, Inc, so it felt old news to me.  {shrug}
-
-The Hibari documentation has a brief photo illustration of how random
-slicing works, see [[http://hibari.github.io/hibari-doc/hibari-sysadmin-guide.en.html#chain-migration][Hibari Sysadmin Guide, chain migration]]
-
-For a comprehensive description, please see these two papers:
-
-#+BEGIN_QUOTE
-Reliable and Randomized Data Distribution Strategies for Large Scale Storage Systems
-Alberto Miranda et al.
-http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.226.5609
-                                                  (short version, HIPC'11)
-
-Random Slicing: Efficient and Scalable Data Placement for Large-Scale
-    Storage Systems 
-Alberto Miranda et al.
-DOI: http://dx.doi.org/10.1145/2632230 (long version, ACM Transactions
-                              on Storage, Vol. 10, No. 3, Article 9, 2014)
-#+END_QUOTE
-
-** We use random slicing to map CoC file names -> Machi cluster ID/name
-
-We will use a single random slicing map.  This map (called ~Map~ in
-the descriptions below), together with the random slicing hash
-function (called ~rs_hash()~ below), will be used to map:
-
-#+BEGIN_QUOTE
-    CoC client-visible file name -> Machi cluster ID/name/thingie
-#+END_QUOTE
-
-** Machi cluster ID/name management: TBD, but, really, should be simple
-
-The mapping from:
-
-#+BEGIN_QUOTE
-    Machi CoC member ID/name/thingie -> ???
-#+END_QUOTE
-
-... remains To Be Determined.  But, really, this is going to be pretty
-simple.  The ID/name/thingie will probably be a human-friendly,
-printable ASCII string, and the "???" will probably be a single Machi
-cluster projection data structure.
-
-The Machi projection is enough information to contact any member of
-that cluster and, if necessary, request the most up-to-date projection
-information required to use that cluster.
-
-It's likely that the projection given by this map will be out-of-date,
-so the client must be ready to use the standard Machi procedure to
-request the cluster's current projection, in any case.
-
-* 3. A simple illustration
-
-I'm borrowing an illustration from the HibariDB documentation here,
-but it fits my purposes quite well.  (And I originally created that
-image, and the use license is OK.)
-
-#+CAPTION: Illustration of 'Map', using four Machi clusters
-
-[[./migration-4.png]]
-
-Assume that we have a random slicing map called ~Map~.  This particular
-~Map~ maps the unit interval onto 4 Machi clusters:
-
-| Hash range  | Cluster ID |
-|-------------+------------|
-| 0.00 - 0.25 | Cluster1   |
-| 0.25 - 0.33 | Cluster4   |
-| 0.33 - 0.58 | Cluster2   |
-| 0.58 - 0.66 | Cluster4   |
-| 0.66 - 0.91 | Cluster3   |
-| 0.91 - 1.00 | Cluster4   |
-
-Then, if we had CoC file name "~foo~", the hash ~SHA("foo")~ maps to about
-0.05 on the unit interval.  So, according to ~Map~, the value of
-~rs_hash("foo",Map) = Cluster1~.  Similarly, ~SHA("hello")~ is about
-0.67 on the unit interval, so ~rs_hash("hello",Map) = Cluster3~.
-
-* 4. An additional assumption: clients will want some control over file placement
-
-We will continue to use the 4-cluster diagram from the previous
-section.
-
-When a client wishes to append data to a Machi file, the Machi server
-chooses the file name & byte offset for storing that data.  This
-feature is why Machi's eventual consistency operating mode is so
-nifty: it allows us to merge together files safely at any time because
-any two client append operations will always write to different files
-& different offsets.
-
-** Our new assumption: client control over initial file placement
-
-The CoC management scheme may decide that files need to migrate to
-other clusters.  The reason could be for storage load or I/O load
-balancing reasons.  It could be because a cluster is being
-decomissioned by its owners.  There are many legitimate reasons why a
-file that is initially created on cluster ID X has been moved to
-cluster ID Y.
-
-However, there are also legitimate reasons for why the client would want
-control over the choice of Machi cluster when the data is first
-written.  The single biggest reason is load balancing.  Assuming that
-the client (or the CoC management layer acting on behalf of the CoC
-client) knows the current utilization across the participating Machi
-clusters, then it may be very helpful to send new append() requests to
-under-utilized clusters.
-
-** Cool!  Except for a couple of problems...
-
-If the client wants to store some data
-on Cluster2 and therefore sends an ~append("foo",CoolData)~ request to
-the head of Cluster2 (which the client magically knows how to
-contact), then the result will look something like
-~{ok,"foo.s923.z47",ByteOffset}~.
-
-Therefore, the file name "~foo.s923.z47~" must be used by any Machi
-CoC client in order to retrieve the CoolData bytes.
-
-*** Problem #1: "foo.s923.z47" doesn't always map via random slicing to Cluster2
-
-... if we ignore the problem of "CoC files may be redistributed in the
-future", then we still have a problem.
-
-In fact, the value of ~ps_hash("foo.s923.z47",Map)~ is Cluster1.
-
-*** Problem #2: We want CoC files to move around automatically
-
-If the CoC client stores two pieces of information, the file name
-"~foo.s923.z47~" and the Cluster ID Cluster2, then what happens when the
-cluster-of-clusters system decides to rebalance files across all
-machines?  The CoC manager may decide to move our file to Cluster66.
-
-How will a future CoC client wishes to retrieve CoolData when Cluster2
-no longer stores the required file?
-
-**** When migrating the file, we could put a "pointer" on Cluster2 that points to the new location, Cluster66.
-
-This scheme is a bit brittle, even if all of the pointers are always
-created 100% correctly.  Also, if Cluster2 is ever unavailable, then
-we cannot fetch our CoolData, even though the file moved away from
-Cluster2 several years ago.
-
-The scheme would also introduce extra round-trips to the servers
-whenever we try to read a file where we do not know the most
-up-to-date cluster ID for.
-
-**** We could store a pointer to file "foo.s923.z47"'s location in an LDAP database!
-
-Or we could store it in Riak.  Or in another, external database.  We'd
-rather not create such an external dependency, however.  Furthermore,
-we would also have the same problem of updating this external database
-each time that a file is moved/rebalanced across the CoC.
-
-* 5. Proposal: Break the opacity of Machi file names, slightly
-
-Assuming that Machi keeps the scheme of creating file names (in
-response to ~append()~ and ~sequencer_new_range()~ calls) based on a
-predictable client-supplied prefix and an opaque suffix, e.g.,
-
-~append("foo",CoolData) -> {ok,"foo.s923.z47",ByteOffset}.~
-
-... then we propose that all CoC and Machi parties be aware of this
-naming scheme, i.e. that Machi assigns file names based on:
-
-~ClientSuppliedPrefix ++ "." ++ SomeOpaqueFileNameSuffix~
-
-The Machi system doesn't care about the file name -- a Machi server
-will treat the entire file name as an opaque thing.  But this document
-is called the "Name Game" for a reason!
-
-What if the CoC client could peek inside of the opaque file name
-suffix in order to remove (or add) the CoC location information that
-we need?
-
-** The details: legend
-
-- ~T~   = the target CoC member/Cluster ID chosen at the time of ~append()~
-- ~p~   = file prefix, chosen by the CoC client (This is exactly the Machi client-chosen file prefix).
-- ~s.z~ = the Machi file server opaque file name suffix (Which we
-  happen to know is a combination of sequencer ID plus file serial
-  number.  This implementation may change, for example, to use a
-  standard GUID string (rendered into ASCII hexadecimal digits) instead.)
-- ~K~   = the CoC placement key
-
-We use a variation of ~rs_hash()~, called ~rs_hash_with_float()~.  The
-former uses a string as its 1st argument; the latter uses a floating
-point number as its 1st argument.  Both return a cluster ID name
-thingie.
-
-#+BEGIN_SRC erlang
-%% type specs, Erlang style
--spec rs_hash(string(), rs_hash:map()) -> rs_hash:cluster_id().
--spec rs_hash_with_float(float(), rs_hash:map()) -> rs_hash:cluster_id().
-#+END_SRC
-
-NOTE: Use of floating point terms is not required.  For example,
-integer arithmetic could be used, if using a sufficiently large
-interval to create an even & smooth distribution of hashes across the
-expected maximum number of clusters.
-
-For example, if the maximum CoC cluster size would be 4,000 individual
-Machi clusters, then a minimum of 12 bits of integer space is required
-to assign one integer per Machi cluster.  However, for load balancing
-purposes, a finer grain of (for example) 100 integers per Machi
-cluster would permit file migration to move increments of
-approximately 1% of single Machi cluster's storage capacity.  A
-minimum of 19 bits of hash space would be necessary to accomodate
-these constraints.
-
-** The details: CoC file write
-
-1. CoC client chooses ~p~ and ~T~ (i.e., the file prefix & target cluster)
-2. CoC client knows the CoC ~Map~
-3. CoC client calculates a value ~K~ such that ~rs_hash_with_float(K,Map) = T~, using the method described below.
-4. CoC client requests @ cluster ~T~: ~append_chunk(p,K,...) -> {ok,p.K.s.z,ByteOffset}~
-5. CoC stores/uses the file name ~p.K.s.z~.
-
-** The details: CoC file read
-
-1. CoC client knows the file name ~p.K.s.z~ and parses it to find
-   ~K~'s value.
-2. CoC client knows the CoC ~Map~
-3. Coc calculates ~rs_hash_with_float(K,Map) = T~
-4. CoC client requests @ cluster ~T~: ~read_chunk(p.K.s.z,...) ->~ ... success!
-
-** The details: calculating 'K', the CoC placement key
-
-1. We know ~Map~, the current CoC mapping.
-2. We look inside of ~Map~, and we find all of the unit interval ranges
-   that map to our desired target cluster ~T~.  Let's call this list
-   ~MapList = [Range1=(start,end],Range2=(start,end],...]~.
-3. In our example, ~T=Cluster2~.  The example ~Map~ contains a single
-   unit interval range for ~Cluster2~, ~[(0.33,0.58]]~.
-4. Choose a uniformally random number ~r~ on the unit interval.
-5. Calculate placement key ~K~ by mapping ~r~ onto the concatenation
-   of the CoC hash space range intervals in ~MapList~.  For example,
-   if ~r=0.5~, then ~K = 0.33 + 0.5*(0.58-0.33) = 0.455~, which is
-   exactly in the middle of the ~(0.33,0.58]~ interval.
-6. If necessary, encode ~K~ in a file name-friendly manner, e.g., convert it to hexadecimal ASCII digits to create file name ~p.K.s.z~.
-
-** The details: calculating 'K', an alternative method
-
-If the Law of Large Numbers and our random number generator do not create the kind of smooth & even distribution of files across the CoC as we wish, an alternative method of calculating ~K~ follows.
-
-If each server in each Machi cluster keeps track of the CoC ~Map~ and also of all values of ~K~ for all files that it stores, then we can simply ask a cluster member to recommend a value of ~K~ that is least represented by existing files.
-
-* 6. File migration (aka rebalancing/reparitioning/redistribution)
-
-** What is "file migration"?
-
-As discussed in section 5, the client can have good reason for wanting
-to have some control of the initial location of the file within the
-cluster.  However, the cluster manager has an ongoing interest in
-balancing resources throughout the lifetime of the file.  Disks will
-get full, hardware will change, read workload will fluctuate,
-etc etc.
-
-This document uses the word "migration" to describe moving data from
-one CoC cluster to another.  In other systems, this process is
-described with words such as rebalancing, repartitioning, and
-resharding.  For Riak Core applications, the mechanisms are "handoff"
-and "ring resizing". See the [[http://hadoop.apache.org/docs/current/hadoop-project-dist/hadoop-hdfs/HdfsUserGuide.html#Balancer][Hadoop file balancer]] for another example.
-
-A simple variation of the Random Slicing hash algorithm can easily
-accomodate Machi's need to migrate files without interfering with
-availability.  Machi's migration task is much simpler due to the
-immutable nature of Machi file data.
-
-** Change to Random Slicing
-
-The map used by the Random Slicing hash algorithm needs a few simple
-changes to make file migration straightforward.
-
-- Add a "generation number", a strictly increasing number (similar to
-  a Machi cluster's "epoch number") that reflects the history of
-  changes made to the Random Slicing map
-- Use a list of Random Slicing maps instead of a single map, one map
-  per possibility that files may not have been migrated yet out of
-  that map.
-
-As an example:
-
-#+CAPTION: Illustration of 'Map', using four Machi clusters
-
-[[./migration-3to4.png]]
-
-And the new Random Slicing map might look like this:
-
-| Generation number | 7          |
-|-------------------+------------|
-| SubMap            | 1          |
-|-------------------+------------|
-| Hash range        | Cluster ID |
-|-------------------+------------|
-| 0.00 - 0.33       | Cluster1   |
-| 0.33 - 0.66       | Cluster2   |
-| 0.66 - 1.00       | Cluster3   |
-|-------------------+------------|
-| SubMap            | 2          |
-|-------------------+------------|
-| Hash range        | Cluster ID |
-|-------------------+------------|
-| 0.00 - 0.25       | Cluster1   |
-| 0.25 - 0.33       | Cluster4   |
-| 0.33 - 0.58       | Cluster2   |
-| 0.58 - 0.66       | Cluster4   |
-| 0.66 - 0.91       | Cluster3   |
-| 0.91 - 1.00       | Cluster4   |
-
-When a new Random Slicing map contains a single submap, then its use
-is identical to the original Random Slicing algorithm.  If the map
-contains multiple submaps, then the access rules change a bit:
-
-- Write operations always go to the latest/largest submap.
-- Read operations attempt to read from all unique submaps.
-  - Skip searching submaps that refer to the same cluster ID.
-    - In this example, unit interval value 0.10 is mapped to Cluster1
-      by both submaps.
-  - Read from latest/largest submap to oldest/smallest submap.
-  - If not found in any submap, search a second time (to handle races
-    with file copying between submaps).
-  - If the requested data is found, optionally copy it directly to the
-    latest submap (as a variation of read repair which really simply
-    accelerates the migration process and can reduce the number of
-    operations required to query servers in multiple submaps).
-
-The cluster-of-clusters manager is responsible for:
-
-- Managing the various generations of the CoC Random Slicing maps,
-  including distributing them to CoC clients.
-- Managing the processes that are responsible for copying "cold" data,
-  i.e., files data that is not regularly accessed, to its new submap
-  location.
-- When migration of a file to its new cluster is confirmed successful,
-  delete it from the old cluster.
-
-In example map #7, the CoC manager will copy files with unit interval
-assignments in ~(0.25,0.33]~, ~(0.58,0.66]~, and ~(0.91,1.00]~ from their
-old locations in cluster IDs Cluster1/2/3 to their new cluster,
-Cluster4.  When the CoC manager is satisfied that all such files have
-been copied to Cluster4, then the CoC manager can create and
-distribute a new map, such as:
-
-| Generation number | 8          |
-|-------------------+------------|
-| SubMap            | 1          |
-|-------------------+------------|
-| Hash range        | Cluster ID |
-|-------------------+------------|
-| 0.00 - 0.25       | Cluster1   |
-| 0.25 - 0.33       | Cluster4   |
-| 0.33 - 0.58       | Cluster2   |
-| 0.58 - 0.66       | Cluster4   |
-| 0.66 - 0.91       | Cluster3   |
-| 0.91 - 1.00       | Cluster4   |
-
-One limitation of HibariDB that I haven't fixed is not being able to
-perform more than one migration at a time.  The trade-off is that such
-migration is difficult enough across two submaps; three or more
-submaps becomes even more complicated.
-
-Fortunately for Machi, its file data is immutable and therefore can
-easily manage many migrations in parallel, i.e., its submap list may
-be several maps long, each one for an in-progress file migration.
-
-* Acknowledgements
-
-The source for the "migration-4.png" and "migration-3to4.png" images
-come from the [[http://hibari.github.io/hibari-doc/images/migration-3to4.png][HibariDB documentation]].
-

doc/cluster/migration-3to4.fig

@@ -0,0 +1,103 @@
+#FIG 3.2  Produced by xfig version 3.2.5b
+Landscape
+Center
+Inches
+Letter  
+94.00
+Single
+-2
+1200 2
+6 7425 2700 8700 3300
+4 0 0 50 -1 2 18 0.0000 4 195 645 7425 2895 After\001
+4 0 0 50 -1 2 18 0.0000 4 255 1215 7425 3210 Migration\001
+-6
+6 7425 450 8700 1050
+4 0 0 50 -1 2 18 0.0000 4 195 780 7425 675 Before\001
+4 0 0 50 -1 2 18 0.0000 4 255 1215 7425 990 Migration\001
+-6
+6 75 1425 6900 2325
+6 4875 1425 6900 2325
+6 5400 1575 6375 2175
+4 0 0 50 -1 2 14 0.0000 4 165 390 5400 1800 Not\001
+4 0 0 50 -1 2 14 0.0000 4 225 945 5400 2100 migrated\001
+-6
+2 2 1 2 0 7 50 -1 -1 6.000 0 0 -1 0 0 5
+	 4950 1500 6825 1500 6825 2250 4950 2250 4950 1500
+-6
+6 2475 1425 4500 2325
+6 3000 1575 3975 2175
+4 0 0 50 -1 2 14 0.0000 4 165 390 3000 1800 Not\001
+4 0 0 50 -1 2 14 0.0000 4 225 945 3000 2100 migrated\001
+-6
+2 2 1 2 0 7 50 -1 -1 6.000 0 0 -1 0 0 5
+	 2550 1500 4425 1500 4425 2250 2550 2250 2550 1500
+-6
+6 75 1425 2100 2325
+6 600 1575 1575 2175
+4 0 0 50 -1 2 14 0.0000 4 165 390 600 1800 Not\001
+4 0 0 50 -1 2 14 0.0000 4 225 945 600 2100 migrated\001
+-6
+2 2 1 2 0 7 50 -1 -1 6.000 0 0 -1 0 0 5
+	 150 1500 2025 1500 2025 2250 150 2250 150 1500
+-6
+-6
+2 1 0 2 0 7 50 -1 -1 6.000 0 0 -1 1 0 2
+	1 1 3.00 60.00 120.00
+	 150 4200 150 3750
+2 1 0 2 0 7 50 -1 -1 6.000 0 0 -1 1 0 2
+	1 1 3.00 60.00 120.00
+	 3750 4200 3750 3750
+2 1 0 2 0 7 50 -1 -1 6.000 0 0 -1 1 0 2
+	1 1 3.00 60.00 120.00
+	 2025 4200 2025 3750
+2 1 0 2 0 7 50 -1 -1 6.000 0 0 -1 1 0 2
+	1 1 3.00 60.00 120.00
+	 7350 4200 7350 3750
+2 1 0 2 0 7 50 -1 -1 6.000 0 0 -1 1 0 2
+	1 1 3.00 60.00 120.00
+	 5550 4200 5550 3750
+2 2 0 3 0 7 50 -1 -1 0.000 0 0 -1 0 0 5
+	 2550 0 2550 1500 150 1500 150 0 2550 0
+2 2 0 3 0 7 50 -1 -1 0.000 0 0 -1 0 0 5
+	 4950 0 4950 1500 2550 1500 2550 0 4950 0
+2 2 0 3 0 7 50 -1 -1 0.000 0 0 -1 0 0 5
+	 7350 0 7350 1500 4950 1500 4950 0 7350 0
+2 2 0 3 0 7 50 -1 -1 0.000 0 0 -1 0 0 5
+	 150 2250 2025 2250 2025 3750 150 3750 150 2250
+2 2 0 3 0 7 50 -1 -1 0.000 0 0 -1 0 0 5
+	 4425 2250 4950 2250 4950 3750 4425 3750 4425 2250
+2 2 0 3 0 7 50 -1 -1 0.000 0 0 -1 0 0 5
+	 4950 2250 6825 2250 6825 3750 4950 3750 4950 2250
+2 2 0 3 0 7 50 -1 -1 0.000 0 0 -1 0 0 5
+	 6825 2250 7350 2250 7350 3750 6825 3750 6825 2250
+2 2 0 3 0 7 50 -1 -1 0.000 0 0 -1 0 0 5
+	 2025 2250 2550 2250 2550 3750 2025 3750 2025 2250
+2 2 0 3 0 7 50 -1 -1 0.000 0 0 -1 0 0 5
+	 2550 2250 4425 2250 4425 3750 2550 3750 2550 2250
+4 0 0 50 -1 2 18 0.0000 4 195 480 75 4500 0.00\001
+4 0 0 50 -1 2 18 0.0000 4 195 480 6825 4500 1.00\001
+4 0 0 50 -1 2 18 0.0000 4 195 480 1725 4500 0.25\001
+4 0 0 50 -1 2 18 0.0000 4 195 480 3525 4500 0.50\001
+4 0 0 50 -1 2 18 0.0000 4 195 480 5250 4500 0.75\001
+4 0 0 50 -1 2 14 0.0000 4 240 1710 450 1275 ~33% total keys\001
+4 0 0 50 -1 2 14 0.0000 4 240 1710 2925 1275 ~33% total keys\001
+4 0 0 50 -1 2 14 0.0000 4 240 1710 5250 1275 ~33% total keys\001
+4 0 0 50 -1 2 14 0.0000 4 180 495 2025 3525 ~8%\001
+4 0 0 50 -1 2 14 0.0000 4 240 1710 300 3525 ~25% total keys\001
+4 0 0 50 -1 2 14 0.0000 4 240 1710 2625 3525 ~25% total keys\001
+4 0 0 50 -1 2 14 0.0000 4 180 495 4425 3525 ~8%\001
+4 0 0 50 -1 2 14 0.0000 4 240 1710 5025 3525 ~25% total keys\001
+4 0 0 50 -1 2 14 0.0000 4 180 495 6825 3525 ~8%\001
+4 0 0 50 -1 2 24 0.0000 4 270 195 2175 3075 4\001
+4 0 0 50 -1 2 24 0.0000 4 270 195 4575 3075 4\001
+4 0 0 50 -1 2 24 0.0000 4 270 195 6975 3075 4\001
+4 0 0 50 -1 2 24 0.0000 4 270 1245 600 600 Chain1\001
+4 0 0 50 -1 2 24 0.0000 4 270 1245 3000 600 Chain2\001
+4 0 0 50 -1 2 24 0.0000 4 270 1245 5400 600 Chain3\001
+4 0 0 50 -1 2 24 0.0000 4 270 285 2100 2625 C\001
+4 0 0 50 -1 2 24 0.0000 4 270 285 4500 2625 C\001
+4 0 0 50 -1 2 24 0.0000 4 270 285 6900 2625 C\001
+4 0 0 50 -1 2 24 0.0000 4 270 1245 525 2850 Chain1\001
+4 0 0 50 -1 2 24 0.0000 4 270 1245 2925 2850 Chain2\001
+4 0 0 50 -1 2 24 0.0000 4 270 1245 5325 2850 Chain3\001
+4 0 0 50 -1 2 18 0.0000 4 240 4350 1350 4875 Cluster locator, on the unit interval\001

doc/cluster/name-game-sketch.org

@@ -0,0 +1,481 @@
+-*- mode: org; -*-
+#+TITLE: Machi cluster "name game" sketch
+#+AUTHOR: Scott
+#+STARTUP: lognotedone hidestars indent showall inlineimages
+#+SEQ_TODO: TODO WORKING WAITING DONE
+#+COMMENT: M-x visual-line-mode
+#+COMMENT: Also, disable auto-fill-mode
+
+* 1. "Name Games" with random-slicing style consistent hashing
+
+Our goal: to distribute lots of files very evenly across a large
+collection of individual, small Machi chains.
+
+* 2. Assumptions
+
+** Basic familiarity with Machi high level design and Machi's "projection"
+
+The [[https://github.com/basho/machi/blob/master/doc/high-level-machi.pdf][Machi high level design document]] contains all of the basic
+background assumed by the rest of this document.
+
+** Analogy: "neighborhood : city :: Machi chain : Machi cluster"
+
+Analogy: The word "machi" in Japanese means small town or
+neighborhood.  As the Tokyo Metropolitan Area is built from many
+machis and smaller cities, therefore a big, partitioned file store can
+be built out of many small Machi chains.
+
+** Familiarity with the Machi chain concept
+
+It's clear (I hope!) from
+the [[https://github.com/basho/machi/blob/master/doc/high-level-machi.pdf][Machi high level design document]] that Machi alone does not support
+any kind of file partitioning/distribution/sharding across multiple
+small Machi chains.  There must be another layer above a Machi chain to
+provide such partitioning services.
+
+Using the [[https://github.com/basho/machi/tree/master/prototype/demo-day-hack][cluster quick-and-dirty prototype]] as an
+architecture sketch, let's now assume that we have ~n~ independent Machi
+chains.  We assume that each of these chains has the same
+chain length in the nominal case, e.g. chain length of 3.
+We wish to provide partitioned/distributed file storage
+across all ~n~ chains.  We call the entire collection of ~n~ Machi
+chains a "cluster".
+
+We may wish to have several types of Machi clusters.  For example:
+
++ Chain length of 1 for "don't care if it gets lost,
+  store stuff very very cheaply" data.
++ Chain length of 2 for normal data.
+  + Equivalent to quorum replication's reliability with 3 copies.
++ Chain length of 7 for critical, unreplaceable data.
+  + Equivalent to quorum replication's reliability with 15 copies.
+
+Each of these types of chains will have a name ~N~ in the
+namespace.  The role of the cluster namespace will be demonstrated in
+Section 3 below.
+
+** Continue an early assumption: a Machi chain is unaware of clustering
+
+Let's continue with an assumption that an individual Machi chain
+inside of a cluster is completely unaware of the cluster layer.
+
+** The reader is familiar with the random slicing technique
+
+I'd done something very-very-nearly-like-this for the Hibari database
+6 years ago.  But the Hibari technique was based on stuff I did at
+Sendmail, Inc, in 2000, so this technique feels like old news to me.
+{shrug}
+
+The following section provides an illustrated example.
+Very quickly, the random slicing algorithm is:
+
+- Hash a string onto the unit interval [0.0, 1.0)
+- Calculate h(unit interval point, Map) -> bin, where ~Map~ divides
+  the unit interval into bins (or partitions or shards).
+
+Machi's adaptation is in step 1: we do not hash any strings.  Instead, we
+simply choose a number on the unit interval.  This number is called
+the "cluster locator number".
+
+As described later in this doc, Machi file names are structured into
+several components.  One component of the file name contains the cluster
+locator number; we use the number as-is for step 2 above.
+
+*** For more information about Random Slicing
+
+For a comprehensive description of random slicing, please see the
+first two papers.  For a quicker summary, please see the third
+reference.
+
+#+BEGIN_QUOTE
+Reliable and Randomized Data Distribution Strategies for Large Scale Storage Systems
+Alberto Miranda et al.
+http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.226.5609
+                                                  (short version, HIPC'11)
+
+Random Slicing: Efficient and Scalable Data Placement for Large-Scale
+    Storage Systems 
+Alberto Miranda et al.
+DOI: http://dx.doi.org/10.1145/2632230 (long version, ACM Transactions
+                              on Storage, Vol. 10, No. 3, Article 9, 2014)
+
+[[http://hibari.github.io/hibari-doc/hibari-sysadmin-guide.en.html#chain-migration][Hibari Sysadmin Guide, chain migration section]].
+http://hibari.github.io/hibari-doc/hibari-sysadmin-guide.en.html#chain-migration
+#+END_QUOTE
+
+* 3. A simple illustration
+
+We use a variation of the Random Slicing hash that we will call
+~rs_hash_with_float()~.  The Erlang-style function type is shown
+below.
+
+#+BEGIN_SRC erlang
+%% type specs, Erlang-style
+-spec rs_hash_with_float(float(), rs_hash:map()) -> rs_hash:chain_id().
+#+END_SRC
+
+I'm borrowing an illustration from the HibariDB documentation here,
+but it fits my purposes quite well.  (I am the original creator of that
+image, and also the use license is compatible.)
+
+#+CAPTION: Illustration of 'Map', using four Machi chains
+
+[[./migration-4.png]]
+
+Assume that we have a random slicing map called ~Map~.  This particular
+~Map~ maps the unit interval onto 4 Machi chains:
+
+| Hash range  | Chain ID |
+|-------------+----------|
+| 0.00 - 0.25 | Chain1   |
+| 0.25 - 0.33 | Chain4   |
+| 0.33 - 0.58 | Chain2   |
+| 0.58 - 0.66 | Chain4   |
+| 0.66 - 0.91 | Chain3   |
+| 0.91 - 1.00 | Chain4   |
+
+Assume that the system chooses a cluster locator of 0.05.
+According to ~Map~, the value of
+~rs_hash_with_float(0.05,Map) = Chain1~.
+Similarly, ~rs_hash_with_float(0.26,Map) = Chain4~.
+
+This example should look very similar to Hibari's technique.
+The Hibari documentation has a brief photo illustration of how random
+slicing works, see [[http://hibari.github.io/hibari-doc/hibari-sysadmin-guide.en.html#chain-migration][Hibari Sysadmin Guide, chain migration]].
+
+* 4. Use of the cluster namespace: name separation plus chain type
+
+Let us assume that the cluster framework provides several different types
+of chains:
+
+| Chain length | Namespace    | Consistency Mode | Comment                          |
+|--------------+--------------+------------------+----------------------------------|
+|            3 | ~normal~     | eventual         | Normal storage redundancy & cost |
+|            2 | ~reduced~    | eventual         | Reduced cost storage             |
+|            1 | ~risky~      | eventual         | Really, really cheap storage     |
+|            7 | ~paranoid~   | eventual         | Safety-critical storage          |
+|            3 | ~sequential~ | strong           | Strong consistency               |
+|--------------+--------------+------------------+----------------------------------|
+
+The client may want to choose the amount of redundancy that its
+application requires: normal, reduced cost, or perhaps even a single
+copy.  The cluster namespace is used by the client to signal this
+intention.
+
+Further, the cluster administrators may wish to use the namespace to
+provide separate storage for different applications.  Jane's
+application may use the namespace "jane-normal" and Bob's app uses
+"bob-reduced".  Administrators may definine separate groups of
+chains on separate servers to serve these two applications.
+
+* 5. In its lifetime, a file may be moved to different chains
+
+The cluster management scheme may decide that files need to migrate to
+other chains -- i.e., file that is initially created on chain ID ~X~
+has been moved to chain ID ~Y~.
+
++ For storage load or I/O load balancing reasons.
++ Because a chain is being decommissioned by the sysadmin.
+
+* 6. Floating point is not required ... it is merely convenient for explanation
+
+NOTE: Use of floating point terms is not required.  For example,
+integer arithmetic could be used, if using a sufficiently large
+interval to create an even & smooth distribution of hashes across the
+expected maximum number of chains.
+
+For example, if the maximum cluster size would be 4,000 individual
+Machi chains, then a minimum of 12 bits of integer space is required
+to assign one integer per Machi chain.  However, for load balancing
+purposes, a finer grain of (for example) 100 integers per Machi
+chain would permit file migration to move increments of
+approximately 1% of single Machi chain's storage capacity.  A
+minimum of 12+7=19 bits of hash space would be necessary to accommodate
+these constraints.
+
+It is likely that Machi's final implementation will choose a 24 bit
+integer (or perhaps 32 bits) to represent the cluster locator.
+
+* 7. Proposal: Break the opacity of Machi file names, slightly.
+
+Machi assigns file names based on:
+
+~ClientSuppliedPrefix ++ "^" ++ SomeOpaqueFileNameSuffix~
+
+What if some parts of the system could peek inside of the opaque file name
+suffix in order to look at the cluster location information that we might
+code in the filename suffix?
+
+We break the system into parts that speak two levels of protocols,
+"high" and "low".
+
++ The high level protocol is used outside of the Machi cluster
++ The low level protocol is used inside of the Machi cluster
+
+Both protocols are based on a Protocol Buffers specification and
+implementation.  Other protocols, such as HTTP, will be added later.
+
+#+BEGIN_SRC
+     +-----------------------+
+     | Machi external client |
+     | e.g. Riak CS          |
+     +-----------------------+
+          ^
+          | Machi "high" API
+          | ProtoBuffs protocol     Machi cluster boundary: outside
+.........................................................................
+          |                         Machi cluster boundary: inside
+          v
+     +--------------------------+    +------------------------+
+     | Machi "high" API service |    | Machi HTTP API service |
+     +--------------------------+    +------------------------+
+          ^                                       |
+          |              +------------------------+
+          v              v
+     +------------------------+
+     | Cluster bridge service |
+     +------------------------+
+          ^
+          | Machi "low" API
+          | ProtoBuffs protocol                                             
+          +----------------------------------------+----+----+
+          |                                        |    |    |  
+          v                                        v    v    v  
+       +-------------------------+              ... other chains...
+       | Chain C1 (logical view) |
+       |  +--------------+       |  
+       |  | FLU server 1 |       |  
+       |  |  +--------------+    |  
+       |  +--| FLU server 2 |    |  
+       |     +--------------+    |  In reality, API bridge talks directly
+       +-------------------------+  to each FLU server in a chain.       
+#+END_SRC
+
+** The notation we use
+
+- ~N~   = the cluster namespace, chosen by the client.
+- ~p~   = file prefix, chosen by the client.
+- ~L~   = the cluster locator (a number, type is implementation-dependent)
+- ~Map~ = a mapping of cluster locators to chains
+- ~T~   = the target chain ID/name
+- ~u~   = a unique opaque file name suffix, e.g. a GUID string
+- ~F~   = a Machi file name, i.e., a concatenation of ~p^L^N^u~
+
+** The details: cluster file append
+
+0. Cluster client chooses ~N~ and ~p~ (i.e., cluster namespace and
+   file prefix) and sends the append request to a Machi cluster member
+   via the Protocol Buffers "high" API.
+1. Cluster bridge chooses ~T~ (i.e., target chain), based on criteria
+   such as disk utilization percentage.
+2. Cluster bridge knows the cluster ~Map~ for namespace ~N~.
+3. Cluster bridge choose some cluster locator value ~L~ such that
+   ~rs_hash_with_float(L,Map) = T~ (see algorithm below).
+4. Cluster bridge sends its request to chain
+   ~T~: ~append_chunk(p,L,N,...) -> {ok,p^L^N^u,ByteOffset}~
+5. Cluster bridge forwards the reply tuple to the client.
+6. Client stores/uses the file name ~F = p^L^N^u~.
+
+** The details: Cluster file read
+
+0. Cluster client sends the read request to a Machi cluster member via
+   the Protocol Buffers "high" API.
+1. Cluster bridge parses the file name ~F~  to find
+   the values of ~L~ and ~N~ (recall, ~F = p^L^N^u~).
+2. Cluster bridge knows the Cluster ~Map~ for type ~N~.
+3. Cluster bridge calculates ~rs_hash_with_float(L,Map) = T~
+4. Cluster bridge sends request to chain ~T~:
+   ~read_chunk(F,...) ->~ ... reply
+5. Cluster bridge forwards the reply to the client.
+
+** The details: calculating 'L' (the cluster locator number) to match a desired target chain
+
+1. We know ~Map~, the current cluster mapping for a cluster namespace ~N~.
+2. We look inside of ~Map~, and we find all of the unit interval ranges
+   that map to our desired target chain ~T~.  Let's call this list
+   ~MapList = [Range1=(start,end],Range2=(start,end],...]~.
+3. In our example, ~T=Chain2~.  The example ~Map~ contains a single
+   unit interval range for ~Chain2~, ~[(0.33,0.58]]~.
+4. Choose a uniformly random number ~r~ on the unit interval.
+5. Calculate the cluster locator ~L~ by mapping ~r~ onto the concatenation
+   of the cluster hash space range intervals in ~MapList~.  For example,
+   if ~r=0.5~, then ~L = 0.33 + 0.5*(0.58-0.33) = 0.455~, which is
+   exactly in the middle of the ~(0.33,0.58]~ interval.
+
+** A bit more about the cluster namespaces's meaning and use
+
+For use by Riak CS, for example, we'd likely start with the following
+namespaces ... working our way down the list as we add new features
+and/or re-implement existing CS features.
+
+- "standard" = Chain length = 3, eventually consistency mode
+- "reduced" = Chain length = 2, eventually consistency mode.
+- "stanchion7" = Chain length = 7, strong consistency mode.  Perhaps
+  use this namespace for the metadata required to re-implement the
+  operations that are performed by today's Stanchion application.
+
+We want the cluster framework to:
+
+- provide means of creating and managing
+  chains of different types, e.g., chain length, consistency mode.
+- manage the mapping of cluster namespace
+  names to the chains in the system.
+- provide query functions to map a cluster
+  namespace name to a cluster map,
+  e.g. ~get_cluster_latest_map("reduced") -> Map{generation=7,...}~.
+
+* 8. File migration (a.k.a. rebalancing/reparitioning/resharding/redistribution)
+
+** What is "migration"?
+
+This section describes Machi's file migration.  Other storage systems
+call this process as "rebalancing", "repartitioning", "resharding" or
+"redistribution".
+For Riak Core applications, it is called "handoff" and "ring resizing"
+(depending on the context).
+See also the [[http://hadoop.apache.org/docs/current/hadoop-project-dist/hadoop-hdfs/HdfsUserGuide.html#Balancer][Hadoop file balancer]] for another example of a data
+migration process.
+
+As discussed in section 5, the client can have good reason for wanting
+to have some control of the initial location of the file within the
+chain.  However, the chain manager has an ongoing interest in
+balancing resources throughout the lifetime of the file.  Disks will
+get full, hardware will change, read workload will fluctuate,
+etc etc.
+
+This document uses the word "migration" to describe moving data from
+one Machi chain to another chain within a cluster system.
+
+A simple variation of the Random Slicing hash algorithm can easily
+accommodate Machi's need to migrate files without interfering with
+availability.  Machi's migration task is much simpler due to the
+immutable nature of Machi file data.
+
+** Change to Random Slicing
+
+The map used by the Random Slicing hash algorithm needs a few simple
+changes to make file migration straightforward.
+
+- Add a "generation number", a strictly increasing number (similar to
+  a Machi chain's "epoch number") that reflects the history of
+  changes made to the Random Slicing map
+- Use a list of Random Slicing maps instead of a single map, one map
+  per chance that files may not have been migrated yet out of
+  that map.
+
+As an example:
+
+#+CAPTION: Illustration of 'Map', using four Machi chains
+
+[[./migration-3to4.png]]
+
+And the new Random Slicing map for some cluster namespace ~N~ might look
+like this:
+
+| Generation number / Namespace | 7 / reduced |
+|-------------------------------+-------------|
+| SubMap                        | 1           |
+|-------------------------------+-------------|
+| Hash range                    | Chain ID    |
+|-------------------------------+-------------|
+| 0.00 - 0.33                   | Chain1      |
+| 0.33 - 0.66                   | Chain2      |
+| 0.66 - 1.00                   | Chain3      |
+|-------------------------------+-------------|
+| SubMap                        | 2           |
+|-------------------------------+-------------|
+| Hash range                    | Chain ID    |
+|-------------------------------+-------------|
+| 0.00 - 0.25                   | Chain1      |
+| 0.25 - 0.33                   | Chain4      |
+| 0.33 - 0.58                   | Chain2      |
+| 0.58 - 0.66                   | Chain4      |
+| 0.66 - 0.91                   | Chain3      |
+| 0.91 - 1.00                   | Chain4      |
+
+When a new Random Slicing map contains a single submap, then its use
+is identical to the original Random Slicing algorithm.  If the map
+contains multiple submaps, then the access rules change a bit:
+
+- Write operations always go to the newest/largest submap.
+- Read operations attempt to read from all unique submaps.
+  - Skip searching submaps that refer to the same chain ID.
+    - In this example, unit interval value 0.10 is mapped to Chain1
+      by both submaps.
+  - Read from newest/largest submap to oldest/smallest submap.
+  - If not found in any submap, search a second time (to handle races
+    with file copying between submaps).
+  - If the requested data is found, optionally copy it directly to the
+    newest submap.   (This is a variation of read repair (RR). RR here
+    accelerates the migration process and can reduce the number of
+    operations required to query servers in multiple submaps).
+
+The cluster manager is responsible for:
+
+- Managing the various generations of the cluster Random Slicing maps for
+  all namespaces.
+- Distributing namespace maps to cluster bridges.
+- Managing the processes that are responsible for copying "cold" data,
+  i.e., files data that is not regularly accessed, to its new submap
+  location.
+- When migration of a file to its new chain is confirmed successful,
+  delete it from the old chain.
+
+In example map #7, the cluster manager will copy files with unit interval
+assignments in ~(0.25,0.33]~, ~(0.58,0.66]~, and ~(0.91,1.00]~ from their
+old locations in chain IDs Chain1/2/3 to their new chain,
+Chain4.  When the cluster manager is satisfied that all such files have
+been copied to Chain4, then the cluster manager can create and
+distribute a new map, such as:
+
+| Generation number / Namespace | 8 / reduced |
+|-------------------------------+-------------|
+| SubMap                        | 1           |
+|-------------------------------+-------------|
+| Hash range                    | Chain ID    |
+|-------------------------------+-------------|
+| 0.00 - 0.25                   | Chain1      |
+| 0.25 - 0.33                   | Chain4      |
+| 0.33 - 0.58                   | Chain2      |
+| 0.58 - 0.66                   | Chain4      |
+| 0.66 - 0.91                   | Chain3      |
+| 0.91 - 1.00                   | Chain4      |
+
+The HibariDB system performs data migrations in almost exactly this
+manner.  However, one important
+limitation of HibariDB is not being able to
+perform more than one migration at a time.  HibariDB's data is
+mutable.  Mutation causes many problems when migrating data
+across two submaps; three or more submaps was too complex to implement
+quickly and correctly.
+
+Fortunately for Machi, its file data is immutable and therefore can
+easily manage many migrations in parallel, i.e., its submap list may
+be several maps long, each one for an in-progress file migration.
+
+* 9. Other considerations for FLU/sequencer implementations
+
+** Append to existing file when possible
+
+The sequencer should always assign new offsets to the latest/newest
+file for any prefix, as long as all prerequisites are also true,
+
+- The epoch has not changed.  (In AP mode, epoch change -> mandatory
+  file name suffix change.)
+- The cluster locator number is stable.
+- The latest file for prefix ~p~ is smaller than maximum file size for
+  a FLU's configuration.
+
+The stability of the cluster locator number is an implementation detail that
+must be managed by the cluster bridge.
+
+Reuse of the same file is not possible if the bridge always chooses a
+different cluster locator number ~L~ or if the client always uses a unique
+file prefix ~p~.  The latter is a sign of a misbehaved client; the
+former is a poorly-implemented bridge.
+
+* 10. Acknowledgments
+
+The original source for the "migration-4.png" and "migration-3to4.png" images
+come from the [[http://hibari.github.io/hibari-doc/images/migration-3to4.png][HibariDB documentation]].
+

doc/dev-clone-compile.md

@@ -0,0 +1,30 @@
+# Clone and compile Machi
+
+Clone the Machi source repo and compile the source and test code.  Run
+the following commands at your login shell:
+
+    cd /tmp
+    git clone https://github.com/basho/machi.git
+    cd machi
+    git checkout master
+    make          # or 'gmake' if GNU make uses an alternate name
+
+Then run the unit test suite.  This may take up to two minutes or so
+to finish.
+
+    make test
+
+At the end, the test suite should report that all tests passed.  The
+actual number of tests shown in the "All `X` tests passed" line may be
+different than the example below.
+
+    [... many lines omitted ...]
+    module 'event_logger'
+    module 'chain_mgr_legacy'
+    =======================================================
+      All 90 tests passed.
+
+If you had a test failure, a likely cause may be a limit on the number
+of file descriptors available to your user process.  (Recent releases
+of OS X have a limit of 1024 file descriptors, which may be too slow.)
+The output of the `limit -n` will tell you your file descriptor limit.

doc/dev-prerequisites.md

@@ -0,0 +1,38 @@
+## Machi developer environment prerequisites
+
+1. Machi requires an 64-bit variant of UNIX: OS X, FreeBSD, Linux, or
+   Solaris machine is a standard developer environment for C and C++
+   applications (64-bit versions).
+2. You'll need the `git` source management utility.
+3. You'll need the 64-bit Erlang/OTP 17 runtime environment.  Please
+   don't use earlier or later versions until we have a chance to fix
+   the compilation warnings that versions R16B and 18 will trigger.
+   Also, please verify that you are not using a 32-bit Erlang/OTP
+   runtime package.
+
+For `git` and the Erlang runtime, please use your OS-specific
+package manager to install these.  If your package manager doesn't
+have 64-bit Erlang/OTP version 17 available, then we recommend using the
+[precompiled packages available at Erlang Solutions](https://www.erlang-solutions.com/resources/download.html).
+
+Also, please verify that you have enough file descriptors available to
+your user processes.  The output of `ulimit -n` should report at least
+4,000 file descriptors available.  If your limit is lower (a frequent
+problem for OS X users), please increase it to at least 4,000.
+
+# Using Vagrant to set up a developer environment for Machi
+
+The Machi source directory contains a `Vagrantfile` for creating an
+Ubuntu Linux-based virtual machine for compiling and running Machi.
+This file is in the
+[$SRC_TOP/priv/humming-consensus-demo.vagrant](../priv/humming-consensus-demo.vagrant)
+directory.
+
+If used as-is, the virtual machine specification is modest.
+
+* 1 virtual CPU
+* 512MB virtual memory
+* 768MB swap space
+* 79GB sparse virtual disk image.  After installing prerequisites and
+  compiling Machi, the root file system uses approximately 2.7 GBytes.
+

doc/flu-and-chain-lifecycle.org

@@ -0,0 +1,617 @@
+FLU and Chain Life Cycle Management -*- mode: org; -*-
+#+STARTUP: lognotedone hidestars indent showall inlineimages
+#+COMMENT: To generate the outline section: egrep '^\*[*]* ' doc/flu-and-chain-lifecycle.org | egrep -v '^\* Outline' | sed -e 's/^\*\*\* /    + /' -e 's/^\*\* /  + /' -e 's/^\* /+ /'
+
+* FLU and Chain Life Cycle Management
+
+In an ideal world, we (the Machi development team) would have a full
+vision of how Machi would be managed, down to the last detail of
+beautiful CLI character and network protocol bit.  Our vision isn't
+complete yet, so we are working one small step at a time.
+
+* Outline
+
++ FLU and Chain Life Cycle Management
++ Terminology review
+  + Terminology: Machi run-time components/services/thingies
+  + Terminology: Machi chain data structures
+  + Terminology: Machi cluster data structures
++ Overview of administrative life cycles
+  + Cluster administrative life cycle
+  + Chain administrative life cycle
+  + FLU server administrative life cycle
++ Quick admin: declarative management of Machi FLU and chain life cycles
+  + Quick admin uses the "rc.d" config scheme for life cycle management
+  + Quick admin's declarative "language": an Erlang-flavored AST
+    + Term 'host': define a new host for FLU services
+    + Term 'flu': define a new FLU
+    + Term 'chain': define or reconfigure a chain
+  + Executing quick admin AST files via the 'machi-admin' utility
+    + Checking the syntax of an AST file
+    + Executing an AST file
+  + Using quick admin to manage multiple machines
++ The "rc.d" style configuration file scheme
+  + Riak had a similar configuration file editing problem (and its solution)
+  + Machi's "rc.d" file scheme.
+  + FLU life cycle management using "rc.d" style files
+    + The key configuration components of a FLU
+  + Chain life cycle management using "rc.d" style files
+    + The key configuration components of a chain
+
+* Terminology review
+
+** Terminology: Machi run-time components/services/thingies
+
++ FLU: a basic Machi server, responsible for managing a collection of
+  files.
+
++ Chain: a small collection of FLUs that maintain replicas of the same
+  collection of files.  A chain is usually small, 1-3 servers, where
+  more than 3 would be used only in cases when availability of
+  certain data is critical despite failures of several machines.
+  + The length of a chain is directly proportional to its
+    replication factor, e.g., a chain length=3 will maintain
+    (nominally) 3 replicas of each file.
+  + To maintain file availability when ~F~ failures have occurred, a
+    chain must be at least ~F+1~ members long.  (In comparison, the
+    quorum replication technique requires ~2F+1~ members in the
+    general case.)
+
++ Cluster: A collection of Machi chains that are used to store files
+  in a horizontally partitioned/sharded/distributed manner.
+
+** Terminology: Machi data structures
+
++ Projection: used to define a single chain: the chain's consistency
+  mode (strong or eventual consistency), all members (from an
+  administrative point of view), all active members (from a runtime,
+  automatically-managed point of view), repairing/file-syncing members
+  (also runtime, auto-managed), and so on
+
++ Epoch: A version number of a projection.  The epoch number is used
+  by both clients & servers to manage transitions from one projection
+  to another, e.g., when the chain is temporarily shortened by the
+  failure of a member FLU server.
+
+** Terminology: Machi cluster data structures
+
++ Namespace: A collection of human-friendly names that are mapped to
+  groups of Machi chains that provide the same type of storage
+  service: consistency mode, replication policy, etc.
+  + A single namespace name, e.g. ~normal-ec~, is paired with a single
+    cluster map (see below).
+  + Example: ~normal-ec~ might be a collection of Machi chains in
+    eventually-consistent mode that are of length=3.
+  + Example: ~risky-ec~ might be a collection of Machi chains in
+    eventually-consistent mode that are of length=1.
+  + Example: ~mgmt-critical~ might be a collection of Machi chains in
+    strongly-consistent mode that are of length=7.
+
++ Cluster map: Encodes the rules which partition/shard/distribute
+  the files stored in a particular namespace across a group of chains
+  that collectively store the namespace's files.
+
++ Chain weight: A value assigned to each chain within a cluster map
+  structure that defines the relative storage capacity of a chain
+  within the namespace.  For example, a chain weight=150 has 50% more
+  capacity than a chain weight=100.
+
++ Cluster map epoch: The version number assigned to a cluster map.
+
+* Overview of administrative life cycles
+
+** Cluster administrative life cycle
+
++ Cluster is first created
++ Adds namespaces (e.g. consistency policy + chain length policy) to
+  the cluster
++ Chains are added to/removed from a namespace to increase/decrease the
+  namespace's storage capacity.
++ Adjust chain weights within a namespace, e.g., to shift files
+  within the namespace to chains with greater storage capacity
+  resources and/or runtime I/O resources.
+
+A cluster "file migration" is the process of moving files from one
+namespace member chain to another for purposes of shifting &
+re-balancing storage capacity and/or runtime I/O capacity.
+
+** Chain administrative life cycle
+
++ A chain is created with an initial FLU membership list.
++ Chain may be administratively modified zero or more times to
+  add/remove member FLU servers.
++ A chain may be decommissioned.
+
+See also: http://basho.github.io/machi/edoc/machi_lifecycle_mgr.html
+
+** FLU server administrative life cycle
+
++ A FLU is created after an administrator chooses the FLU's runtime
+  location is selected by the administrator: which machine/virtual
+  machine, IP address and TCP port allocation, etc.
++ An unassigned FLU may be added to a chain by chain administrative
+  policy.
++ A FLU that is assigned to a chain may be removed from that chain by
+  chain administrative policy.
+  + In the current implementation, the FLU's Erlang processes will be
+    halted.  Then the FLU's data and metadata files will be moved to
+    another area of the disk for safekeeping.  Later, a "garbage
+    collection" process can be used for reclaiming disk space used by
+    halted FLU servers.
+
+See also: http://basho.github.io/machi/edoc/machi_lifecycle_mgr.html
+
+* Quick admin: declarative management of Machi FLU and chain life cycles
+
+The "quick admin" scheme is a temporary (?) tool for managing Machi
+FLU server and chain life cycles in a declarative manner.  The API is
+described in this section.
+
+** Quick admin uses the "rc.d" config scheme for life cycle management
+
+As described at the top of
+http://basho.github.io/machi/edoc/machi_lifecycle_mgr.html, the "rc.d"
+config files do not manage "policy".  "Policy" is doing the right
+thing with a Machi cluster from a systems administrator's
+point of view.  The "rc.d" config files can only implement decisions
+made according to policy.
+
+The "quick admin" tool is a first attempt at automating policy
+decisions in a safe way (we hope) that is also easy to implement (we
+hope) with a variety of systems management tools, e.g. Chef, Puppet,
+Ansible, Saltstack, or plain-old-human-at-a-keyboard.
+
+** Quick admin's declarative "language": an Erlang-flavored AST
+
+The "language" that an administrator uses to express desired policy
+changes is not (yet) a true language.  As a quick implementation hack,
+the current language is an Erlang-flavored abstract syntax tree
+(AST).  The tree isn't very deep, either, frequently just one
+element tall.  (Not much of a tree, is it?)
+
+There are three terms in the language currently:
+
++ ~host~, define a new host that can execute FLU servers
++ ~flu~, define a new FLU
++ ~chain~, define a new chain or re-configure an existing chain with
+  the same name
+
+*** Term 'host': define a new host for FLU services
+
+In this context, a host is a machine, virtual machine, or container
+that can execute the Machi application and can therefore provide FLU
+services, i.e. file service, Humming Consensus management.
+
+Two formats may be used to define a new host:
+
+#+BEGIN_SRC
+{host, Name, Props}.
+{host, Name, AdminI, ClientI, Props}.
+#+END_SRC
+
+The shorter tuple is shorthand notation for the latter.  If the
+shorthand form is used, then it will be converted automatically to the
+long form as:
+
+#+BEGIN_SRC
+{host, Name, AdminI=Name, ClientI=Name, Props}.
+#+END_SRC
+
+Type information, description, and restrictions:
+
++ ~Name::string()~ The ~Name~ attribute must be unique.  Note that it
+  is possible to define two different hosts, one using a DNS hostname
+  and one using an IP address.  The user must avoid this
+  double-definition because it is not enforced by quick admin.
+  + The ~Name~ field is used for cross-reference purposes with other
+    terms, e.g., ~flu~ and ~chain~.
+  + There is no syntax yet for removing a host definition.
+
++ ~AdminI::string()~ A DNS hostname or IP address for cluster
+  administration purposes, e.g. SSH access.
+  + This field is unused at the present time.
+
++ ~ClientI::string()~ A DNS hostname or IP address for Machi's client
+  protocol access, e.g., Protocol Buffers network API service.
+  + This field is unused at the present time.
+
++ ~props::proplist()~ is an Erlang-style property list for specifying
+  additional configuration options, debugging information, sysadmin
+  comments, etc.
+
++ A full-featured admin tool should also include managing several
+  other aspects of configuration related to a "host".  For example,
+  for any single IP address, quick admin assumes that there will be
+  exactly one Erlang VM that is running the Machi application.  Of
+  course, it is possible to have dozens of Erlang VMs on the same
+  (let's assume for clarity) hardware machine and all running Machi
+  ... but there are additional aspects of such a machine that quick
+  admin does not account for
+  + multiple IP addresses per machine
+  + multiple Machi package installation paths
+  + multiple Machi config files (e.g. cuttlefish config, ~etc.conf~,
+    ~vm.args~)
+  + multiple data directories/file system mount points
+    + This is also a management problem for quick admin for a single
+      Machi package on a machine to take advantage of bulk data
+      storage using multiple multiple file system mount points.
+  + multiple Erlang VM host names, required for distributed Erlang,
+    which is used for communication with ~machi~ and ~machi-admin~
+    command line utilities.
+  + and others....
+
+*** Term 'flu': define a new FLU
+
+A new FLU is defined relative to a previously-defined ~host~ entities;
+an exception will be thrown if the ~host~ cannot be cross-referenced.
+
+#+BEGIN_SRC
+{flu, Name, HostName, Port, Props}
+#+END_SRC
+
+Type information, description, and restrictions:
+
++ ~Name::atom()~ The name of the FLU, as a human-friendly name and
+  also for internal management use; please note the ~atom()~ type.
+  This name must be unique.
+  + The ~Name~ field is used for cross-reference purposes with the
+    ~chain~ term.
+  + There is no syntax yet for removing a FLU definition.
+
++ ~Hostname::string()~ The cross-reference name of the ~host~ that
+  this FLU should run on.
+
++ ~Port::non_neg_integer()~ The TCP port used by this FLU server's
+  Protocol Buffers network API listener service
+
++ ~props::proplist()~ is an Erlang-style property list for specifying
+  additional configuration options, debugging information, sysadmin
+  comments, etc.
+
+*** Term 'chain': define or reconfigure a chain
+
+A chain is defined relative to zero or more previously-defined ~flu~
+entities; an exception will be thrown if any ~flu~ cannot be
+cross-referenced.
+
+Two formats may be used to define/reconfigure a chain:
+
+#+BEGIN_SRC
+{chain, Name, FullList, Props}.
+{chain, Name, CMode, FullList, Witnesses, Props}.
+#+END_SRC
+
+The shorter tuple is shorthand notation for the latter.  If the
+shorthand form is used, then it will be converted automatically to the
+long form as:
+
+#+BEGIN_SRC
+{chain, Name, ap_mode, FullList, [], Props}.
+#+END_SRC
+
+Type information, description, and restrictions:
+
++ ~Name::atom()~ The name of the chain, as a human-friendly name and
+  also for internal management use; please note the ~atom()~ type.
+  This name must be unique.
+  + There is no syntax yet for removing a chain definition.
+
++ ~CMode::'ap_mode'|'cp_mode'~ Defines the consistency mode of the
+  chain, either eventual consistency or strong consistency,
+  respectively.
+  + A chain cannot change consistency mode, e.g., from
+    strong~->~eventual consistency.
+
++ ~FullList::list(atom())~ Specifies the list of full-service FLU
+  servers, i.e. servers that provide file data & metadata services as
+  well as Humming Consensus.  Each atom in the list must
+  cross-reference with a previously defined ~chain~; an exception will
+  be thrown if any ~flu~ cannot be cross-referenced.
+
++ ~Witnesses::list(atom())~ Specifies the list of witness-only
+  servers, i.e. servers that only participate in Humming Consensus.
+  Each atom in the list must cross-reference with a previously defined
+  ~chain~; an exception will be thrown if any ~flu~ cannot be
+  cross-referenced.
+  + This list must be empty for eventual consistency chains.
+
++ ~props::proplist()~ is an Erlang-style property list for specifying
+  additional configuration options, debugging information, sysadmin
+  comments, etc.
+
++ If this term specifies a new ~chain~ name, then all of the member
+  FLU servers (full & witness types) will be bootstrapped to a
+  starting configuration.
+
++ If this term specifies a previously-defined ~chain~ name, then all
+  of the member FLU servers (full & witness types, respectively) will
+  be adjusted to add or remove members, as appropriate.
+  + Any FLU servers added to either list must not be assigned to any
+    other chain, or they must be a member of this specific chain.
+  + Any FLU servers removed from either list will be halted.
+    (See the "FLU server administrative life cycle" section above.)
+
+** Executing quick admin AST files via the 'machi-admin' utility
+
+Examples of quick admin AST files can be found in the
+~priv/quick-admin/examples~ directory.  Below is an example that will
+define a new host ( ~"localhost"~ ), three new FLU servers ( ~f1~ & ~f2~
+and ~f3~ ), and an eventually consistent chain ( ~c1~ ) that uses the new
+FLU servers:
+
+#+BEGIN_SRC
+{host, "localhost", []}.
+{flu,f1,"localhost",20401,[]}.
+{flu,f2,"localhost",20402,[]}.
+{flu,f3,"localhost",20403,[]}.
+{chain,c1,[f1,f2,f3],[]}.
+#+END_SRC
+
+*** Checking the syntax of an AST file
+
+Given an AST config file, ~/path/to/ast/file~, its basic syntax and
+correctness can be checked without executing it.
+
+#+BEGIN_SRC
+./rel/machi/bin/machi-admin quick-admin-check /path/to/ast/file
+#+END_SRC
+
++ The utility will exit with status zero and output ~ok~ if the syntax
+  and proposed configuration appears to be correct.
++ If there is an error, the utility will exit with status one, and an
+  error message will be printed.
+
+*** Executing an AST file
+
+Given an AST config file, ~/path/to/ast/file~, it can be executed
+using the command:
+
+#+BEGIN_SRC
+./rel/machi/bin/machi-admin quick-admin-apply /path/to/ast/file RelativeHost
+#+END_SRC
+
+... where the last argument, ~RelativeHost~, should be the exact
+spelling of one of the previously defined AST ~host~ entities,
+*and also* is the same host that the ~machi-admin~ utility is being
+executed on.
+
+Restrictions and warnings:
+
++ This is alpha quality software.
+
++ There is no "undo".
+  + Of course there is, but you need to resort to doing things like
+    using ~machi attach~ to attach to the server's CLI to then execute
+    magic Erlang incantations to stop FLUs, unconfigure chains, etc.
+    + Oh, and delete some files with magic paths, also.
+
+** Using quick admin to manage multiple machines
+
+A quick sketch follows:
+
+1. Create the AST file to specify all of the changes that you wish to
+   make to all hosts, FLUs, and/or chains, e.g., ~/tmp/ast.txt~.
+2. Check the basic syntax with the ~quick-admin-check~ argument to
+   ~machi-admin~. 
+3. If the syntax is good, then copy ~/tmp/ast.txt~ to all hosts in the
+   cluster, using the same path, ~/tmp/ast.txt~.
+4. For each machine in the cluster, run:
+#+BEGIN_SRC
+./rel/machi/bin/machi-admin quick-admin-apply /tmp/ast.txt RelativeHost
+#+END_SRC
+
+... where RelativeHost is the AST ~host~ name of the machine that you
+are executing the ~machi-admin~ command on.  The command should be
+successful, with exit status 0 and outputting the string ~ok~.
+
+Finally, for each machine in the cluster, a listing of all files in
+the directory ~rel/machi/etc/quick-admin-archive~ should show exactly
+the same files, one for each time that ~quick-admin-apply~ has been
+run successfully on that machine.
+
+* The "rc.d" style configuration file scheme
+
+This configuration scheme is inspired by BSD UNIX's ~init(8)~ process
+manager's configuration style, called "rc.d" after the name of the
+directory where these files are stored, ~/etc/rc.d~.  The ~init~
+process is responsible for (among other things) starting UNIX
+processes at machine boot time and stopping them when the machine is
+shut down.
+
+The original scheme used by ~init~ to start processes at boot time was
+a single Bourne shell script called ~/etc/rc~.  When a new software
+package was installed that required a daemon to be started at boot
+time, text was added to the ~/etc/rc~ file.  Uninstalling packages was
+much trickier, because it meant removing lines from a file that
+*is a computer program (run by the Bourne shell, a Turing-complete
+programming language)*.  Error-free editing of the ~/etc/rc~ script
+was impossible in all cases.
+
+Later, ~init~'s configuration was split into a few master Bourne shell
+scripts and a subdirectory, ~/etc/rc.d~.  The subdirectory contained
+shell scripts that were responsible for boot time starting of a single
+daemon or service, e.g. NFS or an HTTP server.  When a new software
+package was added, a new file was added to the ~rc.d~ subdirectory.
+When a package was removed, the corresponding file in ~rc.d~ was
+removed.  With this simple scheme, addition & removal of boot time
+scripts was vastly simplified.
+
+** Riak had a similar configuration file editing problem (and its solution)
+
+Another software product from Basho Technologies, Riak, had a similar
+configuration file editing problem.  One file in particular,
+~app.config~, had a syntax that made it difficult both for human
+systems administrators and also computer programs to edit the file in
+a syntactically correct manner.
+
+Later releases of Riak switched to an alternative configuration file
+format, one inspired by the BSD UNIX ~sysctl(8)~ utility and
+~sysctl.conf(5)~ file syntax.  The ~sysctl.conf~ format is much easier
+to manage by computer programs to add items.  Removing items is not
+100% simple, however: the correct lines must be identified and then
+removed (e.g. with Perl or a text editor or combination of ~grep -v~
+and ~mv~), but removing any comment lines that "belong" to the removed
+config item(s) is not any easy for a 1-line shell script to do 100%
+correctly.
+
+Machi will use the ~sysctl.conf~ style configuration for some
+application configuration variables.  However, adding & removing FLUs
+and chains will be managed using the "rc.d" style because of the
+"rc.d" scheme's simplicity and tolerance of mistakes by administrators
+(human or computer).
+
+** Machi's "rc.d" file scheme.
+
+Machi will use a single subdirectory that will contain configuration
+files for some life cycle management task, e.g. a single FLU or a
+single chain.
+
+The contents of the file should be a single Erlang term, serialized in
+ASCII form as Erlang source code statement, i.e. a single Erlang term
+~T~ that is formatted by ~io:format("~w.",[T]).~.  This file must be
+parseable by the Erlang function ~file:consult()~.
+
+Later versions of Machi may change the file format to be more familiar
+to administrators who are unaccustomed to Erlang language syntax.
+
+** FLU life cycle management using "rc.d" style files
+
+*** The key configuration components of a FLU
+
+1. The machine (or virtual machine) to run it on.
+2. The Machi software package's artifacts to execute.
+3. The disk device(s) used to store Machi file data & metadata, "rc.d"
+   style config files, etc.
+4. The name, IP address and TCP port assigned to the FLU service.
+5. Its chain assignment.
+
+Notes:
+
++ Items 1-3 are currently outside of the scope of this life cycle
+  document.  We assume that human administrators know how to do these
+  things.
++ Item 4's properties are explicitly managed by a FLU-defining "rc.d"
+  style config file.
++ Item 5 is managed by the chain life cycle management system.
+
+Here is an example of a properly formatted FLU config file:
+
+#+BEGIN_SRC
+{p_srvr,f1,machi_flu1_client,"192.168.72.23",20401,[]}.
+#+END_SRC
+
+... which corresponds to the following Erlang record definition:
+
+#+BEGIN_SRC
+-record(p_srvr, {
+          name            :: atom(),
+          proto_mod = 'machi_flu1_client' :: atom(), % Module name
+          address         :: term(), % Protocol-specific
+          port            :: term(), % Protocol-specific
+          props = []      :: list()  % proplist for other related info
+         }).
+#+END_SRC
+
++ ~name~ is ~f1~.  This is name of the FLU.  This name should be
+  unique over the lifetime of the administrative domain and thus
+  managed by external policy.  This name must be the same as the name
+  of the config file that defines the FLU.
++ ~proto_mod~ is used for internal management purposes and should be
+  considered a mandatory constant.
++ ~address~ is "192.168.72.23".  The DNS hostname or IP address used
+  by other servers to communicate with this FLU. This must be a valid
+  IP address, previously assigned to this machine/VM using the
+  appropriate operating system-specific procedure.
++ ~port~ is TCP port 20401.  The TCP port number that the FLU listens
+  to for incoming Protocol Buffers-serialized communication.  This TCP
+  port must not be in use (now or in the future) by another Machi FLU
+  or any other process running on this machine/VM.
++ ~props~ is an Erlang-style property list for specifying additional
+  configuration options, debugging information, sysadmin comments,
+  etc.
+  
+** Chain life cycle management using "rc.d" style files
+
+Unlike FLUs, chains have a self-management aspect that makes a chain
+life cycle different from a single FLU server.  Machi's chains are
+self-managing, via Humming Consensus; see the
+https://github.com/basho/machi/tree/master/doc/ directory for much
+more detail about Humming Consensus.  After FLUs have received their
+initial chain configuration for Humming Consensus, the FLUs will
+manage the chain (and each other) by themselves.
+
+However, Humming Consensus does not handle three chain management
+problems:
+
+1. Specifying the very first chain configuration,
+2. Altering the membership of the chain (i.e. adding/removing FLUs
+   from the chain),
+3. Stopping the chain permanently.
+
+A chain "rc.d" file will only be used to bootstrap a newly-defined FLU
+server.  It's like a piece of glue information to introduce the new
+FLU to the Humming Consensus group that is managing the chain's
+dynamic state (e.g. which members are up or down).  In all other
+respects, chain config files are ignored by life cycle management code.
+However, to mimic the life cycle of the FLU server's "rc.d" config
+files, a chain "rc.d" files is not deleted until the chain has been
+decommissioned (i.e. defined with length=0).
+
+*** The key configuration components of a chain
+
+1. The name of the chain.
+2. Consistency mode: eventually consistent or strongly consistent.
+3. The membership list of all FLU servers in the chain.
+   + Remember, all servers in a single chain will manage full replicas
+     of the same collection of Machi files.
+4. If the chain is defined to use strongly consistent mode, then a
+   list of "witness servers" may also be defined.  See the
+   [https://github.com/basho/machi/tree/master/doc/] documentation for
+   more information on witness servers.
+   + The witness list must be empty for all chains in eventual
+     consistency mode. 
+
+Here is an example of a properly formatted chain config file:
+
+#+BEGIN_SRC
+{chain_def_v1,c1,ap_mode,
+              [{p_srvr,f1,machi_flu1_client,"localhost",20401,[]},
+               {p_srvr,f2,machi_flu1_client,"localhost",20402,[]},
+               {p_srvr,f3,machi_flu1_client,"localhost",20403,[]}],
+              [],[],[],
+              [f1,f2,f3],
+              [],[]}.
+#+END_SRC
+
+... which corresponds to the following Erlang record definition:
+
+#+BEGIN_SRC
+-record(chain_def_v1, {
+          name            :: atom(),         % chain name
+          mode            :: 'ap_mode' | 'cp_mode',
+          full = []       :: [p_srvr()],
+          witnesses = []  :: [p_srvr()],
+          old_full = []   :: [atom()], % guard against some races
+          old_witnesses=[] :: [atom()], % guard against some races
+          local_run = []  :: [atom()], % must be tailored to each machine!
+          local_stop = [] :: [atom()], % must be tailored to each machine!
+          props = []      :: list()   % proplist for other related info
+         }).
+#+END_SRC
+
++ ~name~ is ~c1~, the name of the chain.  This name should be unique
+  over the lifetime of the administrative domain and thus managed by
+  external policy.  This name must be the same as the name of the
+  config file that defines the chain.
++ ~mode~ is ~ap_mode~, an internal code symbol for eventual
+  consistency mode.
++ ~full~ is a list of Erlang ~#p_srvr{}~ records for full-service
+  members of the chain, i.e., providing Machi file data & metadata
+  storage services.
++ ~witnesses~ is a list of Erlang ~#p_srvr{}~ records for witness-only
+  FLU servers, i.e., providing only Humming Consensus service.
++ The next four fields are used for internal management only.
++ ~props~ is an Erlang-style property list for specifying additional
+  configuration options, debugging information, sysadmin comments,
+  etc.
+

doc/humming-consensus-demo.md

@@ -0,0 +1,372 @@
+
+# Table of contents
+
+* [Hands-on experiments with Machi and Humming Consensus](#hands-on)
+* [Using the network partition simulator and convergence demo test code](#partition-simulator)
+
+<a name="hands-on">
+# Hands-on experiments with Machi and Humming Consensus
+
+## Prerequisites
+
+Please refer to the
+[Machi development environment prerequisites doc](./dev-prerequisites.md)
+for Machi developer environment prerequisites.
+
+If you do not have an Erlang/OTP runtime system available, but you do
+have [the Vagrant virtual machine](https://www.vagrantup.com/) manager
+available, then please refer to the instructions in the prerequisites
+doc for using Vagrant.
+
+<a name="clone-compile">
+## Clone and compile the code
+
+Please see the
+[Machi 'clone and compile' doc](./dev-clone-compile.md)
+for the short list of steps required to fetch the Machi source code
+from GitHub and to compile &amp; test Machi.
+
+## Running three Machi instances on a single machine
+
+All of the commands that should be run at your login shell (e.g. Bash,
+c-shell) can be cut-and-pasted from this document directly to your
+login shell prompt.
+
+Run the following command:
+
+    make stagedevrel
+
+This will create a directory structure like this:
+          
+          |-dev1-|... stand-alone Machi app + subdirectories
+    |-dev-|-dev2-|... stand-alone Machi app + directories
+          |-dev3-|... stand-alone Machi app + directories
+    
+Each of the `dev/dev1`, `dev/dev2`, and `dev/dev3` are stand-alone
+application instances of Machi and can be run independently of each
+other on the same machine.  This demo will use all three.
+
+The lifecycle management utilities for Machi are a bit immature,
+currently.  They assume that each Machi server runs on a host with a
+unique hostname -- there is no flexibility built-in yet to easily run
+multiple Machi instances on the same machine.  To continue with the
+demo, we need to use `sudo` or `su` to obtain superuser privileges to
+edit the `/etc/hosts` file.
+
+Please add the following line to `/etc/hosts`, using this command:
+
+    sudo sh -c 'echo "127.0.0.1 machi1 machi2 machi3" >> /etc/hosts'
+
+Next, we will use a shell script to finish setting up our cluster.  It
+will do the following for us:
+
+* Verify that the new line that was added to `/etc/hosts` is correct.
+* Modify the `etc/app.config` files to configure the Humming Consensus
+  chain manager's actions logged to the `log/console.log` file.
+* Start the three application instances.
+* Verify that the three instances are running correctly.
+* Configure a single chain, with one FLU server per application
+  instance.
+
+Please run this script using this command:
+
+    ./priv/humming-consensus-demo.setup.sh
+
+If the output looks like this (and exits with status zero), then the
+script was successful.
+
+    Step: Verify that the required entries in /etc/hosts are present
+    Step: add a verbose logging option to app.config
+    Step: start three three Machi application instances
+    pong
+    pong
+    pong
+    Step: configure one chain to start a Humming Consensus group with three members
+    Result: ok
+    Result: ok
+    Result: ok
+
+We have now created a single replica chain, called `c1`, that has
+three file servers participating in the chain.  Thanks to the
+hostnames that we added to `/etc/hosts`, all are using the localhost
+network interface.
+
+    | App instance | Pseudo   | FLU name | TCP port |
+    | directory    | Hostname |          |   number |
+    |--------------+----------+----------+----------|
+    | dev1         | machi1   | flu1     |    20401 |
+    | dev2         | machi2   | flu2     |    20402 |
+    | dev3         | machi3   | flu3     |    20403 |
+
+The log files for each application instance can be found in the
+`./dev/devN/log/console.log` file, where the `N` is the instance
+number: 1, 2, or 3.
+
+## Understanding the chain manager's log file output
+
+After running the `./priv/humming-consensus-demo.setup.sh` script,
+let's look at the last few lines of the `./dev/dev1/log/console.log`
+log file for Erlang VM process #1.
+
+    2016-03-09 10:16:35.676 [info] <0.105.0>@machi_lifecycle_mgr:process_pending_flu:422 Started FLU f1 with supervisor pid <0.128.0>
+    2016-03-09 10:16:35.676 [info] <0.105.0>@machi_lifecycle_mgr:move_to_flu_config:540 Creating FLU config file f1
+    2016-03-09 10:16:35.790 [info] <0.105.0>@machi_lifecycle_mgr:bootstrap_chain2:312 Configured chain c1 via FLU f1 to mode=ap_mode all=[f1,f2,f3] witnesses=[]
+    2016-03-09 10:16:35.790 [info] <0.105.0>@machi_lifecycle_mgr:move_to_chain_config:546 Creating chain config file c1
+    2016-03-09 10:16:44.139 [info] <0.132.0> CONFIRM epoch 1141 <<155,42,7,221>> upi [] rep [] auth f1 by f1
+    2016-03-09 10:16:44.271 [info] <0.132.0> CONFIRM epoch 1148 <<57,213,154,16>> upi [f1] rep [] auth f1 by f1
+    2016-03-09 10:16:44.864 [info] <0.132.0> CONFIRM epoch 1151 <<239,29,39,70>> upi [f1] rep [f3] auth f1 by f1
+    2016-03-09 10:16:45.235 [info] <0.132.0> CONFIRM epoch 1152 <<173,17,66,225>> upi [f2] rep [f1,f3] auth f2 by f1
+    2016-03-09 10:16:47.343 [info] <0.132.0> CONFIRM epoch 1154 <<154,231,224,149>> upi [f2,f1,f3] rep [] auth f2 by f1
+
+Let's pick apart some of these lines.  We have started all three
+servers at about the same time.  We see some race conditions happen,
+and some jostling and readjustment happens pretty quickly in the first
+few seconds.
+
+* `Started FLU f1 with supervisor pid <0.128.0>`
+  * This VM, #1,
+  started a FLU (Machi data server) with the name `f1`.  In the Erlang
+  process supervisor hierarchy, the process ID of the top supervisor
+  is `<0.128.0>`.
+* `Configured chain c1 via FLU f1 to mode=ap_mode all=[f1,f2,f3] witnesses=[]`
+  * A bootstrap configuration for a chain named `c1` has been created.
+  * The FLUs/data servers that are eligible for participation in the
+    chain have names `f1`, `f2`, and `f3`.
+  * The chain will operate in eventual consistency mode (`ap_mode`)
+  * The witness server list is empty.  Witness servers are never used
+    in eventual consistency mode.
+* `CONFIRM epoch 1141 <<155,42,7,221>> upi [] rep [] auth f1 by f1`
+  * All participants in epoch 1141 are unanimous in adopting epoch
+    1141's projection.  All active membership lists are empty, so
+    there is no functional chain replication yet, at least as far as
+    server `f1` knows
+  * The epoch's abbreviated checksum is `<<155,42,7,221>>`.
+  * The UPI list, i.e. the replicas whose data is 100% in sync is
+    `[]`, the empty list.  (UPI = Update Propagation Invariant)
+  * The list of servers that are under data repair (`rep`) is also
+    empty, `[]`.
+  * This projection was authored by server `f1`.
+  * The log message was generated by server `f1`.
+* `CONFIRM epoch 1148 <<57,213,154,16>> upi [f1] rep [] auth f1 by f1`
+  * Now the server `f1` has created a chain of length 1, `[f1]`.
+  * Chain repair/file re-sync is not required when the UPI server list
+    changes from length 0 -> 1.
+* `CONFIRM epoch 1151 <<239,29,39,70>> upi [f1] rep [f3] auth f1 by f1`
+  * Server `f1` has noticed that server `f3` is alive.  Apparently it
+    has not yet noticed that server `f2` is also running.
+  * Server `f3` is in the repair list.
+* `CONFIRM epoch 1152 <<173,17,66,225>> upi [f2] rep [f1,f3] auth f2 by f1`
+  * Server `f2` is apparently now aware that all three servers are running.
+  * The previous configuration used by `f2` was `upi [f2]`, i.e., `f2`
+    was running in a chain of one.  `f2` noticed that `f1` and `f3`
+    were now available and has started adding them to the chain.
+  * All new servers are always added to the tail of the chain in the
+    repair list.
+  * In eventual consistency mode, a UPI change like this is OK.
+    * When performing a read, a client must read from both tail of the
+      UPI list and also from all repairing servers.
+    * When performing a write, the client writes to both the UPI
+      server list and also the repairing list, in that order.
+      * I.e., the client concatenates both lists,
+      `UPI ++ Repairing`, for its chain configuration for the write.
+  * Server `f2` will trigger file repair/re-sync shortly.
+    * The waiting time for starting repair has been configured to be
+      extremely short, 1 second.  The default waiting time is 10
+      seconds, in case Humming Consensus remains unstable.
+* `CONFIRM epoch 1154 <<154,231,224,149>> upi [f2,f1,f3] rep [] auth f2 by f1`
+  * File repair/re-sync has finished.  All file data on all servers
+    are now in sync.
+  * The UPI/in-sync part of the chain is now `[f2,f1,f3]`, and there
+    are no servers under repair.
+
+## Let's create some failures
+
+Here are some suggestions for creating failures.
+
+* Use the `./dev/devN/bin/machi stop` and `./dev/devN/bin/machi start`
+  commands to stop & start VM #`N`.
+* Stop a VM abnormally by using `kill`.  The OS process name to look
+  for is `beam.smp`.
+* Suspend and resume a VM, using the `SIGSTOP` and `SIGCONT` signals.
+  * E.g. `kill -STOP 9823` and `kill -CONT 9823`
+
+The network partition simulator is not (yet) available when running
+Machi in this mode.  Please see the next section for instructions on
+how to use partition simulator.
+
+
+<a name="partition-simulator">
+# Using the network partition simulator and convergence demo test code
+
+This is the demo code mentioned in the presentation that Scott Lystig
+Fritchie gave at the
+[RICON 2015 conference](http://ricon.io).
+* [slides (PDF format)](http://ricon.io/speakers/slides/Scott_Fritchie_Ricon_2015.pdf)
+* [video](https://www.youtube.com/watch?v=yR5kHL1bu1Q)
+
+## A complete example of all input and output
+
+If you don't have an Erlang/OTP 17 runtime environment available,
+please see this file for full input and output of a strong consistency
+length=3 chain test:
+https://gist.github.com/slfritchie/8352efc88cc18e62c72c
+This file contains all commands input and all simulator output from a
+sample run of the simulator.
+
+To help interpret the output of the test, please skip ahead to the
+"The test output is very verbose" section.
+
+## Prerequisites
+
+If you don't have `git` and/or the Erlang 17 runtime system available
+on your OS X, FreeBSD, Linux, or Solaris machine, please take a look
+at the [Prerequisites section](#prerequisites) first.  When you have
+installed the prerequisite software, please return back here.
+
+## Clone and compile the code
+
+Please briefly visit the [Clone and compile the code](#clone-compile)
+section.  When finished, please return back here.
+
+## Run an interactive Erlang CLI shell
+
+Run the following command at your login shell:
+
+    erl -pz .eunit ebin deps/*/ebin
+
+If you are using Erlang/OTP version 17, you should see some CLI output
+that looks like this:
+
+    Erlang/OTP 17 [erts-6.4] [source] [64-bit] [smp:8:8] [async-threads:10] [hipe] [kernel-poll:false] [dtrace]
+    
+    Eshell V6.4  (abort with ^G)
+    1>
+
+## The test output is very verbose ... what are the important parts?
+
+The output of the Erlang command
+`machi_chain_manager1_converge_demo:help()` will display the following
+guide to the output of the tests.
+
+    A visualization of the convergence behavior of the chain self-management
+    algorithm for Machi.
+    
+      1. Set up some server and chain manager pairs.
+      2. Create a number of different network partition scenarios, where
+         (simulated) partitions may be symmetric or asymmetric.  Then stop changing
+         the partitions and keep the simulated network stable (and perhaps broken).
+      3. Run a number of iterations of the algorithm in parallel by poking each
+         of the manager processes on a random'ish basis.
+      4. Afterward, fetch the chain transition changes made by each FLU and
+         verify that no transition was unsafe.
+    
+    During the iteration periods, the following is a cheatsheet for the output.
+    See the internal source for interpreting the rest of the output.
+    
+        'SET partitions = '
+    
+            A pair-wise list of actors which cannot send messages.  The
+            list is uni-directional.  If there are three servers (a,b,c),
+            and if the partitions list is '[{a,b},{b,c}]' then all
+            messages from a->b and b->c will be dropped, but any other
+            sender->recipient messages will be delivered successfully.
+    
+        'x uses:'
+    
+            The FLU x has made an internal state transition and is using
+            this epoch's projection as operating chain configuration.  The
+            rest of the line is a summary of the projection.
+    
+        'CONFIRM epoch {N}'
+    
+            This message confirms that all of the servers listed in the
+            UPI and repairing lists of the projection at epoch {N} have
+            agreed to use this projection because they all have written
+            this projection to their respective private projection stores.
+            The chain is now usable by/available to all clients.
+    
+        'Sweet, private projections are stable'
+    
+            This report announces that this iteration of the test cycle
+            has passed successfully.  The report that follows briefly
+            summarizes the latest private projection used by each
+            participating server.  For example, when in strong consistency
+            mode with 'a' as a witness and 'b' and 'c' as real servers:
+    
+            %% Legend:
+            %% server name, epoch ID, UPI list, repairing list, down list, ...
+            %%                         ... witness list, 'false' (a constant value)
+    
+            [{a,{{1116,<<23,143,246,55>>},[a,b],[],[c],[a],false}},
+             {b,{{1116,<<23,143,246,55>>},[a,b],[],[c],[a],false}}]
+    
+            Both servers 'a' and 'b' agree on epoch 1116 with epoch ID
+            {1116,<<23,143,246,55>>} where UPI=[a,b], repairing=[],
+            down=[c], and witnesses=[a].
+    
+            Server 'c' is not shown because 'c' has wedged itself OOS (out
+            of service) by configuring a chain length of zero.
+    
+            If no servers are listed in the report (i.e. only '[]' is
+            displayed), then all servers have wedged themselves OOS, and
+            the chain is unavailable.
+    
+        'DoIt,' 
+    
+            This marks a group of tick events which trigger the manager
+            processes to evaluate their environment and perhaps make a
+            state transition.
+    
+    A long chain of 'DoIt,DoIt,DoIt,' means that the chain state has
+    (probably) settled to a stable configuration, which is the goal of the
+    algorithm.
+    
+    Press control-c to interrupt the test....".
+
+## Run a test in eventual consistency mode
+
+Run the following command at the Erlang CLI prompt:
+
+    machi_chain_manager1_converge_demo:t(3, [{private_write_verbose,true}]).
+
+The first argument, `3`, is the number of servers to participate in
+the chain.  Please note:
+
+* Chain lengths as short as 1 or 2 are valid, but the results are a
+  bit boring.
+* Chain lengths as long as 7 or 9 can be used, but they may
+  suffer from longer periods of churn/instability before all chain
+  managers reach agreement via humming consensus.  (It is future work
+  to shorten the worst of the unstable churn latencies.)
+* In eventual consistency mode, chain lengths may be even numbers,
+  e.g. 2, 4, or 6.
+* The simulator will choose partition events from the permutations of
+  all 1, 2, and 3 node partition pairs.  The total runtime will
+  increase *dramatically* with chain length.
+    * Chain length 2: about 3 partition cases
+    * Chain length 3: about 35 partition cases
+    * Chain length 4: about 230 partition cases
+    * Chain length 5: about 1100 partition cases
+
+## Run a test in strong consistency mode (with witnesses):
+
+*NOTE:* Due to a bug in the test code, please do not try to run the
+ convergence test in strong consistency mode and also without the
+ correct minority number of witness servers!  If in doubt, please run
+ the commands shown below exactly.
+
+Run the following command at the Erlang CLI prompt:
+
+    machi_chain_manager1_converge_demo:t(3, [{private_write_verbose,true}, {consistency_mode, cp_mode}, {witnesses, [a]}]).
+
+The first argument, `3`, is the number of servers to participate in
+the chain.  Chain lengths as long as 7 or 9 can be used, but they may
+suffer from longer periods of churn/instability before all chain
+managers reach agreement via humming consensus.
+
+Due to the bug mentioned above, please use the following
+commands when running with chain lengths of 5 or 7, respectively.
+
+    machi_chain_manager1_converge_demo:t(5, [{private_write_verbose,true}, {consistency_mode, cp_mode}, {witnesses, [a,b]}]).
+    machi_chain_manager1_converge_demo:t(7, [{private_write_verbose,true}, {consistency_mode, cp_mode}, {witnesses, [a,b,c]}]).
+

doc/overview.edoc

@@ -1,170 +0,0 @@
-
-@title Machi: a small village of replicated files
-
-@doc 
-
-== About This EDoc Documentation ==
-
-This EDoc-style documentation will concern itself only with Erlang
-function APIs and function & data types.  Higher-level design and
-commentary will remain outside of the Erlang EDoc system; please see
-the "Pointers to Other Machi Documentation" section below for more
-details.
-
-Readers should beware that this documentation may be out-of-sync with
-the source code.  When in doubt, use the `make edoc' command to
-regenerate all HTML pages.
-
-It is the developer's responsibility to re-generate the documentation
-periodically and commit it to the Git repo.
-
-== Machi Code Overview ==
-
-=== Chain Manager ===
-
-The Chain Manager is responsible for managing the state of Machi's
-"Chain Replication" state.  This role is roughly analogous to the
-"Riak Core" application inside of Riak, which takes care of
-coordinating replica placement and replica repair.
-
-For each primitive data server in the cluster, a Machi FLU, there is a
-Chain Manager process that manages its FLU's role within the Machi
-cluster's Chain Replication scheme.  Each Chain Manager process
-executes locally and independently to manage the distributed state of
-a single Machi Chain Replication chain.
-
-  <ul>
-
-  <li> To contrast with Riak Core ... Riak Core's claimant process is
-       solely responsible for managing certain critical aspects of
-       Riak Core distributed state.  Machi's Chain Manager process
-       performs similar tasks as Riak Core's claimant.  However, Machi
-       has several active Chain Manager processes, one per FLU server,
-       instead of a single active process like Core's claimant.  Each
-       Chain Manager process acts independently; each is constrained
-       so that it will reach consensus via independent computation
-       &amp; action.
-
-       Full discussion of this distributed consensus is outside the
-       scope of this document; see the "Pointers to Other Machi
-       Documentation" section below for more information.
-  </li>
-  <li> Machi differs from a Riak Core application because Machi's
-       replica placement policy is simply, "All Machi servers store
-       replicas of all Machi files".
-       Machi is intended to be a primitive building block for creating larger
-       cluster-of-clusters where files are
-       distributed/fragmented/sharded across a large pool of
-       independent Machi clusters.
-  </li>
-  <li> See
-       [https://www.usenix.org/legacy/events/osdi04/tech/renesse.html]
-       for a copy of the paper, "Chain Replication for Supporting High
-       Throughput and Availability" by Robbert van Renesse and Fred
-       B. Schneider.
-  </li>
-  </ul>
-
-=== FLU ===
-
-The FLU is the basic storage server for Machi.
-
-  <ul>
-  <li> The name FLU is taken from "flash storage unit" from the paper
-       "CORFU: A Shared Log Design for Flash Clusters" by
-       Balakrishnan, Malkhi, Prabhakaran, and Wobber.  See
-       [https://www.usenix.org/conference/nsdi12/technical-sessions/presentation/balakrishnan]
-  </li>
-  <li> In CORFU, the sequencer step is a prerequisite step that is
-       performed by a separate component, the Sequencer.
-       In Machi, the `append_chunk()' protocol message has
-       an implicit "sequencer" operation applied by the "head" of the
-       Machi Chain Replication chain.  If a client wishes to write
-       data that has already been assigned a sequencer position, then
-       the `write_chunk()' API function is used.
-  </li>
-  </ul>
-
-For each FLU, there are three independent tasks that are implemented
-using three different Erlang processes:
-
-  <ul>
-  <li> A FLU server, implemented primarily by `machi_flu.erl'.
-  </li>
-  <li> A projection store server, implemented primarily by
-      `machi_projection_store.erl'. 
-  </li>
-  <li> A chain state manager server, implemented primarily by
-       `machi_chain_manager1.erl'.
-  </li>
-  </ul>
-
-From the perspective of failure detection, it is very convenient that
-all three FLU-related services (file server, sequencer server, and
-projection server) are accessed using the same single TCP port.
-
-=== Projection (data structure) ===
-
-The projection is a data structure that specifies the current state
-of the Machi cluster: all FLUs, which FLUS are considered
-up/running or down/crashed/stopped, which FLUs are actively
-participants in the Chain Replication protocol, and which FLUs are
-under "repair" (i.e., having their data resyncronized when
-newly-added to a cluster or when restarting after a crash).
-
-=== Projection Store (server) ===
-
-The projection store is a storage service that is implemented by an
-Erlang/OTP `gen_server' process that is associated with each
-FLU.  Conceptually, the projection store is an array of
-write-once registers.  For each projection store register, the
-key is a 2-tuple of an epoch number (`non_neg_integer()' type)
-and a projection type (`public' or `private' type); the value is
-a projection data structure (`projection_v1()' type).
-
-=== Client and Proxy Client ===
-
-Machi is intentionally avoiding using distributed Erlang for Machi's
-communication.  This design decision makes Erlang-side code more
-difficult &amp; complex but allows us the freedom of implementing
-parts of Machi in other languages without major
-protocol&amp;API&amp;glue code changes later in the product's
-lifetime.
-
-There are two layers of interface for Machi clients.
-
-  <ul>
-  <li> The `machi_flu1_client' module implements an API that uses a
-       TCP socket directly.
-  </li>
-  <li> The `machi_proxy_flu1_client' module implements an API that
-       uses a local, long-lived `gen_server' process as a proxy for
-       the remote, perhaps disconnected-or-crashed Machi FLU server.
-  </li>
-  </ul>
-
-The types for both modules ought to be the same.  However, due to
-rapid code churn, some differences might exist.  Any major difference
-is (almost by definition) a bug: please open a GitHub issue to request
-a correction.
-
-== TODO notes ==
-
-Any use of the string "TODO" in upper/lower/mixed case, anywhere in
-the code, is a reminder signal of unfinished work.
-
-== Pointers to Other Machi Documentation ==
-
-<ul>
-<li> If you are viewing this document locally, please look in the
-     `../doc/' directory,
-</li>
-<li> If you are viewing this document via the Web, please find the
-     documentation via this link: 
-     [http://github.com/basho/machi/tree/master/doc/]
-     Please be aware that this link points to the `master' branch
-     of the Machi source repository and therefore may be
-     out-of-sync with non-`master' branch code.
-</li>
-
-</ul>

doc/src.high-level/high-level-chain-mgr.tex

@@ -23,8 +23,8 @@
 \copyrightdata{978-1-nnnn-nnnn-n/yy/mm} 
 \doi{nnnnnnn.nnnnnnn}
 
-\titlebanner{Draft \#0.91, June 2015}
+\titlebanner{Draft \#0.92, October 2015}
-\preprintfooter{Draft \#0.91, June 2015}
+\preprintfooter{Draft \#0.92, October 2015}
 
 \title{Chain Replication metadata management in Machi, an immutable
   file store}
@@ -50,19 +50,23 @@ For an overview of the design of the larger Machi system, please see
 TODO Fix, after all of the recent changes to this document.
 
 Machi is an immutable file store, now in active development by Basho
-Japan KK.  Machi uses Chain Replication to maintain strong consistency
+Japan KK.  Machi uses Chain Replication\footnote{Chain
-of file updates to all replica servers in a Machi cluster.  Chain
 Replication is a variation of primary/backup replication where the
 order of updates between the primary server and each of the backup
-servers is strictly ordered into a single ``chain''.  Management of
+servers is strictly ordered into a single ``chain''.}
-Chain Replication's metadata, e.g., ``What is the current order of
+to maintain strong consistency
-servers in the chain?'', remains an open research problem.  The
+of file updates to all replica servers in a Machi cluster.  
-current state of the art for Chain Replication metadata management
-relies on an external oracle (e.g., ZooKeeper) or the Elastic
-Replication algorithm.
 
 This document describes the Machi chain manager, the component
-responsible for managing Chain Replication metadata state.  The chain
+responsible for managing Chain Replication metadata state.
+Management of
+chain metadata, e.g., ``What is the current order of
+servers in the chain?'', remains an open research problem.  The
+current state of the art for Chain Replication metadata management
+relies on an external oracle (e.g., based on ZooKeeper) or the Elastic
+Replication \cite{elastic-chain-replication} algorithm.
+
+The chain
 manager uses a new technique, based on a variation of CORFU, called
 ``humming consensus''.
 Humming consensus does not require active participation by all or even
@@ -89,20 +93,18 @@ to perform these management tasks.  Chain metadata state and state
 management tasks include:
 
 \begin{itemize}
-\item Preserving data integrity of all metadata and data stored within
-  the chain.  Data loss is not an option.
 \item Preserving stable knowledge of chain membership (i.e. all nodes in
-   the chain, regardless of operational status). A systems
+   the chain, regardless of operational status). We expect that a systems
-   administrator is expected to make ``permanent'' decisions about
+   administrator will make all ``permanent'' decisions about
    chain membership.
 \item Using passive and/or active techniques to track operational
-   state/status, e.g., up, down, restarting, full data sync, partial
+   state/status, e.g., up, down, restarting, full data sync in progress, partial
-   data sync, etc.
+   data sync in progress, etc.
 \item Choosing the run-time replica ordering/state of the chain, based on
    current member status and past operational history.  All chain
    state transitions must be done safely and without data loss or
    corruption.
-\item As a new node is added to the chain administratively or old node is
+\item When a new node is added to the chain administratively or old node is
    restarted, adding the node to the chain safely and perform any data
    synchronization/repair required to bring the node's data into
    full synchronization with the other nodes.
@@ -111,39 +113,27 @@ management tasks include:
 \subsection{Ultimate goal: Preserve data integrity of Chain Replicated data}
 
 Preservation of data integrity is paramount to any chain state
-management technique for Machi.  Even when operating in an eventually
+management technique for Machi.  Loss or corruption of chain data must
-consistent mode, Machi must not lose data without cause outside of all
+be avoided.
-design, e.g., all particpants crash permanently.
 
 \subsection{Goal: Contribute to Chain Replication metadata management research}
 
 We believe that this new self-management algorithm, humming consensus,
 contributes a novel approach to Chain Replication metadata management.
-The ``monitor
-and mangage your neighbor'' technique proposed in Elastic Replication
-(Section \ref{ssec:elastic-replication}) appears to be the current
-state of the art in the distributed systems research community.
 Typical practice in the IT industry appears to favor using an external
-oracle, e.g., using ZooKeeper as a trusted coordinator.  
+oracle, e.g., built on top of ZooKeeper as a trusted coordinator.  
 
-See Section~\ref{sec:cr-management-review} for a brief review.
+See Section~\ref{sec:cr-management-review} for a brief review of
+techniques used today.
 
 \subsection{Goal: Support both eventually consistent \& strongly consistent modes of operation}
 
-Machi's first use cases are all for use as a file store in an eventually
+Chain Replication was originally designed by van Renesse and Schneider
-consistent environment.
+\cite{chain-replication} for applications that require strong
-In eventually consistent mode, humming consensus
+consistency, e.g. sequential consistency.  However, Machi has use
-allows a Machi cluster to fragment into
+cases where more relaxed eventual consistency semantics are
-arbitrary islands of network partition, all the way down to 100\% of
+sufficient.  We wish to use the same Chain Replication management
-members running in complete network isolation from each other.
+technique for both strong and eventual consistency environments.
-Furthermore, it provides enough agreement to allow
-formerly-partitioned members to coordinate the reintegration and
-reconciliation of their data when partitions are healed.
-
-Later, we wish the option of supporting strong consistency
-applications such as CORFU-style logging while reusing all (or most)
-of Machi's infrastructure.  Such strongly consistent operation is the
-main focus of this document.
 
 \subsection{Anti-goal: Minimize churn}
 
@@ -204,6 +194,18 @@ would probably be preferable to add the feature to Riak Ensemble
 rather than to use ZooKeeper (and for Basho to document ZK, package
 ZK, provide commercial ZK support, etc.).
 
+\subsection{An external management oracle, implemented by
+  active/standby application failover}
+
+This technique has been used in production of HibariDB.  The customer
+very carefully deployed the oracle using the Erlang/OTP ``application
+controller'' on two machines to provide active/standby failover of the
+management oracle.  The customer was willing to monitor this service
+very closely and was prepared to intervene manually during network
+partitions.  (This controller is very susceptible to ``split brain
+syndrome''.)  While this feature of Erlang/OTP is useful in other
+environments, we believe is it not sufficient for Machi's needs.
+
 \section{Assumptions}
 \label{sec:assumptions}
 
@@ -212,8 +214,8 @@ Paxos, Raft, et al.), why bother with a slightly different set of
 assumptions and a slightly different protocol?
 
 The answer lies in one of our explicit goals: to have an option of
-running in an ``eventually consistent'' manner.  We wish to be able to
+running in an ``eventually consistent'' manner.  We wish to be 
-make progress, i.e., remain available in the CAP sense, even if we are
+remain available, even if we are
 partitioned down to a single isolated node.  VR, Paxos, and Raft
 alone are not sufficient to coordinate service availability at such
 small scale.  The humming consensus algorithm can manage
@@ -247,13 +249,15 @@ synchronized by NTP.
 
 The protocol and algorithm presented here do not specify or require any
 timestamps, physical or logical.  Any mention of time inside of data
-structures are for human/historic/diagnostic purposes only.
+structures are for human and/or diagnostic purposes only.
 
-Having said that, some notion of physical time is suggested for
+Having said that, some notion of physical time is suggested
-purposes of efficiency.  It's recommended that there be some ``sleep
+occasionally for
+purposes of efficiency.  For example, some ``sleep
 time'' between iterations of the algorithm: there is no need to ``busy
-wait'' by executing the algorithm as quickly as possible.  See also
+wait'' by executing the algorithm as many times per minute as
-Section~\ref{ssub:when-to-calc}.
+possible.
+See also Section~\ref{ssub:when-to-calc}.
 
 \subsection{Failure detector model}
 
@@ -276,55 +280,73 @@ eventual consistency.  Discussion of strongly consistent CP
 mode is always the default; exploration of AP mode features in this document
 will always be explictly noted.
 
-\subsection{Use of the ``wedge state''}
+%%\subsection{Use of the ``wedge state''}
+%%
+%%A participant in Chain Replication will enter ``wedge state'', as
+%%described by the Machi high level design \cite{machi-design} and by CORFU,
+%%when it receives information that
+%%a newer projection (i.e., run-time chain state reconfiguration) is
+%%available.  The new projection may be created by a system
+%%administrator or calculated by the self-management algorithm.
+%%Notification may arrive via the projection store API or via the file
+%%I/O API.
+%%
+%%When in wedge state, the server will refuse all file write I/O API
+%%requests until the self-management algorithm has determined that
+%%humming consensus has been decided (see next bullet item).  The server
+%%may also refuse file read I/O API requests, depending on its CP/AP
+%%operation mode.
+%%
+%%\subsection{Use of ``humming consensus''}
+%%
+%%CS literature uses the word ``consensus'' in the context of the problem
+%%description at \cite{wikipedia-consensus}
+%%.
+%%This traditional definition differs from what is described here as
+%%``humming consensus''.
+%%
+%%``Humming consensus'' describes
+%%consensus that is derived only from data that is visible/known at the current
+%%time.
+%%The algorithm will calculate
+%%a rough consensus despite not having input from a quorum majority
+%%of chain members.  Humming consensus may proceed to make a
+%%decision based on data from only a single participant, i.e., only the local
+%%node.
+%%
+%%See Section~\ref{sec:humming-consensus} for detailed discussion.
 
-A participant in Chain Replication will enter ``wedge state'', as
+%%\subsection{Concurrent chain managers execute humming consensus independently}
-described by the Machi high level design \cite{machi-design} and by CORFU,
+%%
-when it receives information that
+%%Each Machi file server has its own concurrent chain manager
-a newer projection (i.e., run-time chain state reconfiguration) is
+%%process embedded within it.  Each chain manager process will
-available.  The new projection may be created by a system
+%%execute the humming consensus algorithm using only local state (e.g.,
-administrator or calculated by the self-management algorithm.
+%%the $P_{current}$ projection currently used by the local server) and
-Notification may arrive via the projection store API or via the file
+%%values observed in everyone's projection stores
-I/O API.
+%%(Section~\ref{sec:projection-store}).
+%%
+%%The chain manager communicates with the local Machi
+%%file server using the wedge and un-wedge request API.  When humming
+%%consensus has chosen a projection $P_{new}$ to replace $P_{current}$,
+%%the value of $P_{new}$ is included in the un-wedge request.
 
-When in wedge state, the server will refuse all file write I/O API
+\subsection{The reader is familiar with CORFU}
-requests until the self-management algorithm has determined that
-humming consensus has been decided (see next bullet item).  The server
-may also refuse file read I/O API requests, depending on its CP/AP
-operation mode.
 
-\subsection{Use of ``humming consensus''}
+Machi borrows heavily from the techniques and data structures used by
+CORFU \cite[corfu1],\cite[corfu2].  We hope that the reader is
+familiar with CORFU's features, including:
 
-CS literature uses the word ``consensus'' in the context of the problem
+\begin{itemize}
-description at \cite{wikipedia-consensus}
+\item write-once registers for log data storage,
-.
+\item the epoch, which defines a period of time when a cluster's configuration
-This traditional definition differs from what is described here as
+is stable,
-``humming consensus''.
+\item strictly increasing epoch numbers, which are identifiers
-
+for particular epochs,
-``Humming consensus'' describes
+\item projections, which define the chain order and other details of
-consensus that is derived only from data that is visible/known at the current
+  data replication within the cluster, and
-time.
+\item the wedge state, used by servers to coordinate cluster changes
-The algorithm will calculate
+  during epoch transitions.
-a rough consensus despite not having input from all/majority
+\end{itemize}
-of chain members.  Humming consensus may proceed to make a
-decision based on data from only a single participant, i.e., only the local
-node.
-
-See Section~\ref{sec:humming-consensus} for detailed discussion.
-
-\subsection{Concurrent chain managers execute humming consensus independently}
-
-Each Machi file server has its own concurrent chain manager
-process embedded within it.  Each chain manager process will
-execute the humming consensus algorithm using only local state (e.g.,
-the $P_{current}$ projection currently used by the local server) and
-values observed in everyone's projection stores
-(Section~\ref{sec:projection-store}).
-
-The chain manager communicates with the local Machi
-file server using the wedge and un-wedge request API.  When humming
-consensus has chosen a projection $P_{new}$ to replace $P_{current}$,
-the value of $P_{new}$ is included in the un-wedge request.
 
 \section{The projection store}
 \label{sec:projection-store}
@@ -343,19 +365,15 @@ this key.  The
 store's value is either the special `unwritten' value\footnote{We use
   $\bot$ to denote the unwritten value.} or else a binary blob that is
 immutable thereafter; the projection data structure is
-serialized and stored in this binary blob.
+serialized and stored in this binary blob.  See
-
+\ref{sub:the-projection} for more detail.
-The projection store is vital for the correct implementation of humming
-consensus (Section~\ref{sec:humming-consensus}).  The write-once
-register primitive allows us to reason about the store's behavior
-using the same logical tools and techniques as the CORFU ordered log.
 
 \subsection{The publicly-writable half of the projection store}
 
 The publicly-writable projection store is used to share information
 during the first half of humming consensus algorithm.  Projections
 in the public half of the store form a log of
-suggestions\footnote{I hesitate to use the word ``propose'' or ``proposal''
+suggestions\footnote{I hesitate to use the words ``propose'' or ``proposal''
   anywhere in this document \ldots until I've done a more formal
   analysis of the protocol.  Those words have too many connotations in
   the context of consensus protocols such as Paxos and Raft.}
@@ -369,8 +387,9 @@ Any chain member may read from the public half of the store.
 
 The privately-writable projection store is used to store the
 Chain Replication metadata state (as chosen by humming consensus)
-that is in use now by the local Machi server as well as previous
+that is in use now by the local Machi server. Earlier projections
-operation states.
+remain in the private half to keep a historical
+record of chain state transitions by the local server.
 
 Only the local server may write values into the private half of store.
 Any chain member may read from the private half of the store.
@@ -386,35 +405,30 @@ The private projection store serves multiple purposes, including:
   its sequence of $P_{current}$ projection changes.
 \end{itemize}
 
-The private half of the projection store is not replicated.
-
 \section{Projections: calculation, storage, and use}
 \label{sec:projections}
 
 Machi uses a ``projection'' to determine how its Chain Replication replicas
-should operate; see \cite{machi-design} and
+should operate; see \cite{machi-design} and \cite{corfu1}.
-\cite{corfu1}.  At runtime, a cluster must be able to respond both to
-administrative changes (e.g., substituting a failed server with
-replacement hardware) as well as local network conditions (e.g., is
-there a network partition?).
-
-The projection defines the operational state of Chain Replication's
-chain order as well the (re-)synchronization of data managed by by
-newly-added/failed-and-now-recovering members of the chain.  This
-chain metadata, together with computational processes that manage the
-chain, must be managed in a safe manner in order to avoid unintended
-data loss of data managed by the chain.
-
 The concept of a projection is borrowed
 from CORFU but has a longer history, e.g., the Hibari key-value store
 \cite{cr-theory-and-practice} and goes back in research for decades,
 e.g., Porcupine \cite{porcupine}.
 
+The projection defines the operational state of Chain Replication's
+chain order as well the (re-)synchronization of data managed by by
+newly-added/failed-and-now-recovering members of the chain.
+At runtime, a cluster must be able to respond both to
+administrative changes (e.g., substituting a failed server with
+replacement hardware) as well as local network conditions (e.g., is
+there a network partition?).
+
 \subsection{The projection data structure}
 \label{sub:the-projection}
 
 {\bf NOTE:} This section is a duplicate of the ``The Projection and
-the Projection Epoch Number'' section of \cite{machi-design}.
+the Projection Epoch Number'' section of the ``Machi: an immutable
+file store'' design doc \cite{machi-design}.
 
 The projection data
 structure defines the current administration \& operational/runtime
@@ -445,6 +459,7 @@ Figure~\ref{fig:projection}.  To summarize the major components:
             active_upi      :: [m_server()],
             repairing       :: [m_server()],
             down_members    :: [m_server()],
+            witness_servers :: [m_server()],
             dbg_annotations :: proplist()
         }).
 \end{verbatim}
@@ -454,13 +469,12 @@ Figure~\ref{fig:projection}.  To summarize the major components:
 
 \begin{itemize}
 \item {\tt epoch\_number} and {\tt epoch\_csum} The epoch number and
-  projection checksum are unique identifiers for this projection.
+  projection checksum together form the unique identifier for this projection.
 \item {\tt creation\_time} Wall-clock time, useful for humans and
   general debugging effort.
 \item {\tt author\_server} Name of the server that calculated the projection.
 \item {\tt all\_members} All servers in the chain, regardless of current
-  operation status.  If all operating conditions are perfect, the
+  operation status.
-  chain should operate in the order specified here.
 \item {\tt active\_upi} All active chain members that we know are
   fully repaired/in-sync with each other and therefore the Update
   Propagation Invariant (Section~\ref{sub:upi}) is always true.
@@ -468,7 +482,10 @@ Figure~\ref{fig:projection}.  To summarize the major components:
   are in active data repair procedures.
 \item {\tt down\_members} All members that the {\tt author\_server}
   believes are currently down or partitioned.
-\item {\tt dbg\_annotations} A ``kitchen sink'' proplist, for code to
+\item {\tt witness\_servers} If witness servers (Section~\ref{zzz})
+  are used in strong consistency mode, then they are listed here.  The
+  set of {\tt witness\_servers} is a subset of {\tt all\_members}.
+\item {\tt dbg\_annotations} A ``kitchen sink'' property list, for code to
   add any hints for why the projection change was made, delay/retry
   information, etc.
 \end{itemize}
@@ -478,7 +495,8 @@ Figure~\ref{fig:projection}.  To summarize the major components:
 According to the CORFU research papers, if a server node $S$ or client
 node $C$ believes that epoch $E$ is the latest epoch, then any information
 that $S$ or $C$ receives from any source that an epoch $E+\delta$ (where
-$\delta > 0$) exists will push $S$ into the ``wedge'' state and $C$ into a mode
+$\delta > 0$) exists will push $S$ into the ``wedge'' state
+and force $C$ into a mode
 of searching for the projection definition for the newest epoch.
 
 In the humming consensus description in
@@ -506,7 +524,7 @@ Humming consensus requires that any projection be identified by both
 the epoch number and the projection checksum, as described in
 Section~\ref{sub:the-projection}.
 
-\section{Managing multiple projection store replicas}
+\section{Managing projection store replicas}
 \label{sec:managing-multiple-projection-stores}
 
 An independent replica management technique very similar to the style
@@ -515,11 +533,63 @@ replicas of Machi's projection data structures.
 The major difference is that humming consensus
 {\em does not necessarily require}
 successful return status from a minimum number of participants (e.g.,
-a quorum).
+a majority quorum).
+
+\subsection{Writing to public projection stores}
+\label{sub:proj-store-writing}
+
+Writing replicas of a projection $P_{new}$ to the cluster's public
+projection stores is similar to writing in a Dynamo-like system.
+The significant difference with Chain Replication is how we interpret
+the return status of each write operation.
+
+In cases of {\tt error\_written} status,
+the process may be aborted and read repair
+triggered.  The most common reason for {\tt error\_written} status
+is that another actor in the system has concurrently
+already calculated another
+(perhaps different\footnote{The {\tt error\_written} may also
+indicate that another server has performed read repair on the exact
+projection $P_{new}$ that the local server is trying to write!})
+projection using the same projection epoch number.
+
+\subsection{Writing to private projection stores}
+
+Only the local server/owner may write to the private half of a
+projection store.  Private projection store values are never subject
+to read repair.
+
+\subsection{Reading from public projection stores}
+\label{sub:proj-store-reading}
+
+A read is simple: for an epoch $E$, send a public projection read API
+operation to all participants.  Usually, the ``get latest epoch''
+variety is used.
+
+The minimum number of non-error responses is only one.\footnote{The local
+projection store should always be available, even if no other remote
+replica projection stores are available.}  If all available servers
+return a single, unanimous value $V_u, V_u \ne \bot$, then $V_u$ is
+the final result for epoch $E$.
+Any non-unanimous values are considered unresolvable for the
+epoch.  This disagreement is resolved by newer
+writes to the public projection stores during subsequent iterations of
+humming consensus.
+
+Unavailable servers may not necessarily interfere with making a decision.
+Humming consensus
+only uses as many public projections as are available at the present
+moment of time.  Assume that some server $S$ is unavailable at time $t$ and
+becomes available at some later $t+\delta$.
+If at $t+\delta$ we
+discover that $S$'s public projection store for key $E$
+contains some disagreeing value $V_{weird}$, then the disagreement
+will be resolved in the exact same manner that would have been used as if we
+had seen the disagreeing values at the earlier time $t$.
 
 \subsection{Read repair: repair only unwritten values}
 
-The idea of ``read repair'' is also shared with Riak Core and Dynamo
+The ``read repair'' concept is also shared with Riak Core and Dynamo
 systems.  However, Machi has situations where read repair cannot truly
 ``fix'' a key because two different values have been written by two
 different replicas.
@@ -530,85 +600,24 @@ values, all participants in humming consensus merely agree that there
 were multiple suggestions at that epoch which must be resolved by the
 creation and writing of newer projections with later epoch numbers.}
 Machi's projection store read repair can only repair values that are
-unwritten, i.e., storing $\bot$.
+unwritten, i.e., currently storing $\bot$.
 
-The value used to repair $\bot$ values is the ``best'' projection that
+The value used to repair unwritten $\bot$ values is the ``best'' projection that
 is currently available for the current epoch $E$.  If there is a single,
 unanimous value $V_{u}$ for the projection at epoch $E$, then $V_{u}$
-is use to repair all projections stores at $E$ that contain $\bot$
+is used to repair all projections stores at $E$ that contain $\bot$
 values.  If the value of $K$ is not unanimous, then the ``highest
 ranked value'' $V_{best}$ is used for the repair; see
 Section~\ref{sub:ranking-projections} for a description of projection
 ranking.
 
-\subsection{Writing to public projection stores}
+If a non-$\bot$ value exists, then by definition\footnote{Definition
-\label{sub:proj-store-writing}
+  of a write-once register} this value is immutable.  The only
-
+conflict resolution path is to write a new projection with a newer and
-Writing replicas of a projection $P_{new}$ to the cluster's public
+larger epoch number. Once a public projection with epoch number $E$ is
-projection stores is similar, in principle, to writing a Chain
+written, projections with epochs smaller than $E$ are ignored by
-Replication-managed system or Dynamo-like system.  But unlike Chain
-Replication, the order doesn't really matter.
-In fact, the two steps below may be performed in parallel.
-The significant difference with Chain Replication is how we interpret
-the return status of each write operation.
-
-\begin{enumerate}
-\item Write $P_{new}$ to the local server's public projection store
-  using $P_{new}$'s epoch number $E$ as the key.
-  As a side effect, a successful write will trigger
-  ``wedge'' status in the local server, which will then cascade to other
-  projection-related activity by the local chain manager.
-\item Write $P_{new}$ to key $E$ of each remote public projection store of
-  all participants in the chain.
-\end{enumerate}
-
-In cases of {\tt error\_written} status,
-the process may be aborted and read repair
-triggered.  The most common reason for {\tt error\_written} status
-is that another actor in the system has
-already calculated another (perhaps different) projection using the
-same projection epoch number and that
-read repair is necessary.  The {\tt error\_written} may also
-indicate that another server has performed read repair on the exact
-projection $P_{new}$ that the local server is trying to write!
-
-\subsection{Writing to private projection stores}
-
-Only the local server/owner may write to the private half of a
-projection store.  Also, the private projection store is not replicated.
-
-\subsection{Reading from public projection stores}
-\label{sub:proj-store-reading}
-
-A read is simple: for an epoch $E$, send a public projection read API
-request to all participants.  As when writing to the public projection
-stores, we can ignore any timeout/unavailable return
-status.\footnote{The success/failure status of projection reads and
-  writes is {\em not} ignored with respect to the chain manager's
-  internal liveness tracker.  However, the liveness tracker's state is
-  typically only used when calculating new projections.}  If we
-discover any unwritten values $\bot$, the read repair protocol is
-followed.
-
-The minimum number of non-error responses is only one.\footnote{The local
-projection store should always be available, even if no other remote
-replica projection stores are available.}  If all available servers
-return a single, unanimous value $V_u, V_u \ne \bot$, then $V_u$ is
-the final result for epoch $E$.
-Any non-unanimous values are considered complete disagreement for the
-epoch.  This disagreement is resolved by humming consensus by later
-writes to the public projection stores during subsequent iterations of
 humming consensus.
 
-We are not concerned with unavailable servers.  Humming consensus
-only uses as many public projections as are available at the present
-moment of time.  If some server $S$ is unavailable at time $t$ and
-becomes available at some later $t+\delta$, and if at $t+\delta$ we
-discover that $S$'s public projection store for key $E$
-contains some disagreeing value $V_{weird}$, then the disagreement
-will be resolved in the exact same manner that would be used as if we
-had found the disagreeing values at the earlier time $t$.
-
 \section{Phases of projection change, a prelude to Humming Consensus}
 \label{sec:phases-of-projection-change}
 
@@ -671,7 +680,7 @@ straightforward; see
 Section~\ref{sub:proj-store-writing} for the technique for writing
 projections to all participating servers' projection stores.
 Humming Consensus does not care
-if the writes succeed or not: its final phase, adopting a
+if the writes succeed or not.  The next phase, adopting a
 new projection, will determine which write operations are usable.
 
 \subsection{Adoption a new projection}
@@ -685,8 +694,8 @@ to avoid direct parallels with protocols such as Raft and Paxos.)
 In general, a projection $P_{new}$ at epoch $E_{new}$ is adopted by a
 server only if
 the change in state from the local server's current projection to new
-projection, $P_{current} \rightarrow P_{new}$ will not cause data loss,
+projection, $P_{current} \rightarrow P_{new}$, will not cause data loss:
-e.g., the Update Propagation Invariant and all other safety checks
+the Update Propagation Invariant and all other safety checks
 required by chain repair in Section~\ref{sec:repair-entire-files}
 are correct. For example, any new epoch must be strictly larger than
 the current epoch, i.e., $E_{new} > E_{current}$.
@@ -696,16 +705,12 @@ available public projection stores.  If the result is not a single
 unanmous projection, then we return to the step in
 Section~\ref{sub:projection-calculation}.  If the result is a {\em
   unanimous} projection $P_{new}$ in epoch $E_{new}$, and if $P_{new}$
-does not violate chain safety checks, then the local node may
+does not violate chain safety checks, then the local node will:
-replace its local $P_{current}$ projection with $P_{new}$.
 
-Not all safe projection transitions are useful, however.  For example,
+\begin{itemize}
-it's trivally safe to suggest projection $P_{zero}$, where the chain
+\item write $P_{current}$ to the local private projection store, and
-length is zero.  In an eventual consistency environment, projection
+\item set its local operating state $P_{current} \leftarrow P_{new}$.
-$P_{one}$ where the chain length is exactly one is also trivially
+\end{itemize}
-safe.\footnote{Although, if the total number of participants is more
-  than one, eventual consistency would demand that $P_{self}$ cannot
-  be used forever.}
 
 \section{Humming Consensus}
 \label{sec:humming-consensus}
@@ -714,13 +719,11 @@ Humming consensus describes consensus that is derived only from data
 that is visible/available at the current time.  It's OK if a network
 partition is in effect and not all chain members are available;
 the algorithm will calculate a rough consensus despite not
-having input from all chain members.  Humming consensus
+having input from all chain members.
-may proceed to make a decision based on data from only one
-participant, i.e., only the local node.
 
 \begin{itemize}
 
-\item When operating in AP mode, i.e., in eventual consistency mode, humming
+\item When operating in eventual consistency mode, humming
 consensus may reconfigure a chain of length $N$ into $N$
 independent chains of length 1.  When a network partition heals, the
 humming consensus is sufficient to manage the chain so that each
@@ -728,11 +731,12 @@ replica's data can be repaired/merged/reconciled safely.
 Other features of the Machi system are designed to assist such
 repair safely.
 
-\item When operating in CP mode, i.e., in strong consistency mode, humming
+\item When operating in strong consistency mode, any
-consensus would require additional restrictions.  For example, any
+chain shorter than the quorum majority of
-chain that didn't have a minimum length of the quorum majority size of
+all members is invalid and therefore cannot be used.  Any server with
-all members would be invalid and therefore would not move itself out
+a too-short chain cannot not move itself out
-of wedged state.  In very general terms, this requirement for a quorum
+of wedged state and is therefore unavailable for general file service.
+In very general terms, this requirement for a quorum
 majority of surviving participants is also a requirement for Paxos,
 Raft, and ZAB. See Section~\ref{sec:split-brain-management} for a
 proposal to handle ``split brain'' scenarios while in CP mode.
@@ -752,8 +756,6 @@ Section~\ref{sec:phases-of-projection-change}: network monitoring,
 calculating new projections, writing projections, then perhaps
 adopting the newest projection (which may or may not be the projection
 that we just wrote).
-Beginning with Section~\ref{sub:flapping-state}, we provide
-additional detail to the rough outline of humming consensus.
 
 \begin{figure*}[htp]
 \resizebox{\textwidth}{!}{
@@ -801,15 +803,15 @@ is used by the flowchart and throughout this section.
 
 \item[$\mathbf{P_{current}}$] The projection actively used by the local
   node right now.  It is also the projection with largest
-  epoch number in the local node's private projection store.
+  epoch number in the local node's {\em private} projection store.
 
 \item[$\mathbf{P_{newprop}}$] A new projection suggestion, as
   calculated by the local server
   (Section~\ref{sub:humming-projection-calculation}).
 
 \item[$\mathbf{P_{latest}}$] The highest-ranked projection with the largest
-  single epoch number that has been read from all available public
+  single epoch number that has been read from all available {\em public}
-  projection stores, including the local node's public projection store.
+  projection stores.
 
 \item[Unanimous] The $P_{latest}$ projection is unanimous if all
   replicas in all accessible public projection stores are effectively
@@ -828,7 +830,7 @@ is used by the flowchart and throughout this section.
 The flowchart has three columns, from left to right:
 
 \begin{description}
-\item[Column A] Is there any reason to change?
+\item[Column A] Is there any reason to act?
 \item[Column B] Do I act?
 \item[Column C] How do I act?
   \begin{description}
@@ -863,12 +865,12 @@ In today's implementation, there is only a single criterion for
 determining the alive/perhaps-not-alive status of a remote server $S$:
 is $S$'s projection store available now?  This question is answered by
 attemping to read the projection store on server $S$.  
-If successful, then we assume that all
+If successful, then we assume that $S$ and all of $S$'s network services
-$S$ is available.  If $S$'s projection store is not available for any
+are available.  If $S$'s projection store is not available for any
-reason (including timeout), we assume $S$ is entirely unavailable.
+reason (including timeout), we inform the local ``fitness server''
-This simple single
+that we have had a problem querying $S$.  The fitness service may then
-criterion appears to be sufficient for humming consensus, according to
+take additional monitoring/querying actions before informing us (in a
-simulations of arbitrary network partitions.
+later iteration) that $S$ should be considered down.
 
 %% {\bf NOTE:} The projection store API is accessed via TCP.  The network
 %% partition simulator, mentioned above and described at
@@ -883,64 +885,10 @@ Column~A of Figure~\ref{fig:flowchart}.
 See also, Section~\ref{sub:projection-calculation}.
 
 Execution starts at ``Start'' state of Column~A of
-Figure~\ref{fig:flowchart}.  Rule $A20$'s uses recent success \&
+Figure~\ref{fig:flowchart}.  Rule $A20$'s uses judgement from the
-failures in accessing other public projection stores to select a hard
+local ``fitness server'' to select a definite
 boolean up/down status for each participating server.
 
-\subsubsection{Calculating flapping state}
-
-Also at this stage, the chain manager calculates its local
-``flapping'' state.  The name ``flapping'' is borrowed from IP network
-engineer jargon ``route flapping'':
-
-\begin{quotation}
-``Route flapping is caused by pathological conditions
-(hardware errors, software errors, configuration errors, intermittent
-errors in communications links, unreliable connections, etc.) within
-the network which cause certain reachability information to be
-repeatedly advertised and withdrawn.''  \cite{wikipedia-route-flapping}
-\end{quotation}
-
-\paragraph{Flapping due to constantly changing network partitions and/or server crashes and restarts}
-
-Currently, Machi does not attempt to dampen, smooth, or ignore recent
-history of constantly flapping peer servers.  If necessary, a failure
-detector such as the $\phi$ accrual failure detector
-\cite{phi-accrual-failure-detector} can be used to help mange such
-situations.
-
-\paragraph{Flapping due to asymmetric network partitions}
-
-The simulator's behavior during stable periods where at least one node
-is the victim of an asymmetric network partition is \ldots weird,
-wonderful, and something I don't completely understand yet.  This is
-another place where we need more eyes reviewing and trying to poke
-holes in the algorithm.
-
-In cases where any node is a victim of an asymmetric network
-partition, the algorithm oscillates in a very predictable way: each
-server $S$ makes the same $P_{new}$ projection at epoch $E$ that $S$ made
-during a previous recent epoch $E-\delta$ (where $\delta$ is small, usually
-much less than 10).  However, at least one node makes a suggestion that
-makes rough consensus impossible.  When any epoch $E$ is not
-acceptable (because some node disagrees about something, e.g.,
-which nodes are down),
-the result is more new rounds of suggestions that create a repeating
-loop that lasts as long as the asymmetric partition lasts.
-
-From the perspective of $S$'s chain manager, the pattern of this
-infinite loop is easy to detect: $S$ inspects the pattern of the last
-$L$ projections that it has suggested, e.g., the last 10.
-Tiny details such as the epoch number and creation timestamp will
-differ, but the major details such as UPI list and repairing list are
-the same.
-
-If the major details of the last $L$ projections authored and
-suggested by $S$ are the same, then $S$ unilaterally decides that it
-is ``flapping'' and enters flapping state.  See
-Section~\ref{sub:flapping-state} for additional disucssion of the
-flapping state.
-
 \subsubsection{When to calculate a new projection}
 \label{ssub:when-to-calc}
 
@@ -949,7 +897,7 @@ calculate a new projection.  The timer interval is typically
 0.5--2.0 seconds, if the cluster has been stable.  A client may call an
 external API call to trigger a new projection, e.g., if that client
 knows that an environment change has happened and wishes to trigger a
-response prior to the next timer firing.
+response prior to the next timer firing (e.g.~at state $C200$).
 
 It's recommended that the timer interval be staggered according to the
 participant ranking rules in Section~\ref{sub:ranking-projections};
@@ -970,15 +918,14 @@ done by state $C110$ and that writing a public projection is done by
 states $C300$ and $C310$.
 
 Broadly speaking, there are a number of decisions made in all three
-columns of Figure~\ref{fig:flowchart} to decide if and when any type
+columns of Figure~\ref{fig:flowchart} to decide if and when a
-of projection should be written at all.  Sometimes, the best action is
+projection should be written at all.  Sometimes, the best action is
 to do nothing.
 
 \subsubsection{Column A: Is there any reason to change?}
 
 The main tasks of the flowchart states in Column~A is to calculate a
-new projection $P_{new}$ and perhaps also the inner projection
+new projection $P_{new}$.  Then we try to figure out which
-$P_{new2}$ if we're in flapping mode.  Then we try to figure out which
 projection has the greatest merit: our current projection
 $P_{current}$, the new projection $P_{new}$, or the latest epoch
 $P_{latest}$.  If our local $P_{current}$ projection is best, then
@@ -1011,7 +958,7 @@ The main decisions that states in Column B need to make are:
 
 It's notable that if $P_{new}$ is truly the best projection available
 at the moment, it must always first be written to everyone's
-public projection stores and only then processed through another
+public projection stores and only afterward processed through another
 monitor \& calculate loop through the flowchart.
 
 \subsubsection{Column C: How do I act?}
@@ -1053,14 +1000,14 @@ therefore the suggested projections at epoch $E$ are not unanimous.
 \paragraph{\#2: The transition from current $\rightarrow$ new projection is
 safe}
 
-Given the projection that the server is currently using,
+Given the current projection
 $P_{current}$, the projection $P_{latest}$ is evaluated by numerous
 rules and invariants, relative to $P_{current}$.
 If such rule or invariant is
 violated/false, then the local server will discard $P_{latest}$.
 
-The transition from $P_{current} \rightarrow P_{latest}$ is checked
+The transition from $P_{current} \rightarrow P_{latest}$ is protected
-for safety and sanity.  The conditions used for the check include:
+by rules and invariants that include:
 
 \begin{enumerate}
 \item The Erlang data types of all record members are correct.
@@ -1073,161 +1020,13 @@ for safety and sanity.  The conditions used for the check include:
   The same re-reordering restriction applies to all
   servers in $P_{latest}$'s repairing list relative to
   $P_{current}$'s repairing list.
-\item Any server $S$ that was added to $P_{latest}$'s UPI list must
+\item Any server $S$ that is newly-added to $P_{latest}$'s UPI list must
   appear in the tail the UPI list.  Furthermore, $S$ must have been in
   $P_{current}$'s repairing list and had successfully completed file
-  repair prior to the transition.
+  repair prior to $S$'s promotion from the repairing list to the tail
+  of the UPI list.
 \end{enumerate}
 
-\subsection{Additional discussion of flapping state}
-\label{sub:flapping-state}
-All $P_{new}$ projections
-calculated while in flapping state have additional diagnostic
-information added, including:
-
-\begin{itemize}
-\item Flag: server $S$ is in flapping state.
-\item Epoch number \& wall clock timestamp when $S$ entered flapping state.
-\item The collection of all other known participants who are also
-  flapping (with respective starting epoch numbers).
-\item A list of nodes that are suspected of being partitioned, called the
-  ``hosed list''.  The hosed list is a union of all other hosed list
-  members that are ever witnessed, directly or indirectly, by a server
-  while in flapping state.
-\end{itemize}
-
-\subsubsection{Flapping diagnostic data accumulates}
-
-While in flapping state, this diagnostic data is gathered from
-all available participants and merged together in a CRDT-like manner.
-Once added to the diagnostic data list, a datum remains until
-$S$ drops out of flapping state.  When flapping state stops, all
-accumulated diagnostic data is discarded.
-
-This accumulation of diagnostic data in the projection data
-structure acts in part as a substitute for a separate gossip protocol.
-However, since all participants are already communicating with each
-other via read \& writes to each others' projection stores, the diagnostic
-data can propagate in a gossip-like manner via the projection stores.
-
-\subsubsection{Flapping example (part 1)}
-\label{ssec:flapping-example}
-
-Any server listed in the ``hosed list'' is suspected of having some
-kind of network communication problem with some other server.  For
-example, let's examine a scenario involving a Machi cluster of servers
-$a$, $b$, $c$, $d$, and $e$.  Assume there exists an asymmetric network
-partition such that messages from $a \rightarrow b$ are dropped, but
-messages from $b \rightarrow a$ are delivered.\footnote{If this
-  partition were happening at or below the level of a reliable
-  delivery network protocol like TCP, then communication in {\em both}
-  directions would be affected by an asymmetric partition.
-  However, in this model, we are
-  assuming that a ``message'' lost during a network partition is a
-  uni-directional projection API call or its response.}
-
-Once a participant $S$ enters flapping state, it starts gathering the
-flapping starting epochs and hosed lists from all of the other
-projection stores that are available.  The sum of this info is added
-to all projections calculated by $S$.
-For example, projections authored by $a$ will say that $a$ believes
-that $b$ is down. 
-Likewise, projections authored by $b$ will say that $b$ believes
-that $a$ is down. 
-
-\subsubsection{The inner projection (flapping example, part 2)}
-\label{ssec:inner-projection}
-
-\ldots We continue the example started in the previous subsection\ldots
-
-Eventually, in a gossip-like manner, all other participants will
-eventually find that their hosed list is equal to $[a,b]$.  Any other
-server, for example server $c$, will then calculate another
-projection, $P_{new2}$, using the assumption that both $a$ and $b$
-are down in addition to all other known unavailable servers.
-
-\begin{itemize}
-\item If operating in the default CP mode, both $a$ and $b$ are down
-  and therefore not eligible to participate in Chain Replication.
-  %% The chain may continue service if a $c$, $d$, $e$ and/or witness
-  %% servers can try to form a correct UPI list for the chain.
-  This may cause an availability problem for the chain: we may not
-  have a quorum of participants (real or witness-only) to form a
-  correct UPI chain.
-\item If operating in AP mode, $a$ and $b$ can still form two separate
-  chains of length one, using UPI lists of $[a]$ and $[b]$, respectively. 
-\end{itemize}
-
-This re-calculation, $P_{new2}$, of the new projection is called an
-``inner projection''.  The inner projection definition is nested
-inside of its parent projection, using the same flapping disagnostic
-data used for other flapping status tracking.
-
-When humming consensus has determined that a projection state change
-is necessary and is also safe (relative to both the outer and inner
-projections), then the outer projection\footnote{With the inner
-  projection $P_{new2}$ nested inside of it.} is written to
-the local private projection store.
-With respect to future iterations of
-humming consensus, the innter projection is ignored.
-However, with respect to Chain Replication, the server's subsequent
-behavior 
-{\em will consider the inner projection only}.  The inner projection
-is used to order the UPI and repairing parts of the chain and trigger
-wedge/un-wedge behavior.  The inner projection is also
-advertised to Machi clients.
-
-The epoch of the inner projection, $E^{inner}$ is always less than or
-equal to the epoch of the outer projection, $E$.  The $E^{inner}$
-epoch typically only changes when new servers are added to the hosed
-list.
-
-To attempt a rough analogy, the outer projection is the carrier wave
-that is used to transmit the inner projection and its accompanying
-gossip of diagnostic data.
-
-\subsubsection{Outer projection churn, inner projection stability}
-
-One of the intriguing features of humming consensus's reaction to
-asymmetric partition: flapping behavior continues for as long as
-an any asymmetric partition exists.
-
-\subsubsection{Stability in symmetric partition cases}
-
-Although humming consensus hasn't been formally proven to handle all
-asymmetric and symmetric partition cases, the current implementation
-appears to converge rapidly to a single chain state in all symmetric
-partition cases.  This is in contrast to asymmetric partition cases,
-where ``flapping'' will continue on every humming consensus iteration
-until all asymmetric partition disappears.  A formal proof is an area of
-future work.
-
-\subsubsection{Leaving flapping state and discarding inner projection}
-
-There are two events that can trigger leaving flapping state.
-
-\begin{itemize}
-
-\item A server $S$ in flapping state notices that its long history of
-  repeatedly suggesting the same projection will be broken:
-  $S$ instead calculates some differing projection instead.
-  This change in projection history happens whenever a perceived network
-  partition changes in any way.
-
-\item Server $S$ reads a public projection suggestion, $P_{noflap}$, that is
-  authored by another server $S'$, and that $P_{noflap}$ no longer
-  contains the flapping start epoch for $S'$ that is present in the
-  history that $S$ has maintained while $S$ has been in
-  flapping state.
-
-\end{itemize}
-
-When either trigger event happens, server $S$ will exit flapping state.  All
-new projections authored by $S$ will have all flapping diagnostic data
-removed.  This includes stopping use of the inner projection: the UPI
-list of the inner projection is copied to the outer projection's UPI
-list, to avoid a drastic change in UPI membership.
-
 \subsection{Ranking projections}
 \label{sub:ranking-projections}
 
@@ -1480,7 +1279,7 @@ as the foundation for Machi's data loss prevention techniques.
 \begin{figure}
 \centering
 $
-[\overbrace{\underbrace{H_1}_\textbf{Head}, M_{11}, T_1,
+[\overbrace{\underbrace{H_1}_\textbf{Head}, M_{11}, \ldots, T_1,
                         H_2, M_{21},
                         \ldots
                         \underbrace{T_2}_\textbf{Tail}}^\textbf{Chain (U.P.~Invariant preserving)}
@@ -1789,7 +1588,7 @@ Manageability, availability and performance in Porcupine: a highly scalable, clu
 {\tt http://homes.cs.washington.edu/\%7Elevy/ porcupine.pdf}
 
 \bibitem{chain-replication}
-van Renesse, Robbert et al.
+van Renesse, Robbert and Schneider, Fred.
 Chain Replication for Supporting High Throughput and Availability.
 Proceedings of the 6th Conference on Symposium on Operating Systems
 Design \& Implementation (OSDI'04) - Volume 6, 2004.

doc/src.high-level/high-level-machi.tex

@@ -1489,7 +1489,7 @@ In Usenix ATC 2009.
 {\tt https://www.usenix.org/legacy/event/usenix09/ tech/full\_papers/terrace/terrace.pdf}
 
 \bibitem{chain-replication}
-van Renesse, Robbert et al.
+van Renesse, Robbert and Schneider, Fred.
 Chain Replication for Supporting High Throughput and Availability.
 Proceedings of the 6th Conference on Symposium on Operating Systems
 Design \& Implementation (OSDI'04) - Volume 6, 2004.

filter-dialyzer-dep-warnings

@@ -1,12 +0,0 @@
-####################### patterns for general errors in dep modules:
-^protobuffs\.erl:
-^protobuffs_[a-z_]*\.erl:
-^leexinc\.hrl:[0-9][0-9]*: 
-^machi_chain_manager1.erl:[0-9][0-9]*: Guard test RetrospectiveP::'false' =:= 'true' can never succeed
-^machi_pb\.erl:[0-9][0-9]*: 
-^pokemon_pb\.erl:[0-9][0-9]*: 
-####################### patterns for unknown functions:
-^  basho_bench_config:get/2
-^  erl_prettypr:format/1
-^  erl_syntax:form_list/1
-^  machi_partition_simulator:get/1

include/machi.hrl

@@ -18,10 +18,9 @@
 %%
 %% -------------------------------------------------------------------
 
--define(MAX_FILE_SIZE, 256*1024*1024).     % 256 MBytes
+%% @doc Now 4GiBytes, could be up to 64bit due to PB message limit of
--define(MAX_CHUNK_SIZE, ((1 bsl 32) - 1)).
+%% chunk size
-%% -define(DATA_DIR, "/Volumes/SAM1/seq-tests/data").
+-define(DEFAULT_MAX_FILE_SIZE, ((1 bsl 32) - 1)).
--define(DATA_DIR, "./data").
 -define(MINIMUM_OFFSET, 1024).
 
 %% 0th draft of checksum typing with 1st byte.
@@ -30,8 +29,35 @@
 -define(CSUM_TAG_SERVER_SHA, 2).             % Server-genereated SHA1
 -define(CSUM_TAG_SERVER_REGEN_SHA, 3).       % Server-regenerated SHA1
 
+-define(CSUM_TAG_NONE_ATOM, none).
+-define(CSUM_TAG_CLIENT_SHA_ATOM, client_sha).
+-define(CSUM_TAG_SERVER_SHA_ATOM, server_sha).
+-define(CSUM_TAG_SERVER_REGEN_SHA_ATOM, server_regen_sha).
+
 %% Protocol Buffers goop
 -define(PB_MAX_MSG_SIZE, (33*1024*1024)).
 -define(PB_PACKET_OPTS, [{packet, 4}, {packet_size, ?PB_MAX_MSG_SIZE}]).
 
+%% TODO: it's used in flu_sup and elsewhere, change this to suitable name
 -define(TEST_ETS_TABLE, test_ets_table).
+
+-define(DEFAULT_COC_NAMESPACE, "").
+-define(DEFAULT_COC_LOCATOR,    0).
+
+-record(ns_info, {
+          version = 0  :: machi_dt:namespace_version(),
+          name = <<>>  :: machi_dt:namespace(),
+          locator = 0  :: machi_dt:locator()
+         }).
+
+-record(append_opts, {
+          chunk_extra = 0             :: machi_dt:chunk_size(),
+          preferred_file_name         :: 'undefined' | machi_dt:file_name_s(),
+          flag_fail_preferred = false :: boolean()
+         }).
+
+-record(read_opts, {
+          no_checksum = false         :: boolean(),
+          no_chunk = false            :: boolean(),
+          needs_trimmed = false       :: boolean()
+         }).

include/machi_merkle_tree.hrl

@@ -0,0 +1,20 @@
+%% machi merkle tree records
+
+-record(naive, {
+          chunk_size = 1048576   :: pos_integer(), %% default 1 MB
+          recalc = true          :: boolean(),
+          root                   :: 'undefined' | binary(),
+          lvl1 = []              :: [ binary() ],
+          lvl2 = []              :: [ binary() ],
+          lvl3 = []              :: [ binary() ],
+          leaves = []            :: [ { Offset :: pos_integer(),
+                                        Size :: pos_integer(),
+                                        Csum :: binary()} ]
+         }).
+
+-record(mt, {
+          filename               :: string(),
+          tree                   :: #naive{},
+          backend = 'naive'      :: 'naive'
+         }).
+

include/machi_projection.hrl

@@ -1,6 +1,6 @@
 %% -------------------------------------------------------------------
 %%
-%% Copyright (c) 2007-2014 Basho Technologies, Inc.  All Rights Reserved.
+%% Copyright (c) 2007-2015 Basho Technologies, Inc.  All Rights Reserved.
 %%
 %% This file is provided to you under the Apache License,
 %% Version 2.0 (the "License"); you may not use this file
@@ -22,10 +22,11 @@
 -define(MACHI_PROJECTION_HRL, true).
 
 -type pv1_consistency_mode() :: 'ap_mode' | 'cp_mode'.
+-type pv1_chain_name():: atom().
 -type pv1_csum()      :: binary().
 -type pv1_epoch()     :: {pv1_epoch_n(), pv1_csum()}.
 -type pv1_epoch_n()   :: non_neg_integer().
--type pv1_server()    :: atom() | binary().
+-type pv1_server()    :: atom().
 -type pv1_timestamp() :: {non_neg_integer(), non_neg_integer(), non_neg_integer()}.
 
 -record(p_srvr, {
@@ -55,6 +56,7 @@
           epoch_number    :: pv1_epoch_n() | ?SPAM_PROJ_EPOCH,
           epoch_csum      :: pv1_csum(),
           author_server   :: pv1_server(),
+          chain_name = ch_not_def_yet :: pv1_chain_name(),
           all_members     :: [pv1_server()],
           witnesses = []  :: [pv1_server()],
           creation_time   :: pv1_timestamp(),
@@ -75,4 +77,16 @@
 %% create a consistent projection ranking score.
 -define(MAX_CHAIN_LENGTH, 64).
 
+-record(chain_def_v1, {
+          name            :: atom(),         % chain name
+          mode            :: pv1_consistency_mode(),
+          full = []       :: [p_srvr()],
+          witnesses = []  :: [p_srvr()],
+          old_full = []   :: [pv1_server()], % guard against some races
+          old_witnesses=[] :: [pv1_server()], % guard against some races
+          local_run = []  :: [pv1_server()], % must be tailored to each machine!
+          local_stop = [] :: [pv1_server()], % must be tailored to each machine!
+          props = []      :: list()   % proplist for other related info
+         }).
+
 -endif. % !MACHI_PROJECTION_HRL

priv/humming-consensus-demo.setup.sh

@@ -0,0 +1,56 @@
+#!/bin/sh
+
+echo "Step: Verify that the required entries in /etc/hosts are present"
+for i in 1 2 3; do
+    grep machi$i /etc/hosts | egrep -s '^127.0.0.1' > /dev/null 2>&1
+    if [ $? -ne 0 ]; then
+        echo ""
+        echo "'grep -s machi$i' failed. Aborting, sorry."
+        exit 1
+    fi
+    ping -c 1 machi$i > /dev/null 2>&1
+    if [ $? -ne 0 ]; then
+        echo ""
+        echo "Ping attempt on host machi$i failed. Aborting."
+        echo ""
+        ping -c 1 machi$i
+        exit 1
+    fi
+done
+
+echo "Step: add a verbose logging option to app.config"
+for i in 1 2 3; do
+    ed ./dev/dev$i/etc/app.config <<EOF > /dev/null 2>&1
+/verbose_confirm
+a
+{chain_manager_opts, [{private_write_verbose_confirm,true}]},
+{stability_time, 1},
+.
+w
+q
+EOF
+done
+
+echo "Step: start three three Machi application instances"
+for i in 1 2 3; do
+    ./dev/dev$i/bin/machi start
+    ./dev/dev$i/bin/machi ping
+    if [ $? -ne 0 ]; then
+        echo "Sorry, a 'ping' check for instance dev$i failed. Aborting."
+        exit 1
+    fi
+done
+
+echo "Step: configure one chain to start a Humming Consensus group with three members"
+
+# Note: $CWD of each Machi proc is two levels below the source code root dir.
+LIFECYCLE000=../../priv/quick-admin-examples/demo-000
+for i in 3 2 1; do
+    ./dev/dev$i/bin/machi-admin quick-admin-apply $LIFECYCLE000 machi$i
+    if [ $? -ne 0 ]; then
+        echo "Sorry, 'machi-admin quick-admin-apply failed' on machi$i. Aborting."
+        exit 1
+    fi
+done
+
+exit 0

priv/humming-consensus-demo.vagrant/Vagrantfile

@@ -0,0 +1,93 @@
+# -*- mode: ruby -*-
+# vi: set ft=ruby :
+
+# All Vagrant configuration is done below. The "2" in Vagrant.configure
+# configures the configuration version (we support older styles for
+# backwards compatibility). Please don't change it unless you know what
+# you're doing.
+Vagrant.configure(2) do |config|
+  # The most common configuration options are documented and commented below.
+  # For a complete reference, please see the online documentation at
+  # https://docs.vagrantup.com.
+
+  # Every Vagrant development environment requires a box. You can search for
+  # boxes at https://atlas.hashicorp.com/search.
+  # If this Vagrant box has not been downloaded before (e.g. using "vagrant box add"),
+  # then Vagrant will automatically download the VM image from HashiCorp.
+  config.vm.box = "hashicorp/precise64"
+  # If using a FreeBSD box, Bash may not be installed.
+  # Use the config.ssh.shell setting to specify an alternate shell.
+  # Note, however, that any code in the 'config.vm.provision' section
+  # would then have to use this shell's syntax!
+  #   config.ssh.shell = "/bin/csh -l"
+
+  # Disable automatic box update checking. If you disable this, then
+  # boxes will only be checked for updates when the user runs
+  # `vagrant box outdated`. This is not recommended.
+  # config.vm.box_check_update = false
+
+  # Create a forwarded port mapping which allows access to a specific port
+  # within the machine from a port on the host machine. In the example below,
+  # accessing "localhost:8080" will access port 80 on the guest machine.
+  # config.vm.network "forwarded_port", guest: 80, host: 8080
+
+  # Create a private network, which allows host-only access to the machine
+  # using a specific IP.
+  # config.vm.network "private_network", ip: "192.168.33.10"
+
+  # Create a public network, which generally matched to bridged network.
+  # Bridged networks make the machine appear as another physical device on
+  # your network.
+  # config.vm.network "public_network"
+
+  # Share an additional folder to the guest VM. The first argument is
+  # the path on the host to the actual folder. The second argument is
+  # the path on the guest to mount the folder. And the optional third
+  # argument is a set of non-required options.
+  # config.vm.synced_folder "../data", "/vagrant_data"
+
+  # Provider-specific configuration so you can fine-tune various
+  # backing providers for Vagrant. These expose provider-specific options.
+  # Example for VirtualBox:
+  #
+  config.vm.provider "virtualbox" do |vb|
+    # Display the VirtualBox GUI when booting the machine
+    # vb.gui = true
+ 
+    # Customize the amount of memory on the VM:
+    vb.memory = "512"
+  end
+  #
+  # View the documentation for the provider you are using for more
+  # information on available options.
+
+  # Define a Vagrant Push strategy for pushing to Atlas. Other push strategies
+  # such as FTP and Heroku are also available. See the documentation at
+  # https://docs.vagrantup.com/v2/push/atlas.html for more information.
+  # config.push.define "atlas" do |push|
+  #   push.app = "YOUR_ATLAS_USERNAME/YOUR_APPLICATION_NAME"
+  # end
+
+  # Enable provisioning with a shell script. Additional provisioners such as
+  # Puppet, Chef, Ansible, Salt, and Docker are also available. Please see the
+  # documentation for more information about their specific syntax and use.
+  config.vm.provision "shell", inline: <<-SHELL
+    # Install prerequsites
+    # Support here for FreeBSD is experimental
+    apt-get update ; sudo apt-get install -y git sudo rsync ; # Ubuntu Linux
+    env ASSUME_ALWAYS_YES=yes pkg install -f git sudo rsync ; # FreeBSD 10
+
+    # Install dependent packages, using slf-configurator
+    git clone https://github.com/slfritchie/slf-configurator.git
+    chown -R vagrant ./slf-configurator
+    (cd slf-configurator ; sudo sh -x ./ALL.sh)
+    echo 'export PATH=${PATH}:/usr/local/erlang/17.5/bin' >> ~vagrant/.bashrc
+    export PATH=${PATH}:/usr/local/erlang/17.5/bin
+    ## echo 'set path = ( $path  /usr/local/erlang/17.5/bin )' >> ~vagrant/.cshrc
+    ## setenv PATH /usr/local/erlang/17.5/bin:$PATH
+
+    git clone https://github.com/basho/machi.git
+    (cd machi ; git checkout master ; make && make test )
+    chown -R vagrant ./machi
+  SHELL
+end

priv/make-faq.pl

@@ -36,7 +36,7 @@ while (<I>) {
             $indent = " " x ($count * 4);
             s/^#*\s*[0-9. ]*//;
             $anchor = "n$label";
-            printf T1 "%s+ [%s %s](#%s)\n", $indent, $label, $_, $anchor;
+            printf T1 "%s+ [%s. %s](#%s)\n", $indent, $label, $_, $anchor;
             printf T2 "<a name=\"%s\">\n", $anchor;
             $line =~ s/(#+)\s*[0-9. ]*/$1 $label.  /;
             print T2 $line;

priv/quick-admin-examples/000

@@ -0,0 +1 @@
+{host, "localhost", []}.

priv/quick-admin-examples/001

@@ -0,0 +1,4 @@
+{flu,f1,"localhost",20401,[]}.
+{flu,f2,"localhost",20402,[]}.
+{flu,f3,"localhost",20403,[]}.
+{chain,c1,[f1,f2,f3],[]}.

priv/quick-admin-examples/002

@@ -0,0 +1,4 @@
+{flu,f4,"localhost",20404,[]}.
+{flu,f5,"localhost",20405,[]}.
+{flu,f6,"localhost",20406,[]}.
+{chain,c2,[f4,f5,f6],[]}.

priv/quick-admin-examples/demo-000

@@ -0,0 +1,7 @@
+{host, "machi1", []}.
+{host, "machi2", []}.
+{host, "machi3", []}.
+{flu,f1,"machi1",20401,[]}.
+{flu,f2,"machi2",20402,[]}.
+{flu,f3,"machi3",20403,[]}.
+{chain,c1,[f1,f2,f3],[]}.

priv/test-for-gh-pr.sh

@@ -4,6 +4,7 @@ if [ "${TRAVIS_PULL_REQUEST}" = "false" ]; then
 	echo '$TRAVIS_PULL_REQUEST is false, skipping tests'
 	exit 0
 else
-	echo '$TRAVIS_PULL_REQUEST is not false, running tests'
+	echo '$TRAVIS_PULL_REQUEST is not false ($TRAVIS_PULL_REQUEST), running tests'
 	make test
+	make dialyzer
 fi

rebar.config

@@ -1,15 +1,20 @@
-{require_otp_vsn, "17"}.
+{require_otp_vsn, "17|18"}.
 
 %%% {erl_opts, [warnings_as_errors, {parse_transform, lager_transform}, debug_info]}.
 {erl_opts, [{parse_transform, lager_transform}, debug_info]}.
 {edoc_opts, [{dir, "./edoc"}]}.
 
 {deps, [
+        {cuttlefish, ".*", {git, "git://github.com/basho/cuttlefish.git", {branch, "develop"}}},
+        {sext, ".*", {git, "git://github.com/basho/sext.git", {branch, "master"}}},
+        {eleveldb, ".*", {git, "git://github.com/basho/eleveldb.git", {branch, "develop"}}},
         {lager, ".*", {git, "git://github.com/basho/lager.git", {tag, "2.2.0"}}},
         {protobuffs, "0.8.*", {git, "git://github.com/basho/erlang_protobuffs.git", {tag, "0.8.1p4"}}},
         {riak_dt, ".*", {git, "git://github.com/basho/riak_dt.git", {branch, "develop"}}},
+        {ranch, ".*", {git, "git://github.com/ninenines/ranch.git", {branch, "master"}}},
         {node_package, ".*", {git, "git://github.com/basho/node_package.git", {branch, "develop"}}},
-        {eper, ".*", {git, "git://github.com/basho/eper.git", {tag, "0.78"}}}
+        {eper, ".*", {git, "git://github.com/basho/eper.git", {tag, "0.92-basho1"}}},
+        {cluster_info, ".*", {git, "git://github.com/basho/cluster_info", {branch, "develop"}}}
         ]}.
 
 {sub_dirs, ["rel", "apps/machi"]}.

rel/files/app.config

@@ -1,25 +1,35 @@
 [
  {machi, [
           %% Data directory for all FLUs.
-          {flu_data_dir, "{{platform_data_dir}}"},
+          {flu_data_dir, "{{platform_data_dir}}/flu"},
+
+          %% FLU config directory
+          {flu_config_dir, "{{platform_etc_dir}}/flu-config"},
+
+          %% Chain config directory
+          {chain_config_dir, "{{platform_etc_dir}}/chain-config"},
 
           %% FLUs to start at app start.
-          {initial_flus, [
+          %% This task has moved to machi_flu_sup and machi_lifecycle_mgr.
-                          %% Remember, this is a list, so separate all tuples
-                          %% with a comma.
-                          %%
-                          %% {Name::atom(), Port::pos_integer(), proplist()}
-                          %%
-                          %% For example: {my_name_is_a, 12500, []}
-
-                         ]},
 
           %% Number of metadata manager processes to run per FLU.
           %% Default = 10
           %% {metadata_manager_count, 2},
 
+          %% Default options for chain manager processes.
+          %% {chain_manager_opts, [{private_write_verbose,true},
+          %%                       {private_write_verbose_confirm,true}]},
+
+          %% Platform vars (mirror of reltool packaging)
+          {platform_data_dir, "{{platform_data_dir}}"},
+          {platform_etc_dir,  "{{platform_etc_dir}}"},
+
           %% Do not delete, do not put Machi config items after this line.
           {final_comma_stopper, do_not_delete}
          ]
+  },
+  {lager, [
+           {error_logger_hwm, 5000} % lager's default of 50/sec is too low
+          ]
   }
 ].

rel/files/machi-admin

@@ -22,23 +22,41 @@ cd $RUNNER_BASE_DIR
 SCRIPT=`basename $0`
 
 usage() {
-    echo "Usage: $SCRIPT { test | "
+    echo "Usage: $SCRIPT { quick-admin-check | quick-admin-apply | "
     echo "                    top }"
 }
 
 case "$1" in
-    test)
+    quick-admin-check)
         # Make sure the local node IS running
         node_up_check
 
         shift
 
-        # Parse out the node name to pass to the client
+        NODE_NAME=${NAME_ARG#* } # target machi server node name
-        NODE_NAME=${NAME_ARG#* }
+        IN_FILE="$1"
 
-        $ERTS_PATH/erl -noshell $NAME_PARAM machi_test$NAME_HOST $COOKIE_ARG \
+        $ERTS_PATH/erl -noshell -noinput $NAME_PARAM machi_test$NAME_HOST $COOKIE_ARG \
-                       -pa $RUNNER_LIB_DIR/basho-patches \
+                       -remsh $NODE_NAME \
-                       -eval "case catch(machi:client_test(\"$NODE_NAME\")) of \
+                       -eval "Me = self(), spawn('"$NODE_NAME"', fun() -> X = (catch(machi_lifecycle_mgr:quick_admin_sanity_check(\"$IN_FILE\"))), Me ! {res, X} end), XX = receive {res, Res} -> Res after 10*1000 -> timeout end, io:format(user, \"Result: ~p\n\", [XX]), case XX of \
+                               ok -> init:stop();                             \
+                               _  -> init:stop(1)                             \
+                              end."
+
+        ;;
+    quick-admin-apply)
+        # Make sure the local node IS running
+        node_up_check
+
+        shift
+
+        NODE_NAME=${NAME_ARG#* } # target machi server node name
+        IN_FILE="$1"
+        RELATIVE_HOST="$2"
+
+        $ERTS_PATH/erl -noshell -noinput $NAME_PARAM machi_test$NAME_HOST $COOKIE_ARG \
+                       -remsh $NODE_NAME \
+                       -eval "Me = self(), spawn('"$NODE_NAME"', fun() -> X = (catch(machi_lifecycle_mgr:quick_admin_apply(\"$IN_FILE\", \"$RELATIVE_HOST\"))), Me ! {res, X} end), XX = receive {res, Res} -> Res after 10*1000 -> timeout end, io:format(user, \"Result: ~p\n\", [XX]), case XX of \
                                ok -> init:stop();                             \
                                _  -> init:stop(1)                             \
                               end."

rel/gen_dev

@@ -0,0 +1,16 @@
+#! /bin/sh
+#
+# Example usage: gen_dev dev4 vars.src vars
+#
+# Generate an overlay config for devNNN from vars.src and write to vars
+#
+
+NAME=$1
+TEMPLATE=$2
+VARFILE=$3
+
+NODE="$NAME@127.0.0.1"
+
+echo "Generating $NAME - node='$NODE'"
+sed -e "s/@NODE@/$NODE/" \
+    < $TEMPLATE > $VARFILE

rel/reltool.config

@@ -47,6 +47,7 @@
 
 {overlay, [
            {mkdir, "data"},
+           {mkdir, "data/^PRESERVE"},
            {mkdir, "log"},
 
            %% Copy base files for starting and interacting w/ node
@@ -93,6 +94,20 @@
 
            {template, "files/vm.args", "etc/vm.args"},
            {template, "files/app.config", "etc/app.config"},
+           {mkdir, "etc/chain-config"},
+           {mkdir, "etc/flu-config"},
+           {mkdir, "etc/pending"},
+           {mkdir, "etc/rejected"},
+
+           %% Experiment: quick-admin
+           {mkdir, "etc/quick-admin-archive"},
+           {mkdir, "priv"},
+           {mkdir, "priv/quick-admin-examples"},
+           {copy, "../priv/quick-admin-examples/000", "priv/quick-admin-examples"},
+           {copy, "../priv/quick-admin-examples/001", "priv/quick-admin-examples"},
+           {copy, "../priv/quick-admin-examples/002", "priv/quick-admin-examples"},
+           {copy, "../priv/quick-admin-examples/demo-000", "priv/quick-admin-examples/demo-000"},
+
            {mkdir, "lib/basho-patches"}
            %% {copy, "../apps/machi/ebin/etop_txt.beam", "lib/basho-patches"}
           ]}.

rel/vars.config

@@ -1,6 +1,9 @@
 %% -*- mode: erlang;erlang-indent-level: 4;indent-tabs-mode: nil -*-
 %% ex: ft=erlang ts=4 sw=4 et
 
+%% NOTE: When modifying this file, also keep its near cousin
+%%       config file rel/vars/dev_vars.config.src in sync!
+
 %% Platform-specific installation paths
 {platform_bin_dir,  "./bin"}.
 {platform_data_dir, "./data"}.

rel/vars/dev_vars.config.src

@@ -0,0 +1,48 @@
+%% -*- mode: erlang;erlang-indent-level: 4;indent-tabs-mode: nil -*-
+%% ex: ft=erlang ts=4 sw=4 et
+
+%% NOTE: When modifying this file, also keep its near cousin
+%%       config file rel/vars/dev_vars.config.src in sync!
+
+%% Platform-specific installation paths
+{platform_bin_dir,  "./bin"}.
+{platform_data_dir, "./data"}.
+{platform_etc_dir,  "./etc"}.
+{platform_lib_dir,  "./lib"}.
+{platform_log_dir,  "./log"}.
+
+%%
+%% etc/app.config
+%%
+{sasl_error_log,    "{{platform_log_dir}}/sasl-error.log"}.
+{sasl_log_dir,      "{{platform_log_dir}}/sasl"}.
+
+%% lager
+{console_log_default, file}.
+
+%%
+%% etc/vm.args
+%%
+{node,         "@NODE@"}.
+{crash_dump,   "{{platform_log_dir}}/erl_crash.dump"}.
+
+%%
+%% bin/machi
+%%
+{runner_script_dir,  "\`cd \\`dirname $0\\` 1>/dev/null && /bin/pwd\`"}.
+{runner_base_dir,    "{{runner_script_dir}}/.."}.
+{runner_etc_dir,     "$RUNNER_BASE_DIR/etc"}.
+{runner_log_dir,     "$RUNNER_BASE_DIR/log"}.
+{runner_lib_dir,     "$RUNNER_BASE_DIR/lib"}.
+{runner_patch_dir,   "$RUNNER_BASE_DIR/lib/basho-patches"}.
+{pipe_dir,           "/tmp/$RUNNER_BASE_DIR/"}.
+{runner_user,        ""}.
+{runner_wait_process, "machi_flu_sup"}.
+{runner_ulimit_warn, 65536}.
+
+%%
+%% cuttlefish
+%%
+{cuttlefish,         ""}. % blank = off
+{cuttlefish_conf,    "machi.conf"}.
+

src/machi.app.src

@@ -1,13 +1,10 @@
 {application, machi, [
     {description, "A village of write-once files."},
-    {vsn, "0.0.0"},
+    {vsn, "0.0.1"},
-    {applications, [kernel, stdlib, crypto]},
+    {applications, [kernel, stdlib, crypto, cluster_info, ranch]},
     {mod,{machi_app,[]}},
     {registered, []},
     {env, [
-           {flu_list,
+    %% Don't use this static env for defaults, or we will fall into config hell.
-            [
-             %%%%%% {flu_a, 32900, "./data.flu_a"}
-            ]}
     ]}
 ]}.

src/machi.proto

@@ -48,9 +48,10 @@ enum Mpb_GeneralStatusCode {
      PARTITION = 4;
      NOT_WRITTEN = 5;
      WRITTEN = 6;
-     NO_SUCH_FILE = 7;
+     TRIMMED = 7; // The whole file was trimmed
-     PARTIAL_READ = 8;
+     NO_SUCH_FILE = 8;
-     BAD_EPOCH = 9;
+     PARTIAL_READ = 9;
+     BAD_EPOCH = 10;
      BAD_JOSS = 255;    // Only for testing by the Taipan
 }
 
@@ -86,6 +87,14 @@ message Mpb_ChunkCSum {
     optional bytes csum = 2;
 }
 
+message Mpb_Chunk {
+    required uint64 offset = 1;
+    required string file_name = 2;
+    required bytes chunk = 3;
+    // TODO: must be required, in future?
+    optional Mpb_ChunkCSum csum = 4;
+}
+
 // epoch_id() type
 message Mpb_EpochID {
     required uint32 epoch_number = 1;
@@ -161,11 +170,18 @@ message Mpb_AuthResp {
 // High level API: append_chunk() request & response
 
 message Mpb_AppendChunkReq {
-    optional bytes placement_key = 1;
+    // General namespace arguments
-    required string prefix = 2;
+    /* In single chain/non-clustered environment, use namespace="" */
-    required bytes chunk = 3;
+    required string namespace = 1;
-    required Mpb_ChunkCSum csum = 4;
+
-    optional uint32 chunk_extra = 5;
+    required string prefix = 10;
+    required bytes chunk = 11;
+    required Mpb_ChunkCSum csum = 12;
+
+    optional uint32 chunk_extra = 20;
+    optional string preferred_file_name = 21;
+    /* Fail the operation if our preferred file name is not available */
+    optional bool flag_fail_preferred = 22 [default=false];
 }
 
 message Mpb_AppendChunkResp {
@@ -177,10 +193,7 @@ message Mpb_AppendChunkResp {
 // High level API: write_chunk() request & response
 
 message Mpb_WriteChunkReq {
-    required string file = 1;
+    required Mpb_Chunk chunk = 10;
-    required uint64 offset = 2;
-    required bytes chunk = 3;
-    required Mpb_ChunkCSum csum = 4;
 }
 
 message Mpb_WriteChunkResp {
@@ -190,33 +203,34 @@ message Mpb_WriteChunkResp {
 // High level API: read_chunk() request & response
 
 message Mpb_ReadChunkReq {
-    required string file = 1;
+    // No namespace arguments are required because NS is embedded
-    required uint64 offset = 2;
+    // inside of the file name.
-    required uint32 size = 3;
+
+    required Mpb_ChunkPos chunk_pos = 10;
 
     // Use flag_no_checksum=non-zero to skip returning the chunk's checksum.
     // TODO: not implemented yet.
-    optional uint32 flag_no_checksum = 4 [default=0];
+    optional bool flag_no_checksum = 20 [default=false];
 
     // Use flag_no_chunk=non-zero to skip returning the chunk (which
     // only makes sense if flag_no_checksum is not set).
     // TODO: not implemented yet.
-    optional uint32 flag_no_chunk = 5 [default=0];
+    optional bool flag_no_chunk = 21 [default=false];
+
+    // TODO: not implemented yet.
+    optional bool flag_needs_trimmed = 22 [default=false];
 }
 
 message Mpb_ReadChunkResp {
     required Mpb_GeneralStatusCode status = 1;
-    optional bytes chunk = 2;
+    repeated Mpb_Chunk chunks = 2;
-    optional Mpb_ChunkCSum csum = 3;
+    repeated Mpb_ChunkPos trimmed = 3;
 }
 
-
 // High level API: trim_chunk() request & response
 
 message Mpb_TrimChunkReq {
-    required string file = 1;
+    required Mpb_ChunkPos chunk_pos = 1;
-    required uint64 offset = 2;
-    required uint32 size = 3;
 }
 
 message Mpb_TrimChunkResp {
@@ -240,6 +254,8 @@ message Mpb_ChecksumListResp {
 // High level API: list_files() request & response
 
 message Mpb_ListFilesReq {
+    // TODO: Add flag for file glob/regexp/other filter type
+    // TODO: What else could go wrong?
 }
 
 message Mpb_ListFilesResp {
@@ -326,18 +342,17 @@ message Mpb_ProjectionV1 {
     required uint32 epoch_number = 1;
     required bytes epoch_csum = 2;
     required string author_server = 3;
-    repeated string all_members = 4;
+    required string chain_name = 4;
-    repeated string witnesses = 5;
+    repeated string all_members = 5;
-    required Mpb_Now creation_time = 6;
+    repeated string witnesses = 6;
-    required Mpb_Mode mode = 7;
+    required Mpb_Now creation_time = 7;
-    repeated string upi = 8;
+    required Mpb_Mode mode = 8;
-    repeated string repairing = 9;
+    repeated string upi = 9;
-    repeated string down = 10;
+    repeated string repairing = 10;
-    optional bytes opaque_flap = 11;
+    repeated string down = 11;
-    optional bytes opaque_inner = 12;
+    required bytes opaque_dbg = 12;
-    required bytes opaque_dbg = 13;
+    required bytes opaque_dbg2 = 13;
-    required bytes opaque_dbg2 = 14;
+    repeated Mpb_MembersDictEntry members_dict = 14;
-    repeated Mpb_MembersDictEntry members_dict = 15;
 }
 
 //////////////////////////////////////////
@@ -352,6 +367,7 @@ message Mpb_ProjectionV1 {
 // append_chunk()
 // write_chunk()
 // read_chunk()
+// trim_chunk()
 // checksum_list()
 // list_files()
 // wedge_status()
@@ -372,12 +388,20 @@ message Mpb_ProjectionV1 {
 // Low level API: append_chunk()
 
 message Mpb_LL_AppendChunkReq {
-    required Mpb_EpochID epoch_id = 1;
+    // General namespace arguments
-    optional bytes placement_key = 2;
+    required uint32 namespace_version = 1;
-    required string prefix = 3;
+    required string namespace = 2;
-    required bytes chunk = 4;
+    required uint32 locator = 3;
-    required Mpb_ChunkCSum csum = 5;
+
-    optional uint32 chunk_extra = 6;
+    required Mpb_EpochID epoch_id = 10;
+    required string prefix = 11;
+    required bytes chunk = 12;
+    required Mpb_ChunkCSum csum = 13;
+
+    optional uint32 chunk_extra = 20;
+    optional string preferred_file_name = 21;
+    /* Fail the operation if our preferred file name is not available */
+    optional bool flag_fail_preferred = 22 [default=false];
 }
 
 message Mpb_LL_AppendChunkResp {
@@ -389,11 +413,12 @@ message Mpb_LL_AppendChunkResp {
 // Low level API: write_chunk()
 
 message Mpb_LL_WriteChunkReq {
-    required Mpb_EpochID epoch_id = 1;
+    // General namespace arguments
-    required string file = 2;
+    required uint32 namespace_version = 1;
-    required uint64 offset = 3;
+    required string namespace = 2;
-    required bytes chunk = 4;
+
-    required Mpb_ChunkCSum csum = 5;
+    required Mpb_EpochID epoch_id = 10;
+    required Mpb_Chunk chunk = 11;
 }
 
 message Mpb_LL_WriteChunkResp {
@@ -403,32 +428,54 @@ message Mpb_LL_WriteChunkResp {
 // Low level API: read_chunk()
 
 message Mpb_LL_ReadChunkReq {
-    required Mpb_EpochID epoch_id = 1;
+    // General namespace arguments
-    required string file = 2;
+    required uint32 namespace_version = 1;
-    required uint64 offset = 3;
+    required string namespace = 2;
-    required uint32 size = 4;
+
+    required Mpb_EpochID epoch_id = 10;
+    required Mpb_ChunkPos chunk_pos = 11;
 
     // Use flag_no_checksum=non-zero to skip returning the chunk's checksum.
     // TODO: not implemented yet.
-    optional uint32 flag_no_checksum = 5 [default=0];
+    optional bool flag_no_checksum = 20 [default=false];
 
     // Use flag_no_chunk=non-zero to skip returning the chunk (which
     // only makes sense if flag_checksum is not set).
     // TODO: not implemented yet.
-    optional uint32 flag_no_chunk = 6 [default=0];
+    optional bool flag_no_chunk = 21 [default=false];
+
+    optional bool flag_needs_trimmed = 22 [default=false];
 }
 
 message Mpb_LL_ReadChunkResp {
     required Mpb_GeneralStatusCode status = 1;
-    optional bytes chunk = 2;
+    repeated Mpb_Chunk chunks = 2;
-    optional Mpb_ChunkCSum csum = 3;
+    repeated Mpb_ChunkPos trimmed = 3;
+}
+
+// Low level API: trim_chunk()
+
+message Mpb_LL_TrimChunkReq {
+    // General namespace arguments
+    required uint32 namespace_version = 1;
+    required string namespace = 2;
+
+    required Mpb_EpochID epoch_id = 10;
+    required string file = 11;
+    required uint64 offset = 12;
+    required uint32 size = 13;
+
+    optional bool trigger_gc = 20 [default=false];
+}
+
+message Mpb_LL_TrimChunkResp {
+    required Mpb_GeneralStatusCode status = 1;
 }
 
 // Low level API: checksum_list()
 
 message Mpb_LL_ChecksumListReq {
-    required Mpb_EpochID epoch_id = 1;
+    required string file = 1;
-    required string file = 2;
 }
 
 message Mpb_LL_ChecksumListResp {
@@ -459,7 +506,9 @@ message Mpb_LL_WedgeStatusReq {
 message Mpb_LL_WedgeStatusResp {
     required Mpb_GeneralStatusCode status = 1;
     optional Mpb_EpochID epoch_id = 2;
-    optional uint32 wedged_flag = 3;
+    optional bool wedged_flag = 3;
+    optional uint32 namespace_version = 4;
+    optional string namespace = 5;
 }
 
 // Low level API: delete_migration()
@@ -588,11 +637,12 @@ message Mpb_LL_Request {
     optional Mpb_LL_AppendChunkReq append_chunk = 30;
     optional Mpb_LL_WriteChunkReq write_chunk = 31;
     optional Mpb_LL_ReadChunkReq read_chunk = 32;
-    optional Mpb_LL_ChecksumListReq checksum_list = 33;
+    optional Mpb_LL_TrimChunkReq trim_chunk = 33;
-    optional Mpb_LL_ListFilesReq list_files = 34;
+    optional Mpb_LL_ChecksumListReq checksum_list = 34;
-    optional Mpb_LL_WedgeStatusReq wedge_status = 35;
+    optional Mpb_LL_ListFilesReq list_files = 35;
-    optional Mpb_LL_DeleteMigrationReq delete_migration = 36;
+    optional Mpb_LL_WedgeStatusReq wedge_status = 36;
-    optional Mpb_LL_TruncHackReq trunc_hack = 37;
+    optional Mpb_LL_DeleteMigrationReq delete_migration = 37;
+    optional Mpb_LL_TruncHackReq trunc_hack = 38;
 }
 
 message Mpb_LL_Response {
@@ -622,9 +672,10 @@ message Mpb_LL_Response {
     optional Mpb_LL_AppendChunkResp append_chunk = 30;
     optional Mpb_LL_WriteChunkResp write_chunk = 31;
     optional Mpb_LL_ReadChunkResp read_chunk = 32;
-    optional Mpb_LL_ChecksumListResp checksum_list = 33;
+    optional Mpb_LL_TrimChunkResp trim_chunk = 33;
-    optional Mpb_LL_ListFilesResp list_files = 34;
+    optional Mpb_LL_ChecksumListResp checksum_list = 34;
-    optional Mpb_LL_WedgeStatusResp wedge_status = 35;
+    optional Mpb_LL_ListFilesResp list_files = 35;
-    optional Mpb_LL_DeleteMigrationResp delete_migration = 36;
+    optional Mpb_LL_WedgeStatusResp wedge_status = 36;
-    optional Mpb_LL_TruncHackResp trunc_hack = 37;
+    optional Mpb_LL_DeleteMigrationResp delete_migration = 37;
+    optional Mpb_LL_TruncHackResp trunc_hack = 38;
 }

src/machi_admin_util.erl

@@ -73,8 +73,13 @@ verify_file_checksums_local2(Sock1, EpochID, Path0) ->
         {ok, FH} ->
             File = re:replace(Path, ".*/", "", [{return, binary}]),
             try
-                ReadChunk = fun(_File, Offset, Size) ->
+                ReadChunk = fun(F, Offset, Size) ->
-                                    file:pread(FH, Offset, Size)
+                                    case file:pread(FH, Offset, Size) of
+                                        {ok, Bin} ->
+                                            {ok, {[{F, Offset, Bin, undefined}], []}};
+                                        Err ->
+                                            Err
+                                    end
                             end,
                 verify_file_checksums_common(Sock1, EpochID, File, ReadChunk)
             after
@@ -85,17 +90,18 @@ verify_file_checksums_local2(Sock1, EpochID, Path0) ->
     end.
 
 verify_file_checksums_remote2(Sock1, EpochID, File) ->
+    NSInfo = undefined,
     ReadChunk = fun(File_name, Offset, Size) ->
-                        ?FLU_C:read_chunk(Sock1, EpochID,
+                        ?FLU_C:read_chunk(Sock1, NSInfo, EpochID,
-                                          File_name, Offset, Size)
+                                          File_name, Offset, Size, undefined)
                 end,
     verify_file_checksums_common(Sock1, EpochID, File, ReadChunk).
 
-verify_file_checksums_common(Sock1, EpochID, File, ReadChunk) ->
+verify_file_checksums_common(Sock1, _EpochID, File, ReadChunk) ->
     try
-        case ?FLU_C:checksum_list(Sock1, EpochID, File) of
+        case ?FLU_C:checksum_list(Sock1, File) of
             {ok, InfoBin} ->
-                {Info, _} = machi_csum_table:split_checksum_list_blob_decode(InfoBin),
+                Info = machi_csum_table:split_checksum_list_blob_decode(InfoBin),
                 Res = lists:foldl(verify_chunk_checksum(File, ReadChunk),
                                   [], Info),
                 {ok, Res};
@@ -110,9 +116,11 @@ verify_file_checksums_common(Sock1, EpochID, File, ReadChunk) ->
     end.
 
 verify_chunk_checksum(File, ReadChunk) ->
-    fun({Offset, Size, <<_Tag:1/binary, CSum/binary>>}, Acc) ->
+    fun({0, ?MINIMUM_OFFSET, none}, []) ->
+            [];
+       ({Offset, Size, <<_Tag:1/binary, CSum/binary>>}, Acc) ->
             case ReadChunk(File, Offset, Size) of
-                {ok, Chunk} ->
+                {ok, {[{_, Offset, Chunk, _}], _}} ->
                     CSum2 = machi_util:checksum_chunk(Chunk),
                     if CSum == CSum2 ->
                             Acc;

src/machi_app.erl

@@ -36,12 +36,8 @@
 -export([start/2, stop/1]).
 
 start(_StartType, _StartArgs) ->
-    case machi_sup:start_link() of
+    machi_cinfo:register(),
-        {ok, Pid} ->
+    machi_sup:start_link().
-            {ok, Pid};
-        Error ->
-            Error
-                end.
 
 stop(_State) ->
     ok.

src/machi_basho_bench_driver.erl

@@ -1,6 +1,6 @@
 %% -------------------------------------------------------------------
 %%
-%% Copyright (c) 2007-2015 Basho Technologies, Inc.  All Rights Reserved.
+%% Copyright (c) 2007-2016 Basho Technologies, Inc.  All Rights Reserved.
 %%
 %% This file is provided to you under the Apache License,
 %% Version 2.0 (the "License"); you may not use this file
@@ -43,23 +43,25 @@
 %% could add new entries to this ETS table.
 %%
 %% Now we can use various integer-centric key generators that are
-%% already bundled with basho_bench.
+%% already bundled with basho_bench.  NOTE: this scheme does not allow
+%% mixing of 'append' and 'read' operations in the same config.  Basho
+%% Bench does not support different key generators for different
+%% operations, unfortunately.  The work-around is to run two different
+%% Basho Bench instances: on for 'append' ops with a key generator for
+%% the desired prefix(es), and the other for 'read' ops with an
+%% integer key generator.
 %%
-%% TODO: Add CRC checking, when feasible and when supported on the
+%% TODO: The 'read' operator will always read chunks at exactly the
-%% server side.
+%% byte offset & size as the original append/write ops.  If reads are
-%%
+%% desired at any arbitrary offset & size, then a new strategy is
-%% TODO: As an alternate idea, if we know that the chunks written are
+%% required.
-%% always the same size, and if we don't care about CRC checking, then
-%% all we need to know are the file names & file sizes on the server:
-%% we can then pick any valid offset within that file.  That would
-%% certainly be more scalable than the zillion-row-ETS-table, which is
-%% definitely RAM-hungry.
 
 -module(machi_basho_bench_driver).
 
 -export([new/1, run/4]).
 
 -record(m, {
+          id,
           conn,
           max_key
          }).
@@ -81,7 +83,7 @@ new(Id) ->
                                      {read_concurrency, true}]),
             ets:insert(ETS, {max_key, 0}),
             ets:insert(ETS, {total_bytes, 0}),
-            MaxKeys = load_ets_table(Conn, ETS),
+            MaxKeys = load_ets_table_maybe(Conn, ETS),
             ?INFO("Key preload: finished, ~w keys loaded", [MaxKeys]),
             Bytes = ets:lookup_element(ETS, total_bytes, 2),
             ?INFO("Key preload: finished, chunk list specifies ~s MBytes of chunks",
@@ -90,12 +92,14 @@ new(Id) ->
        true ->
             ok
     end,
-    {ok, #m{conn=Conn}}.
+    {ok, #m{id=Id, conn=Conn}}.
 
 run(append, KeyGen, ValueGen, #m{conn=Conn}=S) ->
     Prefix = KeyGen(),
     Value = ValueGen(),
-    case machi_cr_client:append_chunk(Conn, Prefix, Value, ?THE_TIMEOUT) of
+    CSum = machi_util:make_client_csum(Value),
+    AppendOpts = {append_opts,0,undefined,false}, % HACK FIXME
+    case machi_cr_client:append_chunk(Conn, undefined, Prefix, Value, CSum, AppendOpts, ?THE_TIMEOUT) of
         {ok, Pos} ->
             EtsKey = ets:update_counter(?ETS_TAB, max_key, 1),
             true = ets:insert(?ETS_TAB, {EtsKey, Pos}),
@@ -112,9 +116,26 @@ run(read, KeyGen, _ValueGen, #m{conn=Conn, max_key=MaxKey}=S) ->
     Idx = KeyGen() rem MaxKey,
     %% {File, Offset, Size, _CSum} = ets:lookup_element(?ETS_TAB, Idx, 2),
     {File, Offset, Size} = ets:lookup_element(?ETS_TAB, Idx, 2),
-    case machi_cr_client:read_chunk(Conn, File, Offset, Size, ?THE_TIMEOUT) of
+    ReadOpts = {read_opts,false,false,false}, % HACK FIXME
-        {ok, _Chunk} ->
+    case machi_cr_client:read_chunk(Conn, undefined, File, Offset, Size, ReadOpts, ?THE_TIMEOUT) of
+        {ok, {Chunks, _Trimmed}} ->
+            %% io:format(user, "Chunks ~P\n", [Chunks, 15]),
+            %% {ok, S};
+            case lists:all(fun({File2, Offset2, Chunk, CSum}) ->
+                                   {_Tag, CS} = machi_util:unmake_tagged_csum(CSum),
+                                   CS2 = machi_util:checksum_chunk(Chunk),
+                                   if CS == CS2 ->
+                                           true;
+                                      CS /= CS2 ->
+                                           ?ERROR("Client-side checksum error for file ~p offset ~p expected ~p got ~p\n", [File2, Offset2, CS, CS2]),
+                                           false
+                                   end
+                           end, Chunks) of
+                true ->
                     {ok, S};
+                false ->
+                    {error, bad_checksum, S}
+            end;
         {error, _}=Err ->
             ?ERROR("read file ~p offset ~w size ~w: ~w\n",
                    [File, Offset, Size, Err]),
@@ -132,21 +153,40 @@ find_server_info(_Id) ->
             Ps
     end.
 
+load_ets_table_maybe(Conn, ETS) ->
+    case basho_bench_config:get(operations, undefined) of
+        undefined ->
+            ?ERROR("The 'operations' key is missing from the config file, aborting", []),
+            exit(bad_config);
+        Ops when is_list(Ops) ->
+            case lists:keyfind(read, 1, Ops) of
+                {read,_} ->
+                    load_ets_table(Conn, ETS);
+                false ->
+                    ?INFO("No 'read' op in the 'operations' list ~p, skipping ETS table load.", [Ops]),
+                    0
+            end
+    end.
+
 load_ets_table(Conn, ETS) ->
     {ok, Fs} = machi_cr_client:list_files(Conn),
     [begin
-         {ok, InfoBin} = machi_cr_client:checksum_list(Conn, File),
+         {ok, InfoBin} = machi_cr_client:checksum_list(Conn, File, ?THE_TIMEOUT),
-         {PosList, _} = machi_flu1:split_checksum_list_blob_decode(InfoBin),
+         PosList = machi_csum_table:split_checksum_list_blob_decode(InfoBin),
+         ?INFO("File ~s len PosList ~p\n", [File, length(PosList)]),
          StartKey = ets:update_counter(ETS, max_key, 0),
-         %% _EndKey = lists:foldl(fun({Off,Sz,CSum}, K) ->
+         {_, C, Bytes} = lists:foldl(fun({_Off,0,_CSum}, {_K, _C, _Bs}=Acc) ->
-         %%                               V = {File, Off, Sz, CSum},
+                                             Acc;
-         {_, Bytes} = lists:foldl(fun({Off,Sz,_CSum}, {K, Bs}) ->
+                                        ({0,_Sz,_CSum}, {_K, _C, _Bs}=Acc) ->
+                                             Acc;
+                                        ({Off,Sz,_CSum}, {K, C, Bs}) ->
                                              V = {File, Off, Sz},
                                              ets:insert(ETS, {K, V}),
-                                          {K + 1, Bs + Sz}
+                                             {K + 1, C + 1, Bs + Sz}
-                                  end, {StartKey, 0}, PosList),
+                                     end, {StartKey, 0, 0}, PosList),
-         ets:update_counter(ETS, max_key, length(PosList)),
+         _ = ets:update_counter(ETS, max_key, C),
-         ets:update_counter(ETS, total_bytes, Bytes)
+         _ = ets:update_counter(ETS, total_bytes, Bytes),
+         ok
      end || {_Size, File} <- Fs],
     ets:update_counter(?ETS_TAB, max_key, 0).
 

src/machi_chain_manager1.erl

@@ -92,8 +92,11 @@
 -define(REPAIR_START_STABILITY_TIME, 10).
 -endif. % TEST
 
-%% Magic constant for looping "too frequently" breaker.  TODO revisit & revise.
+%% Maximum length of the history of adopted projections (via C120).
--define(TOO_FREQUENT_BREAKER, 10).
+-define(MAX_HISTORY_LENGTH, 8).
+
+%% Magic constant for looping "too frequently" breaker.
+-define(TOO_FREQUENT_BREAKER, (?MAX_HISTORY_LENGTH+5)).
 
 -define(RETURN2(X), begin (catch put(why2, [?LINE|get(why2)])), X end).
 
@@ -103,20 +106,19 @@
 %% Amount of epoch number skip-ahead for set_chain_members call
 -define(SET_CHAIN_MEMBERS_EPOCH_SKIP, 1111).
 
-%% Maximum length of the history of adopted projections (via C120).
--define(MAX_HISTORY_LENGTH, 30).
-
 %% API
 -export([start_link/2, start_link/3, stop/1, ping/1,
-         set_chain_members/2, set_chain_members/3, set_active/2,
+         set_chain_members/2, set_chain_members/6, set_active/2,
          trigger_react_to_env/1]).
 -export([init/1, handle_call/3, handle_cast/2, handle_info/2,
-         terminate/2, code_change/3]).
+         terminate/2, format_status/2, code_change/3]).
 
 -export([make_chmgr_regname/1, projection_transitions_are_sane/2,
          simple_chain_state_transition_is_sane/3,
          simple_chain_state_transition_is_sane/5,
          chain_state_transition_is_sane/6]).
+-export([perhaps_call/5, % for partition simulator use w/machi_fitness
+         init_remember_down_list/0]).
 %% Exports so that EDoc docs generated for these internal funcs.
 -export([mk/3]).
 
@@ -129,8 +131,7 @@
 -export([test_calc_projection/2,
          test_write_public_projection/2,
          test_read_latest_public_projection/2]).
--export([perhaps_call/5, % for partition simulator use w/machi_fitness
+-export([update_remember_down_list/1,
-         init_remember_down_list/0, update_remember_down_list/1,
          get_remember_down_list/0]).
 
 -ifdef(EQC).
@@ -167,13 +168,22 @@ ping(Pid) ->
 %% with lowest rank, i.e. name z* first, name a* last.
 
 set_chain_members(Pid, MembersDict) ->
-    set_chain_members(Pid, MembersDict, []).
+    set_chain_members(Pid, ch0_name, 0, ap_mode, MembersDict, []).
 
-set_chain_members(Pid, MembersDict, Witness_list) ->
+set_chain_members(Pid, ChainName, OldEpoch, CMode, MembersDict, Witness_list)
-    case lists:all(fun(Witness) -> orddict:is_key(Witness, MembersDict) end,
+  when is_atom(ChainName) andalso
+       is_integer(OldEpoch) andalso OldEpoch >= 0 andalso
+       (CMode == ap_mode orelse CMode == cp_mode) andalso
+       is_list(MembersDict) andalso
+       is_list(Witness_list) ->
+    case lists:all(fun({X, #p_srvr{name=X}}) -> true;
+                      (_)                    -> false
+                   end, MembersDict)
+         andalso
+         lists:all(fun(Witness) -> orddict:is_key(Witness, MembersDict) end,
                     Witness_list) of
         true ->
-            Cmd = {set_chain_members, MembersDict, Witness_list},
+            Cmd = {set_chain_members, ChainName, OldEpoch, CMode, MembersDict, Witness_list},
             gen_server:call(Pid, Cmd, infinity);
         false ->
             {error, bad_arg}
@@ -224,11 +234,13 @@ test_read_latest_public_projection(Pid, ReadRepairP) ->
 %% manager's pid in MgrOpts and use direct gen_server calls to the
 %% local projection store.
 
-init({MyName, InitMembersDict, MgrOpts}) ->
+init({MyName, InitMembersDict, MgrOpts0}) ->
     put(ttt, [?LINE]),
-    random:seed(now()),
+    _ = random:seed(now()),
     init_remember_down_list(),
+    MgrOpts = MgrOpts0 ++ application:get_env(machi, chain_manager_opts, []),
     Opt = fun(Key, Default) -> proplists:get_value(Key, MgrOpts, Default) end,
+
     InitWitness_list = Opt(witnesses, []),
     ZeroAll_list = [P#p_srvr.name || {_,P} <- orddict:to_list(InitMembersDict)],
     ZeroProj = make_none_projection(0, MyName, ZeroAll_list,
@@ -280,7 +292,7 @@ put(ttt, [?LINE]),
                          last_down=[no_such_server_initial_value_only],
                          fitness_svr=machi_flu_psup:make_fitness_regname(MyName)
                         }, Proj),
-    {_, S2} = do_set_chain_members_dict(MembersDict, S),
+    S2 = do_set_chain_members_dict(MembersDict, S),
     S3 = if ActiveP == false ->
                  S2;
             ActiveP == true ->
@@ -290,12 +302,17 @@ put(ttt, [?LINE]),
 
 handle_call({ping}, _From, S) ->
     {reply, pong, S};
-handle_call({set_chain_members, MembersDict, Witness_list}, _From,
+handle_call({set_chain_members, SetChainName, SetOldEpoch, CMode,
+             MembersDict, Witness_list}, _From,
             #ch_mgr{name=MyName,
                     proj=#projection_v1{all_members=OldAll_list,
                                         epoch_number=OldEpoch,
+                                        chain_name=ChainName,
                                         upi=OldUPI}=OldProj}=S) ->
-    {Reply, S2} = do_set_chain_members_dict(MembersDict, S),
+    true = (OldEpoch == 0) % in this case we want unconditional set of ch name
+           orelse
+           (SetOldEpoch == OldEpoch andalso SetChainName == ChainName),
+    S2 = do_set_chain_members_dict(MembersDict, S),
     %% TODO: should there be any additional sanity checks?  Right now,
     %% if someone does something bad, then do_react_to_env() will
     %% crash, which will crash us, and we'll restart in a sane & old
@@ -309,10 +326,10 @@ handle_call({set_chain_members, MembersDict, Witness_list}, _From,
                                 {NUPI, All_list -- NUPI}
                         end,
     NewEpoch = OldEpoch + ?SET_CHAIN_MEMBERS_EPOCH_SKIP,
-    CMode = calc_consistency_mode(Witness_list),
     ok = set_consistency_mode(machi_flu_psup:make_proj_supname(MyName), CMode),
     NewProj = machi_projection:update_checksum(
                 OldProj#projection_v1{author_server=MyName,
+                                      chain_name=SetChainName,
                                       creation_time=now(),
                                       mode=CMode,
                                       epoch_number=NewEpoch,
@@ -324,7 +341,11 @@ handle_call({set_chain_members, MembersDict, Witness_list}, _From,
                                       members_dict=MembersDict}),
     S3 = set_proj(S2#ch_mgr{proj_history=queue:new(),
                             consistency_mode=CMode}, NewProj),
-    {_QQ, S4} = do_react_to_env(S3),
+    {Res, S4} = do_react_to_env(S3),
+    Reply = case Res of
+                {_,_,_} -> ok
+                % Dialyzer says that all vals match with the 3-tuple pattern
+            end,
     {reply, Reply, S4};
 handle_call({set_active, Boolean}, _From, #ch_mgr{timer=TRef}=S) ->
     case {Boolean, TRef} of
@@ -356,8 +377,8 @@ handle_call({test_read_latest_public_projection, ReadRepairP}, _From, S) ->
     {reply, Res, S2};
 handle_call({trigger_react_to_env}=Call, _From, S) ->
     gobble_calls(Call),
-    {TODOtodo, S2} = do_react_to_env(S),
+    {Res, S2} = do_react_to_env(S),
-    {reply, TODOtodo, S2};
+    {reply, Res, S2};
 handle_call(_Call, _From, S) ->
     io:format(user, "\nBad call to ~p: ~p\n", [S#ch_mgr.name, _Call]),
     {reply, whaaaaaaaaaa, S}.
@@ -369,6 +390,7 @@ handle_cast(_Cast, S) ->
 handle_info(tick_check_environment, #ch_mgr{ignore_timer=true}=S) ->
     {noreply, S};
 handle_info(tick_check_environment, S) ->
+    gobble_ticks(),
     {{_Delta, Props, _Epoch}, S1} = do_react_to_env(S),
     S2 = sanitize_repair_state(S1),
     S3 = perhaps_start_repair(S2),
@@ -400,6 +422,11 @@ handle_info(Msg, #ch_mgr{name=MyName}=S) ->
 terminate(_Reason, _S) ->
     ok.
 
+format_status(_Opt, [_PDict, Status]) ->
+    Fields = record_info(fields, ch_mgr),
+    [_Name | Values] = tuple_to_list(Status),
+    lists:zip(Fields, Values).
+
 code_change(_OldVsn, S, _Extra) ->
     {ok, S}.
 
@@ -436,7 +463,7 @@ get_my_proj_boot_info(MgrOpts, DefaultDict, DefaultProj, ProjType) ->
             {DefaultDict, DefaultProj};
         Store ->
             {ok, P} = machi_projection_store:read_latest_projection(Store,
-                                                                    ProjType),
+                                                                    ProjType, 7789),
             {P#projection_v1.members_dict, P}
     end.
 
@@ -529,6 +556,7 @@ cl_write_public_proj2(FLUs, Partitions, Epoch, Proj, IgnoreWrittenErrorP, S) ->
                    end
            end, {true, []}, FLUs),
     %% io:format(user, "\nWrite public ~w by ~w: ~w\n", [Epoch, S#ch_mgr.name, Rs]),
+    %% io:format(user, "mgr ~w epoch ~w Rs ~p\n", [S#ch_mgr.name, Epoch, Rs]),
     {{remote_write_results, Rs}, S}.
 
 do_cl_read_latest_public_projection(ReadRepairP,
@@ -550,12 +578,41 @@ do_cl_read_latest_public_projection(ReadRepairP,
 read_latest_projection_call_only(ProjectionType, AllHosed,
                                  #ch_mgr{proj=CurrentProj}=S) ->
     #projection_v1{all_members=All_list} = CurrentProj,
-    All_queried_list = All_list -- AllHosed,
+    All_queried_list = lists:sort(All_list -- AllHosed),
+    read_latest_projection_call_only1(ProjectionType, AllHosed,
+                                      All_queried_list, S).
 
-    {Rs, S2} = read_latest_projection_call_only2(ProjectionType,
+read_latest_projection_call_only1(ProjectionType, AllHosed,
+                                  All_queried_list, S) ->
+    {Rs_tmp, S2} = read_latest_projection_call_only2(ProjectionType,
                                                      All_queried_list, S),
-    FLUsRs = lists:zip(All_queried_list, Rs),
+    New_all_maybe =
-    {All_queried_list, FLUsRs, S2}.
+        lists:usort(
+          lists:flatten(
+            [A_l || #projection_v1{all_members=A_l} <- Rs_tmp])) -- AllHosed,
+    case New_all_maybe -- All_queried_list of
+        [] ->
+            FLUsRs = lists:zip(All_queried_list, Rs_tmp),
+            {All_queried_list, FLUsRs, S2};
+        [AnotherFLU|_] ->
+            %% Stop AnotherFLU proxy, in unexpected case where it's open
+            try
+                Proxy = proxy_pid(AnotherFLU, S2),
+                ?FLU_PC:stop_proxies([Proxy])
+            catch _:_ -> ok
+            end,
+            MD = orddict:from_list(
+                  lists:usort(
+                   lists:flatten(
+                    [orddict:to_list(D) || #projection_v1{members_dict=D} <- Rs_tmp]))),
+            Another_P_srvr = orddict:fetch(AnotherFLU, MD),
+            {ok, Proxy2} = ?FLU_PC:start_link(Another_P_srvr),
+            S3 = S2#ch_mgr{proxies_dict=orddict:store(AnotherFLU, Proxy2,
+                                                      S2#ch_mgr.proxies_dict)},
+            read_latest_projection_call_only1(
+              ProjectionType, AllHosed,
+              lists:usort([AnotherFLU|All_queried_list]), S3)
+    end.
 
 read_latest_projection_call_only2(ProjectionType, All_queried_list, S) ->
     {_UpNodes, Partitions, S2} = calc_up_nodes(S),
@@ -595,6 +652,8 @@ rank_and_sort_projections_with_extra(All_queried_list, FLUsRs, ProjectionType,
             Witness_list = CurrentProj#projection_v1.witnesses,
             NoneProj = make_none_projection(0, MyName, [], Witness_list,
                                             orddict:new()),
+            ChainName = CurrentProj#projection_v1.chain_name,
+            NoneProj2 = NoneProj#projection_v1{chain_name=ChainName},
             Extra2 = [{all_members_replied, true},
                       {all_queried_list, All_queried_list},
                       {flus_rs, FLUsRs},
@@ -603,7 +662,7 @@ rank_and_sort_projections_with_extra(All_queried_list, FLUsRs, ProjectionType,
                       {bad_answer_flus, BadAnswerFLUs},
                       {bad_answers, BadAnswers},
                       {not_unanimous_answers, []}],
-            {not_unanimous, NoneProj, Extra2, S};
+            {not_unanimous, NoneProj2, Extra2, S};
        ProjectionType == public, UnwrittenRs /= [] ->
             {needs_repair, FLUsRs, [flarfus], S};
        true ->
@@ -717,13 +776,14 @@ calc_projection2(LastProj, RelativeToServer, AllHosed, Dbg,
                          runenv=RunEnv1,
                          repair_final_status=RepairFS}=S) ->
     #projection_v1{epoch_number=OldEpochNum,
+                   chain_name=ChainName,
                    members_dict=MembersDict,
                    witnesses=OldWitness_list,
                    upi=OldUPI_list,
                    repairing=OldRepairing_list
                   } = LastProj,
     LastUp = lists:usort(OldUPI_list ++ OldRepairing_list),
-    AllMembers = (S#ch_mgr.proj)#projection_v1.all_members,
+    AllMembers = CurrentProj#projection_v1.all_members,
     {Up0, Partitions, RunEnv2} = calc_up_nodes(MyName,
                                                AllMembers, RunEnv1),
     Up = Up0 -- AllHosed,
@@ -780,7 +840,10 @@ calc_projection2(LastProj, RelativeToServer, AllHosed, Dbg,
                         D_foo=[{repair_done, {repair_final_status, ok, (S#ch_mgr.proj)#projection_v1.epoch_number}}],
                         {NewUPI_list ++ Repairing_list2, [], RunEnv2};
                    true ->
-                        D_foo=[d_foo2],
+                        D_foo=[d_foo2, {sim_p,Simulator_p},
+                               {simr_p,SimRepair_p}, {same_epoch,SameEpoch_p},
+                               {rel_to,RelativeToServer},
+                               {repch,RepChk_LastInUPI}, {repair_fs,RepairFS}],
                         {NewUPI_list, OldRepairing_list, RunEnv2}
                 end;
             {_ABC, _XYZ} ->
@@ -815,10 +878,11 @@ calc_projection2(LastProj, RelativeToServer, AllHosed, Dbg,
         end,
     ?REACT({calc,?LINE,[{new_upi, NewUPI},{new_rep, NewRepairing}]}),
 
-    P = machi_projection:new(OldEpochNum + 1,
+    P0 = machi_projection:new(OldEpochNum + 1,
                               MyName, MembersDict, Down, NewUPI, NewRepairing,
                               D_foo ++
                                   Dbg ++ [{ps, Partitions},{nodes_up, Up}]),
+    P1 = P0#projection_v1{chain_name=ChainName},
     P2 = if CMode == cp_mode ->
                  UpWitnesses = [W || W <- Up, lists:member(W, OldWitness_list)],
                  Majority = full_majority_size(AllMembers),
@@ -827,7 +891,7 @@ calc_projection2(LastProj, RelativeToServer, AllHosed, Dbg,
                  SoFar = length(NewUPI ++ NewRepairing),
                  if SoFar >= Majority ->
                          ?REACT({calc,?LINE,[]}),
-                         P;
+                         P1;
                     true ->
                          Need = Majority - SoFar,
                          UpWitnesses = [W || W <- Up,
@@ -836,7 +900,7 @@ calc_projection2(LastProj, RelativeToServer, AllHosed, Dbg,
                                  Ws = lists:sublist(UpWitnesses, Need),
                                  ?REACT({calc,?LINE,[{ws, Ws}]}),
                                  machi_projection:update_checksum(
-                                   P#projection_v1{upi=Ws++NewUPI});
+                                   P1#projection_v1{upi=Ws++NewUPI});
                             true ->
                                  ?REACT({calc,?LINE,[]}),
                                  P_none0 = make_none_projection(
@@ -849,6 +913,7 @@ calc_projection2(LastProj, RelativeToServer, AllHosed, Dbg,
                                                "Not enough witnesses are available now"
                                        end,
                                  P_none1 = P_none0#projection_v1{
+                                             chain_name=ChainName,
                                              %% Stable creation time!
                                              creation_time={1,2,3},
                                              dbg=[{none_projection,true},
@@ -869,7 +934,7 @@ calc_projection2(LastProj, RelativeToServer, AllHosed, Dbg,
                  end;
             CMode == ap_mode ->
                  ?REACT({calc,?LINE,[]}),
-                 P
+                 P1
          end,
     P3 = machi_projection:update_checksum(
            P2#projection_v1{mode=CMode, witnesses=OldWitness_list}),
@@ -1021,28 +1086,30 @@ rank_projection(#projection_v1{author_server=_Author,
 do_set_chain_members_dict(MembersDict, #ch_mgr{proxies_dict=OldProxiesDict}=S)->
     _ = ?FLU_PC:stop_proxies(OldProxiesDict),
     ProxiesDict = ?FLU_PC:start_proxies(MembersDict),
-    {ok, S#ch_mgr{members_dict=MembersDict,
+    S#ch_mgr{members_dict=MembersDict,
-                  proxies_dict=ProxiesDict}}.
+             proxies_dict=ProxiesDict}.
 
 do_react_to_env(#ch_mgr{name=MyName,
                         proj=#projection_v1{epoch_number=Epoch,
                                             members_dict=[]=OldDict}=OldProj,
                         opts=Opts}=S) ->
+    put(ttt, [?LINE]),
     %% Read from our local *public* projection store.  If some other
     %% chain member has written something there, and if we are a
     %% member of that chain, then we'll adopt that projection and then
     %% start actively humming in that chain.
-    {NewMembersDict, NewProj} =
+    {NewMD, NewProj} =
         get_my_public_proj_boot_info(Opts, OldDict, OldProj),
-    case orddict:is_key(MyName, NewMembersDict) of
+    case orddict:is_key(MyName, NewMD) of
         false ->
-            {{empty_members_dict, [], Epoch}, S};
+            {{empty_members_dict1, [], Epoch}, S};
         true ->
-            {_, S2} = do_set_chain_members_dict(NewMembersDict, S),
+            CMode = NewProj#projection_v1.mode,
-            CMode = calc_consistency_mode(NewProj#projection_v1.witnesses),
+            S2 = do_set_chain_members_dict(NewMD, S),
-            {{empty_members_dict, [], Epoch},
+            {Reply, S3} = react_to_env_C110(NewProj,
-             set_proj(S2#ch_mgr{members_dict=NewMembersDict,
+                                            S2#ch_mgr{members_dict=NewMD,
-                                consistency_mode=CMode}, NewProj)}
+                                                      consistency_mode=CMode}),
+            {Reply, S3}
     end;
 do_react_to_env(S) ->
     put(ttt, [?LINE]),
@@ -1144,7 +1211,7 @@ react_to_env_A10(S) ->
     ?REACT(a10),
     react_to_env_A20(0, poll_private_proj_is_upi_unanimous(S)).
 
-react_to_env_A20(Retries, #ch_mgr{name=MyName}=S) ->
+react_to_env_A20(Retries, #ch_mgr{name=MyName, proj=P_current}=S) ->
     ?REACT(a20),
     init_remember_down_list(),
     {UnanimousTag, P_latest, ReadExtra, S2} =
@@ -1172,17 +1239,34 @@ react_to_env_A20(Retries, #ch_mgr{name=MyName}=S) ->
         false when P_latest#projection_v1.epoch_number /= LastComplaint,
                    P_latest#projection_v1.all_members /= [] ->
             put(rogue_server_epoch, P_latest#projection_v1.epoch_number),
-            error_logger:info_msg("Chain manager ~p found latest public "
+            error_logger:info_msg("Chain manager ~w found latest public "
-                                  "projection ~p has author ~p has a "
+                                  "projection ~w with author ~w has a "
-                                  "members list ~p that does not include me.\n",
+                                  "members list ~w that does not include me.  "
+                                  "We assume this is a result of administrator "
+                                  "action and will thus wedge ourselves until "
+                                  "we are re-added to the chain or shutdown.\n",
                                   [S#ch_mgr.name,
                                    P_latest#projection_v1.epoch_number,
                                    P_latest#projection_v1.author_server,
-                                   P_latest#projection_v1.all_members]);
+                                   P_latest#projection_v1.all_members]),
+            EpochID = machi_projection:make_epoch_id(P_current),
+            ProjStore = get_projection_store_pid_or_regname(S),
+            {ok, NotifyPid} = machi_projection_store:get_wedge_notify_pid(ProjStore),
+            _QQ = machi_flu1:update_wedge_state(NotifyPid, true, EpochID),
+            #projection_v1{epoch_number=Epoch,
+                           chain_name=ChainName,
+                           all_members=All_list,
+                           witnesses=Witness_list,
+                           members_dict=MembersDict} = P_current,
+            P_none0 = make_none_projection(Epoch,
+                                           MyName, All_list, Witness_list, MembersDict),
+            P_none = P_none0#projection_v1{chain_name=ChainName},
+            {{now_using,[],Epoch}, set_proj(S2, P_none)};
         _ ->
-            ok
+            react_to_env_A21(Retries, UnanimousTag, P_latest, ReadExtra, S2)
-    end,
+    end.
 
+react_to_env_A21(Retries, UnanimousTag, P_latest, ReadExtra, S) ->
     %% The UnanimousTag isn't quite sufficient for our needs.  We need
     %% to determine if *all* of the UPI+Repairing FLUs are members of
     %% the unanimous server replies.  All Repairing FLUs should be up
@@ -1227,7 +1311,7 @@ react_to_env_A20(Retries, #ch_mgr{name=MyName}=S) ->
            true ->
                 exit({badbad, UnanimousTag})
         end,
-    react_to_env_A29(Retries, P_latest, LatestUnanimousP, ReadExtra, S2).
+    react_to_env_A29(Retries, P_latest, LatestUnanimousP, ReadExtra, S).
 
 react_to_env_A29(Retries, P_latest, LatestUnanimousP, _ReadExtra,
                  #ch_mgr{consistency_mode=CMode,
@@ -1261,7 +1345,6 @@ react_to_env_A29(Retries, P_latest, LatestUnanimousP, _ReadExtra,
                     ?REACT({a29, ?LINE,
                             [{zerf_backstop, true},
                              {zerf_in, machi_projection:make_summary(Zerf)}]}),
-                    %% io:format(user, "zerf_in: A29: ~p: ~w\n\t~p\n", [MyName,  machi_projection:make_summary(Zerf), get(yyy_hack)]),
                     #projection_v1{dbg=ZerfDbg} = Zerf,
                     Backstop = if Zerf#projection_v1.upi == [] ->
                                        [];
@@ -1281,7 +1364,8 @@ react_to_env_A29(Retries, P_latest, LatestUnanimousP, _ReadExtra,
     end.
 
 react_to_env_A30(Retries, P_latest, LatestUnanimousP, P_current_calc,
-                 #ch_mgr{name=MyName, consistency_mode=CMode} = S) ->
+                 #ch_mgr{name=MyName, proj=P_current,
+                         consistency_mode=CMode} = S) ->
     V = case file:read_file("/tmp/moomoo."++atom_to_list(S#ch_mgr.name)) of {ok,_} -> true; _ -> false end,
     if V -> io:format(user, "A30: ~w: ~p\n", [S#ch_mgr.name, get(react)]); true -> ok end,
     ?REACT(a30),
@@ -1301,15 +1385,17 @@ react_to_env_A30(Retries, P_latest, LatestUnanimousP, P_current_calc,
             P = #projection_v1{down=Down} =
                 make_none_projection(Epoch + 1, MyName, All_list,
                                      Witness_list, MembersDict),
+            ChainName = P_current#projection_v1.chain_name,
+            P1 = P#projection_v1{chain_name=ChainName},
             P_newprop = if CMode == ap_mode ->
                                 %% Not really none proj: just myself, AP style
                                 machi_projection:update_checksum(
-                                  P#projection_v1{upi=[MyName],
+                                  P1#projection_v1{upi=[MyName],
                                                   down=Down -- [MyName],
                                                   dbg=[{hosed_list,AllHosed}]});
                            CMode == cp_mode ->
                                 machi_projection:update_checksum(
-                                  P#projection_v1{dbg=[{hosed_list,AllHosed}]})
+                                  P1#projection_v1{dbg=[{hosed_list,AllHosed}]})
                         end,
             react_to_env_A40(Retries, P_newprop, P_latest, LatestUnanimousP,
                              P_current_calc, true, S);
@@ -1382,13 +1468,22 @@ react_to_env_A40(Retries, P_newprop, P_latest, LatestUnanimousP,
                 %% we have a disagreement.
                 not ordsets:is_disjoint(P_latest_s, Down_s)
         end,
+    AmExcludedFromLatestAll_p =
+        P_latest#projection_v1.epoch_number /= 0
+        andalso
+        (not lists:member(MyName, P_latest#projection_v1.all_members)),
     ?REACT({a40, ?LINE,
             [{latest_author, P_latest#projection_v1.author_server},
+             {am_excluded_from_latest_all_p, AmExcludedFromLatestAll_p},
              {author_is_down_p, LatestAuthorDownP},
              {rank_latest, Rank_latest},
              {rank_newprop, Rank_newprop}]}),
 
     if
+        AmExcludedFromLatestAll_p ->
+            ?REACT({a40, ?LINE, [{latest,machi_projection:make_summary(P_latest)}]}),
+            react_to_env_A50(P_latest, [], S);
+
         AmHosedP ->
             ExpectedUPI = if CMode == cp_mode -> [];
                              CMode == ap_mode -> [MyName]
@@ -1554,12 +1649,10 @@ react_to_env_A40(Retries, P_newprop, P_latest, LatestUnanimousP,
                        end,
             if GoTo50_p ->
                     ?REACT({a40, ?LINE, []}),
-%% io:format(user, "CONFIRM debug question line ~w\n", [?LINE]),
                     FinalProps = [{throttle_seconds, 0}],
                     react_to_env_A50(P_latest, FinalProps, S);
                true ->
                     ?REACT({a40, ?LINE, []}),
-io:format(user, "CONFIRM debug question line ~w\n", [?LINE]),
                     react_to_env_C300(P_newprop, P_latest, S)
             end
     end.
@@ -1569,7 +1662,6 @@ react_to_env_A50(P_latest, FinalProps, #ch_mgr{proj=P_current}=S) ->
     ?REACT({a50, ?LINE, [{current_epoch, P_current#projection_v1.epoch_number},
                          {latest_epoch, P_latest#projection_v1.epoch_number},
                          {final_props, FinalProps}]}),
-    %% if S#ch_mgr.name == c -> io:format(user, "A50: ~w: ~p\n", [S#ch_mgr.name, get(react)]); true -> ok end,
     V = case file:read_file("/tmp/moomoo."++atom_to_list(S#ch_mgr.name)) of {ok,_} -> true; _ -> false end,
     if V -> io:format(user, "A50: ~w: ~p\n", [S#ch_mgr.name, get(react)]); true -> ok end,
     {{no_change, FinalProps, P_current#projection_v1.epoch_number}, S}.
@@ -1823,7 +1915,7 @@ react_to_env_C100_inner(Author_latest, NotSanesDict0, _MyName,
     S2 = S#ch_mgr{not_sanes=NotSanesDict, sane_transitions=0},
     case orddict:fetch(Author_latest, NotSanesDict) of
         N when N > ?TOO_FREQUENT_BREAKER ->
-            %% ?V("\n\nYOYO ~w breaking the cycle of:\n  current: ~w\n  new    : ~w\n", [_MyName, machi_projection:make_summary(S#ch_mgr.proj), machi_projection:make_summary(P_latest)]),
+            ?V("\n\nYOYO ~w breaking the cycle insane-freq=~w by-author=~w of:\n  current: ~w\n  new    : ~w\n", [_MyName, N, Author_latest, machi_projection:make_summary(S#ch_mgr.proj), machi_projection:make_summary(P_latest)]),
             ?REACT({c100, ?LINE, [{not_sanes_author_count, N}]}),
             react_to_env_C103(P_newprop, P_latest, P_current_calc, S2);
         N ->
@@ -1844,12 +1936,14 @@ react_to_env_C103(#projection_v1{epoch_number=_Epoch_newprop} = _P_newprop,
                    members_dict=MembersDict} = P_current,
     P_none0 = make_none_projection(Epoch_latest,
                                    MyName, All_list, Witness_list, MembersDict),
-    P_none1 = P_none0#projection_v1{dbg=[{none_projection,true}]},
+    ChainName = P_current#projection_v1.chain_name,
+    P_none1 = P_none0#projection_v1{chain_name=ChainName,
+                                    dbg=[{none_projection,true}]},
     P_none = machi_projection:update_checksum(P_none1),
     ?REACT({c103, ?LINE,
             [{current_epoch, P_current#projection_v1.epoch_number},
              {none_projection_epoch, P_none#projection_v1.epoch_number}]}),
-    io:format(user, "SET add_admin_down(~w) at ~w =====================================\n", [MyName, time()]),
+    io:format(user, "SET add_admin_down(~w) at ~w current_epoch ~w none_proj_epoch ~w =====================================\n", [MyName, time(), P_current#projection_v1.epoch_number, P_none#projection_v1.epoch_number]),
     machi_fitness:add_admin_down(S#ch_mgr.fitness_svr, MyName, []),
     timer:sleep(5*1000),
     io:format(user, "SET delete_admin_down(~w) at ~w =====================================\n", [MyName, time()]),
@@ -1886,7 +1980,7 @@ react_to_env_C110(P_latest, #ch_mgr{name=MyName} = S) ->
     %% In contrast to the public projection store writes, Humming Consensus
     %% doesn't care about the status of writes to the public store: it's
     %% always relying only on successful reads of the public store.
-    case {?FLU_PC:write_projection(MyStorePid, private, P_latest2,?TO*30),Goo} of
+    case {?FLU_PC:write_projection(MyStorePid, private, P_latest2,?TO*30+66),Goo} of
         {ok, Goo} ->
             ?REACT({c110, [{write, ok}]}),
             react_to_env_C111(P_latest, P_latest2, Extra1, MyStorePid, S);
@@ -1972,7 +2066,6 @@ react_to_env_C120(P_latest, FinalProps, #ch_mgr{proj_history=H,
     ?REACT(c120),
     H2   = add_and_trunc_history(P_latest, H, ?MAX_HISTORY_LENGTH),
 
-    %% diversion_c120_verbose_goop(P_latest, S),
     ?REACT({c120, [{latest, machi_projection:make_summary(P_latest)}]}),
     S2 = set_proj(S#ch_mgr{proj_history=H2,
                            sane_transitions=Xtns + 1}, P_latest),
@@ -1980,20 +2073,21 @@ react_to_env_C120(P_latest, FinalProps, #ch_mgr{proj_history=H,
              false ->
                  S2;
              {{_ConfEpoch, _ConfCSum}, ConfTime} ->
-                 io:format(user, "\nCONFIRM debug C120 ~w was annotated ~w\n", [S#ch_mgr.name, P_latest#projection_v1.epoch_number]),
+                 P_latestEpoch = P_latest#projection_v1.epoch_number,
+                 io:format(user, "\nCONFIRM debug C120 ~w was annotated ~w\n", [S#ch_mgr.name, P_latestEpoch]),
                  S2#ch_mgr{proj_unanimous=ConfTime}
          end,
     V = case file:read_file("/tmp/moomoo."++atom_to_list(S#ch_mgr.name)) of {ok,_} -> true; _ -> false end,
     if V -> io:format("C120: ~w: ~p\n", [S#ch_mgr.name, get(react)]); true -> ok end,
     {{now_using, FinalProps, P_latest#projection_v1.epoch_number}, S3}.
 
-add_and_trunc_history(P_latest, H, MaxLength) ->
+add_and_trunc_history(#projection_v1{epoch_number=0}, H, _MaxLength) ->
+    H;
+add_and_trunc_history(#projection_v1{} = P_latest, H, MaxLength) ->
     Latest_U_R = {P_latest#projection_v1.upi, P_latest#projection_v1.repairing},
-    H2 = if P_latest#projection_v1.epoch_number > 0 ->
+    add_and_trunc_history(Latest_U_R, H, MaxLength);
-                 queue:in(Latest_U_R, H);
+add_and_trunc_history(Item, H, MaxLength) ->
-            true ->
+    H2 = queue:in(Item, H),
-                 H
-         end,
     case queue:len(H2) of
         X when X > MaxLength ->
             {_V, Hxx} = queue:out(H2),
@@ -2006,10 +2100,9 @@ react_to_env_C200(Retries, P_latest, S) ->
     ?REACT(c200),
     try
         AuthorProxyPid = proxy_pid(P_latest#projection_v1.author_server, S),
-        ?FLU_PC:kick_projection_reaction(AuthorProxyPid, [])
+        %% This is just advisory, we don't need a sync reply.
+        ?FLU_PC:kick_projection_reaction(AuthorProxyPid, [], 100)
     catch _Type:_Err ->
-            %% ?V("TODO: tell_author_yo is broken: ~p ~p\n",
-            %%           [_Type, _Err]),
         ok
     end,
     react_to_env_C210(Retries, S).
@@ -2200,6 +2293,7 @@ projection_transition_is_sane_except_si_epoch(
                  creation_time=CreationTime1,
                  mode=CMode1,
                  author_server=AuthorServer1,
+                 chain_name=ChainName1,
                  all_members=All_list1,
                  witnesses=Witness_list1,
                  down=Down_list1,
@@ -2211,6 +2305,7 @@ projection_transition_is_sane_except_si_epoch(
                  creation_time=CreationTime2,
                  mode=CMode2,
                  author_server=AuthorServer2,
+                 chain_name=ChainName2,
                  all_members=All_list2,
                  witnesses=Witness_list2,
                  down=Down_list2,
@@ -2231,7 +2326,8 @@ projection_transition_is_sane_except_si_epoch(
     true = is_binary(CSum1) andalso is_binary(CSum2),
     {_,_,_} = CreationTime1,
     {_,_,_} = CreationTime2,
-    true = is_atom(AuthorServer1) andalso is_atom(AuthorServer2), % todo type may change?
+    true = is_atom(AuthorServer1) andalso is_atom(AuthorServer2),
+    true = is_atom(ChainName1) andalso is_atom(ChainName2),
     true = is_list(All_list1) andalso is_list(All_list2),
     true = is_list(Witness_list1) andalso is_list(Witness_list2),
     true = is_list(Down_list1) andalso is_list(Down_list2),
@@ -2243,6 +2339,9 @@ projection_transition_is_sane_except_si_epoch(
     %% projection_transition_is_sane_with_si_epoch().
     true = Epoch2 >= Epoch1,
 
+    %% Don't change chain names in the middle of the stream.
+    true = (ChainName1 == ChainName2),
+
     %% No duplicates
     true = lists:sort(Witness_list2) == lists:usort(Witness_list2),
     true = lists:sort(Down_list2) == lists:usort(Down_list2),
@@ -2250,7 +2349,7 @@ projection_transition_is_sane_except_si_epoch(
     true = lists:sort(Repairing_list2) == lists:usort(Repairing_list2),
 
     %% Disjoint-ness
-    All_list1 = All_list2,                 % todo will probably change
+    %% %% %% %% %% %% %% %% All_list1 = All_list2,                 % todo will probably change
     %% true = lists:sort(All_list2) == lists:sort(Down_list2 ++ UPI_list2 ++
     %%                                                Repairing_list2),
     [] = [X || X <- Witness_list2, not lists:member(X, All_list2)],
@@ -2355,8 +2454,7 @@ poll_private_proj_is_upi_unanimous_sleep(Count, #ch_mgr{runenv=RunEnv}=S) ->
             S2
     end.
 
-poll_private_proj_is_upi_unanimous3(#ch_mgr{name=MyName, proj=P_current,
+poll_private_proj_is_upi_unanimous3(#ch_mgr{name=MyName, proj=P_current} = S) ->
-                                            opts=MgrOpts} = S) ->
     UPI = P_current#projection_v1.upi,
     EpochID = machi_projection:make_epoch_id(P_current),
     {Rs, S2} = read_latest_projection_call_only2(private, UPI, S),
@@ -2389,33 +2487,30 @@ poll_private_proj_is_upi_unanimous3(#ch_mgr{name=MyName, proj=P_current,
                     Annotation = make_annotation(EpochID, Now),
                     NewDbg2 = [Annotation|P_currentFull#projection_v1.dbg2],
                     NewProj = P_currentFull#projection_v1{dbg2=NewDbg2},
-                    ProjStore = case get_projection_store_regname(MgrOpts) of
+                    ProjStore = get_projection_store_pid_or_regname(S),
-                                   undefined ->
-                                       machi_flu_psup:make_proj_supname(MyName);
-                                   PStr ->
-                                       PStr
-                                end,
                     #projection_v1{epoch_number=_EpochRep,
                                    epoch_csum= <<_CSumRep:4/binary,_/binary>>,
+                                   author_server=AuthRep,
                                    upi=_UPIRep,
                                    repairing=_RepairingRep} = NewProj,
                     ok = machi_projection_store:write(ProjStore, private, NewProj),
-                    case proplists:get_value(private_write_verbose, S#ch_mgr.opts) of
+                    case proplists:get_value(private_write_verbose_confirm, S#ch_mgr.opts) of
                         true ->
-                            io:format(user, "\n~s CONFIRM epoch ~w ~w upi ~w rep ~w by ~w\n", [machi_util:pretty_time(), _EpochRep, _CSumRep, _UPIRep, _RepairingRep, MyName]);
+                            error_logger:info_msg("CONFIRM epoch ~w ~w upi ~w rep ~w auth ~w by ~w\n", [_EpochRep, _CSumRep, _UPIRep, _RepairingRep, AuthRep, MyName]);
                         _ ->
                             ok
                     end,
                     %% Unwedge our FLU.
                     {ok, NotifyPid} = machi_projection_store:get_wedge_notify_pid(ProjStore),
                     _ = machi_flu1:update_wedge_state(NotifyPid, false, EpochID),
-                    S2#ch_mgr{proj_unanimous=Now};
+                    #ch_mgr{proj_history=H} = S2,
+                    H2 = add_and_trunc_history({confirm, Epoch}, H,
+                                               ?MAX_HISTORY_LENGTH),
+                    S2#ch_mgr{proj_unanimous=Now, proj_history=H2};
                 _ ->
                     S2
             end;
         _Else ->
-            %% io:format(user, "poll by ~w: want ~W got ~W\n",
-            %%           [MyName, EpochID, 6, _Else, 8]),
             S2
     end.
 
@@ -2451,6 +2546,14 @@ gobble_calls(StaticCall) ->
             ok
     end.
 
+gobble_ticks() ->
+    receive
+        tick_check_environment ->
+            gobble_ticks()
+    after 0 ->
+            ok
+    end.
+
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
 
 perhaps_start_repair(#ch_mgr{name=MyName,
@@ -2466,12 +2569,13 @@ perhaps_start_repair(#ch_mgr{name=MyName,
             %% RepairOpts = [{repair_mode, check}, verbose],
             RepairFun = fun() -> do_repair(S, RepairOpts, CMode) end,
             LastUPI = lists:last(UPI),
+            StabilityTime = application:get_env(machi, stability_time, ?REPAIR_START_STABILITY_TIME),
             IgnoreStabilityTime_p = proplists:get_value(ignore_stability_time,
                                                         S#ch_mgr.opts, false),
             case timer:now_diff(os:timestamp(), Start) div 1000000 of
                 N when MyName == LastUPI andalso
                        (IgnoreStabilityTime_p orelse
-                        N >= ?REPAIR_START_STABILITY_TIME) ->
+                        N >= StabilityTime) ->
                     {WorkerPid, _Ref} = spawn_monitor(RepairFun),
                     S#ch_mgr{repair_worker=WorkerPid,
                              repair_start=os:timestamp(),
@@ -2512,8 +2616,8 @@ do_repair(#ch_mgr{name=MyName,
             T1 = os:timestamp(),
             RepairId = proplists:get_value(repair_id, Opts, id1),
             error_logger:info_msg(
-              "Repair start: tail ~p of ~p -> ~p, ~p ID ~w\n",
+              "Repair ~w start: tail ~p of ~p -> ~p, ~p\n",
-              [MyName, UPI0, Repairing, RepairMode, RepairId]),
+              [RepairId, MyName, UPI0, Repairing, RepairMode]),
 
             UPI = UPI0 -- Witness_list,
             Res = machi_chain_repair:repair(RepairMode, MyName, Repairing, UPI,
@@ -2526,10 +2630,9 @@ do_repair(#ch_mgr{name=MyName,
                       end,
             Stats = [{K, ets:lookup_element(ETS, K, 2)} || K <- ETS_T_Keys],
             error_logger:info_msg(
-              "Repair ~s: tail ~p of ~p finished ~p repair ID ~w: "
+              "Repair ~w ~s: tail ~p of ~p finished ~p: "
-              "~p\nStats ~p\n",
+              "~p Stats: ~p\n",
-              [Summary, MyName, UPI0, RepairMode, RepairId,
+              [RepairId, Summary, MyName, UPI0, RepairMode, Res, Stats]),
-               Res, Stats]),
             ets:delete(ETS),
             exit({repair_final_status, Res});
         _ ->
@@ -2766,6 +2869,7 @@ full_majority_size(L) when is_list(L) ->
     full_majority_size(length(L)).
 
 make_zerf(#projection_v1{epoch_number=OldEpochNum,
+                         chain_name=ChainName,
                          all_members=AllMembers,
                          members_dict=MembersDict,
                          witnesses=OldWitness_list
@@ -2788,7 +2892,8 @@ make_zerf(#projection_v1{epoch_number=OldEpochNum,
                                      MyName, AllMembers, OldWitness_list,
                                      MembersDict),
             machi_projection:update_checksum(
-              P#projection_v1{mode=cp_mode,
+              P#projection_v1{chain_name=ChainName,
+                              mode=cp_mode,
                               dbg2=[zerf_none,{up,Up},{maj,MajoritySize}]});
         true ->
             make_zerf2(OldEpochNum, Up, MajoritySize, MyName,
@@ -2803,7 +2908,6 @@ make_zerf2(OldEpochNum, Up, MajoritySize, MyName, AllMembers, OldWitness_list,
         Proj2 = Proj#projection_v1{dbg2=[{make_zerf,Epoch},
                                          {yyy_hack, get(yyy_hack)},
                                          {up,Up},{maj,MajoritySize}]},
-        %% io:format(user, "ZERF ~w\n",[machi_projection:make_summary(Proj2)]),
         Proj2
     catch
         throw:{zerf,no_common} ->
@@ -2880,41 +2984,36 @@ zerf_find_last_annotated(FLU, MajoritySize, S) ->
             []                                  % lists:flatten() will destroy
     end.
 
-perhaps_verbose_c111(P_latest2, S) ->
+perhaps_verbose_c111(P_latest2, #ch_mgr{name=MyName, opts=Opts}=S) ->
-    case proplists:get_value(private_write_verbose, S#ch_mgr.opts) of
+    PrivWriteVerb = proplists:get_value(private_write_verbose, Opts, false),
-        true ->
+    PrivWriteVerbCONFIRM = proplists:get_value(private_write_verbose_confirm, Opts, false),
+    if PrivWriteVerb orelse PrivWriteVerbCONFIRM ->
             Dbg2X = lists:keydelete(react, 1,
                                     P_latest2#projection_v1.dbg2) ++
                 [{is_annotated,is_annotated(P_latest2)}],
             P_latest2x = P_latest2#projection_v1{dbg2=Dbg2X}, % limit verbose len.
             Last2 = get(last_verbose),
             Summ2 = machi_projection:make_summary(P_latest2x),
-            if P_latest2#projection_v1.upi == [],
+            if PrivWriteVerb, Summ2 /= Last2 ->
-               (S#ch_mgr.proj)#projection_v1.upi /= [] ->
+                    put(last_verbose, Summ2),
-                    <<CSumRep:4/binary,_/binary>> =
+                    error_logger:info_msg("~p uses plain: ~w \n",
-                                          P_latest2#projection_v1.epoch_csum,
+                       [MyName, Summ2]);
-                    io:format(user, "\n~s CONFIRM epoch ~w ~w upi ~w rep ~w by ~w\n", [machi_util:pretty_time(), (S#ch_mgr.proj)#projection_v1.epoch_number, CSumRep, P_latest2#projection_v1.upi, P_latest2#projection_v1.repairing, S#ch_mgr.name]);
                true ->
                     ok
             end,
-            case proplists:get_value(private_write_verbose,
+            if PrivWriteVerbCONFIRM,
-                                     S#ch_mgr.opts) of
+               P_latest2#projection_v1.upi == [],
-                true when Summ2 /= Last2 ->
+               (S#ch_mgr.proj)#projection_v1.upi /= [] ->
-                    put(last_verbose, Summ2),
+                    <<CSumRep:4/binary,_/binary>> =
-                    ?V("\n~s ~p uses plain: ~w \n",
+                                          P_latest2#projection_v1.epoch_csum,
-                       [machi_util:pretty_time(), S#ch_mgr.name, Summ2]);
+                    error_logger:info_msg("CONFIRM epoch ~w ~w upi ~w rep ~w auth ~w by ~w\n", [(S#ch_mgr.proj)#projection_v1.epoch_number, CSumRep, P_latest2#projection_v1.upi, P_latest2#projection_v1.repairing, P_latest2#projection_v1.author_server, S#ch_mgr.name]);
-                _ ->
+               true ->
                     ok
             end;
-        _ ->
+       true ->
             ok
     end.
 
-calc_consistency_mode(_Witness_list = []) ->
-    ap_mode;
-calc_consistency_mode(_Witness_list) ->
-    cp_mode.
-
 set_proj(S, Proj) ->
     S#ch_mgr{proj=Proj, proj_unanimous=false}.
 
@@ -2947,3 +3046,10 @@ get_unfit_list(FitnessServer) ->
             []
     end.
 
+get_projection_store_pid_or_regname(#ch_mgr{name=MyName, opts=MgrOpts}) ->
+    case get_projection_store_regname(MgrOpts) of
+        undefined ->
+            machi_flu_psup:make_proj_supname(MyName);
+        PStr ->
+            PStr
+    end.

src/machi_chain_repair.erl

@@ -103,9 +103,10 @@ repair(ap_mode=ConsistencyMode, Src, Repairing, UPI, MembersDict, ETS, Opts) ->
     Add = fun(Name, Pid) -> put(proxies_dict, orddict:store(Name, Pid, get(proxies_dict))) end,
     OurFLUs = lists:usort([Src] ++ Repairing ++ UPI), % AP assumption!
     RepairMode = proplists:get_value(repair_mode, Opts, repair),
-    Verb = proplists:get_value(verbose, Opts, true),
+    Verb = proplists:get_value(verbose, Opts, false),
+    RepairId = proplists:get_value(repair_id, Opts, id1),
     Res = try
-              [begin
+              _ = [begin
                        {ok, Proxy} = machi_proxy_flu1_client:start_link(P),
                        Add(FLU, Proxy)
                    end || {FLU,P} <- MembersDict, lists:member(FLU, OurFLUs)],
@@ -116,31 +117,39 @@ repair(ap_mode=ConsistencyMode, Src, Repairing, UPI, MembersDict, ETS, Opts) ->
                                        get_file_lists(Proxy, FLU, Dict)
                                end, D, ProxiesDict),
               MissingFileSummary = make_missing_file_summary(D2, OurFLUs),
-              ?VERB("MissingFileSummary ~p\n", [MissingFileSummary]),
+              %% ?VERB("~w MissingFileSummary ~p\n",[RepairId,MissingFileSummary]),
+              lager:info("Repair ~w MissingFileSummary ~p\n",
+                         [RepairId, MissingFileSummary]),
 
               [ets:insert(ETS, {{directive_bytes, FLU}, 0}) || FLU <- OurFLUs],
               %% Repair files from perspective of Src, i.e. tail(UPI).
               SrcProxy = orddict:fetch(Src, ProxiesDict),
               {ok, EpochID} = machi_proxy_flu1_client:get_epoch_id(
                                 SrcProxy, ?SHORT_TIMEOUT),
-              ?VERB("Make repair directives: "),
+              %% ?VERB("Make repair directives: "),
               Ds =
                   [{File, make_repair_directives(
                             ConsistencyMode, RepairMode, File, Size, EpochID,
                             Verb,
                             Src, OurFLUs, ProxiesDict, ETS)} ||
                       {File, {Size, _MissingList}} <- MissingFileSummary],
-              ?VERB(" done\n"),
+              %% ?VERB(" done\n"),
+              lager:info("Repair ~w repair directives finished\n", [RepairId]),
               [begin
                    [{_, Bytes}] = ets:lookup(ETS, {directive_bytes, FLU}),
-                   ?VERB("Out-of-sync data for FLU ~p: ~s MBytes\n",
+                   %% ?VERB("Out-of-sync data for FLU ~p: ~s MBytes\n",
-                         [FLU, mbytes(Bytes)])
+                   %%       [FLU, mbytes(Bytes)]),
+                   lager:info("Repair ~w "
+                              "Out-of-sync data for FLU ~p: ~s MBytes\n",
+                         [RepairId, FLU, mbytes(Bytes)]),
+                   ok
                end || FLU <- OurFLUs],
 
-              ?VERB("Execute repair directives: "),
+              %% ?VERB("Execute repair directives: "),
               ok = execute_repair_directives(ConsistencyMode, Ds, Src, EpochID,
                                              Verb, OurFLUs, ProxiesDict, ETS),
-              ?VERB(" done\n"),
+              %% ?VERB(" done\n"),
+              lager:info("Repair ~w repair directives finished\n", [RepairId]),
               ok
           catch
               What:Why ->
@@ -198,7 +207,7 @@ make_repair_compare_fun(SrcFLU) ->
             T_a =< T_b
     end.
 
-make_repair_directives(ConsistencyMode, RepairMode, File, Size, EpochID,
+make_repair_directives(ConsistencyMode, RepairMode, File, Size, _EpochID,
                        Verb, Src, FLUs0, ProxiesDict, ETS) ->
     true = (Size < ?MAX_OFFSET),
     FLUs = lists:usort(FLUs0),
@@ -207,11 +216,9 @@ make_repair_directives(ConsistencyMode, RepairMode, File, Size, EpochID,
               Proxy = orddict:fetch(FLU, ProxiesDict),
               OffSzCs =
                   case machi_proxy_flu1_client:checksum_list(
-                         Proxy, EpochID, File, ?LONG_TIMEOUT) of
+                         Proxy, File, ?LONG_TIMEOUT) of
                       {ok, InfoBin} ->
-                          {Info, _} =
+                          machi_csum_table:split_checksum_list_blob_decode(InfoBin);
-                            machi_flu1:split_checksum_list_blob_decode(InfoBin),
-                          Info;
                       {error, no_such_file} ->
                           []
                   end,
@@ -229,7 +236,6 @@ make_repair_directives(ConsistencyMode, RepairMode, File, Size, EpochID,
 
 make_repair_directives2(C2, ConsistencyMode, RepairMode,
                        File, Verb, Src, FLUs, ProxiesDict, ETS) ->
-    ?VERB("."),
     make_repair_directives3(C2, ConsistencyMode, RepairMode,
                             File, Verb, Src, FLUs, ProxiesDict, ETS, []).
 
@@ -259,7 +265,18 @@ make_repair_directives3([{Offset, Size, CSum, _FLU}=A|Rest0],
             %%     byte range from all FLUs
             %% 3b. Log big warning about data loss.
             %% 4. Log any other checksum discrepencies as they are found.
-            exit({todo_repair_sanity_check, ?LINE, File, Offset, As})
+            QQ = [begin
+                      Pxy = orddict:fetch(FLU, ProxiesDict),
+                      {ok, EpochID} = machi_proxy_flu1_client:get_epoch_id(
+                                        Pxy, ?SHORT_TIMEOUT),
+                      NSInfo = undefined,
+                      XX = machi_proxy_flu1_client:read_chunk(
+                             Pxy, NSInfo, EpochID, File, Offset, Size, undefined,
+                             ?SHORT_TIMEOUT),
+                      {FLU, XX}
+                  end || {__Offset, __Size, __CSum, FLU} <- As],
+
+            exit({todo_repair_sanity_check, ?LINE, File, Offset, {as,As}, {qq,QQ}})
     end,
     %% List construction guarantees us that there's at least one ?MAX_OFFSET
     %% item remains.  Sort order + our "taking" of all exact Offset+Size
@@ -280,15 +297,16 @@ make_repair_directives3([{Offset, Size, CSum, _FLU}=A|Rest0],
                                true  -> Src;
                                false -> hd(Gots)
                            end,
-                 [ets:update_counter(ETS, {directive_bytes, FLU_m}, Size) ||
+                 _ = [ets:update_counter(ETS, {directive_bytes, FLU_m}, Size) ||
                          FLU_m <- Missing],
                  if Missing == [] ->
                          noop;
                     true ->
                          {copy, A, Missing}
-                 end;
+                 end
-            ConsistencyMode == cp_mode ->
+            %%      end;
-                 exit({todo_cp_mode, ?MODULE, ?LINE})
+            %% ConsistencyMode == cp_mode ->
+            %%      exit({todo_cp_mode, ?MODULE, ?LINE})
          end,
     Acc2 = if Do == noop -> Acc;
               true       -> [Do|Acc]
@@ -311,38 +329,42 @@ execute_repair_directives(ap_mode=_ConsistencyMode, Ds, _Src, EpochID, Verb,
                             {ProxiesDict, EpochID, Verb, ETS}, Ds),
     ok.
 
-execute_repair_directive({File, Cmds}, {ProxiesDict, EpochID, Verb, ETS}=Acc) ->
+execute_repair_directive({File, Cmds}, {ProxiesDict, EpochID, _Verb, ETS}=Acc) ->
     EtsKeys = [{in_files, t_in_files}, {in_chunks, t_in_chunks},
                {in_bytes, t_in_bytes}, {out_files, t_out_files},
                {out_chunks, t_out_chunks}, {out_bytes, t_out_bytes}],
     [ets:insert(ETS, {L_K, 0}) || {L_K, _T_K} <- EtsKeys],
     F = fun({copy, {Offset, Size, TaggedCSum, MySrc}, MyDsts}, Acc2) ->
                 SrcP = orddict:fetch(MySrc, ProxiesDict),
-                case ets:lookup_element(ETS, in_chunks, 2) rem 100 of
+                %% case ets:lookup_element(ETS, in_chunks, 2) rem 100 of
-                    0 -> ?VERB(".", []);
+                %%     0 -> ?VERB(".2", []);
-                    _ -> ok
+                %%     _ -> ok
-                end,
+                %% end,
                 _T1 = os:timestamp(),
-                {ok, Chunk} = machi_proxy_flu1_client:read_chunk(
+                %% TODO: support case multiple written or trimmed chunks returned
-                                SrcP, EpochID, File, Offset, Size,
+                NSInfo = undefined,
+                {ok, {[{_, Offset, Chunk, _ReadCSum}|OtherChunks], []=_TrimmedList}} =
+                    machi_proxy_flu1_client:read_chunk(
+                      SrcP, NSInfo, EpochID, File, Offset, Size, undefined,
                       ?SHORT_TIMEOUT),
+                [] = OtherChunks,
                 _T2 = os:timestamp(),
                 <<_Tag:1/binary, CSum/binary>> = TaggedCSum,
                 case machi_util:checksum_chunk(Chunk) of
                     CSum_now when CSum_now == CSum ->
-                        [begin
+                        _ = [begin
                                  DstP = orddict:fetch(DstFLU, ProxiesDict),
                                  _T3 = os:timestamp(),
                                  ok = machi_proxy_flu1_client:write_chunk(
-                                    DstP, EpochID, File, Offset, Chunk,
+                                        DstP, NSInfo, EpochID, File, Offset, Chunk, TaggedCSum,
                                         ?SHORT_TIMEOUT),
                                  _T4 = os:timestamp()
                              end || DstFLU <- MyDsts],
-                        ets:update_counter(ETS, in_chunks, 1),
+                        _ = ets:update_counter(ETS, in_chunks, 1),
-                        ets:update_counter(ETS, in_bytes, Size),
+                        _ = ets:update_counter(ETS, in_bytes, Size),
                         N = length(MyDsts),
-                        ets:update_counter(ETS, out_chunks, N),
+                        _ = ets:update_counter(ETS, out_chunks, N),
-                        ets:update_counter(ETS, out_bytes, N*Size),
+                        _ = ets:update_counter(ETS, out_bytes, N*Size),
                         Acc2;
                     CSum_now ->
                         error_logger:error_msg(
@@ -361,7 +383,7 @@ execute_repair_directive({File, Cmds}, {ProxiesDict, EpochID, Verb, ETS}=Acc) ->
         end,
     ok = lists:foldl(F, ok, Cmds),
     %% Copy this file's stats to the total counts.
-    [ets:update_counter(ETS, T_K, ets:lookup_element(ETS, L_K, 2)) ||
+    _ = [ets:update_counter(ETS, T_K, ets:lookup_element(ETS, L_K, 2)) ||
             {L_K, T_K} <- EtsKeys],
     Acc.
 

src/machi_cinfo.erl

@@ -0,0 +1,104 @@
+%% -------------------------------------------------------------------
+%%
+%% Copyright (c) 2007-2015 Basho Technologies, Inc.  All Rights Reserved.
+%%
+%% This file is provided to you under the Apache License,
+%% Version 2.0 (the "License"); you may not use this file
+%% except in compliance with the License.  You may obtain
+%% a copy of the License at
+%%
+%%   http://www.apache.org/licenses/LICENSE-2.0
+%%
+%% Unless required by applicable law or agreed to in writing,
+%% software distributed under the License is distributed on an
+%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+%% KIND, either express or implied.  See the License for the
+%% specific language governing permissions and limitations
+%% under the License.
+%%
+%% -------------------------------------------------------------------
+
+%% @doc cluster_info callback module for machi specific information
+%% gathering.
+
+-module(machi_cinfo).
+
+%% cluster_info callbacks
+-export([register/0, cluster_info_init/0, cluster_info_generator_funs/0]).
+
+%% for debug in interactive shell
+-export([dump/0,
+         public_projection/1, private_projection/1,
+         chain_manager/1, fitness/1, flu1/1]).
+
+-include("machi_projection.hrl").
+
+-spec register() -> ok.
+register() ->
+    ok = cluster_info:register_app(?MODULE).
+
+-spec cluster_info_init() -> ok.
+cluster_info_init() ->
+    ok.
+
+-spec cluster_info_generator_funs() -> [{string(), fun((pid()) -> ok)}].
+cluster_info_generator_funs() ->
+    FluNames = [Name || {Name, _, _, _} <- supervisor:which_children(machi_flu_sup)],
+    lists:flatten([generator_funs_package(Name) || Name <- FluNames]).
+
+generator_funs_package(FluName) ->
+    [{"Public projection of FLU " ++ atom_to_list(FluName),
+      cinfo_wrapper(fun public_projection/1, FluName)},
+     {"Private projection of FLU " ++ atom_to_list(FluName),
+      cinfo_wrapper(fun private_projection/1, FluName)},
+     {"Chain manager status of FLU " ++ atom_to_list(FluName),
+      cinfo_wrapper(fun chain_manager/1, FluName)},
+     {"Fitness server status of FLU " ++ atom_to_list(FluName),
+      cinfo_wrapper(fun fitness/1, FluName)},
+     {"FLU1 status of FLU " ++ atom_to_list(FluName),
+      cinfo_wrapper(fun flu1/1, FluName)}].
+
+dump() ->
+    {{Y,M,D},{HH,MM,SS}} = calendar:local_time(),
+    Filename = lists:flatten(io_lib:format(
+                               "machi-ci-~4..0B~2..0B~2..0B-~2..0B~2..0B~2..0B.html",
+                               [Y,M,D,HH,MM,SS])),
+    cluster_info:dump_local_node(Filename).
+
+-spec public_projection(atom()) -> [{atom(), term()}].
+public_projection(FluName) ->
+    projection(FluName, public).
+
+-spec private_projection(atom()) -> [{atom(), term()}].
+private_projection(FluName) ->
+    projection(FluName, private).
+
+-spec chain_manager(atom()) -> term().
+chain_manager(FluName) ->
+    Mgr = machi_flu_psup:make_mgr_supname(FluName),
+    sys:get_status(Mgr).
+
+-spec fitness(atom()) -> term().
+fitness(FluName) ->
+    Fitness = machi_flu_psup:make_fitness_regname(FluName),
+    sys:get_status(Fitness).
+
+-spec flu1(atom()) -> [{atom(), term()}].
+flu1(FluName) ->
+    State = machi_flu1_append_server:current_state(FluName),
+    machi_flu1_append_server:format_state(State).
+
+%% Internal functions
+
+projection(FluName, Kind) ->
+    ProjStore = machi_flu1:make_projection_server_regname(FluName),
+    {ok, Projection} = machi_projection_store:read_latest_projection(
+                         whereis(ProjStore), Kind),
+    Fields = record_info(fields, projection_v1),
+    [_Name | Values] = tuple_to_list(Projection),
+    lists:zip(Fields, Values).
+
+cinfo_wrapper(Fun, FluName) ->
+    fun(C) ->
+            cluster_info:format(C, "~p", [Fun(FluName)])
+    end.

src/machi_config.erl

@@ -0,0 +1,43 @@
+%% -------------------------------------------------------------------
+%%
+%% Copyright (c) 2007-2015 Basho Technologies, Inc.  All Rights Reserved.
+%%
+%% This file is provided to you under the Apache License,
+%% Version 2.0 (the "License"); you may not use this file
+%% except in compliance with the License.  You may obtain
+%% a copy of the License at
+%%
+%%   http://www.apache.org/licenses/LICENSE-2.0
+%%
+%% Unless required by applicable law or agreed to in writing,
+%% software distributed under the License is distributed on an
+%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+%% KIND, either express or implied.  See the License for the
+%% specific language governing permissions and limitations
+%% under the License.
+%%
+%% -------------------------------------------------------------------
+
+%% @doc Configuration consulting utilities. Some conventions:
+%% - The function name should match with exact configuration
+%%   name in `app.config' or `advanced.config' of `machi' section.
+%% - The default value of that configuration is expected to be in
+%%   cuttlefish schema file. Otherwise some macro in headers may
+%%   be chosen.
+%% - Documentation of the configuration is supposed to be written
+%%   in cuttlefish schema file, rather than @doc section of the function.
+%% - spec of the function should be written.
+%% - Returning `undefined' is strongly discouraged. Return some default
+%%   value instead.
+%% - `application:get_env/3' is recommended. See `max_file_size/0' for
+%%   example.
+
+-module(machi_config).
+
+-include("machi.hrl").
+
+-export([max_file_size/0]).
+
+-spec max_file_size() -> pos_integer().
+max_file_size() ->
+    application:get_env(machi, max_file_size, ?DEFAULT_MAX_FILE_SIZE).

src/machi_csum_table.erl

@@ -1,108 +1,233 @@
+%% -------------------------------------------------------------------
+%%
+%% Copyright (c) 2007-2016 Basho Technologies, Inc.  All Rights Reserved.
+%%
+%% This file is provided to you under the Apache License,
+%% Version 2.0 (the "License"); you may not use this file
+%% except in compliance with the License.  You may obtain
+%% a copy of the License at
+%%
+%%   http://www.apache.org/licenses/LICENSE-2.0
+%%
+%% Unless required by applicable law or agreed to in writing,
+%% software distributed under the License is distributed on an
+%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+%% KIND, either express or implied.  See the License for the
+%% specific language governing permissions and limitations
+%% under the License.
+%%
+%% -------------------------------------------------------------------
+
 -module(machi_csum_table).
 
 -export([open/2,
-         find/3, write/4, trim/3,
+         find/3,
-         sync/1,
+         write/6, write/4, trim/5,
+         find_leftneighbor/2, find_rightneighbor/2,
+         all_trimmed/3, any_trimmed/3,
+         all_trimmed/2,
          calc_unwritten_bytes/1,
-         close/1, delete/1]).
+         split_checksum_list_blob_decode/1,
-
+         all/1,
--export([encode_csum_file_entry/3, decode_csum_file_entry/1]).
+         close/1, delete/1,
+         foldl_chunks/3]).
 
 -include("machi.hrl").
 
 -ifdef(TEST).
--export([split_checksum_list_blob_decode/1]).
+-include_lib("eunit/include/eunit.hrl").
 -endif.
 
 -record(machi_csum_table,
-        {file :: filename:filename(),
+        {file :: string(),
-         fd   :: file:descriptor(),
+         table :: eleveldb:db_ref()}).
-         table :: ets:tid()}).
 
 -type table() :: #machi_csum_table{}.
 -type byte_sequence() :: { Offset :: non_neg_integer(),
                            Size   :: pos_integer()|infinity }.
+-type chunk() :: {Offset :: machi_dt:file_offset(),
+                  Size :: machi_dt:chunk_size(),
+                  machi_dt:chunk_csum() | trimmed | none}.
 
 -export_type([table/0]).
 
--spec open(filename:filename(), proplists:proplists()) ->
+-spec open(string(), proplists:proplist()) ->
                   {ok, table()} | {error, file:posix()}.
+
 open(CSumFilename, _Opts) ->
-    T = ets:new(?MODULE, [private, ordered_set]),
+    LevelDBOptions = [{create_if_missing, true},
+                      %% Keep this table small so as not to interfere
+                      %% operating system's file cache, which is for
+                      %% Machi's main read efficiency
+                      {total_leveldb_mem_percent, 10}],
+    {ok, T} = eleveldb:open(CSumFilename, LevelDBOptions),
+    %% Dummy entry for reserved headers
+    ok = eleveldb:put(T,
+                      sext:encode({0, ?MINIMUM_OFFSET}),
+                      sext:encode(?CSUM_TAG_NONE_ATOM),
+                      [{sync, true}]),
     C0 = #machi_csum_table{
             file=CSumFilename,
             table=T},
-    case file:read_file(CSumFilename) of
+    {ok, C0}.
-        %% , [read, raw, binary]) of
-        {ok, Bin} ->
-            List = case split_checksum_list_blob_decode(Bin) of
-                       {List0, <<>>} ->
-                           List0;
-                       {List0, _Junk} ->
-                           %% Partially written, needs repair TODO
-                           %% [write(CSumFilename, List),
-                           List0
-                   end,
-            %% assuming all entries are strictly ordered by offset,
-            %% trim command should always come after checksum entry.
-            %% *if* by any chance that order cound not be kept, we
-            %% still can do ordering check and monotonic merge here.
-            ets:insert(T, List);
-        {error, enoent} ->
-            ok;
-        Error ->
-            throw(Error)
-    end,
-    {ok, Fd} = file:open(CSumFilename, [raw, binary, append]),
-    {ok, C0#machi_csum_table{fd=Fd}}.
 
--spec find(table(), machi_dt:chunk_pos(), machi_dt:chunk_size()) ->
+-spec split_checksum_list_blob_decode(binary())-> [chunk()].
-                  {ok, machi_dt:chunk_csum()} | {error, trimmed|notfound}.
+split_checksum_list_blob_decode(Bin) ->
+    erlang:binary_to_term(Bin).
+
+
+-define(has_overlap(LeftOffset, LeftSize, RightOffset, RightSize),
+        ((LeftOffset - (RightOffset+RightSize)) * (LeftOffset+LeftSize - RightOffset) < 0)).
+
+-spec find(table(), machi_dt:file_offset(), machi_dt:chunk_size())
+          -> [chunk()].
 find(#machi_csum_table{table=T}, Offset, Size) ->
-    %% TODO: Check whether all bytes here are written or not
+    {ok, I} = eleveldb:iterator(T, [], keys_only),
-    case ets:lookup(T, Offset) of
+    EndKey = sext:encode({Offset+Size, 0}),
-        [{Offset, Size, trimmed}] -> {error, trimmed};
+    StartKey = sext:encode({Offset, Size}),
-        [{Offset, Size, Checksum}] -> {ok, Checksum};
+    {ok, FirstKey} = case eleveldb:iterator_move(I, StartKey) of
-        [{Offset, _, _}] -> {error, unknown_chunk};
+                         {error, invalid_iterator} ->
-        [] -> {error, unknown_chunk}
+                             try
-    end.
+                                 %% Assume that the invalid_iterator is because
-
+                                 %% we tried to move to the end via StartKey.
--spec write(table(), machi_dt:chunk_pos(), machi_dt:chunk_size(),
+                                 %% Instead, move there directly.
-            machi_dt:chunk_csum()) ->
+                                 {ok, _} = eleveldb:iterator_move(I, last),
-                   ok | {error, used|file:posix()}.
+                                 {ok, _} = eleveldb:iterator_move(I, prev)
-write(#machi_csum_table{fd=Fd, table=T}, Offset, Size, CSum) ->
+                             catch
-    Binary = encode_csum_file_entry_bin(Offset, Size, CSum),
+                                 _:_ ->
-    case file:write(Fd, Binary) of
+                                     {ok, _} = eleveldb:iterator_move(I, first)
-        ok ->
-            case ets:insert_new(T, {Offset, Size, CSum}) of
-                true ->
-                    ok;
-                false ->
-                    {error, written}
                              end;
-        Error ->
+                         {ok, _} = R0 ->
-            Error
+                             case eleveldb:iterator_move(I, prev) of
+                                 {error, invalid_iterator} ->
+                                     R0;
+                                 {ok, _} = R1 ->
+                                     R1
+                             end
+                     end,
+    _ = eleveldb:iterator_close(I),
+    FoldFun = fun({K, V}, Acc) ->
+                      {TargetOffset, TargetSize} = sext:decode(K),
+                      case ?has_overlap(TargetOffset, TargetSize, Offset, Size) of
+                          true ->
+                              [{TargetOffset, TargetSize, sext:decode(V)}|Acc];
+                          false ->
+                              Acc
+                      end;
+                 (_K, Acc) ->
+                      lager:error("~p wrong option", [_K]),
+                      Acc
+              end,
+    lists:reverse(eleveldb_fold(T, FirstKey, EndKey, FoldFun, [])).
+
+%% @doc Updates all chunk info, by deleting existing entries if exists
+%% and putting new chunk info
+-spec write(table(),
+            machi_dt:file_offset(), machi_dt:chunk_size(),
+            machi_dt:chunk_csum()|'none'|'trimmed',
+            undefined|chunk(), undefined|chunk()) ->
+                   ok | {error, term()}.
+write(#machi_csum_table{table=T} = CsumT, Offset, Size, CSum,
+      LeftUpdate, RightUpdate) ->
+    PutOps =
+        [{put,
+          sext:encode({Offset, Size}),
+          sext:encode(CSum)}]
+        ++ case LeftUpdate of
+               {LO, LS, LCsum} when LO + LS =:= Offset ->
+                   [{put,
+                     sext:encode({LO, LS}),
+                     sext:encode(LCsum)}];
+               undefined ->
+                   []
+           end
+        ++ case RightUpdate of
+               {RO, RS, RCsum} when RO =:= Offset + Size ->
+                   [{put,
+                     sext:encode({RO, RS}),
+                     sext:encode(RCsum)}];
+               undefined ->
+                   []
+           end,
+    Chunks = find(CsumT, Offset, Size),
+    DeleteOps = lists:map(fun({O, L, _}) ->
+                                  {delete, sext:encode({O, L})}
+                          end, Chunks),
+%% io:format(user, "PutOps: ~P\n", [PutOps, 20]),
+%% io:format(user, "DelOps: ~P\n", [DeleteOps, 20]),
+    eleveldb:write(T, DeleteOps ++ PutOps, [{sync, true}]).
+
+-spec find_leftneighbor(table(), non_neg_integer()) ->
+                               undefined | chunk().
+find_leftneighbor(CsumT, Offset) ->
+    case find(CsumT, Offset, 1) of
+        [] -> undefined;
+        [{Offset, _, _}] -> undefined;
+        [{LOffset, _, CsumOrTrimmed}] -> {LOffset, Offset - LOffset, CsumOrTrimmed}
     end.
 
--spec trim(table(), machi_dt:chunk_pos(), machi_dt:chunk_size()) ->
+-spec find_rightneighbor(table(), non_neg_integer()) ->
-                  ok | {error, file:posix()}.
+                                undefined | chunk().
-trim(#machi_csum_table{fd=Fd, table=T}, Offset, Size) ->
+find_rightneighbor(CsumT, Offset) ->
-    Binary = encode_csum_file_entry_bin(Offset, Size, trimmed),
+    case find(CsumT, Offset, 1) of
-    case file:write(Fd, Binary) of
+        [] -> undefined;
-        ok ->
+        [{Offset, _, _}] -> undefined;
-            true = ets:insert(T, {Offset, Size, trimmed}),
+        [{ROffset, RSize, CsumOrTrimmed}] ->
-            ok;
+            {Offset, ROffset + RSize - Offset, CsumOrTrimmed}
-        Error ->
-            Error
     end.
 
--spec sync(table()) -> ok | {error, file:posix()}.
+-spec write(table(), machi_dt:file_offset(), machi_dt:file_size(),
-sync(#machi_csum_table{fd=Fd}) ->
+            machi_dt:chunk_csum()|none|trimmed) ->
-    file:sync(Fd).
+                   ok | {error, trimmed|file:posix()}.
+write(CsumT, Offset, Size, CSum) ->
+    write(CsumT, Offset, Size, CSum, undefined, undefined).
+
+trim(CsumT, Offset, Size, LeftUpdate, RightUpdate) ->
+    write(CsumT, Offset, Size,
+          trimmed, %% Should this be much smaller like $t or just 't'
+          LeftUpdate, RightUpdate).
+
+%% @doc returns whether all bytes in a specific window is continously
+%% trimmed or not
+-spec all_trimmed(table(), non_neg_integer(), non_neg_integer()) -> boolean().
+all_trimmed(#machi_csum_table{table=T}, Left, Right) ->
+    FoldFun = fun({_, _}, false) ->
+                      false;
+                 ({K, V}, Pos) when is_integer(Pos) andalso Pos =< Right ->
+                      case {sext:decode(K), sext:decode(V)} of
+                          {{Pos, Size}, trimmed} ->
+                              Pos + Size;
+                          {{Offset, Size}, _}
+                            when Offset + Size =< Left ->
+                              Left;
+                          _Eh ->
+                              false
+                      end
+              end,
+    case eleveldb:fold(T, FoldFun, Left, [{verify_checksums, true}]) of
+        false -> false;
+        Right -> true;
+        LastTrimmed when LastTrimmed < Right -> false;
+        _ -> %% LastTrimmed > Pos0, which is a irregular case but ok
+            true
+    end.
+
+%% @doc returns whether all bytes 0-Pos0 is continously trimmed or
+%% not, including header.
+-spec all_trimmed(table(), non_neg_integer()) -> boolean().
+all_trimmed(CsumT, Pos0) ->
+    all_trimmed(CsumT, 0, Pos0).
+
+-spec any_trimmed(table(),
+                  pos_integer(),
+                  machi_dt:chunk_size()) -> boolean().
+any_trimmed(CsumT, Offset, Size) ->
+    Chunks = find(CsumT, Offset, Size),
+    lists:any(fun({_, _, State}) -> State =:= trimmed end, Chunks).
 
 -spec calc_unwritten_bytes(table()) -> [byte_sequence()].
-calc_unwritten_bytes(#machi_csum_table{table=T}) ->
+calc_unwritten_bytes(#machi_csum_table{table=_} = CsumT) ->
-    case lists:sort(ets:tab2list(T)) of
+    case lists:sort(all(CsumT)) of
         [] ->
             [{?MINIMUM_OFFSET, infinity}];
         Sorted ->
@@ -110,94 +235,34 @@ calc_unwritten_bytes(#machi_csum_table{table=T}) ->
             build_unwritten_bytes_list(Sorted, LastOffset, [])
     end.
 
+all(CsumT) ->
+    FoldFun = fun(E, Acc) -> [E|Acc] end,
+    lists:reverse(foldl_chunks(FoldFun, [], CsumT)).
+
 -spec close(table()) -> ok.
-close(#machi_csum_table{table=T, fd=Fd}) ->
+close(#machi_csum_table{table=T}) ->
-    true = ets:delete(T),
+    ok = eleveldb:close(T).
-    ok = file:close(Fd).
 
 -spec delete(table()) -> ok.
-delete(#machi_csum_table{file=F} = C) ->
+delete(#machi_csum_table{table=T, file=F}) ->
-    catch close(C),
+    catch eleveldb:close(T),
-    case file:delete(F) of
+    %% TODO change this to directory walk
-        ok -> ok;
+    case os:cmd("rm -rf " ++ F) of
-        {error, enoent} -> ok;
+        "" -> ok;
         E -> E
     end.
 
-%% @doc Encode `Offset + Size + TaggedCSum' into an `iolist()' type for
+-spec foldl_chunks(fun((chunk(),  Acc0 :: term()) -> Acc :: term()),
-%% internal storage by the FLU.
+                   Acc0 :: term(), table()) -> Acc :: term().
-
+foldl_chunks(Fun, Acc0, #machi_csum_table{table=T}) ->
--spec encode_csum_file_entry(
+    FoldFun = fun({K, V}, Acc) ->
-        machi_dt:file_offset(), machi_dt:chunk_size(), machi_dt:chunk_s()) ->
+                      {Offset, Len} = sext:decode(K),
-        iolist().
+                      Fun({Offset, Len, sext:decode(V)}, Acc);
-encode_csum_file_entry(Offset, Size, TaggedCSum) ->
+                 (_K, Acc) ->
-    Len = 8 + 4 + byte_size(TaggedCSum),
+                      _ = lager:error("~p: wrong option?", [_K]),
-    [<<$w, Len:8/unsigned-big, Offset:64/unsigned-big, Size:32/unsigned-big>>,
+                      Acc
-     TaggedCSum].
+              end,
-
+    eleveldb:fold(T, FoldFun, Acc0, [{verify_checksums, true}]).
-%% @doc Encode `Offset + Size + TaggedCSum' into an `binary()' type for
-%% internal storage by the FLU.
-
--spec encode_csum_file_entry_bin(
-        machi_dt:file_offset(), machi_dt:chunk_size(), machi_dt:chunk_s()) ->
-        binary().
-encode_csum_file_entry_bin(Offset, Size, trimmed) ->
-    <<$t, Offset:64/unsigned-big, Size:32/unsigned-big>>;
-encode_csum_file_entry_bin(Offset, Size, TaggedCSum) ->
-    Len = 8 + 4 + byte_size(TaggedCSum),
-    <<$w, Len:8/unsigned-big, Offset:64/unsigned-big, Size:32/unsigned-big,
-      TaggedCSum/binary>>.
-
-%% @doc Decode a single `binary()' blob into an
-%%      `{Offset,Size,TaggedCSum}' tuple.
-%%
-%% The internal encoding (which is currently exposed to the outside world
-%% via this function and related ones) is:
-%%
-%% <ul>
-%% <li> 1 byte: record length
-%% </li>
-%% <li> 8 bytes (unsigned big-endian): byte offset
-%% </li>
-%% <li> 4 bytes (unsigned big-endian): chunk size
-%% </li>
-%% <li> all remaining bytes: tagged checksum (1st byte = type tag)
-%% </li>
-%% </ul>
-%%
-%% See `machi.hrl' for the tagged checksum types, e.g.,
-%% `?CSUM_TAG_NONE'.
-
--spec decode_csum_file_entry(binary()) ->
-        error |
-        {machi_dt:file_offset(), machi_dt:chunk_size(), machi_dt:chunk_s()}.
-decode_csum_file_entry(<<_:8/unsigned-big, Offset:64/unsigned-big, Size:32/unsigned-big, TaggedCSum/binary>>) ->
-    {Offset, Size, TaggedCSum};
-decode_csum_file_entry(_Else) ->
-    error.
-
-%% @doc Split a `binary()' blob of `checksum_list' data into a list of
-%% `{Offset,Size,TaggedCSum}' tuples.
-
--spec split_checksum_list_blob_decode(binary()) ->
-  {list({machi_dt:file_offset(), machi_dt:chunk_size(), machi_dt:chunk_s()}),
-   TrailingJunk::binary()}.
-split_checksum_list_blob_decode(Bin) ->
-    split_checksum_list_blob_decode(Bin, []).
-
-split_checksum_list_blob_decode(<<$w, Len:8/unsigned-big, Part:Len/binary, Rest/binary>>, Acc)->
-    One = <<Len:8/unsigned-big, Part/binary>>,
-    case decode_csum_file_entry(One) of
-        error ->
-            split_checksum_list_blob_decode(Rest, Acc);
-        DecOne ->
-            split_checksum_list_blob_decode(Rest, [DecOne|Acc])
-    end;
-split_checksum_list_blob_decode(<<$t, Offset:64/unsigned-big, Size:32/unsigned-big, Rest/binary>>, Acc) ->
-    %% trimmed offset
-    split_checksum_list_blob_decode(Rest, [{Offset, Size, trimmed}|Acc]);
-split_checksum_list_blob_decode(Rest, Acc) ->
-    {lists:reverse(Acc), Rest}.
 
 -spec build_unwritten_bytes_list( CsumData   :: [{ Offset   :: non_neg_integer(),
                                                    Size     :: pos_integer(),
@@ -218,3 +283,47 @@ build_unwritten_bytes_list([{CurrentOffset, CurrentSize, _Csum}|Rest], LastOffse
     build_unwritten_bytes_list(Rest, (CurrentOffset+CurrentSize), [{LastOffset, Hole}|Acc]);
 build_unwritten_bytes_list([{CO, CS, _Ck}|Rest], _LastOffset, Acc) ->
     build_unwritten_bytes_list(Rest, CO + CS, Acc).
+
+%% @doc If you want to find an overlap among two areas [x, y] and [a,
+%% b] where x &lt; y and a &lt; b; if (a-y)*(b-x) &lt; 0 then there's a
+%% overlap, else, > 0 then there're no overlap. border condition = 0
+%% is not overlap in this offset-size case.
+%% inclusion_match_spec(Offset, Size) ->
+%%     {'>', 0,
+%%      {'*',
+%%       {'-', Offset + Size, '$1'},
+%%       {'-', Offset, {'+', '$1', '$2'}}}}.
+
+-spec eleveldb_fold(eleveldb:db_ref(), binary(), binary(),
+                    fun(({binary(), binary()}, AccType::term()) -> AccType::term()),
+                    AccType0::term()) ->
+                           AccType::term().
+eleveldb_fold(Ref, Start, End, FoldFun, InitAcc) ->
+    {ok, Iterator} = eleveldb:iterator(Ref, []),
+    try
+        eleveldb_do_fold(eleveldb:iterator_move(Iterator, Start),
+                         Iterator, End, FoldFun, InitAcc)
+    catch throw:IteratorClosed ->
+            {error, IteratorClosed}
+    after
+        eleveldb:iterator_close(Iterator)
+    end.
+
+-spec eleveldb_do_fold({ok, binary(), binary()}|{error, iterator_closed|invalid_iterator}|{ok,binary()},
+                       eleveldb:itr_ref(), binary(),
+                       fun(({binary(), binary()}, AccType::term()) -> AccType::term()),
+                       AccType::term()) ->
+                              AccType::term().
+eleveldb_do_fold({ok, Key, Value}, _, End, FoldFun, Acc)
+  when End < Key ->
+    FoldFun({Key, Value}, Acc);
+eleveldb_do_fold({ok, Key, Value}, Iterator, End, FoldFun, Acc) ->
+    eleveldb_do_fold(eleveldb:iterator_move(Iterator, next),
+                     Iterator, End, FoldFun,
+                     FoldFun({Key, Value}, Acc));
+eleveldb_do_fold({error, iterator_closed}, _, _, _, Acc) ->
+            %% It's really an error which is not expected
+    throw({iterator_closed, Acc});
+eleveldb_do_fold({error, invalid_iterator}, _, _, _, Acc) ->
+    %% Probably reached to end
+    Acc.

src/machi_dt.erl

@@ -20,15 +20,24 @@
 
 -module(machi_dt).
 
+-include("machi.hrl").
 -include("machi_projection.hrl").
 
--type chunk()       :: chunk_bin() | {chunk_csum(), chunk_bin()}.
+-type append_opts() :: #append_opts{}.
--type chunk_bin()   :: binary() | iolist().    % client can use either
+-type chunk()       :: chunk_bin() | iolist(). % client can choose either rep.
--type chunk_csum()  :: binary().               % 1 byte tag, N-1 bytes checksum
+-type chunk_bin()   :: binary().               % server returns binary() only.
--type chunk_summary() :: {file_offset(), chunk_size(), binary()}.
+-type chunk_csum()  :: <<>> | chunk_csum_bin() | {csum_tag(), binary()}.
--type chunk_s()     :: binary().               % server always uses binary()
+-type chunk_csum_bin() :: binary().            % 1 byte tag, N-1 bytes checksum
+-type chunk_cstrm() :: 'trimmed' | chunk_csum().
+-type chunk_summary() :: {file_offset(), chunk_size(), chunk_bin(), chunk_cstrm()}.
 -type chunk_pos()   :: {file_offset(), chunk_size(), file_name_s()}.
 -type chunk_size()  :: non_neg_integer().
+
+%% Tags that stand for how that checksum was generated. See
+%% machi_util:make_tagged_csum/{1,2} for further documentation and
+%% implementation.
+-type csum_tag()    :: none | client_sha | server_sha | server_regen_sha.
+
 -type error_general() :: 'bad_arg' | 'wedged' | 'bad_checksum'.
 -type epoch_csum()  :: binary().
 -type epoch_num()   :: -1 | non_neg_integer().
@@ -41,17 +50,26 @@
 -type file_prefix() :: binary() | list().
 -type inet_host()   :: inet:ip_address() | inet:hostname().
 -type inet_port()   :: inet:port_number().
+-type locator()     :: number().
+-type namespace()   :: binary().
+-type namespace_version() :: non_neg_integer().
+-type ns_info()     :: #ns_info{}.
 -type projection()      :: #projection_v1{}.
 -type projection_type() :: 'public' | 'private'.
+-type read_opts()   :: #read_opts{}.
+-type read_opts_x() :: 'undefined' | 'noopt' | 'none' | #read_opts{}.
 
 -export_type([
+              append_opts/0,
               chunk/0,
               chunk_bin/0,
               chunk_csum/0,
+              chunk_csum_bin/0,
+              chunk_cstrm/0,
               chunk_summary/0,
-              chunk_s/0,
               chunk_pos/0,
               chunk_size/0,
+              csum_tag/0,
               error_general/0,
               epoch_csum/0,
               epoch_num/0,
@@ -64,7 +82,13 @@
               file_prefix/0,
               inet_host/0,
               inet_port/0,
+              locator/0,
+              namespace/0,
+              namespace_version/0,
+              ns_info/0,
               projection/0,
-              projection_type/0
+              projection_type/0,
+              read_opts/0,
+              read_opts_x/0
              ]).
 

src/machi_file_proxy.erl

@@ -47,15 +47,18 @@
 
 %% public API
 -export([
-    start_link/2,
+    start_link/3,
     stop/1,
     sync/1,
     sync/2,
     read/3,
+    read/4,
     write/3,
     write/4,
+    trim/4,
     append/2,
-    append/4
+    append/4,
+    checksum_list/1
 ]).
 
 %% gen_server callbacks
@@ -68,7 +71,7 @@
     code_change/3
 ]).
 
--define(TICK, 30*1000). %% XXX FIXME Should be something like 5 seconds
+-define(TICK, 5*1000).
 -define(TICK_THRESHOLD, 5). %% After this + 1 more quiescent ticks, shutdown
 -define(TIMEOUT, 10*1000).
 -define(TOO_MANY_ERRORS_RATIO, 50).
@@ -76,26 +79,26 @@
 -type op_stats()      :: { Total  :: non_neg_integer(),
                            Errors :: non_neg_integer() }.
 
--type byte_sequence() :: { Offset :: non_neg_integer(),
-                           Size   :: pos_integer()|infinity }.
-
 -record(state, {
+    fluname               :: atom(),
     data_dir              :: string() | undefined,
     filename              :: string() | undefined,
     data_path             :: string() | undefined,
     wedged = false        :: boolean(),
     csum_file             :: string()|undefined,
     csum_path             :: string()|undefined,
-    eof_position = 0      :: non_neg_integer(),
+    data_filehandle       :: file:io_device(),
-    unwritten_bytes = []  :: [byte_sequence()],
-    data_filehandle       :: file:filehandle(),
     csum_table            :: machi_csum_table:table(),
+    eof_position = 0      :: non_neg_integer(),
+    max_file_size = ?DEFAULT_MAX_FILE_SIZE :: pos_integer(),
+    rollover = false      :: boolean(),
     tref                  :: reference(), %% timer ref
     ticks = 0             :: non_neg_integer(), %% ticks elapsed with no new operations
     ops = 0               :: non_neg_integer(), %% sum of all ops
     reads = {0, 0}        :: op_stats(),
     writes = {0, 0}       :: op_stats(),
-    appends = {0, 0}      :: op_stats()
+    appends = {0, 0}      :: op_stats(),
+    trims = {0, 0}        :: op_stats()
 }).
 
 %% Public API
@@ -103,9 +106,9 @@
 % @doc Start a new instance of the file proxy service. Takes the filename
 % and data directory as arguments. This function is typically called by the
 % `machi_file_proxy_sup:start_proxy/2' function.
--spec start_link(Filename :: string(), DataDir :: string()) -> any().
+-spec start_link(FluName :: atom(), Filename :: string(), DataDir :: string()) -> any().
-start_link(Filename, DataDir) ->
+start_link(FluName, Filename, DataDir) ->
-    gen_server:start_link(?MODULE, {Filename, DataDir}, []).
+    gen_server:start_link(?MODULE, {FluName, Filename, DataDir}, []).
 
 % @doc Request to stop an instance of the file proxy service.
 -spec stop(Pid :: pid()) -> ok.
@@ -129,16 +132,31 @@ sync(_Pid, Type) ->
     lager:warning("Bad arg to sync: Type ~p", [Type]),
     {error, bad_arg}.
 
-% @doc Read file at offset for length
+% @doc Read file at offset for length. This returns a sequence of all
+% written and trimmed (optional) bytes that overlaps with requested
+% offset and length. Borders are not aligned.
 -spec read(Pid :: pid(),
            Offset :: non_neg_integer(),
-           Length :: non_neg_integer()) -> {ok, Data :: binary(), Checksum :: binary()} |
+           Length :: non_neg_integer()) ->
+                  {ok, [{Filename::string(), Offset :: non_neg_integer(),
+                         Data :: binary(), Checksum :: binary()}]} |
                   {error, Reason :: term()}.
-read(Pid, Offset, Length) when is_pid(Pid) andalso is_integer(Offset) andalso Offset >= 0 
+read(Pid, Offset, Length) ->
+    read(Pid, Offset, Length, #read_opts{}).
+
+-spec read(Pid :: pid(),
+           Offset :: non_neg_integer(),
+           Length :: non_neg_integer(),
+           machi_dt:read_opts_x()) ->
+                  {ok, [{Filename::string(), Offset :: non_neg_integer(),
+                         Data :: binary(), Checksum :: binary()}]} |
+                  {error, Reason :: term()}.
+read(Pid, Offset, Length, #read_opts{}=Opts)
+  when is_pid(Pid) andalso is_integer(Offset) andalso Offset >= 0
        andalso is_integer(Length) andalso Length > 0 ->
-    gen_server:call(Pid, {read, Offset, Length}, ?TIMEOUT);
+    gen_server:call(Pid, {read, Offset, Length, Opts}, ?TIMEOUT);
-read(_Pid, Offset, Length) ->
+read(_Pid, Offset, Length, Opts) ->
-    lager:warning("Bad args to read: Offset ~p, Length ~p", [Offset, Length]),
+    lager:warning("Bad args to read: Offset ~p, Length ~p, Options ~p", [Offset, Length, Opts]),
     {error, bad_arg}.
 
 % @doc Write data at offset
@@ -165,6 +183,12 @@ write(_Pid, Offset, ClientMeta, _Data) ->
     lager:warning("Bad arg to write: Offset ~p, ClientMeta: ~p", [Offset, ClientMeta]),
     {error, bad_arg}.
 
+trim(Pid, Offset, Size, TriggerGC) when is_pid(Pid),
+                                        is_integer(Offset) andalso Offset >= 0,
+                                        is_integer(Size) andalso Size > 0,
+                                        is_boolean(TriggerGC) ->
+    gen_server:call(Pid, {trim ,Offset, Size, TriggerGC}, ?TIMEOUT).
+
 % @doc Append data
 -spec append(Pid :: pid(), Data :: binary()) -> {ok, File :: string(), Offset :: non_neg_integer()}
                                                 |{error, term()}.
@@ -188,10 +212,14 @@ append(_Pid, ClientMeta, Extra, _Data) ->
     lager:warning("Bad arg to append: ClientMeta ~p, Extra ~p", [ClientMeta, Extra]),
     {error, bad_arg}.
 
+-spec checksum_list(pid()) -> {ok, list()}.
+checksum_list(Pid) ->
+    gen_server:call(Pid, {checksum_list}, ?TIMEOUT).
+
 %% gen_server callbacks
 
 % @private
-init({Filename, DataDir}) ->
+init({FluName, Filename, DataDir}) ->
     CsumFile = machi_util:make_checksum_filename(DataDir, Filename),
     {_, DPath} = machi_util:make_data_filename(DataDir, Filename),
     ok = filelib:ensure_dir(CsumFile),
@@ -200,8 +228,11 @@ init({Filename, DataDir}) ->
     UnwrittenBytes = machi_csum_table:calc_unwritten_bytes(CsumTable),
     {Eof, infinity} = lists:last(UnwrittenBytes),
     {ok, FHd} = file:open(DPath, [read, write, binary, raw]),
+    %% Reserve for EC and stuff, to prevent eof when read
+    ok = file:pwrite(FHd, 0, binary:copy(<<"so what?">>, ?MINIMUM_OFFSET div 8)),
     Tref = schedule_tick(),
     St = #state{
+        fluname         = FluName,
         filename        = Filename,
         data_dir        = DataDir,
         data_path       = DPath,
@@ -209,10 +240,10 @@ init({Filename, DataDir}) ->
         data_filehandle = FHd,
         csum_table      = CsumTable,
         tref            = Tref,
-        unwritten_bytes = UnwrittenBytes,
+        eof_position    = erlang:max(Eof, ?MINIMUM_OFFSET),
-        eof_position    = Eof},
+        max_file_size   = machi_config:max_file_size()},
-    lager:debug("Starting file proxy ~p for filename ~p, state = ~p",
+    lager:debug("Starting file proxy ~p for filename ~p, state = ~p, Eof = ~p",
-                [self(), Filename, St]),
+                [self(), Filename, St, Eof]),
     {ok, St}.
 
 % @private
@@ -224,67 +255,65 @@ handle_call({sync, data}, _From, State = #state{ data_filehandle = FHd }) ->
     R = file:sync(FHd),
     {reply, R, State};
 
-handle_call({sync, csum}, _From, State = #state{ csum_table = T }) ->
+handle_call({sync, csum}, _From, State) ->
-    R = machi_csum_table:sync(T),
+    %% machi_csum_table always writes in {sync, true} option, so here
-    {reply, R, State};
+    %% explicit sync isn't actually needed.
+    {reply, ok, State};
 
 handle_call({sync, all}, _From, State = #state{filename = F,
                                                data_filehandle = FHd,
-                                               csum_table = T
+                                               csum_table = _T
                                               }) ->
-    R = machi_csum_table:sync(T),
+    Resp = case file:sync(FHd) of
-    R1 = file:sync(FHd),
+               ok ->
-    Resp = case {R, R1} of
+                   ok;
-        {ok, ok} -> ok;
+               Error ->
-        {ok, O1} -> 
+                   lager:error("Got ~p syncing all files for file ~p",
-                   lager:error("Got ~p during a data file sync on file ~p", [O1, F]), 
+                               [Error, F]),
-                   O1;
+                   Error
-        {O2, ok} -> 
-                   lager:error("Got ~p during a csum file sync on file ~p", [O2, F]), 
-                   O2;
-        {O3, O4} -> 
-                   lager:error("Got ~p ~p syncing all files for file ~p", [O3, O4, F]),
-                   {O3, O4}
     end,
     {reply, Resp, State};
 
 %%% READS
 
-handle_call({read, _Offset, _Length}, _From,
+handle_call({read, _Offset, _Length, _}, _From,
             State = #state{wedged = true,
                            reads = {T, Err}
                           }) ->
     {reply, {error, wedged}, State#state{writes = {T + 1, Err + 1}}};
 
-handle_call({read, Offset, Length}, _From,
+handle_call({read, Offset, Length, _Opts}, _From,
                 State = #state{eof_position = Eof,
                                reads = {T, Err}
-                              }) when Offset + Length > Eof ->
+                              }) when Offset > Eof ->
+    %% make sure [Offset, Offset+Length) has an overlap with file range
     lager:error("Read request at offset ~p for ~p bytes is past the last write offset of ~p",
                 [Offset, Length, Eof]),
     {reply, {error, not_written}, State#state{reads = {T + 1, Err + 1}}};
 
-handle_call({read, Offset, Length}, _From,
+handle_call({read, Offset, Length, Opts}, _From,
             State = #state{filename = F,
                            data_filehandle = FH,
                            csum_table = CsumTable,
-                           unwritten_bytes = U,
                            reads = {T, Err}
                           }) ->
-
+    %% TODO: use these options - NoChunk prevents reading from disks
-    Checksum = case machi_csum_table:find(CsumTable, Offset, Length) of
+    %% NoChecksum doesn't check checksums
-                   {ok, Checksum0} ->
+    #read_opts{no_checksum=NoChecksum, no_chunk=NoChunk,
-                       Checksum0;
+               needs_trimmed=NeedsTrimmed} = Opts,
-                   _ ->
+    {Resp, NewErr} =
-                       undefined
+        case do_read(FH, F, CsumTable, Offset, Length, NoChunk, NoChecksum) of
-               end,
+            {ok, {[], []}} ->
-
-    {Resp, NewErr} = case handle_read(FH, F, Checksum, Offset, Length, U) of
-        {ok, Bytes, Csum} ->
-            {{ok, Bytes, Csum}, Err};
-        eof ->
                 {{error, not_written}, Err + 1};
+            {ok, {Chunks0, Trimmed0}} ->
+                Chunks = slice_both_side(Chunks0, Offset, Offset+Length),
+                Trimmed = case NeedsTrimmed of
+                              true -> Trimmed0;
+                              false -> []
+                          end,
+                {{ok, {Chunks, Trimmed}}, Err};
             Error ->
+                lager:error("Can't read ~p, ~p at File ~p", [Offset, Length, F]),
                 {Error, Err + 1}
         end,
     {reply, Resp, State#state{reads = {T+1, NewErr}}};
@@ -298,35 +327,75 @@ handle_call({write, _Offset, _ClientMeta, _Data}, _From,
     {reply, {error, wedged}, State#state{writes = {T + 1, Err + 1}}};
 
 handle_call({write, Offset, ClientMeta, Data}, _From,
-            State = #state{unwritten_bytes = U,
+            State = #state{filename = F,
-                           filename = F,
                            writes = {T, Err},
                            data_filehandle = FHd,
-                           csum_table = CsumTable
+                           csum_table = CsumTable}) ->
-                          }) ->
 
     ClientCsumTag = proplists:get_value(client_csum_tag, ClientMeta, ?CSUM_TAG_NONE),
     ClientCsum = proplists:get_value(client_csum, ClientMeta, <<>>),
 
-    {Resp, NewErr, NewU} =
+    {Resp, NewErr} =
     case check_or_make_tagged_csum(ClientCsumTag, ClientCsum, Data) of
         {error, {bad_csum, Bad}} ->
             lager:error("Bad checksum on write; client sent ~p, we computed ~p",
                         [ClientCsum, Bad]),
-            {{error, bad_checksum}, Err + 1, U};
+            {{error, bad_checksum}, Err + 1};
         TaggedCsum ->
-            case handle_write(FHd, CsumTable, F, TaggedCsum, Offset, Data, U) of
+            case handle_write(FHd, CsumTable, F, TaggedCsum, Offset, Data) of
-                {ok, NewU1} ->
+                ok ->
-                    {ok, Err, NewU1};
+                    {ok, Err};
                 Error ->
-                    {Error, Err + 1, U}
+                    {Error, Err + 1}
             end
     end,
-    {NewEof, infinity} = lists:last(NewU),
+    {NewEof, infinity} = lists:last(machi_csum_table:calc_unwritten_bytes(CsumTable)),
+    lager:debug("Wrote ~p bytes at ~p of file ~p, NewEOF = ~p~n",
+                [iolist_size(Data), Offset, F, NewEof]),
     {reply, Resp, State#state{writes = {T+1, NewErr},
-                              eof_position = NewEof,
+                              eof_position = NewEof}};
-                              unwritten_bytes = NewU
+
-                             }};
+
+%%% TRIMS
+
+handle_call({trim, _Offset, _ClientMeta, _Data}, _From,
+            State = #state{wedged = true,
+                           writes = {T, Err}
+                          }) ->
+    {reply, {error, wedged}, State#state{writes = {T + 1, Err + 1}}};
+
+handle_call({trim, Offset, Size, _TriggerGC}, _From,
+            State = #state{data_filehandle=FHd,
+                           ops = Ops,
+                           trims = {T, Err},
+                           csum_table = CsumTable}) ->
+
+    case machi_csum_table:all_trimmed(CsumTable, Offset, Offset+Size) of
+        true ->
+            NewState = State#state{ops=Ops+1, trims={T, Err+1}},
+            %% All bytes of that range was already trimmed returns ok
+            %% here, not {error, trimmed}, which means the whole file
+            %% was trimmed
+            maybe_gc(ok, NewState);
+        false ->
+            LUpdate = maybe_regenerate_checksum(
+                        FHd,
+                        machi_csum_table:find_leftneighbor(CsumTable, Offset)),
+            RUpdate = maybe_regenerate_checksum(
+                        FHd,
+                        machi_csum_table:find_rightneighbor(CsumTable, Offset+Size)),
+
+            case machi_csum_table:trim(CsumTable, Offset, Size, LUpdate, RUpdate) of
+                ok ->
+                    {NewEof, infinity} = lists:last(machi_csum_table:calc_unwritten_bytes(CsumTable)),
+                    NewState = State#state{ops=Ops+1,
+                                           trims={T+1, Err},
+                                           eof_position=NewEof},
+                    maybe_gc(ok, NewState);
+                Error ->
+                    {reply, Error, State#state{ops=Ops+1, trims={T, Err+1}}}
+            end
+    end;
 
 %% APPENDS
 
@@ -338,7 +407,6 @@ handle_call({append, _ClientMeta, _Extra, _Data}, _From,
 
 handle_call({append, ClientMeta, Extra, Data}, _From,
             State = #state{eof_position = EofP,
-                           unwritten_bytes = U,
                            filename = F,
                            appends = {T, Err},
                            data_filehandle = FHd,
@@ -348,25 +416,29 @@ handle_call({append, ClientMeta, Extra, Data}, _From,
     ClientCsumTag = proplists:get_value(client_csum_tag, ClientMeta, ?CSUM_TAG_NONE),
     ClientCsum = proplists:get_value(client_csum, ClientMeta, <<>>),
 
-    {Resp, NewErr, NewU} =
+    {Resp, NewErr} =
     case check_or_make_tagged_csum(ClientCsumTag, ClientCsum, Data) of
         {error, {bad_csum, Bad}} ->
             lager:error("Bad checksum; client sent ~p, we computed ~p",
                         [ClientCsum, Bad]),
-            {{error, bad_checksum}, Err + 1, U};
+            {{error, bad_checksum}, Err + 1};
         TaggedCsum ->
-            case handle_write(FHd, CsumTable, F, TaggedCsum, EofP, Data, U) of
+            case handle_write(FHd, CsumTable, F, TaggedCsum, EofP, Data) of
-                {ok, NewU1} ->
+                ok ->
-                    {{ok, F, EofP}, Err, NewU1};
+                    {{ok, F, EofP}, Err};
                 Error ->
-                    {Error, Err + 1, EofP, U}
+                    {Error, Err + 1}
             end
     end,
-    {NewEof, infinity} = lists:last(NewU),
+    NewEof = EofP + byte_size(Data) + Extra,
+    lager:debug("appended ~p bytes at ~p file ~p. NewEofP = ~p",
+                [iolist_size(Data), EofP, F, NewEof]),
     {reply, Resp, State#state{appends = {T+1, NewErr},
-                              eof_position = NewEof + Extra,
+                              eof_position = NewEof}};
-                              unwritten_bytes = NewU
+
-                             }};
+handle_call({checksum_list}, _FRom, State = #state{csum_table=T}) ->
+    All = machi_csum_table:all(T),
+    {reply, {ok, All}, State};
 
 handle_call(Req, _From, State) ->
     lager:warning("Unknown call: ~p", [Req]),
@@ -378,10 +450,23 @@ handle_cast(Cast, State) ->
     {noreply, State}.
 
 % @private
-handle_info(tick, State = #state{eof_position = Eof}) when Eof >= ?MAX_FILE_SIZE ->
+handle_info(tick, State = #state{fluname = FluName,
-    lager:notice("Eof position ~p >= max file size ~p. Shutting down.",
+                                 filename = F,
-                 [Eof, ?MAX_FILE_SIZE]),
+                                 eof_position = Eof,
-    {stop, file_rollover, State};
+                                 max_file_size = MaxFileSize}) when Eof >= MaxFileSize ->
+    %% Older code halted here with {stop, file_rollover, State}.
+    %% However, there may be other requests in our mailbox already
+    %% and/or not yet delivered but in a race with the
+    %% machi_flu_metadata_mgr.  So we close our eleveldb instance (to
+    %% avoid double-open attempt by a new file proxy proc), tell
+    %% machi_flu_metadata_mgr that we request a rollover, then stop.
+    %% terminate() will take care of forwarding messages that are
+    %% caught in the race.
+    lager:notice("Eof ~s position ~p >= max file size ~p. Shutting down.",
+                 [F, Eof, MaxFileSize]),
+    State2 = close_files(State),
+    machi_flu_metadata_mgr:stop_proxy_pid_rollover(FluName, {file, F}),
+    {stop, normal, State2#state{rollover = true}};
 
 %% XXX Is this a good idea? Need to think this through a bit.
 handle_info(tick, State = #state{wedged = true}) ->
@@ -395,7 +480,7 @@ handle_info(tick, State = #state{
                              writes = {WT, WE},
                              appends = {AT, AE}
                             }) when Ops > 100 andalso
-                               trunc(((RE+WE+AE) / RT+WT+AT) * 100) > ?TOO_MANY_ERRORS_RATIO ->
+                               trunc(((RE+WE+AE) / (RT+WT+AT)) * 100) > ?TOO_MANY_ERRORS_RATIO ->
     Errors = RE + WE + AE,
     lager:notice("Got ~p errors. Shutting down.", [Errors]),
     {stop, too_many_errors, State};
@@ -454,9 +539,9 @@ handle_info(Req, State) ->
     {noreply, State}.
 
 % @private
-terminate(Reason, #state{filename = F,
+terminate(Reason, State = #state{fluname = FluName,
-                         data_filehandle = FHd,
+                                 filename = F,
-                         csum_table = T,
+                                 rollover = Rollover_p,
                                  reads = {RT, RE},
                                  writes = {WT, WE},
                                  appends = {AT, AE}
@@ -466,10 +551,12 @@ terminate(Reason, #state{filename = F,
     lager:info("  Reads:  ~p/~p", [RT, RE]),
     lager:info(" Writes:  ~p/~p", [WT, WE]),
     lager:info("Appends:  ~p/~p", [AT, AE]),
-    ok = file:sync(FHd),
+    close_files(State),
-    ok = file:close(FHd),
+    if Rollover_p ->
-    ok = machi_csum_table:sync(T),
+            forward_late_messages(FluName, F, 500);
-    ok = machi_csum_table:close(T),
+       true ->
+            ok
+    end,
     ok.
 
 % @private
@@ -482,7 +569,7 @@ code_change(_OldVsn, State, _Extra) ->
 schedule_tick() ->
     erlang:send_after(?TICK, self(), tick).
 
--spec check_or_make_tagged_csum(Type     :: binary(),
+-spec check_or_make_tagged_csum(Type     :: non_neg_integer(),
                                 Checksum :: binary(),
                                 Data     :: binary() ) -> binary() |
                                                           {error, {bad_csum, Bad :: binary()}}.
@@ -499,21 +586,31 @@ check_or_make_tagged_csum(Tag, InCsum, Data) when Tag == ?CSUM_TAG_CLIENT_SHA;
         false ->
             {error, {bad_csum, Csum}}
     end;
+check_or_make_tagged_csum(?CSUM_TAG_SERVER_REGEN_SHA,
+                          InCsum, Data) ->
+    Csum = machi_util:checksum_chunk(Data),
+    case Csum =:= InCsum of
+        true ->
+            machi_util:make_tagged_csum(server_regen_sha, Csum);
+        false ->
+            {error, {bad_csum, Csum}}
+    end;
 check_or_make_tagged_csum(OtherTag, _ClientCsum, _Data) ->
     lager:warning("Unknown checksum tag ~p", [OtherTag]),
     {error, bad_checksum}.
 
--spec handle_read(FHd        :: file:filehandle(),
+-spec do_read(FHd        :: file:io_device(),
               Filename   :: string(),
-                  TaggedCsum :: undefined|binary(),
+              CsumTable  :: machi_csum_table:table(),
               Offset     :: non_neg_integer(),
               Size       :: non_neg_integer(),
-                  Unwritten  :: [byte_sequence()]
+              NoChunk    :: boolean(),
-             ) -> {ok, Bytes :: binary(), Csum :: binary()} |
+              NoChecksum :: boolean()
-                  eof | 
+             ) -> {ok, {Chunks :: [{string(), Offset::non_neg_integer(), binary(), Csum :: binary()}],
+                        Trimmed :: [{string(), Offset::non_neg_integer(), Size::non_neg_integer()}]}} |
                   {error, bad_checksum} |
                   {error, partial_read} |
-                  {error, not_written} |
+                  {error, file:posix()} |
                   {error, Other :: term() }.
 % @private Attempt a read operation on the given offset and length.
 % <li>
@@ -528,22 +625,36 @@ check_or_make_tagged_csum(OtherTag, _ClientCsum, _Data) ->
 %        tuple is returned.</ul>
 % </li>
 %
-% On success, `{ok, Bytes, Checksum}' is returned.
+do_read(FHd, Filename, CsumTable, Offset, Size, _, _) ->
-handle_read(FHd, Filename, undefined, Offset, Size, U) ->
+    %% Note that find/3 only returns overlapping chunks, both borders
-    handle_read(FHd, Filename, machi_util:make_tagged_csum(none), Offset, Size, U);
+    %% are not aligned to original Offset and Size.
+    ChunkCsums = machi_csum_table:find(CsumTable, Offset, Size),
+    read_all_ranges(FHd, Filename, ChunkCsums, [], []).
 
-handle_read(FHd, Filename, TaggedCsum, Offset, Size, U) ->
+-spec read_all_ranges(file:io_device(), string(),
-    case is_byte_range_unwritten(Offset, Size, U) of
+                      [{non_neg_integer(),non_neg_integer(),trimmed|binary()}],
-        true ->
+                      Chunks :: [{string(), Offset::non_neg_integer(), binary(), Csum::binary()}],
-            {error, not_written};
+                      Trimmed :: [{string(), Offset::non_neg_integer(), Size::non_neg_integer()}]) ->
-        false ->
+                             {ok, {
-            do_read(FHd, Filename, TaggedCsum, Offset, Size)
+                                Chunks :: [{string(), Offset::non_neg_integer(), binary(), Csum::binary()}],
-    end.
+                                Trimmed :: [{string(), Offset::non_neg_integer(), Size::non_neg_integer()}]}} |
+                             {erorr, term()|partial_read}.
+read_all_ranges(_, _, [], ReadChunks, TrimmedChunks) ->
+    %% TODO: currently returns empty list of trimmed chunks
+    {ok, {lists:reverse(ReadChunks), lists:reverse(TrimmedChunks)}};
 
-do_read(FHd, Filename, TaggedCsum, Offset, Size) ->
+read_all_ranges(FHd, Filename, [{Offset, Size, trimmed}|T], ReadChunks, TrimmedChunks) ->
+    read_all_ranges(FHd, Filename, T, ReadChunks, [{Filename, Offset, Size}|TrimmedChunks]);
+
+read_all_ranges(FHd, Filename, [{Offset, Size, TaggedCsum}|T], ReadChunks, TrimmedChunks) ->
     case file:pread(FHd, Offset, Size) of
         eof ->
-            eof;
+            read_all_ranges(FHd, Filename, T, ReadChunks, TrimmedChunks);
+        {ok, Bytes} when byte_size(Bytes) == Size, TaggedCsum =:= none ->
+            read_all_ranges(FHd, Filename, T,
+                            [{Filename, Offset, Bytes,
+                              machi_util:make_tagged_csum(none, <<>>)}|ReadChunks],
+                            TrimmedChunks);
         {ok, Bytes} when byte_size(Bytes) == Size ->
             {Tag, Ck} = machi_util:unmake_tagged_csum(TaggedCsum),
             case check_or_make_tagged_csum(Tag, Ck, Bytes) of
@@ -552,11 +663,15 @@ do_read(FHd, Filename, TaggedCsum, Offset, Size) ->
                                 [Bad, Ck]),
                     {error, bad_checksum};
                 TaggedCsum ->
-                    {ok, Bytes, TaggedCsum};
+                    read_all_ranges(FHd, Filename, T,
+                                    [{Filename, Offset, Bytes, TaggedCsum}|ReadChunks],
+                                    TrimmedChunks);
+                OtherCsum when Tag =:= ?CSUM_TAG_NONE ->
                     %% XXX FIXME: Should we return something other than
                     %% {ok, ....} in this case?
-                OtherCsum when Tag =:= ?CSUM_TAG_NONE ->
+                    read_all_ranges(FHd, Filename, T,
-                    {ok, Bytes, OtherCsum}
+                                    [{Filename, Offset, Bytes, OtherCsum}|ReadChunks],
+                                    TrimmedChunks)
             end;
         {ok, Partial} ->
             lager:error("In file ~p, offset ~p, wanted to read ~p bytes, but got ~p",
@@ -568,14 +683,13 @@ do_read(FHd, Filename, TaggedCsum, Offset, Size) ->
             {error, Other}
     end.
 
--spec handle_write( FHd        :: file:filehandle(),
+-spec handle_write( FHd        :: file:io_device(),
                     CsumTable  :: machi_csum_table:table(),
                     Filename   :: string(),
                     TaggedCsum :: binary(),
                     Offset     :: non_neg_integer(),
-                    Data       :: binary(),
+                    Data       :: binary()
-                    Unwritten  :: [byte_sequence()]
+                   ) -> ok |
-                  ) -> {ok, NewU :: [byte_sequence()]} |
                        {error, written} |
                        {error, Reason :: term()}.
 % @private Implements the write and append operation. The first task is to
@@ -585,153 +699,210 @@ do_read(FHd, Filename, TaggedCsum, Offset, Size) ->
 % checksum and return a "fake" ok response as if the write had been performed
 % when it hasn't really.
 %
-% If a write proceeds, the offset, size and checksum are written to a metadata
+% If a write proceeds, the offset, size and checksum are written to a
-% file, and the internal list of unwritten bytes is modified to reflect the
+% metadata file, and the internal list of unwritten bytes is modified
-% just-performed write.  This is then returned to the caller as 
+% to reflect the just-performed write.  This is then returned to the
-% `{ok, NewUnwritten}' where NewUnwritten is the revised unwritten byte list.
+% caller as `ok'
-handle_write(FHd, CsumTable, Filename, TaggedCsum, Offset, Data, U) ->
+handle_write(FHd, CsumTable, Filename, TaggedCsum, Offset, Data) ->
     Size = iolist_size(Data),
  
-    case is_byte_range_unwritten(Offset, Size, U) of
-        false ->
     case machi_csum_table:find(CsumTable, Offset, Size) of
-                {error, trimmed} = Error ->
+        [] -> %% Nothing should be there
-                    Error;
-                {error, unknown_chunk} ->
-                    %% The specified has some bytes written, while
-                    %% it's not in the checksum table. Trust U and
-                    %% return as it is used.
-                    {error, written};
-                {ok, TaggedCsum} ->
-                    case do_read(FHd, Filename, TaggedCsum, Offset, Size) of
-                        eof ->
-                            lager:warning("This should never happen: got eof while reading at offset ~p in file ~p that's supposedly written",
-                                          [Offset, Filename]),
-                            {error, server_insanity};
-                        {ok, _, _} ->
-                            {ok, U};
-                        _ ->
-                            {error, written}
-                    end;
-                {ok, OtherCsum} ->
-                    %% Got a checksum, but it doesn't match the data block's
-                    lager:error("During a potential write at offset ~p in file ~p, a check for unwritten bytes gave us checksum ~p but the data we were trying to trying to write has checksum ~p",
-                                [Offset, Filename, OtherCsum, TaggedCsum]),
-                    {error, written}
-            end;
-        true ->
             try
-                do_write(FHd, CsumTable, Filename, TaggedCsum, Offset, Size, Data, U)
+                do_write(FHd, CsumTable, Filename, TaggedCsum, Offset, Size, Data)
             catch
-                %%% XXX FIXME: be more specific on badmatch that might
+                %% XXX FIXME: be more specific on badmatch that might
-                %%% occur around line 593 when we write the checksum
+                %% occur around line 593 when we write the checksum
-                %%% file entry for the data blob we just put on the disk
+                %% file entry for the data blob we just put on the disk
                 error:Reason ->
                     {error, Reason}
+            end;
+        [{Offset, Size, TaggedCsum}] ->
+            case do_read(FHd, Filename, CsumTable, Offset, Size, false, false) of
+                {error, _} = E ->
+                    lager:warning("This should never happen: got ~p while reading"
+                                  " at offset ~p in file ~p that's supposedly written",
+                                  [E, Offset, Filename]),
+                    {error, server_insanity};
+                {ok, {[{_, Offset, Data, TaggedCsum}], _}} ->
+                    %% TODO: what if different checksum got from do_read()?
+                    ok;
+                {ok, _Other} ->
+                    %% TODO: leave some debug/warning message here?
+                    {error, written}
+            end;
+        [{Offset, Size, OtherCsum}] ->
+            %% Got a checksum, but it doesn't match the data block's
+            lager:error("During a potential write at offset ~p in file ~p,"
+                        " a check for unwritten bytes gave us checksum ~p"
+                        " but the data we were trying to write has checksum ~p",
+                        [Offset, Filename, OtherCsum, TaggedCsum]),
+            {error, written};
+        _Chunks ->
+            %% TODO: Do we try to read all continuous chunks to see
+            %% wether its total checksum matches client-provided checksum?
+            case machi_csum_table:any_trimmed(CsumTable, Offset, Size) of
+                true ->
+                    %% More than a byte is trimmed, besides, do we
+                    %% have to return exact written bytes? No. Clients
+                    %% must issue read_chunk() with needs_trimmed
+                    %% option as true
+                    {error, trimmed};
+                false ->
+                    %% No byte is trimmed, but at least one byte is written
+                    {error, written}
             end
     end.
 
 % @private Implements the disk writes for both the write and append
 % operation.
--spec do_write( FHd        :: file:descriptor(),
+-spec do_write( FHd        :: file:io_device(),
                 CsumTable  :: machi_csum_table:table(),
                 Filename   :: string(),
                 TaggedCsum :: binary(),
                 Offset     :: non_neg_integer(),
                 Size       :: non_neg_integer(),
-                Data       :: binary(),
+                Data       :: binary()
-                Unwritten  :: [byte_sequence()]
+              ) -> ok | {error, Reason :: term()}.
-              ) -> {ok, NewUnwritten :: [byte_sequence()]} |
+do_write(FHd, CsumTable, Filename, TaggedCsum, Offset, Size, Data) ->
-                   {error, Reason :: term()}.
-do_write(FHd, CsumTable, Filename, TaggedCsum, Offset, Size, Data, U) ->
     case file:pwrite(FHd, Offset, Data) of
         ok ->
             lager:debug("Successful write in file ~p at offset ~p, length ~p",
                         [Filename, Offset, Size]),
-            ok = machi_csum_table:write(CsumTable, Offset, Size, TaggedCsum),
+
-            NewU = update_unwritten(Offset, Size, U),
+            %% Overlapping chunk; calculate checksum
-            lager:debug("Successful write to checksum file for ~p; unwritten bytes are now: ~p",
+            %% read {LOffset, Offset - LOffset} and make csum
-                        [Filename, NewU]),
+            %% as server_sha
-            {ok, NewU};
+            LUpdate = maybe_regenerate_checksum(
+                        FHd,
+                        machi_csum_table:find_leftneighbor(CsumTable, Offset)),
+            RUpdate = maybe_regenerate_checksum(
+                        FHd,
+                        machi_csum_table:find_rightneighbor(CsumTable, Offset+Size)),
+            ok = machi_csum_table:write(CsumTable, Offset, Size,
+                                        TaggedCsum, LUpdate, RUpdate),
+            lager:debug("Successful write to checksum file for ~p",
+                        [Filename]),
+            ok;
         Other ->
             lager:error("Got ~p during write to file ~p at offset ~p, length ~p",
             [Other, Filename, Offset, Size]),
             {error, Other}
     end.
 
--spec is_byte_range_unwritten( Offset    :: non_neg_integer(),
+%% @doc Trim both right and left border of chunks to fit in to given
-                            Size      :: pos_integer(),
+%% range [LeftPos, RightPos]. TODO: write unit tests for this function.
-                            Unwritten :: [byte_sequence()] ) -> boolean().
+
-% @private Given an offset and a size, return `true' if a byte range has
+%% Dialyzer 'can never match': slice_both_side([], _, _) ->
-% <b>not</b> been written. Otherwise, return `false'.
+    %% [];
-is_byte_range_unwritten(Offset, Size, Unwritten) ->
+slice_both_side([], _, _) ->
-    case Unwritten of
+    [];
-        [] ->
+slice_both_side([{F, Offset, Chunk, _Csum}|L], LeftPos, RightPos)
-            lager:critical("Unwritten byte list has 0 entries! This should never happen."),
+  when Offset < LeftPos andalso LeftPos < RightPos ->
-            false;
+    TrashLen = (LeftPos - Offset),
-        [{Eof, infinity}] ->
+    <<_:TrashLen/binary, NewChunk/binary>> = Chunk,
-            Offset >= Eof;
+    NewChecksum = machi_util:make_tagged_csum(?CSUM_TAG_SERVER_REGEN_SHA_ATOM, Chunk),
+    NewH = {F, LeftPos, NewChunk, NewChecksum},
+    slice_both_side([NewH|L], LeftPos, RightPos);
+slice_both_side(Chunks, LeftPos, RightPos) when LeftPos =< RightPos ->
+    %% TODO: optimize
+    [{F, Offset, Chunk, _Csum}|L] = lists:reverse(Chunks),
+    Size = iolist_size(Chunk),
+    if RightPos < Offset + Size ->
+            NewSize = RightPos - Offset,
+            <<NewChunk:NewSize/binary, _/binary>> = Chunk,
+            NewChecksum = machi_util:make_tagged_csum(?CSUM_TAG_SERVER_REGEN_SHA_ATOM, Chunk),
+            lists:reverse([{F, Offset, NewChunk, NewChecksum}|L]);
+       true ->
+            Chunks
+    end.
+
+maybe_regenerate_checksum(_, undefined) ->
+    undefined;
+maybe_regenerate_checksum(_, {_, _, trimmed} = Change) ->
+    Change;
+maybe_regenerate_checksum(FHd, {Offset, Size, _Csum}) ->
+    case file:pread(FHd, Offset, Size) of
+        eof ->
+            error({eof, Offset, Size});
+        {ok, Bytes} when byte_size(Bytes) =:= Size ->
+
+            TaggedCsum = machi_util:make_tagged_csum(server_regen_sha,
+                                                     machi_util:checksum_chunk(Bytes)),
+            {Offset, Size, TaggedCsum};
+        Error ->
+            throw(Error)
+    end.
+
+%% GC: make sure unwritten bytes = [{Eof, infinity}] and Eof is > max
+%% file size walk through the checksum table and make sure all chunks
+%% trimmed Then unlink the file
+-spec maybe_gc(term(), #state{}) ->
+                      {reply, term(), #state{}} | {stop, normal, term(), #state{}}.
+maybe_gc(Reply, S = #state{eof_position = Eof,
+                           max_file_size = MaxFileSize}) when Eof < MaxFileSize ->
+    lager:debug("The file is still small; not trying GC (Eof, MaxFileSize) = (~p, ~p)~n",
+                [Eof, MaxFileSize]),
+    {reply, Reply, S};
+maybe_gc(Reply, S = #state{fluname=FluName,
+                           data_filehandle = FHd,
+                           data_dir = DataDir,
+                           filename = Filename,
+                           eof_position = Eof,
+                           csum_table=CsumTable}) ->
+    case machi_csum_table:all_trimmed(CsumTable, ?MINIMUM_OFFSET, Eof) of
+        true ->
+            lager:debug("GC? Let's do it: ~p.~n", [Filename]),
+            %% Before unlinking a file, it should inform
+            %% machi_flu_filename_mgr that this file is
+            %% deleted and mark it as "trimmed" to avoid
+            %% filename reuse and resurrection. Maybe garbage
+            %% will remain if a process crashed but it also
+            %% should be recovered at filename_mgr startup.
+
+            %% Also, this should be informed *before* file proxy
+            %% deletes files.
+            ok = machi_flu_metadata_mgr:trim_file(FluName, {file, Filename}),
+            ok = file:close(FHd),
+            {_, DPath} = machi_util:make_data_filename(DataDir, Filename),
+            ok = file:delete(DPath),
+            machi_csum_table:delete(CsumTable),
+            {stop, normal, Reply,
+             S#state{data_filehandle=undefined,
+                     csum_table=undefined}};
+        false ->
+            {reply, Reply, S}
+    end.
+
+close_files(State = #state{data_filehandle = FHd,
+                           csum_table = T}) ->
+    case FHd of
+        undefined ->
+            noop; %% file deleted
         _ ->
-            case lookup_unwritten(Offset, Size, Unwritten) of
+            ok = file:sync(FHd),
-                {ok, _}   -> true;
+            ok = file:close(FHd)
-                not_found -> false
+    end,
-            end
+    case T of
+        undefined ->
+            noop; %% file deleted
+        _ ->
+            ok = machi_csum_table:close(T)
+    end,
+    State#state{data_filehandle = undefined, csum_table = undefined}.
+
+forward_late_messages(FluName, F, Timeout) ->
+    receive
+        M ->
+            case machi_flu_metadata_mgr:start_proxy_pid(FluName, {file, F}) of
+                {ok, Pid} ->
+                    Pid ! M;
+                {error, trimmed} ->
+                    lager:error("TODO: FLU ~p file ~p reports trimmed status "
+                                "when forwarding ~P\n",
+                                [FluName, F, M, 20])
+            end,
+            forward_late_messages(FluName, F, Timeout)
+    after Timeout ->
+            ok
     end.
-
--spec lookup_unwritten( Offset    :: non_neg_integer(),
-                        Size      :: pos_integer(),
-                        Unwritten :: [byte_sequence()]
-                      ) -> {ok, byte_sequence()} | not_found.
-% @private Given an offset and a size, scan the list of unwritten bytes and
-% look for a "hole" where a write might be allowed if any exist. If a
-% suitable byte sequence is found, the function returns a tuple of {ok,
-% {Position, Space}} is returned. `not_found' is returned if no suitable
-% space is located.
-lookup_unwritten(_Offset, _Size, []) ->
-    not_found;
-lookup_unwritten(Offset, _Size, [H={Pos, infinity}|_Rest]) when Offset >= Pos ->
-    {ok, H};
-lookup_unwritten(Offset, Size, [H={Pos, Space}|_Rest]) 
-                when Offset >= Pos andalso Offset < Pos+Space 
-                     andalso Size =< (Space - (Offset - Pos)) ->
-    {ok, H};
-lookup_unwritten(Offset, Size, [_H|Rest]) ->
-    %% These are not the droids you're looking for.
-    lookup_unwritten(Offset, Size, Rest).
-
-%%% if the pos is greater than offset + size then we're done. End early.
-
--spec update_unwritten( Offset    :: non_neg_integer(),
-                        Size      :: pos_integer(),
-                        Unwritten :: [byte_sequence()] ) -> NewUnwritten :: [byte_sequence()].
-% @private Given an offset, a size and the unwritten byte list, return an updated
-% and sorted unwritten byte list accounting for any completed write operation.
-update_unwritten(Offset, Size, Unwritten) ->
-    case lookup_unwritten(Offset, Size, Unwritten) of
-        not_found ->
-            lager:error("Couldn't find byte sequence tuple for a write which earlier found a valid spot to write!!! This should never happen!"),
-            Unwritten;
-        {ok, {Offset, Size}} ->
-            %% we neatly filled in our hole...
-            lists:keydelete(Offset, 1, Unwritten);
-        {ok, S={Pos, _}} ->
-            lists:sort(lists:keydelete(Pos, 1, Unwritten) ++
-              update_byte_range(Offset, Size, S))
-    end.
-
--spec update_byte_range( Offset   :: non_neg_integer(),
-                         Size     :: pos_integer(),
-                         Sequence :: byte_sequence() ) -> Updates :: [byte_sequence()].
-% @private Given an offset and size and a byte sequence tuple where a
-% write took place, return a list of updates to the list of unwritten bytes
-% accounting for the space occupied by the just completed write.
-update_byte_range(Offset, Size, {Eof, infinity}) when Offset == Eof ->
-    [{Offset + Size, infinity}];
-update_byte_range(Offset, Size, {Eof, infinity}) when Offset > Eof ->
-    [{Eof, (Offset - Eof)}, {Offset+Size, infinity}];
-update_byte_range(Offset, Size, {Pos, Space}) when Offset == Pos andalso Size < Space ->
-    [{Offset + Size, Space - Size}];
-update_byte_range(Offset, Size, {Pos, Space}) when Offset > Pos ->
-    [{Pos, Offset - Pos}, {Offset+Size, ( (Pos+Space) - (Offset + Size) )}].
-
-

src/machi_file_proxy_sup.erl

@@ -44,7 +44,8 @@ start_link(FluName) ->
     supervisor:start_link({local, make_proxy_name(FluName)}, ?MODULE, []).
 
 start_proxy(FluName, DataDir, Filename) ->
-    supervisor:start_child(make_proxy_name(FluName), [Filename, DataDir]).
+    supervisor:start_child(make_proxy_name(FluName),
+                           [FluName, Filename, DataDir]).
 
 init([]) ->
     SupFlags = {simple_one_for_one, 1000, 10},

src/machi_fitness.erl

@@ -39,11 +39,12 @@
          get_unfit_list/1, update_local_down_list/3,
          add_admin_down/3, delete_admin_down/2,
          send_fitness_update_spam/3,
-         send_spam_to_everyone/1]).
+         send_spam_to_everyone/1,
+         trigger_early_adjustment/2]).
 
 %% gen_server callbacks
 -export([init/1, handle_call/3, handle_cast/2, handle_info/2,
-         terminate/2, code_change/3]).
+         terminate/2, code_change/3, format_status/2]).
 
 -record(state, {
           my_flu_name                :: atom() | binary(),
@@ -81,12 +82,19 @@ send_fitness_update_spam(Pid, FromName, Dict) ->
 send_spam_to_everyone(Pid) ->
     gen_server:call(Pid, {send_spam_to_everyone}, infinity).
 
+%% @doc For testing purposes, we don't want a test to wait for
+%%      wall-clock time to elapse before the fitness server makes a
+%%      down->up status decision.
+
+trigger_early_adjustment(Pid, FLU) ->
+    Pid ! {adjust_down_list, FLU}.
+
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
 
 init([{MyFluName}|Args]) ->
     RegName = machi_flu_psup:make_fitness_regname(MyFluName),
     register(RegName, self()),
-    timer:send_interval(5000, debug_dump),
+    {ok, _} = timer:send_interval(5000, debug_dump),
     UseSimulatorP = proplists:get_value(use_partition_simulator, Args, false),
     {ok, #state{my_flu_name=MyFluName, reg_name=RegName,
                 partition_simulator_p=UseSimulatorP,
@@ -100,24 +108,29 @@ handle_call({update_local_down_list, Down, MembersDict}, _From,
             #state{my_flu_name=MyFluName, pending_map=OldMap,
                    local_down=OldDown, members_dict=OldMembersDict,
                    admin_down=AdminDown}=S) ->
+    verbose("FITNESS: ~w has down suspect ~w\n", [MyFluName, Down]),
     NewMap = store_in_map(OldMap, MyFluName, erlang:now(), Down,
                           AdminDown, [props_yo]),
     S2 = if Down == OldDown, MembersDict == OldMembersDict ->
                  %% Do nothing only if both are equal.  If members_dict is
                  %% changing, that's sufficient reason to spam.
-                 ok;
+                 S;
             true ->
                  do_map_change(NewMap, [MyFluName], MembersDict, S)
          end,
     {reply, ok, S2#state{local_down=Down}};
 handle_call({add_admin_down, DownFLU, DownProps}, _From,
-            #state{local_down=OldDown, admin_down=AdminDown}=S) ->
+            #state{my_flu_name=MyFluName,
+                   local_down=OldDown, admin_down=AdminDown}=S) ->
+    verbose("FITNESS: ~w add admin down ~w\n", [MyFluName, DownFLU]),
     NewAdminDown = [{DownFLU,DownProps}|lists:keydelete(DownFLU, 1, AdminDown)],
     S3 = finish_admin_down(erlang:now(), OldDown, NewAdminDown,
                            [props_yo], S),
     {reply, ok, S3};
 handle_call({delete_admin_down, DownFLU}, _From,
-            #state{local_down=OldDown, admin_down=AdminDown}=S) ->
+            #state{my_flu_name=MyFluName,
+                   local_down=OldDown, admin_down=AdminDown}=S) ->
+    verbose("FITNESS: ~w delete admin down ~w\n", [MyFluName, DownFLU]),
     NewAdminDown = lists:keydelete(DownFLU, 1, AdminDown),
     S3 = finish_admin_down(erlang:now(), OldDown, NewAdminDown,
                            [props_yo], S),
@@ -135,7 +148,8 @@ handle_call(_Request, _From, S) ->
 handle_cast(_Msg, S) ->
     {noreply, S}.
 
-handle_info({adjust_down_list, FLU}, #state{active_unfit=ActiveUnfit}=S) ->
+handle_info({adjust_down_list, FLU}, #state{my_flu_name=MyFluName,
+                                            active_unfit=ActiveUnfit}=S) ->
     NewUnfit = make_unfit_list(S),
     Added_to_new     = NewUnfit -- ActiveUnfit,
     Dropped_from_new = ActiveUnfit -- NewUnfit,
@@ -171,14 +185,16 @@ handle_info({adjust_down_list, FLU}, #state{active_unfit=ActiveUnfit}=S) ->
     %% hiding where we need this extra round of messages to *remove* a
     %% FLU from the active_unfit list?
 
-    schedule_adjust_messages(lists:usort(Added_to_new ++ Dropped_from_new)),
+    _ = schedule_adjust_messages(lists:usort(Added_to_new ++ Dropped_from_new)),
     case {lists:member(FLU,Added_to_new), lists:member(FLU,Dropped_from_new)} of
         {true, true} ->
             error({bad, ?MODULE, ?LINE, FLU, ActiveUnfit, NewUnfit});
         {true, false} ->
-            {noreply, S#state{active_unfit=lists:usort(ActiveUnfit ++ [FLU])}};
+            NewActive = wrap_active(MyFluName,lists:usort(ActiveUnfit++[FLU])),
+            {noreply, S#state{active_unfit=NewActive}};
         {false, true} ->
-            {noreply, S#state{active_unfit=ActiveUnfit -- [FLU]}};
+            NewActive = wrap_active(MyFluName,ActiveUnfit--[FLU]),
+            {noreply, S#state{active_unfit=NewActive}};
         {false, false} ->
             {noreply, S}
     end;
@@ -193,6 +209,11 @@ handle_info(_Info, S) ->
 terminate(_Reason, _S) ->
     ok.
 
+format_status(_Opt, [_PDict, Status]) ->
+    Fields = record_info(fields, state),
+    [_Name | Values] = tuple_to_list(Status),
+    lists:zip(Fields, Values).
+
 code_change(_OldVsn, S, _Extra) ->
     {ok, S}.
 
@@ -290,8 +311,8 @@ proxy_pid(Name, #state{proxies_dict=ProxiesDict}) ->
 
 calc_unfit(All_list, HosedAnnotations) ->
     G = digraph:new(),
-    [digraph:add_vertex(G, V) || V <- All_list],
+    _ = [digraph:add_vertex(G, V) || V <- All_list],
-    [digraph:add_edge(G, V1, V2) || {V1, problem_with, V2} <- HosedAnnotations],
+    _ = [digraph:add_edge(G, V1, V2) || {V1, problem_with, V2} <- HosedAnnotations],
     calc_unfit2(lists:sort(digraph:vertices(G)), G).
 
 calc_unfit2([], G) ->
@@ -345,7 +366,7 @@ do_map_change(NewMap, DontSendList, MembersDict,
               #state{my_flu_name=_MyFluName, pending_map=OldMap}=S) ->
     send_spam(NewMap, DontSendList, MembersDict, S),
     ChangedServers = find_changed_servers(OldMap, NewMap, _MyFluName),
-    schedule_adjust_messages(ChangedServers),
+    _ = schedule_adjust_messages(ChangedServers),
     %% _OldMapV = map_value(OldMap),
     %% _MapV = map_value(NewMap),
     %% io:format(user, "TODO: ~w async tick trigger/scheduling... ~w for:\n"
@@ -411,6 +432,18 @@ map_value(Map) ->
 map_merge(Map1, Map2) ->
     ?MAP:merge(Map1, Map2).
 
+wrap_active(MyFluName, L) ->
+    verbose("FITNESS: ~w has new down list ~w\n", [MyFluName, L]),
+    L.
+
+verbose(Fmt, Args) ->
+    case application:get_env(machi, fitness_verbose) of
+        {ok, true} ->
+            error_logger:info_msg(Fmt, Args);
+        _ ->
+            ok
+    end.
+
 -ifdef(TEST).
 
 dt_understanding_test() ->

src/machi_flu1.erl

@@ -21,7 +21,9 @@
 %% @doc The Machi FLU file server + file location sequencer.
 %%
 %% This module implements only the Machi FLU file server and its
-%% implicit sequencer.  
+%% implicit sequencer together with listener, append server,
+%% file management and file proxy processes.
+
 %% Please see the EDoc "Overview" for details about the FLU as a
 %% primitive file server process vs. the larger Machi design of a FLU
 %% as a sequencer + file server + chain manager group of processes.
@@ -54,34 +56,29 @@
 
 -ifdef(TEST).
 -include_lib("eunit/include/eunit.hrl").
+-export([timing_demo_test_COMMENTED_/0, sort_2lines/2]). % Just to suppress warning
 -endif. % TEST
 
--define(SERVER_CMD_READ_TIMEOUT, 600*1000).
-
 -export([start_link/1, stop/1,
          update_wedge_state/3, wedge_myself/2]).
--export([make_listener_regname/1, make_projection_server_regname/1]).
+-export([make_projection_server_regname/1,
+         ets_table_name/1]).
+%% TODO: remove or replace in OTP way after gen_*'ified
+-export([main2/4]).
 
--record(state, {
+-define(INIT_TIMEOUT, 60*1000).
-          flu_name        :: atom(),
-          proj_store      :: pid(),
-          witness = false :: boolean(),
-          append_pid      :: pid(),
-          tcp_port        :: non_neg_integer(),
-          data_dir        :: string(),
-          wedged = true   :: boolean(),
-          etstab          :: ets:tid(),
-          epoch_id        :: 'undefined' | machi_dt:epoch_id(),
-          pb_mode = undefined  :: 'undefined' | 'high' | 'low',
-          high_clnt       :: 'undefined' | pid(),
-          props = []      :: list()  % proplist
-         }).
 
 start_link([{FluName, TcpPort, DataDir}|Rest])
   when is_atom(FluName), is_integer(TcpPort), is_list(DataDir) ->
-    {ok, spawn_link(fun() -> main2(FluName, TcpPort, DataDir, Rest) end)}.
+    proc_lib:start_link(?MODULE, main2, [FluName, TcpPort, DataDir, Rest],
+                        ?INIT_TIMEOUT).
 
-stop(Pid) ->
+stop(RegName) when is_atom(RegName) ->
+    case whereis(RegName) of
+        undefined -> ok;
+        Pid -> stop(Pid)
+    end;
+stop(Pid) when is_pid(Pid) ->
     case erlang:is_process_alive(Pid) of
         true ->
             Pid ! killme,
@@ -90,19 +87,14 @@ stop(Pid) ->
             error
     end.
 
-update_wedge_state(PidSpec, Boolean, EpochId)
+update_wedge_state(PidSpec, Boolean, EpochId) ->
-  when (Boolean == true orelse Boolean == false), is_tuple(EpochId) ->
+    machi_flu1_append_server:int_update_wedge_state(PidSpec, Boolean, EpochId).
-    PidSpec ! {wedge_state_change, Boolean, EpochId}.
 
-wedge_myself(PidSpec, EpochId)
+wedge_myself(PidSpec, EpochId) ->
-  when is_tuple(EpochId) ->
+    machi_flu1_append_server:int_wedge_myself(PidSpec, EpochId).
-    PidSpec ! {wedge_myself, EpochId}.
 
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%
 
-ets_table_name(FluName) when is_atom(FluName) ->
-    list_to_atom(atom_to_list(FluName) ++ "_epoch").
-
 main2(FluName, TcpPort, DataDir, Props) ->
     {SendAppendPidToProj_p, ProjectionPid} =
         case proplists:get_value(projection_store_registered_name, Props) of
@@ -129,27 +121,17 @@ main2(FluName, TcpPort, DataDir, Props) ->
                 {true, undefined}
         end,
     Witness_p = proplists:get_value(witness_mode, Props, false),
-    S0 = #state{flu_name=FluName,
+
-                proj_store=ProjectionPid,
+    {ok, AppendPid} = start_append_server(FluName, Witness_p, Wedged_p, EpochId),
-                tcp_port=TcpPort,
-                data_dir=DataDir,
-                wedged=Wedged_p,
-                witness=Witness_p,
-                etstab=ets_table_name(FluName),
-                epoch_id=EpochId,
-                props=Props},
-    AppendPid = start_append_server(S0, self()),
-    receive
-        append_server_ack -> ok
-    end,
     if SendAppendPidToProj_p ->
-            machi_projection_store:set_wedge_notify_pid(ProjectionPid,
+            machi_projection_store:set_wedge_notify_pid(ProjectionPid, AppendPid);
-                                                        AppendPid);
        true ->
             ok
     end,
-    S1 = S0#state{append_pid=AppendPid},
+    {ok, ListenerPid} = start_listen_server(FluName, TcpPort, Witness_p, DataDir,
-    ListenPid = start_listen_server(S1),
+                                            ets_table_name(FluName), ProjectionPid,
+                                            Props),
+    %% io:format(user, "Listener started: ~w~n", [{FluName, ListenerPid}]),
 
     Config_e = machi_util:make_config_filename(DataDir, "unused"),
     ok = filelib:ensure_dir(Config_e),
@@ -159,540 +141,24 @@ main2(FluName, TcpPort, DataDir, Props) ->
     ok = filelib:ensure_dir(Projection_e),
 
     put(flu_flu_name, FluName),
-    put(flu_append_pid, S1#state.append_pid),
+    put(flu_append_pid, AppendPid),
     put(flu_projection_pid, ProjectionPid),
-    put(flu_listen_pid, ListenPid),
+    put(flu_listen_pid, ListenerPid),
+    proc_lib:init_ack({ok, self()}),
+
     receive killme -> ok end,
-    (catch exit(S1#state.append_pid, kill)),
+    (catch exit(AppendPid, kill)),
     (catch exit(ProjectionPid, kill)),
-    (catch exit(ListenPid, kill)),
+    (catch exit(ListenerPid, kill)),
     ok.
 
-start_listen_server(S) ->
+start_append_server(FluName, Witness_p, Wedged_p, EpochId) ->
-    proc_lib:spawn_link(fun() -> run_listen_server(S) end).
+    machi_flu1_subsup:start_append_server(FluName, Witness_p, Wedged_p, EpochId).
 
-start_append_server(S, AckPid) ->
+start_listen_server(FluName, TcpPort, Witness_p, DataDir, EtsTab, ProjectionPid,
-    FluPid = self(),
+                    Props) ->
-    proc_lib:spawn_link(fun() -> run_append_server(FluPid, AckPid, S) end).
+    machi_flu1_subsup:start_listener(FluName, TcpPort, Witness_p, DataDir,
-
+                                     EtsTab, ProjectionPid, Props).
-run_listen_server(#state{flu_name=FluName, tcp_port=TcpPort}=S) ->
-    register(make_listener_regname(FluName), self()),
-    SockOpts = ?PB_PACKET_OPTS ++
-        [{reuseaddr, true}, {mode, binary}, {active, false},
-         {backlog,8192}],
-    case gen_tcp:listen(TcpPort, SockOpts) of
-        {ok, LSock} ->
-            listen_server_loop(LSock, S);
-        Else ->
-            error_logger:warning_msg("~s:run_listen_server: "
-                                     "listen to TCP port ~w: ~w\n",
-                                     [?MODULE, TcpPort, Else]),
-            exit({?MODULE, run_listen_server, tcp_port, TcpPort, Else})
-    end.
-
-run_append_server(FluPid, AckPid, #state{flu_name=Name,
-                                         wedged=Wedged_p,epoch_id=EpochId}=S) ->
-    %% Reminder: Name is the "main" name of the FLU, i.e., no suffix
-    register(Name, self()),
-    TID = ets:new(ets_table_name(Name),
-                  [set, protected, named_table, {read_concurrency, true}]),
-    ets:insert(TID, {epoch, {Wedged_p, EpochId}}),
-    AckPid ! append_server_ack,
-    append_server_loop(FluPid, S#state{etstab=TID}).
-
-listen_server_loop(LSock, S) ->
-    {ok, Sock} = gen_tcp:accept(LSock),
-    spawn_link(fun() -> net_server_loop(Sock, S) end),
-    listen_server_loop(LSock, S).
-
-append_server_loop(FluPid, #state{wedged=Wedged_p,
-                                  witness=Witness_p,
-                                  epoch_id=OldEpochId, flu_name=FluName}=S) ->
-    receive
-        {seq_append, From, _Prefix, _Chunk, _CSum, _Extra, _EpochID}
-          when Witness_p ->
-            %% The FLU's net_server_loop() process ought to filter all
-            %% witness states, but we'll keep this clause for extra
-            %% paranoia.
-            From ! witness,
-            append_server_loop(FluPid, S);
-        {seq_append, From, _Prefix, _Chunk, _CSum, _Extra, _EpochID}
-          when Wedged_p ->
-            From ! wedged,
-            append_server_loop(FluPid, S);
-        {seq_append, From, Prefix, Chunk, CSum, Extra, EpochID} ->
-            %% Old is the one from our state, plain old 'EpochID' comes
-            %% from the client.
-            case OldEpochId == EpochID of
-                true ->
-                    spawn(fun() -> 
-                        append_server_dispatch(From, Prefix, Chunk, CSum, Extra, FluName, EpochID) 
-                    end);
-                false ->
-                    From ! {error, bad_epoch}
-            end,
-            append_server_loop(FluPid, S);
-        {wedge_myself, WedgeEpochId} ->
-            if not Wedged_p andalso WedgeEpochId == OldEpochId ->
-                    true = ets:insert(S#state.etstab,
-                                      {epoch, {true, OldEpochId}}),
-                    %% Tell my chain manager that it might want to react to
-                    %% this new world.
-                    Chmgr = machi_chain_manager1:make_chmgr_regname(FluName),
-                    spawn(fun() ->
-                            catch machi_chain_manager1:trigger_react_to_env(Chmgr)
-                          end),
-                    append_server_loop(FluPid, S#state{wedged=true});
-               true ->
-                    append_server_loop(FluPid, S)
-            end;
-        {wedge_state_change, Boolean, {NewEpoch, _}=NewEpochId} ->
-            OldEpoch = case OldEpochId of {OldE, _} -> OldE;
-                                          undefined -> -1
-                       end,
-            if NewEpoch >= OldEpoch ->
-                    true = ets:insert(S#state.etstab,
-                                      {epoch, {Boolean, NewEpochId}}),
-                    append_server_loop(FluPid, S#state{wedged=Boolean,
-                                                       epoch_id=NewEpochId});
-               true ->
-                    append_server_loop(FluPid, S)
-            end;
-        {wedge_status, FromPid} ->
-            #state{wedged=Wedged_p, epoch_id=EpochId} = S,
-            FromPid ! {wedge_status_reply, Wedged_p, EpochId},
-            append_server_loop(FluPid, S);
-        Else ->
-            io:format(user, "append_server_loop: WHA? ~p\n", [Else]),
-            append_server_loop(FluPid, S)
-    end.
-
-net_server_loop(Sock, S) ->
-    case gen_tcp:recv(Sock, 0, ?SERVER_CMD_READ_TIMEOUT) of
-        {ok, Bin} ->
-            {RespBin, S2} = 
-                case machi_pb:decode_mpb_ll_request(Bin) of
-                    LL_req when LL_req#mpb_ll_request.do_not_alter == 2 ->
-                        {R, NewS} = do_pb_ll_request(LL_req, S),
-                        {maybe_encode_response(R), mode(low, NewS)};
-                    _ ->
-                        HL_req = machi_pb:decode_mpb_request(Bin),
-                        1 = HL_req#mpb_request.do_not_alter,
-                        {R, NewS} = do_pb_hl_request(HL_req, make_high_clnt(S)),
-                        {machi_pb:encode_mpb_response(R), mode(high, NewS)}
-                end,
-            if RespBin == async_no_response ->
-                    net_server_loop(Sock, S2);
-               true ->
-                    case gen_tcp:send(Sock, RespBin) of
-                        ok ->
-                            net_server_loop(Sock, S2);
-                        {error, _} ->
-                            (catch gen_tcp:close(Sock)),
-                            exit(normal)
-                    end
-            end;
-        {error, SockError} ->
-            Msg = io_lib:format("Socket error ~w", [SockError]),
-            R = #mpb_ll_response{req_id= <<>>,
-                                 generic=#mpb_errorresp{code=1, msg=Msg}},
-            _Resp = machi_pb:encode_mpb_ll_response(R),
-            %% TODO: Weird that sometimes neither catch nor try/catch
-            %%       can prevent OTP's SASL from logging an error here.
-            %%       Error in process <0.545.0> with exit value: {badarg,[{erlang,port_command,.......
-            %% TODO: is this what causes the intermittent PULSE deadlock errors?
-            %% _ = (catch gen_tcp:send(Sock, _Resp)), timer:sleep(1000),
-            (catch gen_tcp:close(Sock)),
-            exit(normal)
-    end.
-
-maybe_encode_response(async_no_response=X) ->
-    X;
-maybe_encode_response(R) ->
-    machi_pb:encode_mpb_ll_response(R).
-
-mode(Mode, #state{pb_mode=undefined}=S) ->
-    S#state{pb_mode=Mode};
-mode(_, S) ->
-    S.
-
-make_high_clnt(#state{high_clnt=undefined}=S) ->
-    {ok, Proj} = machi_projection_store:read_latest_projection(
-                   S#state.proj_store, private),
-    Ps = [P_srvr || {_, P_srvr} <- orddict:to_list(
-                                     Proj#projection_v1.members_dict)],
-    {ok, Clnt} = machi_cr_client:start_link(Ps),
-    S#state{high_clnt=Clnt};
-make_high_clnt(S) ->
-    S.
-
-do_pb_ll_request(#mpb_ll_request{req_id=ReqID}, #state{pb_mode=high}=S) ->
-    Result = {high_error, 41, "Low protocol request while in high mode"},
-    {machi_pb_translate:to_pb_response(ReqID, unused, Result), S};
-do_pb_ll_request(PB_request, S) ->
-    Req = machi_pb_translate:from_pb_request(PB_request),
-    {ReqID, Cmd, Result, S2} = 
-        case Req of
-            {RqID, {LowCmd, _}=CMD}
-              when LowCmd == low_proj;
-                   LowCmd == low_wedge_status; LowCmd == low_list_files ->
-                %% Skip wedge check for projection commands!
-                %% Skip wedge check for these unprivileged commands
-                {Rs, NewS} = do_pb_ll_request3(CMD, S),
-                {RqID, CMD, Rs, NewS};
-            {RqID, CMD} ->
-                EpochID = element(2, CMD),      % by common convention
-                {Rs, NewS} = do_pb_ll_request2(EpochID, CMD, S),
-                {RqID, CMD, Rs, NewS}
-        end,
-    {machi_pb_translate:to_pb_response(ReqID, Cmd, Result), S2}.
-
-do_pb_ll_request2(EpochID, CMD, S) ->
-    {Wedged_p, CurrentEpochID} = ets:lookup_element(S#state.etstab, epoch, 2),
-    if Wedged_p == true ->
-            {{error, wedged}, S#state{epoch_id=CurrentEpochID}};
-       is_tuple(EpochID)
-       andalso
-       EpochID /= CurrentEpochID ->
-            {Epoch, _} = EpochID,
-            {CurrentEpoch, _} = CurrentEpochID,
-            if Epoch < CurrentEpoch ->
-                    ok;
-               true ->
-                    %% We're at same epoch # but different checksum, or
-                    %% we're at a newer/bigger epoch #.
-                    wedge_myself(S#state.flu_name, CurrentEpochID),
-                    ok
-            end,
-            {{error, bad_epoch}, S#state{epoch_id=CurrentEpochID}};
-       true ->
-            do_pb_ll_request3(CMD, S#state{epoch_id=CurrentEpochID})
-    end.
-
-%% Witness status does not matter below.
-do_pb_ll_request3({low_echo, _BogusEpochID, Msg}, S) ->
-    {Msg, S};
-do_pb_ll_request3({low_auth, _BogusEpochID, _User, _Pass}, S) ->
-    {-6, S};
-do_pb_ll_request3({low_wedge_status, _EpochID}, S) ->
-    {do_server_wedge_status(S), S};
-do_pb_ll_request3({low_proj, PCMD}, S) ->
-    {do_server_proj_request(PCMD, S), S};
-%% Witness status *matters* below
-do_pb_ll_request3({low_append_chunk, _EpochID, PKey, Prefix, Chunk, CSum_tag,
-                CSum, ChunkExtra},
-                  #state{witness=false}=S) ->
-    {do_server_append_chunk(PKey, Prefix, Chunk, CSum_tag, CSum,
-                            ChunkExtra, S), S};
-do_pb_ll_request3({low_write_chunk, _EpochID, File, Offset, Chunk, CSum_tag,
-                   CSum},
-                  #state{witness=false}=S) ->
-    {do_server_write_chunk(File, Offset, Chunk, CSum_tag, CSum, S), S};
-do_pb_ll_request3({low_read_chunk, _EpochID, File, Offset, Size, Opts},
-                  #state{witness=false}=S) ->
-    {do_server_read_chunk(File, Offset, Size, Opts, S), S};
-do_pb_ll_request3({low_checksum_list, _EpochID, File},
-                  #state{witness=false}=S) ->
-    {do_server_checksum_listing(File, S), S};
-do_pb_ll_request3({low_list_files, _EpochID},
-                  #state{witness=false}=S) ->
-    {do_server_list_files(S), S};
-do_pb_ll_request3({low_delete_migration, _EpochID, File},
-                  #state{witness=false}=S) ->
-    {do_server_delete_migration(File, S),
-     #state{witness=false}=S};
-do_pb_ll_request3({low_trunc_hack, _EpochID, File},
-                  #state{witness=false}=S) ->
-    {do_server_trunc_hack(File, S), S};
-do_pb_ll_request3(_, #state{witness=true}=S) ->
-    {{error, bad_arg}, S}.                       % TODO: new status code??
-
-do_pb_hl_request(#mpb_request{req_id=ReqID}, #state{pb_mode=low}=S) ->
-    Result = {low_error, 41, "High protocol request while in low mode"},
-    {machi_pb_translate:to_pb_response(ReqID, unused, Result), S};
-do_pb_hl_request(PB_request, S) ->
-    {ReqID, Cmd} = machi_pb_translate:from_pb_request(PB_request),
-    {Result, S2} = do_pb_hl_request2(Cmd, S),
-    {machi_pb_translate:to_pb_response(ReqID, Cmd, Result), S2}.
-
-do_pb_hl_request2({high_echo, Msg}, S) ->
-    {Msg, S};
-do_pb_hl_request2({high_auth, _User, _Pass}, S) ->
-    {-77, S};
-do_pb_hl_request2({high_append_chunk, _todoPK, Prefix, ChunkBin, TaggedCSum,
-                   ChunkExtra}, #state{high_clnt=Clnt}=S) ->
-    Chunk = {TaggedCSum, ChunkBin},
-    Res = machi_cr_client:append_chunk_extra(Clnt, Prefix, Chunk,
-                                             ChunkExtra),
-    {Res, S};
-do_pb_hl_request2({high_write_chunk, File, Offset, ChunkBin, TaggedCSum},
-                  #state{high_clnt=Clnt}=S) ->
-    Chunk = {TaggedCSum, ChunkBin},
-    Res = machi_cr_client:write_chunk(Clnt, File, Offset, Chunk),
-    {Res, S};
-do_pb_hl_request2({high_read_chunk, File, Offset, Size},
-                  #state{high_clnt=Clnt}=S) ->
-    Res = machi_cr_client:read_chunk(Clnt, File, Offset, Size),
-    {Res, S};
-do_pb_hl_request2({high_trim_chunk, File, Offset, Size},
-                  #state{high_clnt=Clnt}=S) ->
-    Res = machi_cr_client:trim_chunk(Clnt, File, Offset, Size),
-    {Res, S};
-do_pb_hl_request2({high_checksum_list, File}, #state{high_clnt=Clnt}=S) ->
-    Res = machi_cr_client:checksum_list(Clnt, File),
-    {Res, S};
-do_pb_hl_request2({high_list_files}, #state{high_clnt=Clnt}=S) ->
-    Res = machi_cr_client:list_files(Clnt),
-    {Res, S}.
-
-do_server_proj_request({get_latest_epochid, ProjType},
-                       #state{proj_store=ProjStore}) ->
-    machi_projection_store:get_latest_epochid(ProjStore, ProjType);
-do_server_proj_request({read_latest_projection, ProjType},
-                       #state{proj_store=ProjStore}) ->
-    machi_projection_store:read_latest_projection(ProjStore, ProjType);
-do_server_proj_request({read_projection, ProjType, Epoch},
-                       #state{proj_store=ProjStore}) ->
-    machi_projection_store:read(ProjStore, ProjType, Epoch);
-do_server_proj_request({write_projection, ProjType, Proj},
-                       #state{flu_name=FluName, proj_store=ProjStore}) ->
-    if Proj#projection_v1.epoch_number == ?SPAM_PROJ_EPOCH ->
-            %% io:format(user, "DBG ~s ~w ~P\n", [?MODULE, ?LINE, Proj, 5]),
-            Chmgr = machi_flu_psup:make_fitness_regname(FluName),
-            [Map] = Proj#projection_v1.dbg,
-            catch machi_fitness:send_fitness_update_spam(
-                    Chmgr, Proj#projection_v1.author_server, Map);
-       true ->
-            catch machi_projection_store:write(ProjStore, ProjType, Proj)
-    end;
-do_server_proj_request({get_all_projections, ProjType},
-                       #state{proj_store=ProjStore}) ->
-    machi_projection_store:get_all_projections(ProjStore, ProjType);
-do_server_proj_request({list_all_projections, ProjType},
-                       #state{proj_store=ProjStore}) ->
-    machi_projection_store:list_all_projections(ProjStore, ProjType);
-do_server_proj_request({kick_projection_reaction},
-                       #state{flu_name=FluName}) ->
-    %% Tell my chain manager that it might want to react to
-    %% this new world.
-    Chmgr = machi_chain_manager1:make_chmgr_regname(FluName),
-    spawn(fun() ->
-                  catch machi_chain_manager1:trigger_react_to_env(Chmgr)
-          end),
-    async_no_response.
-
-do_server_append_chunk(PKey, Prefix, Chunk, CSum_tag, CSum,
-                       ChunkExtra, S) ->
-    case sanitize_prefix(Prefix) of
-        ok ->
-            do_server_append_chunk2(PKey, Prefix, Chunk, CSum_tag, CSum,
-                                    ChunkExtra, S);
-        _ ->
-            {error, bad_arg}
-    end.
-
-do_server_append_chunk2(_PKey, Prefix, Chunk, CSum_tag, Client_CSum,
-                        ChunkExtra, #state{flu_name=FluName,
-                                           epoch_id=EpochID}=_S) ->
-    %% TODO: Do anything with PKey?
-    try
-        TaggedCSum = check_or_make_tagged_checksum(CSum_tag, Client_CSum,Chunk),
-        R = {seq_append, self(), Prefix, Chunk, TaggedCSum, ChunkExtra, EpochID},
-        FluName ! R,
-        receive
-            {assignment, Offset, File} ->
-                Size = iolist_size(Chunk),
-                {ok, {Offset, Size, File}};
-            witness ->
-                {error, bad_arg};
-            wedged ->
-                {error, wedged}
-        after 10*1000 ->
-                {error, partition}
-        end
-    catch
-        throw:{bad_csum, _CS} ->
-            {error, bad_checksum};
-        error:badarg ->
-            error_logger:error_msg("Message send to ~p gave badarg, make certain server is running with correct registered name\n", [?MODULE]),
-            {error, bad_arg}
-    end.
-
-do_server_write_chunk(File, Offset, Chunk, CSum_tag, CSum, #state{flu_name=FluName}) ->
-    case sanitize_file_string(File) of
-        ok ->
-            {ok, Pid} = machi_flu_metadata_mgr:start_proxy_pid(FluName, {file, File}),
-            Meta = [{client_csum_tag, CSum_tag}, {client_csum, CSum}],
-            machi_file_proxy:write(Pid, Offset, Meta, Chunk);
-        _ ->
-            {error, bad_arg}
-    end.
-
-do_server_read_chunk(File, Offset, Size, _Opts, #state{flu_name=FluName})->
-    %% TODO: Look inside Opts someday.
-    case sanitize_file_string(File) of
-        ok ->
-            {ok, Pid} = machi_flu_metadata_mgr:start_proxy_pid(FluName, {file, File}),
-            case machi_file_proxy:read(Pid, Offset, Size) of
-                %% XXX FIXME 
-                %% For now we are omiting the checksum data because it blows up
-                %% protobufs.
-                {ok, Data, _Csum} -> {ok, Data};
-                Other -> Other
-            end;
-        _ ->
-            {error, bad_arg}
-    end.
-
-do_server_checksum_listing(File, #state{flu_name=FluName, data_dir=DataDir}=_S) ->
-    case sanitize_file_string(File) of
-        ok ->
-            ok = sync_checksum_file(FluName, File),
-            CSumPath = machi_util:make_checksum_filename(DataDir, File),
-            %% TODO: If this file is legitimately bigger than our
-            %% {packet_size,N} limit, then we'll have a difficult time, eh?
-            case file:read_file(CSumPath) of
-                {ok, Bin} ->
-                    if byte_size(Bin) > (?PB_MAX_MSG_SIZE - 1024) ->
-                            %% TODO: Fix this limitation by streaming the
-                            %% binary in multiple smaller PB messages.
-                            %% Also, don't read the file all at once. ^_^
-                            error_logger:error_msg("~s:~w oversize ~s\n",
-                                                   [?MODULE, ?LINE, CSumPath]),
-                            {error, bad_arg};
-                       true ->
-                            {ok, Bin}
-                    end;
-                {error, enoent} ->
-                    {error, no_such_file};
-                {error, _} ->
-                    {error, bad_arg}
-            end;
-        _ ->
-            {error, bad_arg}
-    end.
-
-do_server_list_files(#state{data_dir=DataDir}=_S) ->
-    {_, WildPath} = machi_util:make_data_filename(DataDir, ""),
-    Files = filelib:wildcard("*", WildPath),
-    {ok, [begin
-              {ok, FI} = file:read_file_info(WildPath ++ "/" ++ File),
-              Size = FI#file_info.size,
-              {Size, File}
-          end || File <- Files]}.
-
-do_server_wedge_status(S) ->
-    {Wedged_p, CurrentEpochID0} = ets:lookup_element(S#state.etstab, epoch, 2),
-    CurrentEpochID = if CurrentEpochID0 == undefined ->
-                             ?DUMMY_PV1_EPOCH;
-                        true ->
-                             CurrentEpochID0
-                     end,
-    {Wedged_p, CurrentEpochID}.
-
-do_server_delete_migration(File, #state{data_dir=DataDir}=_S) ->
-    case sanitize_file_string(File) of
-        ok ->
-            {_, Path} = machi_util:make_data_filename(DataDir, File),
-            case file:delete(Path) of
-                ok ->
-                    ok;
-                {error, enoent} ->
-                    {error, no_such_file};
-                _ ->
-                    {error, bad_arg}
-            end;
-        _ ->
-            {error, bad_arg}
-    end.
-
-do_server_trunc_hack(File, #state{data_dir=DataDir}=_S) ->
-    case sanitize_file_string(File) of
-        ok ->
-            {_, Path} = machi_util:make_data_filename(DataDir, File),
-            case file:open(Path, [read, write, binary, raw]) of
-                {ok, FH} ->
-                    try
-                        {ok, ?MINIMUM_OFFSET} = file:position(FH,
-                                                              ?MINIMUM_OFFSET),
-                        ok = file:truncate(FH),
-                        ok
-                    after
-                        file:close(FH)
-                    end;
-                {error, enoent} ->
-                    {error, no_such_file};
-                _ ->
-                    {error, bad_arg}
-            end;
-        _ ->
-            {error, bad_arg}
-    end.
-
-append_server_dispatch(From, Prefix, Chunk, CSum, Extra, FluName, EpochId) ->
-    Result = case handle_append(Prefix, Chunk, CSum, Extra, FluName, EpochId) of
-        {ok, File, Offset} ->
-            {assignment, Offset, File};
-        Other ->
-            Other
-    end,
-    From ! Result,
-    exit(normal).
-
-handle_append(_Prefix, <<>>, _Csum, _Extra, _FluName, _EpochId) ->
-    {error, bad_arg};
-handle_append(Prefix, Chunk, Csum, Extra, FluName, EpochId) ->
-    Res = machi_flu_filename_mgr:find_or_make_filename_from_prefix(FluName, EpochId, {prefix, Prefix}),
-    case Res of
-        {file, F} ->
-            {ok, Pid} = machi_flu_metadata_mgr:start_proxy_pid(FluName, {file, F}),
-            {Tag, CS} = machi_util:unmake_tagged_csum(Csum),
-            Meta = [{client_csum_tag, Tag}, {client_csum, CS}],
-            machi_file_proxy:append(Pid, Meta, Extra, Chunk);
-        Error ->
-            Error
-    end.
-
-sanitize_file_string(Str) ->
-    case has_no_prohibited_chars(Str) andalso machi_util:is_valid_filename(Str) of
-        true -> ok;
-        false -> error
-    end.
-
-has_no_prohibited_chars(Str) ->
-    case re:run(Str, "/") of
-        nomatch ->
-            true;
-        _ ->
-            true
-    end.
-
-sanitize_prefix(Prefix) ->
-    %% We are using '^' as our component delimiter
-    case re:run(Prefix, "/|\\^") of
-        nomatch ->
-            ok;
-        _ ->
-            error
-    end.
-
-sync_checksum_file(FluName, File) ->
-    %% We just lookup the pid here - we don't start a proxy server. If
-    %% there isn't a pid for this file, then we just return ok. The
-    %% csum file was synced when the proxy was shutdown.
-    %%
-    %% If there *is* a pid, we call the sync function to ensure the
-    %% csum file is sync'd before we return. (Or an error if we get
-    %% an error).
-    case machi_flu_metadata_mgr:lookup_proxy_pid(FluName, {file, File}) of
-        undefined ->
-            ok;
-        Pid ->
-          machi_file_proxy:sync(Pid, csum)
-    end.
-
-make_listener_regname(BaseName) ->
-    list_to_atom(atom_to_list(BaseName) ++ "_listener").
 
 %% This is the name of the projection store that is spawned by the
 %% *flu*, for use primarily in testing scenarios.  In normal use, we
@@ -704,26 +170,8 @@ make_listener_regname(BaseName) ->
 make_projection_server_regname(BaseName) ->
     list_to_atom(atom_to_list(BaseName) ++ "_pstore").
 
-check_or_make_tagged_checksum(?CSUM_TAG_NONE, _Client_CSum, Chunk) ->
+ets_table_name(FluName) when is_atom(FluName) ->
-    %% TODO: If the client was foolish enough to use
+    list_to_atom(atom_to_list(FluName) ++ "_epoch").
-    %% this type of non-checksum, then the client gets
-    %% what it deserves wrt data integrity, alas.  In
-    %% the client-side Chain Replication method, each
-    %% server will calculated this independently, which
-    %% isn't exactly what ought to happen for best data
-    %% integrity checking.  In server-side CR, the csum
-    %% should be calculated by the head and passed down
-    %% the chain together with the value.
-    CS = machi_util:checksum_chunk(Chunk),
-    machi_util:make_tagged_csum(server_sha, CS);
-check_or_make_tagged_checksum(?CSUM_TAG_CLIENT_SHA, Client_CSum, Chunk) ->
-    CS = machi_util:checksum_chunk(Chunk),
-    if CS == Client_CSum ->
-            machi_util:make_tagged_csum(server_sha,
-                                        Client_CSum);
-       true ->
-            throw({bad_csum, CS})
-    end.
 
 -ifdef(TEST).
 
@@ -765,7 +213,7 @@ timing_demo_test2() ->
                      lists:foldl(fun(X, _) ->
                                          B = machi_checksums:encode_csum_file_entry_hex(X, 100, CSum),
                                          %% file:write(ZZZ, [B, 10]),
-                                         machi_checksums:decode_csum_file_entry_hex(list_to_binary(B))
+                                         decode_csum_file_entry_hex(list_to_binary(B))
                                  end, x, Xs)
              end),
     io:format(user, "~.3f sec\n", [HexUSec / 1000000]),

src/machi_flu1_append_server.erl

@@ -0,0 +1,193 @@
+%% -------------------------------------------------------------------
+%%
+%% Copyright (c) 2007-2015 Basho Technologies, Inc.  All Rights Reserved.
+%%
+%% This file is provided to you under the Apache License,
+%% Version 2.0 (the "License"); you may not use this file
+%% except in compliance with the License.  You may obtain
+%% a copy of the License at
+%%
+%%   http://www.apache.org/licenses/LICENSE-2.0
+%%
+%% Unless required by applicable law or agreed to in writing,
+%% software distributed under the License is distributed on an
+%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+%% KIND, either express or implied.  See the License for the
+%% specific language governing permissions and limitations
+%% under the License.
+%%
+%% -------------------------------------------------------------------
+
+%% @doc Machi FLU1 append serialization server process
+
+-module(machi_flu1_append_server).
+
+-behavior(gen_server).
+
+-include("machi.hrl").
+-include("machi_projection.hrl").
+
+-ifdef(TEST).
+-include_lib("eunit/include/eunit.hrl").
+-endif. % TEST
+
+-export([start_link/4]).
+
+-export([init/1]).
+-export([handle_call/3, handle_cast/2, handle_info/2,
+         terminate/2, code_change/3]).
+-export([int_update_wedge_state/3, int_wedge_myself/2]).
+-export([current_state/1, format_state/1]).
+
+-record(state, {
+          flu_name        :: atom(),
+          witness = false :: boolean(),
+          wedged = true   :: boolean(),
+          etstab          :: ets:tid(),
+          epoch_id        :: 'undefined' | machi_dt:epoch_id()
+         }).
+
+-define(INIT_TIMEOUT, 60*1000).
+-define(CALL_TIMEOUT, 60*1000).
+
+-spec start_link(pv1_server(), boolean(), boolean(),
+                 undefined | machi_dt:epoch_id()) -> {ok, pid()}.
+start_link(Fluname, Witness_p, Wedged_p, EpochId) ->
+    %% Reminder: Name is the "main" name of the FLU, i.e., no suffix
+    gen_server:start_link({local, Fluname},
+                          ?MODULE, [Fluname, Witness_p, Wedged_p, EpochId],
+                          [{timeout, ?INIT_TIMEOUT}]).
+
+-spec current_state(atom() | pid()) -> term().
+current_state(PidSpec) ->
+    gen_server:call(PidSpec, current_state, ?CALL_TIMEOUT).
+
+format_state(State) ->
+    Fields = record_info(fields, state),
+    [_Name | Values] = tuple_to_list(State),
+    lists:zip(Fields, Values).
+
+int_update_wedge_state(PidSpec, Boolean, EpochId)
+  when is_boolean(Boolean), is_tuple(EpochId) ->
+    gen_server:cast(PidSpec, {wedge_state_change, Boolean, EpochId}).
+
+int_wedge_myself(PidSpec, EpochId)
+  when is_tuple(EpochId) ->
+    gen_server:cast(PidSpec, {wedge_myself, EpochId}).
+
+init([Fluname, Witness_p, Wedged_p, EpochId]) ->
+    TID = ets:new(machi_flu1:ets_table_name(Fluname),
+                  [set, protected, named_table, {read_concurrency, true}]),
+    ets:insert(TID, {epoch, {Wedged_p, EpochId}}),
+    {ok, #state{flu_name=Fluname, witness=Witness_p, wedged=Wedged_p,
+                etstab=TID, epoch_id=EpochId}}.
+
+handle_call({seq_append, _From2, _NSInfo, _EpochID, _Prefix, _Chunk, _TCSum, _Opts},
+            _From, #state{witness=true}=S) ->
+    %% The FLU's machi_flu1_net_server process ought to filter all
+    %% witness states, but we'll keep this clause for extra
+    %% paranoia.
+    {reply, witness, S};
+handle_call({seq_append, _From2, _NSInfo, _EpochID, _Prefix, _Chunk, _TCSum, _Opts},
+            _From, #state{wedged=true}=S) ->
+    {reply, wedged, S};
+handle_call({seq_append, _From2, NSInfo, EpochID,
+             Prefix, Chunk, TCSum, Opts},
+            From, #state{flu_name=FluName, epoch_id=OldEpochId}=S) ->
+    %% Old is the one from our state, plain old 'EpochID' comes
+    %% from the client.
+    _ = case OldEpochId of
+            EpochID ->
+                spawn(fun() ->
+                              append_server_dispatch(From, NSInfo,
+                                                     Prefix, Chunk, TCSum, Opts,
+                                                     FluName, EpochID)
+                      end),
+                {noreply, S};
+            _ ->
+                {reply, {error, bad_epoch}, S}
+        end;
+%% TODO: Who sends this message?
+handle_call(wedge_status, _From,
+            #state{wedged=Wedged_p, epoch_id=EpochId} = S) ->
+    {reply, {wedge_status_reply, Wedged_p, EpochId}, S};
+handle_call(current_state, _From, S) ->
+    {reply, S, S};
+handle_call(Else, From, S) ->
+    io:format(user, "~s:handle_call: WHA? from=~w ~w\n", [?MODULE, From, Else]),
+    {noreply, S}.
+
+handle_cast({wedge_myself, WedgeEpochId},
+            #state{flu_name=FluName, wedged=Wedged_p, epoch_id=OldEpochId}=S) ->
+    if not Wedged_p andalso WedgeEpochId == OldEpochId ->
+            true = ets:insert(S#state.etstab,
+                              {epoch, {true, OldEpochId}}),
+            %% Tell my chain manager that it might want to react to
+            %% this new world.
+            Chmgr = machi_chain_manager1:make_chmgr_regname(FluName),
+            spawn(fun() ->
+                          catch machi_chain_manager1:trigger_react_to_env(Chmgr)
+                  end),
+            {noreply, S#state{wedged=true}};
+       true ->
+            {noreply, S}
+    end;
+handle_cast({wedge_state_change, Boolean, {NewEpoch, _}=NewEpochId},
+            #state{epoch_id=OldEpochId}=S) ->
+    OldEpoch = case OldEpochId of {OldE, _} -> OldE;
+                   undefined -> -1
+               end,
+    if NewEpoch >= OldEpoch ->
+            true = ets:insert(S#state.etstab,
+                              {epoch, {Boolean, NewEpochId}}),
+            {noreply, S#state{wedged=Boolean, epoch_id=NewEpochId}};
+       true ->
+            {noreply, S}
+    end;
+handle_cast(Else, S) ->
+    io:format(user, "~s:handle_cast: WHA? ~p\n", [?MODULE, Else]),
+    {noreply, S}.
+
+handle_info(Else, S) ->
+    io:format(user, "~s:handle_info: WHA? ~p\n", [?MODULE, Else]),
+    {noreply, S}.
+
+terminate(normal, _S) ->
+    ok;
+terminate(Reason, _S) ->
+    lager:warning("~s:terminate: ~w", [?MODULE, Reason]),
+    ok.
+
+code_change(_OldVsn, S, _Extra) ->
+    {ok, S}.
+
+append_server_dispatch(From, NSInfo,
+                       Prefix, Chunk, TCSum, Opts, FluName, EpochId) ->
+    Result = case handle_append(NSInfo,
+                                Prefix, Chunk, TCSum, Opts, FluName, EpochId) of
+        {ok, File, Offset} ->
+            {assignment, Offset, File};
+        Other ->
+            Other
+    end,
+    _ = gen_server:reply(From, Result),
+    ok.
+
+handle_append(NSInfo,
+              Prefix, Chunk, TCSum, Opts, FluName, EpochId) ->
+    Res = machi_flu_filename_mgr:find_or_make_filename_from_prefix(
+            FluName, EpochId, {prefix, Prefix}, NSInfo),
+    case Res of
+        {file, F} ->
+            case machi_flu_metadata_mgr:start_proxy_pid(FluName, {file, F}) of
+                {ok, Pid} ->
+                    {Tag, CS} = machi_util:unmake_tagged_csum(TCSum),
+                    Meta = [{client_csum_tag, Tag}, {client_csum, CS}],
+                    Extra = Opts#append_opts.chunk_extra,
+                    machi_file_proxy:append(Pid, Meta, Extra, Chunk);
+                {error, trimmed} = E ->
+                    E
+            end;
+        Error ->
+            Error
+    end.

src/machi_flu1_client.erl

@@ -38,6 +38,71 @@
 %% TODO This EDoc was written first, and the EDoc and also `-type' and
 %% `-spec' definitions for {@link machi_proxy_flu1_client} and {@link
 %% machi_cr_client} must be improved.
+%%
+%% == Client API implementation notes ==
+%%
+%% At the moment, there are several modules that implement various
+%% subsets of the Machi API. The table below attempts to show how and
+%% why they differ.
+%%
+%% ```
+%% |--------------------------+-------+-----+------+------+-------+----------------|
+%% |                          | PB    |     | #    |      | Conn  | Epoch & NS     |
+%% | Module name              | Level | CR? | FLUS | Impl | Life? | version aware? |
+%% |--------------------------+-------+-----+------+------+-------+----------------|
+%% | machi_pb_high_api_client | high  | yes | many | proc | long  | no             |
+%% | machi_cr_client          | low   | yes | many | proc | long  | no             |
+%% | machi_proxy_flu1_client  | low   | no  | 1    | proc | long  | yes            |
+%% | machi_flu1_client        | low   | no  | 1    | lib  | short | yes            |
+%% |--------------------------+-------+-----+------+------+-------+----------------|
+%% '''
+%%
+%% In terms of use and API layering, the table rows are in highest`->'lowest
+%% order: each level calls the layer immediately below it.
+%%
+%% <dl>
+%% <dt> <b> PB Level</b> </dt>
+%% <dd> The Protocol Buffers API is divided logically into two levels,
+%% "low" and "high".  The low-level protocol is used for intra-chain
+%% communication.  The high-level protocol is used for clients outside
+%% of a Machi chain or Machi cluster of chains.
+%% </dd>
+%% <dt> <b> CR?</b> </dt>
+%% <dd> Does this API support (directly or indirectly) Chain
+%% Replication?  If `no', then the API has no awareness of multiple
+%% replicas of any file or file chunk; unaware clients can only
+%% perform operations at a single Machi FLU's file service or
+%% projection store service.
+%% </dd>
+%% <dt> <b> # FLUs</b> </dt>
+%% <dd> Now many FLUs does this API layer communicate with
+%% simultaneously?  Note that there is a one-to-one correspondence
+%% between this value and the "CR?" column's value.
+%% </dd>
+%% <dt> <b> Impl</b> </dt>
+%% <dd> Implementation: library-only or an Erlang process,
+%%      e.g., `gen_server'.
+%% </dd>
+%% <dt> <b> Conn Life?</b> </dt>
+%% <dd> Expected TCP session connection life: short or long.  At the
+%% lowest level, the {@link machi_flu1_client} API implementation takes
+%% no effort to reconnect to a remote FLU when its single TCP session
+%% is broken.  For long-lived connection life APIs, the server side will
+%% automatically attempt to reconnect to remote FLUs when a TCP session
+%% is broken.
+%% </dd>
+%% <dt> <b> Epoch &amp; NS version aware?</b> </dt>
+%% <dd> Are clients of this API responsible for knowing a chain's EpochID
+%% and namespace version numbers?  If `no', then the server side of the
+%% API will automatically attempt to discover/re-discover the EpochID and
+%% namespace version numbers whenever they change.
+%% </dd>
+%% </dl>
+%%
+%% The only protocol that we expect to be used by entities outside of
+%% a single Machi chain or a multi-chain cluster is the "high"
+%% Protocol Buffers API.  The {@link riak_pb_high_api_client} module
+%% is an Erlang reference implementation of this PB API.
 
 -module(machi_flu1_client).
 
@@ -50,14 +115,15 @@
 -include_lib("pulse_otp/include/pulse_otp.hrl").
 -endif.
 
--define(HARD_TIMEOUT, 2500).
+-define(SHORT_TIMEOUT, 2500).
+-define(LONG_TIMEOUT, (60*1000)).
 
 -export([
          %% File API
-         append_chunk/4, append_chunk/5,
+         append_chunk/6, append_chunk/7,
-         append_chunk_extra/5, append_chunk_extra/6,
+         append_chunk/8, append_chunk/9,
-         read_chunk/5, read_chunk/6,
+         read_chunk/7, read_chunk/8,
-         checksum_list/3, checksum_list/4,
+         checksum_list/2, checksum_list/3,
          list_files/2, list_files/3,
          wedge_status/1, wedge_status/2,
 
@@ -79,34 +145,48 @@
         ]).
 %% For "internal" replication only.
 -export([
-         write_chunk/5, write_chunk/6,
+         write_chunk/7, write_chunk/8,
+         trim_chunk/6,
          delete_migration/3, delete_migration/4,
          trunc_hack/3, trunc_hack/4
         ]).
 
 -type port_wrap()   :: {w,atom(),term()}.
 
-%% @doc Append a chunk (binary- or iolist-style) of data to a file
+-spec append_chunk(port_wrap(),
-%% with `Prefix'.
+                   'undefined' | machi_dt:ns_info(), machi_dt:epoch_id(),
-
+                   machi_dt:file_prefix(), machi_dt:chunk(),
--spec append_chunk(port_wrap(), machi_dt:epoch_id(), machi_dt:file_prefix(), machi_dt:chunk()) ->
+                   machi_dt:chunk_csum()) ->
       {ok, machi_dt:chunk_pos()} | {error, machi_dt:error_general()} | {error, term()}.
-append_chunk(Sock, EpochID, Prefix, Chunk) ->
+append_chunk(Sock, NSInfo, EpochID, Prefix, Chunk, CSum) ->
-    append_chunk2(Sock, EpochID, Prefix, Chunk, 0).
+    append_chunk(Sock, NSInfo, EpochID, Prefix, Chunk, CSum,
+                 #append_opts{}, ?LONG_TIMEOUT).
 
 %% @doc Append a chunk (binary- or iolist-style) of data to a file
-%% with `Prefix'.
+%% with `Prefix' and also request an additional `Extra' bytes.
+%%
+%% For example, if the `Chunk' size is 1 KByte and `Extra' is 4K Bytes, then
+%% the file offsets that follow `Chunk''s position for the following 4K will
+%% be reserved by the file sequencer for later write(s) by the
+%% `write_chunk()' API.
 
 -spec append_chunk(machi_dt:inet_host(), machi_dt:inet_port(),
-                   machi_dt:epoch_id(), machi_dt:file_prefix(), machi_dt:chunk()) ->
+                   'undefined' | machi_dt:ns_info(), machi_dt:epoch_id(),
+                   machi_dt:file_prefix(), machi_dt:chunk(),
+                   machi_dt:chunk_csum()) ->
       {ok, machi_dt:chunk_pos()} | {error, machi_dt:error_general()} | {error, term()}.
-append_chunk(Host, TcpPort, EpochID, Prefix, Chunk) ->
+append_chunk(Host, TcpPort, NSInfo, EpochID, Prefix, Chunk, CSum) ->
-    Sock = connect(#p_srvr{proto_mod=?MODULE, address=Host, port=TcpPort}),
+    append_chunk(Host, TcpPort, NSInfo, EpochID, Prefix, Chunk, CSum,
-    try
+                 #append_opts{}, ?LONG_TIMEOUT).
-        append_chunk2(Sock, EpochID, Prefix, Chunk, 0)
+
-    after
+-spec append_chunk(port_wrap(),
-        disconnect(Sock)
+                   'undefined' | machi_dt:ns_info(), machi_dt:epoch_id(),
-    end.
+                   machi_dt:file_prefix(), machi_dt:chunk(),
+                   machi_dt:chunk_csum(), machi_dt:append_opts(), timeout()) ->
+      {ok, machi_dt:chunk_pos()} | {error, machi_dt:error_general()} | {error, term()}.
+append_chunk(Sock, NSInfo0, EpochID, Prefix, Chunk, CSum, Opts, Timeout) ->
+    NSInfo = machi_util:ns_info_default(NSInfo0),
+    append_chunk2(Sock, NSInfo, EpochID, Prefix, Chunk, CSum, Opts, Timeout).
 
 %% @doc Append a chunk (binary- or iolist-style) of data to a file
 %% with `Prefix' and also request an additional `Extra' bytes.
@@ -116,66 +196,62 @@ append_chunk(Host, TcpPort, EpochID, Prefix, Chunk) ->
 %% be reserved by the file sequencer for later write(s) by the
 %% `write_chunk()' API.
 
--spec append_chunk_extra(port_wrap(), machi_dt:epoch_id(), machi_dt:file_prefix(), machi_dt:chunk(), machi_dt:chunk_size()) ->
+-spec append_chunk(machi_dt:inet_host(), machi_dt:inet_port(),
+                   'undefined' | machi_dt:ns_info(), machi_dt:epoch_id(),
+                   machi_dt:file_prefix(), machi_dt:chunk(),
+                   machi_dt:chunk_csum(), machi_dt:append_opts(), timeout()) ->
       {ok, machi_dt:chunk_pos()} | {error, machi_dt:error_general()} | {error, term()}.
-append_chunk_extra(Sock, EpochID, Prefix, Chunk, ChunkExtra)
+append_chunk(Host, TcpPort, NSInfo0, EpochID,
-  when is_integer(ChunkExtra), ChunkExtra >= 0 ->
+             Prefix, Chunk, CSum, Opts, Timeout) ->
-    append_chunk2(Sock, EpochID, Prefix, Chunk, ChunkExtra).
-
-%% @doc Append a chunk (binary- or iolist-style) of data to a file
-%% with `Prefix' and also request an additional `Extra' bytes.
-%%
-%% For example, if the `Chunk' size is 1 KByte and `Extra' is 4K Bytes, then
-%% the file offsets that follow `Chunk''s position for the following 4K will
-%% be reserved by the file sequencer for later write(s) by the
-%% `write_chunk()' API.
-
--spec append_chunk_extra(machi_dt:inet_host(), machi_dt:inet_port(),
-               machi_dt:epoch_id(), machi_dt:file_prefix(), machi_dt:chunk(), machi_dt:chunk_size()) ->
-      {ok, machi_dt:chunk_pos()} | {error, machi_dt:error_general()} | {error, term()}.
-append_chunk_extra(Host, TcpPort, EpochID, Prefix, Chunk, ChunkExtra)
-  when is_integer(ChunkExtra), ChunkExtra >= 0 ->
     Sock = connect(#p_srvr{proto_mod=?MODULE, address=Host, port=TcpPort}),
     try
-        append_chunk2(Sock, EpochID, Prefix, Chunk, ChunkExtra)
+        NSInfo = machi_util:ns_info_default(NSInfo0),
+        append_chunk2(Sock, NSInfo, EpochID,
+                      Prefix, Chunk, CSum, Opts, Timeout)
     after
         disconnect(Sock)
     end.
 
 %% @doc Read a chunk of data of size `Size' from `File' at `Offset'.
 
--spec read_chunk(port_wrap(), machi_dt:epoch_id(), machi_dt:file_name(), machi_dt:file_offset(), machi_dt:chunk_size()) ->
+-spec read_chunk(port_wrap(), 'undefined' | machi_dt:ns_info(), machi_dt:epoch_id(), machi_dt:file_name(), machi_dt:file_offset(), machi_dt:chunk_size(),
-      {ok, machi_dt:chunk_s()} |
+                 machi_dt:read_opts_x()) ->
+      {ok, {[machi_dt:chunk_summary()], [machi_dt:chunk_pos()]}} |
       {error, machi_dt:error_general() | 'not_written' | 'partial_read'} |
       {error, term()}.
-read_chunk(Sock, EpochID, File, Offset, Size)
+read_chunk(Sock, NSInfo0, EpochID, File, Offset, Size, Opts0)
   when Offset >= ?MINIMUM_OFFSET, Size >= 0 ->
-    read_chunk2(Sock, EpochID, File, Offset, Size).
+    NSInfo = machi_util:ns_info_default(NSInfo0),
+    Opts = machi_util:read_opts_default(Opts0),
+    read_chunk2(Sock, NSInfo, EpochID, File, Offset, Size, Opts).
 
 %% @doc Read a chunk of data of size `Size' from `File' at `Offset'.
 
--spec read_chunk(machi_dt:inet_host(), machi_dt:inet_port(), machi_dt:epoch_id(),
+-spec read_chunk(machi_dt:inet_host(), machi_dt:inet_port(), 'undefined' | machi_dt:ns_info(), machi_dt:epoch_id(),
-                 machi_dt:file_name(), machi_dt:file_offset(), machi_dt:chunk_size()) ->
+                 machi_dt:file_name(), machi_dt:file_offset(), machi_dt:chunk_size(),
-      {ok, machi_dt:chunk_s()} |
+                 machi_dt:read_opts_x()) ->
+      {ok, [machi_dt:chunk_summary()]} |
       {error, machi_dt:error_general() | 'not_written' | 'partial_read'} |
       {error, term()}.
-read_chunk(Host, TcpPort, EpochID, File, Offset, Size)
+read_chunk(Host, TcpPort, NSInfo0, EpochID, File, Offset, Size, Opts0)
   when Offset >= ?MINIMUM_OFFSET, Size >= 0 ->
     Sock = connect(#p_srvr{proto_mod=?MODULE, address=Host, port=TcpPort}),
+    NSInfo = machi_util:ns_info_default(NSInfo0),
+    Opts = machi_util:read_opts_default(Opts0),
     try
-        read_chunk2(Sock, EpochID, File, Offset, Size)
+        read_chunk2(Sock, NSInfo, EpochID, File, Offset, Size, Opts)
     after
         disconnect(Sock)
     end.
 
 %% @doc Fetch the list of chunk checksums for `File'.
 
--spec checksum_list(port_wrap(), machi_dt:epoch_id(), machi_dt:file_name()) ->
+-spec checksum_list(port_wrap(), machi_dt:file_name()) ->
       {ok, binary()} |
       {error, machi_dt:error_general() | 'no_such_file' | 'partial_read'} |
       {error, term()}.
-checksum_list(Sock, EpochID, File) ->
+checksum_list(Sock, File) ->
-    checksum_list2(Sock, EpochID, File).
+    checksum_list2(Sock, File).
 
 %% @doc Fetch the list of chunk checksums for `File'.
 %%
@@ -199,13 +275,13 @@ checksum_list(Sock, EpochID, File) ->
 %% Details of the encoding used inside the `binary()' blog can be found
 %% in the EDoc comments for {@link machi_flu1:decode_csum_file_entry/1}.
 
--spec checksum_list(machi_dt:inet_host(), machi_dt:inet_port(), machi_dt:epoch_id(), machi_dt:file_name()) ->
+-spec checksum_list(machi_dt:inet_host(), machi_dt:inet_port(), machi_dt:file_name()) ->
       {ok, binary()} |
       {error, machi_dt:error_general() | 'no_such_file'} | {error, term()}.
-checksum_list(Host, TcpPort, EpochID, File) when is_integer(TcpPort) ->
+checksum_list(Host, TcpPort, File) when is_integer(TcpPort) ->
     Sock = connect(#p_srvr{proto_mod=?MODULE, address=Host, port=TcpPort}),
     try
-        checksum_list2(Sock, EpochID, File)
+        checksum_list2(Sock, File)
     after
         disconnect(Sock)
     end.
@@ -232,7 +308,7 @@ list_files(Host, TcpPort, EpochID) when is_integer(TcpPort) ->
 %% @doc Fetch the wedge status from the remote FLU.
 
 -spec wedge_status(port_wrap()) ->
-      {ok, {boolean(), machi_dt:epoch_id()}} | {error, term()}.
+      {ok, {boolean(), machi_dt:epoch_id(), machi_dt:namespace_version(),machi_dt:namespace()}} | {error, term()}.
 
 wedge_status(Sock) ->
     wedge_status2(Sock).
@@ -240,7 +316,7 @@ wedge_status(Sock) ->
 %% @doc Fetch the wedge status from the remote FLU.
 
 -spec wedge_status(machi_dt:inet_host(), machi_dt:inet_port()) ->
-      {ok, {boolean(), machi_dt:epoch_id()}} | {error, term()}.
+      {ok, {boolean(), machi_dt:epoch_id(), machi_dt:namespace_version(),machi_dt:namespace()}} | {error, term()}.
 wedge_status(Host, TcpPort) when is_integer(TcpPort) ->
     Sock = connect(#p_srvr{proto_mod=?MODULE, address=Host, port=TcpPort}),
     try
@@ -451,27 +527,46 @@ disconnect(_) ->
 %% @doc Restricted API: Write a chunk of already-sequenced data to
 %% `File' at `Offset'.
 
--spec write_chunk(port_wrap(), machi_dt:epoch_id(), machi_dt:file_name(), machi_dt:file_offset(), machi_dt:chunk()) ->
+-spec write_chunk(port_wrap(), 'undefined' | machi_dt:ns_info(), machi_dt:epoch_id(), machi_dt:file_name(), machi_dt:file_offset(), machi_dt:chunk(), machi_dt:chunk_csum()) ->
       ok | {error, machi_dt:error_general()} | {error, term()}.
-write_chunk(Sock, EpochID, File, Offset, Chunk)
+write_chunk(Sock, NSInfo0, EpochID, File, Offset, Chunk, CSum)
   when Offset >= ?MINIMUM_OFFSET ->
-    write_chunk2(Sock, EpochID, File, Offset, Chunk).
+    NSInfo = machi_util:ns_info_default(NSInfo0),
+    write_chunk2(Sock, NSInfo, EpochID, File, Offset, Chunk, CSum).
 
 %% @doc Restricted API: Write a chunk of already-sequenced data to
 %% `File' at `Offset'.
 
 -spec write_chunk(machi_dt:inet_host(), machi_dt:inet_port(),
-                  machi_dt:epoch_id(), machi_dt:file_name(), machi_dt:file_offset(), machi_dt:chunk()) ->
+                  'undefined' | machi_dt:ns_info(), machi_dt:epoch_id(), machi_dt:file_name(), machi_dt:file_offset(), machi_dt:chunk(), machi_dt:chunk_csum()) ->
       ok | {error, machi_dt:error_general()} | {error, term()}.
-write_chunk(Host, TcpPort, EpochID, File, Offset, Chunk)
+write_chunk(Host, TcpPort, NSInfo0, EpochID, File, Offset, Chunk, CSum)
   when Offset >= ?MINIMUM_OFFSET ->
     Sock = connect(#p_srvr{proto_mod=?MODULE, address=Host, port=TcpPort}),
     try
-        write_chunk2(Sock, EpochID, File, Offset, Chunk)
+        NSInfo = machi_util:ns_info_default(NSInfo0),
+        write_chunk2(Sock, NSInfo, EpochID, File, Offset, Chunk, CSum)
     after
         disconnect(Sock)
     end.
 
+%% @doc Restricted API: Write a chunk of already-sequenced data to
+%% `File' at `Offset'.
+
+-spec trim_chunk(port_wrap(), 'undefined' | machi_dt:ns_info(), machi_dt:epoch_id(), machi_dt:file_name(), machi_dt:file_offset(), machi_dt:chunk_size()) ->
+      ok | {error, machi_dt:error_general()} | {error, term()}.
+trim_chunk(Sock, NSInfo0, EpochID, File0, Offset, Size)
+  when Offset >= ?MINIMUM_OFFSET ->
+    ReqID = <<"id">>,
+    NSInfo = machi_util:ns_info_default(NSInfo0),
+    #ns_info{version=NSVersion, name=NS} = NSInfo,
+    File = machi_util:make_binary(File0),
+    true = (Offset >= ?MINIMUM_OFFSET),
+    Req = machi_pb_translate:to_pb_request(
+            ReqID,
+            {low_trim_chunk, NSVersion, NS, EpochID, File, Offset, Size, 0}),
+    do_pb_request_common(Sock, ReqID, Req).
+
 %% @doc Restricted API: Delete a file after it has been successfully
 %% migrated.
 
@@ -516,83 +611,88 @@ trunc_hack(Host, TcpPort, EpochID, File) when is_integer(TcpPort) ->
 
 %%%%%%%%%%%%%%%%%%%%%%%%%%%
 
-read_chunk2(Sock, EpochID, File0, Offset, Size) ->
+read_chunk2(Sock, NSInfo, EpochID, File0, Offset, Size, Opts) ->
     ReqID = <<"id">>,
+    #ns_info{version=NSVersion, name=NS} = NSInfo,
     File = machi_util:make_binary(File0),
     Req = machi_pb_translate:to_pb_request(
             ReqID,
-            {low_read_chunk, EpochID, File, Offset, Size, []}),
+            {low_read_chunk, NSVersion, NS, EpochID, File, Offset, Size, Opts}),
     do_pb_request_common(Sock, ReqID, Req).
 
-append_chunk2(Sock, EpochID, Prefix0, Chunk0, ChunkExtra) ->
+append_chunk2(Sock, NSInfo, EpochID,
+              Prefix0, Chunk, CSum0, Opts, Timeout) ->
     ReqID = <<"id">>,
-    {Chunk, CSum_tag, CSum} =
-        case Chunk0 of
-            X when is_binary(X) ->
-                {Chunk0, ?CSUM_TAG_NONE, <<>>};
-            {ChunkCSum, Chk} ->
-                {Tag, CS} = machi_util:unmake_tagged_csum(ChunkCSum),
-                {Chk, Tag, CS}
-        end,
-    PKey = <<>>,                                % TODO
     Prefix = machi_util:make_binary(Prefix0),
+    {CSum_tag, CSum} = case CSum0 of
+                           <<>> ->
+                               {?CSUM_TAG_NONE, <<>>};
+                           {_Tag, _CS} ->
+                               CSum0;
+                           B when is_binary(B) ->
+                               machi_util:unmake_tagged_csum(CSum0)
+                       end,
+    #ns_info{version=NSVersion, name=NS, locator=NSLocator} = NSInfo,
+    %% NOTE: The tuple position of NSLocator is a bit odd, because EpochID
+    %%       _must_ be in the 4th position (as NSV & NS must be in 2nd & 3rd).
     Req = machi_pb_translate:to_pb_request(
             ReqID,
-            {low_append_chunk, EpochID, PKey, Prefix, Chunk, CSum_tag, CSum,
+            {low_append_chunk, NSVersion, NS, EpochID, NSLocator,
-             ChunkExtra}),
+             Prefix, Chunk, CSum_tag, CSum, Opts}),
-    do_pb_request_common(Sock, ReqID, Req).
+    do_pb_request_common(Sock, ReqID, Req, true, Timeout).
 
-write_chunk2(Sock, EpochID, File0, Offset, Chunk0) ->
+write_chunk2(Sock, NSInfo, EpochID, File0, Offset, Chunk, CSum0) ->
     ReqID = <<"id">>,
+    #ns_info{version=NSVersion, name=NS} = NSInfo,
     File = machi_util:make_binary(File0),
     true = (Offset >= ?MINIMUM_OFFSET),
-    {Chunk, CSum_tag, CSum} =
+    {CSum_tag, CSum} = case CSum0 of
-        case Chunk0 of
+                           <<>> ->
-            X when is_binary(X) ->
+                               {?CSUM_TAG_NONE, <<>>};
-                {Chunk0, ?CSUM_TAG_NONE, <<>>};
+                           {_Tag, _CS} ->
-            {ChunkCSum, Chk} ->
+                               CSum0;
-                {Tag, CS} = machi_util:unmake_tagged_csum(ChunkCSum),
+                           B when is_binary(B) ->
-                {Chk, Tag, CS}
+                               machi_util:unmake_tagged_csum(CSum0)
                        end,
     Req = machi_pb_translate:to_pb_request(
             ReqID,
-            {low_write_chunk, EpochID, File, Offset, Chunk, CSum_tag, CSum}),
+            {low_write_chunk, NSVersion, NS, EpochID, File, Offset, Chunk, CSum_tag, CSum}),
     do_pb_request_common(Sock, ReqID, Req).
 
 list2(Sock, EpochID) ->
     ReqID = <<"id">>,
     Req = machi_pb_translate:to_pb_request(
-            ReqID, {low_list_files, EpochID}),
+            ReqID, {low_skip_wedge, {low_list_files, EpochID}}),
     do_pb_request_common(Sock, ReqID, Req).
 
 wedge_status2(Sock) ->
     ReqID = <<"id">>,
     Req = machi_pb_translate:to_pb_request(
-            ReqID, {low_wedge_status, undefined}),
+            ReqID, {low_skip_wedge, {low_wedge_status}}),
     do_pb_request_common(Sock, ReqID, Req).
 
 echo2(Sock, Message) ->
     ReqID = <<"id">>,
     Req = machi_pb_translate:to_pb_request(
-            ReqID, {low_echo, undefined, Message}),
+            ReqID, {low_skip_wedge, {low_echo, Message}}),
     do_pb_request_common(Sock, ReqID, Req).
 
-checksum_list2(Sock, EpochID, File) ->
+checksum_list2(Sock, File) ->
     ReqID = <<"id">>,
     Req = machi_pb_translate:to_pb_request(
-            ReqID, {low_checksum_list, EpochID, File}),
+            ReqID, {low_skip_wedge, {low_checksum_list, File}}),
     do_pb_request_common(Sock, ReqID, Req).
 
 delete_migration2(Sock, EpochID, File) ->
     ReqID = <<"id">>,
     Req = machi_pb_translate:to_pb_request(
-            ReqID, {low_delete_migration, EpochID, File}),
+            ReqID, {low_skip_wedge, {low_delete_migration, EpochID, File}}),
     do_pb_request_common(Sock, ReqID, Req).
 
 trunc_hack2(Sock, EpochID, File) ->
     ReqID = <<"id-trunc">>,
     Req = machi_pb_translate:to_pb_request(
-            ReqID, {low_trunc_hack, EpochID, File}),
+            ReqID, {low_skip_wedge, {low_trunc_hack, EpochID, File}}),
     do_pb_request_common(Sock, ReqID, Req).
 
 get_latest_epochid2(Sock, ProjType) ->
@@ -635,18 +735,18 @@ kick_projection_reaction2(Sock, _Options) ->
     ReqID = <<42>>,
     Req = machi_pb_translate:to_pb_request(
                 ReqID, {low_proj, {kick_projection_reaction}}),
-    do_pb_request_common(Sock, ReqID, Req, false).
+    do_pb_request_common(Sock, ReqID, Req, false, ?LONG_TIMEOUT).
 
 do_pb_request_common(Sock, ReqID, Req) ->
-    do_pb_request_common(Sock, ReqID, Req, true).
+    do_pb_request_common(Sock, ReqID, Req, true, ?LONG_TIMEOUT).
 
-do_pb_request_common(Sock, ReqID, Req, GetReply_p) ->
+do_pb_request_common(Sock, ReqID, Req, GetReply_p, Timeout) ->
     erase(bad_sock),
     try
         ReqBin = list_to_binary(machi_pb:encode_mpb_ll_request(Req)),
         ok = w_send(Sock, ReqBin),
         if GetReply_p ->
-                case w_recv(Sock, 0) of
+                case w_recv(Sock, 0, Timeout) of
                     {ok, RespBin} ->
                         Resp = machi_pb:decode_mpb_ll_response(RespBin),
                         {ReqID2, Reply} = machi_pb_translate:from_pb_response(Resp),
@@ -692,7 +792,7 @@ w_connect(#p_srvr{proto_mod=?MODULE, address=Host, port=Port, props=Props}=_P)->
         case proplists:get_value(session_proto, Props, tcp) of
             tcp ->
 put(xxx, goofus),
-                Sock = machi_util:connect(Host, Port, ?HARD_TIMEOUT),
+                Sock = machi_util:connect(Host, Port, ?SHORT_TIMEOUT),
 put(xxx, Sock),
                 ok = inet:setopts(Sock, ?PB_PACKET_OPTS),
                 {w,tcp,Sock};
@@ -716,8 +816,8 @@ w_close({w,tcp,Sock}) ->
     catch gen_tcp:close(Sock),
     ok.
 
-w_recv({w,tcp,Sock}, Amt) ->
+w_recv({w,tcp,Sock}, Amt, Timeout) ->
-    gen_tcp:recv(Sock, Amt, ?HARD_TIMEOUT).
+    gen_tcp:recv(Sock, Amt, Timeout).
 
 w_send({w,tcp,Sock}, IoData) ->
     gen_tcp:send(Sock, IoData).

src/machi_flu1_net_server.erl

@@ -0,0 +1,634 @@
+%% -------------------------------------------------------------------
+%%
+%% Copyright (c) 2007-2015 Basho Technologies, Inc.  All Rights Reserved.
+%%
+%% This file is provided to you under the Apache License,
+%% Version 2.0 (the "License"); you may not use this file
+%% except in compliance with the License.  You may obtain
+%% a copy of the License at
+%%
+%%   http://www.apache.org/licenses/LICENSE-2.0
+%%
+%% Unless required by applicable law or agreed to in writing,
+%% software distributed under the License is distributed on an
+%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+%% KIND, either express or implied.  See the License for the
+%% specific language governing permissions and limitations
+%% under the License.
+%%
+%% -------------------------------------------------------------------
+
+%% @doc Ranch protocol callback module to handle PB protocol over
+%% transport, including both high and low modes.
+
+%% TODO
+%% - Two modes, high and low should be separated at listener level?
+
+-module(machi_flu1_net_server).
+
+-behaviour(gen_server).
+-behaviour(ranch_protocol).
+
+-export([start_link/4]).
+-export([init/1]).
+-export([handle_call/3, handle_cast/2, handle_info/2,
+         terminate/2, code_change/3]).
+
+-include_lib("kernel/include/file.hrl").
+
+-include("machi.hrl").
+-include("machi_pb.hrl").
+-include("machi_projection.hrl").
+
+-ifdef(TEST).
+-include_lib("eunit/include/eunit.hrl").
+-endif. % TEST
+
+-record(state, {
+          %% Ranch's transport management stuff
+          ref         :: ranch:ref(),
+          socket      :: socket(),
+          transport   :: module(),
+
+          %% Machi FLU configurations, common for low and high
+          data_dir    :: string(),
+          witness     :: boolean(),
+          pb_mode     :: undefined | high | low,
+          %% - Used in projection related requests in low mode
+          %% - Used in spawning CR client in high mode
+          proj_store  :: pid(),
+
+          %% Low mode only items
+          %% Current best knowledge, used for wedge_self / bad_epoch check
+          epoch_id    :: undefined | machi_dt:epoch_id(),
+          %% Used in dispatching append_chunk* reqs to the
+          %% append serializing process
+          flu_name    :: pv1_server(),
+          %% Used in server_wedge_status to lookup the table
+          epoch_tab   :: ets:tab(),
+          %% Clustering: cluster map version number
+          namespace_version = 0 :: machi_dt:namespace_version(),
+          %% Clustering: my (and my chain's) assignment to a specific namespace
+          namespace = <<>> :: machi_dt:namespace(),
+
+          %% High mode only
+          high_clnt   :: pid(),
+
+          %% anything you want
+          props = []  :: proplists:proplist()
+         }).
+
+-type socket() :: any().
+-type state()  :: #state{}.
+
+-spec start_link(ranch:ref(), socket(), module(), [term()]) -> {ok, pid()}.
+start_link(Ref, Socket, Transport, [FluName, Witness, DataDir, EpochTab, ProjStore, Props]) ->
+    NS = proplists:get_value(namespace, Props, <<>>),
+    true = is_binary(NS),
+    proc_lib:start_link(?MODULE, init, [#state{ref=Ref,
+                                               socket=Socket,
+                                               transport=Transport,
+                                               flu_name=FluName,
+                                               witness=Witness,
+                                               data_dir=DataDir,
+                                               epoch_tab=EpochTab,
+                                               proj_store=ProjStore,
+                                               namespace=NS,
+                                               props=Props}]).
+
+-spec init(state()) -> no_return().
+init(#state{ref=Ref, socket=Socket, transport=Transport}=State) ->
+    ok = proc_lib:init_ack({ok, self()}),
+    ok = ranch:accept_ack(Ref),
+    {_Wedged_p, CurrentEpochID} = lookup_epoch(State),
+    ok = Transport:setopts(Socket, [{active, once}|?PB_PACKET_OPTS]),
+    gen_server:enter_loop(?MODULE, [], State#state{epoch_id=CurrentEpochID}).
+
+handle_call(Request, _From, S) ->
+    lager:warning("~s:handle_call UNKNOWN message: ~w", [?MODULE, Request]),
+    Reply = {error, {unknown_message, Request}},
+    {reply, Reply, S}.
+
+handle_cast(_Msg, S) ->
+    lager:warning("~s:handle_cast UNKNOWN message: ~w", [?MODULE, _Msg]),
+    {noreply, S}.
+
+%% TODO: Other transport support needed?? TLS/SSL, SCTP
+handle_info({tcp, Socket, Data}=_Info, #state{socket=Socket}=S) ->
+    lager:debug("~s:handle_info: ~w", [?MODULE, _Info]),
+    transport_received(Socket, Data, S);
+handle_info({tcp_closed, Socket}=_Info, #state{socket=Socket}=S) ->
+    lager:debug("~s:handle_info: ~w", [?MODULE, _Info]),
+    transport_closed(Socket, S);
+handle_info({tcp_error, Socket, Reason}=_Info, #state{socket=Socket}=S) ->
+    lager:warning("~s:handle_info (socket=~w) tcp_error: ~w", [?MODULE, Socket, Reason]),
+    transport_error(Socket, Reason, S);
+handle_info(_Info, S) ->
+    lager:warning("~s:handle_info UNKNOWN message: ~w", [?MODULE, _Info]),
+    {noreply, S}.
+
+terminate(normal, #state{socket=undefined}=_S) ->
+    ok;
+terminate(Reason, #state{socket=undefined}=_S) ->
+    lager:warning("~s:terminate (socket=undefined): ~w", [?MODULE, Reason]),
+    ok;
+terminate(normal, #state{socket=Socket}=_S) ->
+    (catch gen_tcp:close(Socket)),
+    ok;
+terminate(Reason, #state{socket=Socket}=_S) ->
+    lager:warning("~s:terminate (socket=Socket): ~w", [?MODULE, Reason]),
+    (catch gen_tcp:close(Socket)),
+    ok.
+
+code_change(_OldVsn, S, _Extra) ->
+    {ok, S}.
+
+%% -- private
+
+%%%% Common transport handling
+
+-spec transport_received(socket(), machi_dt:chunk(), state()) ->
+                                {noreply, state()}.
+transport_received(Socket, <<"QUIT\n">>, #state{socket=Socket}=S) ->
+    {stop, normal, S};
+transport_received(Socket, Bin, #state{transport=Transport}=S) ->
+    {RespBin, S2} =
+        case machi_pb:decode_mpb_ll_request(Bin) of
+            LL_req when LL_req#mpb_ll_request.do_not_alter == 2 ->
+                {R, NewS} = do_pb_ll_request(LL_req, S),
+                {maybe_encode_response(R), set_mode(low, NewS)};
+            _ ->
+                HL_req = machi_pb:decode_mpb_request(Bin),
+                1 = HL_req#mpb_request.do_not_alter,
+                {R, NewS} = do_pb_hl_request(HL_req, make_high_clnt(S)),
+                {machi_pb:encode_mpb_response(R), set_mode(high, NewS)}
+        end,
+    case RespBin of
+        async_no_response ->
+            Transport:setopts(Socket, [{active, once}]),
+            {noreply, S2};
+        _ ->
+            case Transport:send(Socket, RespBin) of
+                ok ->
+                    Transport:setopts(Socket, [{active, once}]),
+                    {noreply, S2};
+                {error, Reason} ->
+                    transport_error(Socket, Reason, S2)
+            end
+    end.
+
+-spec transport_closed(socket(), state()) -> {stop, term(), state()}.
+transport_closed(_Socket, S) ->
+    {stop, normal, S}.
+
+-spec transport_error(socket(), term(), state()) -> no_return().
+transport_error(Socket, Reason, #state{transport=Transport}=_S) ->
+    Msg = io_lib:format("Socket error ~w", [Reason]),
+    R = #mpb_ll_response{req_id= <<>>,
+                         generic=#mpb_errorresp{code=1, msg=Msg}},
+    _Resp = machi_pb:encode_mpb_ll_response(R),
+    %% TODO for TODO comments: comments below with four %s are copy-n-paste'd,
+    %% then it should be considered they are still open and should be addressed.
+    %%%% TODO: Weird that sometimes neither catch nor try/catch
+    %%%%       can prevent OTP's SASL from logging an error here.
+    %%%%       Error in process <0.545.0> with exit value: {badarg,[{erlang,port_command,.......
+    %%%% TODO: is this what causes the intermittent PULSE deadlock errors?
+    %%%% _ = (catch gen_tcp:send(Sock, _Resp)), timer:sleep(1000),
+    (catch Transport:close(Socket)),
+    _ = lager:warning("Socket error (~w -> ~w): ~w",
+                      [Transport:sockname(Socket), Transport:peername(Socket), Reason]),
+    %% TODO: better to exit with `Reason' without logging?
+    exit(normal).
+
+maybe_encode_response(async_no_response=R) ->
+    R;
+maybe_encode_response(R) ->
+    machi_pb:encode_mpb_ll_response(R).
+
+set_mode(Mode, #state{pb_mode=undefined}=S) ->
+    S#state{pb_mode=Mode};
+set_mode(_, S) ->
+    S.
+
+%%%% Low PB mode %%%%
+
+do_pb_ll_request(#mpb_ll_request{req_id=ReqID}, #state{pb_mode=high}=S) ->
+    Result = {high_error, 41, "Low protocol request while in high mode"},
+    {machi_pb_translate:to_pb_response(ReqID, unused, Result), S};
+do_pb_ll_request(PB_request, S) ->
+    Req = machi_pb_translate:from_pb_request(PB_request),
+    {ReqID, Cmd, Result, S2} = 
+        case Req of
+            {RqID, {low_skip_wedge, LowSubCmd}=Cmd0} ->
+                %% Skip wedge check for these unprivileged commands
+                {Rs, NewS} = do_pb_ll_request3(LowSubCmd, S),
+                {RqID, Cmd0, Rs, NewS};
+            {RqID, {low_proj, _LowSubCmd}=Cmd0} ->
+                {Rs, NewS} = do_pb_ll_request3(Cmd0, S),
+                {RqID, Cmd0, Rs, NewS};
+            {RqID, Cmd0} ->
+                %% All remaining must have NSVersion, NS, & EpochID at next pos
+                NSVersion = element(2, Cmd0),
+                NS = element(3, Cmd0),
+                EpochID = element(4, Cmd0),
+                {Rs, NewS} = do_pb_ll_request2(NSVersion, NS, EpochID, Cmd0, S),
+                {RqID, Cmd0, Rs, NewS}
+        end,
+    {machi_pb_translate:to_pb_response(ReqID, Cmd, Result), S2}.
+
+%% do_pb_ll_request2(): Verification of epoch details & namespace details.
+
+do_pb_ll_request2(NSVersion, NS, EpochID, CMD, S) ->
+    {Wedged_p, CurrentEpochID} = lookup_epoch(S),
+    if not is_tuple(EpochID) orelse tuple_size(EpochID) /= 2 ->
+            exit({bad_epoch_id, EpochID, for, CMD});
+       Wedged_p == true ->
+            {{error, wedged}, S#state{epoch_id=CurrentEpochID}};
+       EpochID /= CurrentEpochID ->
+            {Epoch, _} = EpochID,
+            {CurrentEpoch, _} = CurrentEpochID,
+            if Epoch < CurrentEpoch ->
+                    {{error, bad_epoch}, S};
+               true ->
+                    _ = machi_flu1:wedge_myself(S#state.flu_name, CurrentEpochID),
+                    {{error, wedged}, S#state{epoch_id=CurrentEpochID}}
+            end;
+       true ->
+            #state{namespace_version=MyNSVersion, namespace=MyNS} = S,
+            if NSVersion /= MyNSVersion ->
+                    {{error, bad_epoch}, S};
+               NS /= MyNS ->
+                    {{error, bad_arg}, S};
+               true ->
+                    do_pb_ll_request3(CMD, S)
+            end
+    end.
+
+lookup_epoch(#state{epoch_tab=T}) ->
+    %% TODO: race in shutdown to access ets table after owner dies
+    ets:lookup_element(T, epoch, 2).
+
+%% Witness status does not matter below.
+do_pb_ll_request3({low_echo, Msg}, S) ->
+    {Msg, S};
+do_pb_ll_request3({low_auth, _User, _Pass}, S) ->
+    {-6, S};
+do_pb_ll_request3({low_wedge_status}, S) ->
+    {do_server_wedge_status(S), S};
+do_pb_ll_request3({low_proj, PCMD}, S) ->
+    {do_server_proj_request(PCMD, S), S};
+
+%% Witness status *matters* below
+do_pb_ll_request3({low_append_chunk, NSVersion, NS, EpochID, NSLocator,
+                   Prefix, Chunk, CSum_tag,
+                   CSum, Opts},
+                  #state{witness=false}=S) ->
+    NSInfo = #ns_info{version=NSVersion, name=NS, locator=NSLocator},
+    {do_server_append_chunk(NSInfo, EpochID,
+                            Prefix, Chunk, CSum_tag, CSum,
+                            Opts, S), S};
+do_pb_ll_request3({low_write_chunk, _NSVersion, _NS, _EpochID, File, Offset, Chunk, CSum_tag,
+                   CSum},
+                  #state{witness=false}=S) ->
+    {do_server_write_chunk(File, Offset, Chunk, CSum_tag, CSum, S), S};
+do_pb_ll_request3({low_read_chunk, _NSVersion, _NS, _EpochID, File, Offset, Size, Opts},
+                  #state{witness=false} = S) ->
+    {do_server_read_chunk(File, Offset, Size, Opts, S), S};
+do_pb_ll_request3({low_trim_chunk, _NSVersion, _NS, _EpochID, File, Offset, Size, TriggerGC},
+                  #state{witness=false}=S) ->
+    {do_server_trim_chunk(File, Offset, Size, TriggerGC, S), S};
+do_pb_ll_request3({low_checksum_list, File},
+                  #state{witness=false}=S) ->
+    {do_server_checksum_listing(File, S), S};
+do_pb_ll_request3({low_list_files, _EpochID},
+                  #state{witness=false}=S) ->
+    {do_server_list_files(S), S};
+do_pb_ll_request3({low_delete_migration, _EpochID, File},
+                  #state{witness=false}=S) ->
+    {do_server_delete_migration(File, S),
+     #state{witness=false}=S};
+do_pb_ll_request3({low_trunc_hack, _EpochID, File},
+                  #state{witness=false}=S) ->
+    {do_server_trunc_hack(File, S), S};
+
+do_pb_ll_request3(_, #state{witness=true}=S) ->
+    {{error, bad_arg}, S}.                       % TODO: new status code??
+
+do_server_proj_request({get_latest_epochid, ProjType},
+                       #state{proj_store=ProjStore}) ->
+    machi_projection_store:get_latest_epochid(ProjStore, ProjType);
+do_server_proj_request({read_latest_projection, ProjType},
+                       #state{proj_store=ProjStore}) ->
+    machi_projection_store:read_latest_projection(ProjStore, ProjType);
+do_server_proj_request({read_projection, ProjType, Epoch},
+                       #state{proj_store=ProjStore}) ->
+    machi_projection_store:read(ProjStore, ProjType, Epoch);
+do_server_proj_request({write_projection, ProjType, Proj},
+                       #state{flu_name=FluName, proj_store=ProjStore}) ->
+    if Proj#projection_v1.epoch_number == ?SPAM_PROJ_EPOCH ->
+            %% io:format(user, "DBG ~s ~w ~P\n", [?MODULE, ?LINE, Proj, 5]),
+            Chmgr = machi_flu_psup:make_fitness_regname(FluName),
+            [Map] = Proj#projection_v1.dbg,
+            catch machi_fitness:send_fitness_update_spam(
+                    Chmgr, Proj#projection_v1.author_server, Map);
+       true ->
+            catch machi_projection_store:write(ProjStore, ProjType, Proj)
+    end;
+do_server_proj_request({get_all_projections, ProjType},
+                       #state{proj_store=ProjStore}) ->
+    machi_projection_store:get_all_projections(ProjStore, ProjType);
+do_server_proj_request({list_all_projections, ProjType},
+                       #state{proj_store=ProjStore}) ->
+    machi_projection_store:list_all_projections(ProjStore, ProjType);
+do_server_proj_request({kick_projection_reaction},
+                       #state{flu_name=FluName}) ->
+    %% Tell my chain manager that it might want to react to
+    %% this new world.
+    Chmgr = machi_chain_manager1:make_chmgr_regname(FluName),
+    spawn(fun() ->
+                  catch machi_chain_manager1:trigger_react_to_env(Chmgr)
+          end),
+    async_no_response.
+
+do_server_append_chunk(NSInfo, EpochID,
+                       Prefix, Chunk, CSum_tag, CSum,
+                       Opts, S) ->
+    case sanitize_prefix(Prefix) of
+        ok ->
+            do_server_append_chunk2(NSInfo, EpochID,
+                                    Prefix, Chunk, CSum_tag, CSum,
+                                    Opts, S);
+        _ ->
+            {error, bad_arg}
+    end.
+
+do_server_append_chunk2(NSInfo, EpochID,
+                        Prefix, Chunk, CSum_tag, Client_CSum,
+                        Opts, #state{flu_name=FluName,
+                                     epoch_id=EpochID}=_S) ->
+    %% TODO: Do anything with PKey?
+    try
+        TaggedCSum = check_or_make_tagged_checksum(CSum_tag, Client_CSum,Chunk),
+        R = {seq_append, self(), NSInfo, EpochID,
+             Prefix, Chunk, TaggedCSum, Opts},
+        case gen_server:call(FluName, R, 10*1000) of
+            {assignment, Offset, File} ->
+                Size = iolist_size(Chunk),
+                {ok, {Offset, Size, File}};
+            witness ->
+                {error, bad_arg};
+            wedged ->
+                {error, wedged};
+            {error, timeout} ->
+                {error, partition}
+        end
+    catch
+        throw:{bad_csum, _CS} ->
+            {error, bad_checksum};
+        error:badarg ->
+            lager:error("badarg at ~w:do_server_append_chunk2:~w ~w",
+                        [?MODULE, ?LINE, erlang:get_stacktrace()]),
+            {error, bad_arg}
+    end.
+
+do_server_write_chunk(File, Offset, Chunk, CSum_tag, CSum, #state{flu_name=FluName}) ->
+    case sanitize_file_string(File) of
+        ok ->
+            case machi_flu_metadata_mgr:start_proxy_pid(FluName, {file, File}) of
+                {ok, Pid} ->
+                    Meta = [{client_csum_tag, CSum_tag}, {client_csum, CSum}],
+                    machi_file_proxy:write(Pid, Offset, Meta, Chunk);
+                {error, trimmed} = Error ->
+                    Error
+            end;
+        _ ->
+            {error, bad_arg}
+    end.
+
+do_server_read_chunk(File, Offset, Size, Opts, #state{flu_name=FluName})->
+    case sanitize_file_string(File) of
+        ok ->
+            case machi_flu_metadata_mgr:start_proxy_pid(FluName, {file, File}) of
+                {ok, Pid} ->
+                    case machi_file_proxy:read(Pid, Offset, Size, Opts) of
+                        %% XXX FIXME 
+                        %% For now we are omiting the checksum data because it blows up
+                        %% protobufs.
+                        {ok, ChunksAndTrimmed} -> {ok, ChunksAndTrimmed};
+                        Other -> Other
+                    end;
+                {error, trimmed} = Error ->
+                    Error
+            end;
+        _ ->
+            {error, bad_arg}
+    end.
+
+do_server_trim_chunk(File, Offset, Size, TriggerGC, #state{flu_name=FluName}) ->
+    lager:debug("Hi there! I'm trimming this: ~s, (~p, ~p), ~p~n",
+                [File, Offset, Size, TriggerGC]),
+    case sanitize_file_string(File) of
+        ok ->
+            case machi_flu_metadata_mgr:start_proxy_pid(FluName, {file, File}) of
+                {ok, Pid} ->
+                    machi_file_proxy:trim(Pid, Offset, Size, TriggerGC);
+                {error, trimmed} = Trimmed ->
+                    %% Should be returned back to (maybe) trigger repair
+                    Trimmed
+            end;
+        _ ->
+            {error, bad_arg}
+    end.
+
+do_server_checksum_listing(File, #state{flu_name=FluName, data_dir=DataDir}=_S) ->
+    case sanitize_file_string(File) of
+        ok ->
+            case machi_flu_metadata_mgr:start_proxy_pid(FluName, {file, File}) of
+                {ok, Pid} ->
+                    {ok, List} = machi_file_proxy:checksum_list(Pid),
+                    Bin = erlang:term_to_binary(List),
+                    if byte_size(Bin) > (?PB_MAX_MSG_SIZE - 1024) ->
+                            %% TODO: Fix this limitation by streaming the
+                            %% binary in multiple smaller PB messages.
+                            %% Also, don't read the file all at once. ^_^
+                            error_logger:error_msg("~s:~w oversize ~s\n",
+                                                   [?MODULE, ?LINE, DataDir]),
+                            {error, bad_arg};
+                       true ->
+                            {ok, Bin}
+                    end;
+                {error, trimmed} ->
+                    {error, trimmed}
+            end;
+        _ ->
+            {error, bad_arg}
+    end.
+
+do_server_list_files(#state{data_dir=DataDir}=_S) ->
+    {_, WildPath} = machi_util:make_data_filename(DataDir, ""),
+    Files = filelib:wildcard("*", WildPath),
+    {ok, [begin
+              {ok, FI} = file:read_file_info(WildPath ++ "/" ++ File),
+              Size = FI#file_info.size,
+              {Size, File}
+          end || File <- Files]}.
+
+do_server_wedge_status(#state{namespace_version=NSVersion, namespace=NS}=S) ->
+    {Wedged_p, CurrentEpochID0} = lookup_epoch(S),
+    CurrentEpochID = if CurrentEpochID0 == undefined ->
+                             ?DUMMY_PV1_EPOCH;
+                        true ->
+                             CurrentEpochID0
+                     end,
+    {Wedged_p, CurrentEpochID, NSVersion, NS}.
+
+do_server_delete_migration(File, #state{data_dir=DataDir}=_S) ->
+    case sanitize_file_string(File) of
+        ok ->
+            {_, Path} = machi_util:make_data_filename(DataDir, File),
+            case file:delete(Path) of
+                ok ->
+                    ok;
+                {error, enoent} ->
+                    {error, no_such_file};
+                _ ->
+                    {error, bad_arg}
+            end;
+        _ ->
+            {error, bad_arg}
+    end.
+
+do_server_trunc_hack(File, #state{data_dir=DataDir}=_S) ->
+    case sanitize_file_string(File) of
+        ok ->
+            {_, Path} = machi_util:make_data_filename(DataDir, File),
+            case file:open(Path, [read, write, binary, raw]) of
+                {ok, FH} ->
+                    try
+                        {ok, ?MINIMUM_OFFSET} = file:position(FH,
+                                                              ?MINIMUM_OFFSET),
+                        ok = file:truncate(FH),
+                        ok
+                    after
+                        file:close(FH)
+                    end;
+                {error, enoent} ->
+                    {error, no_such_file};
+                _ ->
+                    {error, bad_arg}
+            end;
+        _ ->
+            {error, bad_arg}
+    end.
+
+sanitize_file_string(Str) ->
+    case has_no_prohibited_chars(Str) andalso machi_util:is_valid_filename(Str) of
+        true -> ok;
+        false -> error
+    end.
+
+has_no_prohibited_chars(Str) ->
+    case re:run(Str, "/") of
+        nomatch ->
+            true;
+        _ ->
+            true
+    end.
+
+sanitize_prefix(Prefix) ->
+    %% We are using '^' as our component delimiter
+    case re:run(Prefix, "/|\\^") of
+        nomatch ->
+            ok;
+        _ ->
+            error
+    end.
+
+check_or_make_tagged_checksum(?CSUM_TAG_NONE, _Client_CSum, Chunk) ->
+    %% TODO: If the client was foolish enough to use
+    %% this type of non-checksum, then the client gets
+    %% what it deserves wrt data integrity, alas.  In
+    %% the client-side Chain Replication method, each
+    %% server will calculated this independently, which
+    %% isn't exactly what ought to happen for best data
+    %% integrity checking.  In server-side CR, the csum
+    %% should be calculated by the head and passed down
+    %% the chain together with the value.
+    CS = machi_util:checksum_chunk(Chunk),
+    machi_util:make_tagged_csum(server_sha, CS);
+check_or_make_tagged_checksum(?CSUM_TAG_CLIENT_SHA, Client_CSum, Chunk) ->
+    CS = machi_util:checksum_chunk(Chunk),
+    if CS == Client_CSum ->
+            machi_util:make_tagged_csum(server_sha,
+                                        Client_CSum);
+       true ->
+            throw({bad_csum, CS})
+    end.
+
+%%%% High PB mode %%%%
+
+do_pb_hl_request(#mpb_request{req_id=ReqID}, #state{pb_mode=low}=S) ->
+    Result = {low_error, 41, "High protocol request while in low mode"},
+    {machi_pb_translate:to_pb_response(ReqID, unused, Result), S};
+do_pb_hl_request(PB_request, S) ->
+    {ReqID, Cmd} = machi_pb_translate:from_pb_request(PB_request),
+    {Result, S2} = do_pb_hl_request2(Cmd, S),
+    {machi_pb_translate:to_pb_response(ReqID, Cmd, Result), S2}.
+
+do_pb_hl_request2({high_echo, Msg}, S) ->
+    {Msg, S};
+do_pb_hl_request2({high_auth, _User, _Pass}, S) ->
+    {-77, S};
+do_pb_hl_request2({high_append_chunk=Op, NS, Prefix, Chunk, TaggedCSum, Opts},
+                  #state{high_clnt=Clnt}=S) ->
+    NSInfo = #ns_info{name=NS},                 % TODO populate other fields
+    todo_perhaps_remind_ns_locator_not_chosen(Op),
+    Res = machi_cr_client:append_chunk(Clnt, NSInfo,
+                                       Prefix, Chunk, TaggedCSum, Opts),
+    {Res, S};
+do_pb_hl_request2({high_write_chunk=Op, File, Offset, Chunk, CSum},
+                  #state{high_clnt=Clnt}=S) ->
+    NSInfo = undefined,
+    todo_perhaps_remind_ns_locator_not_chosen(Op),
+    Res = machi_cr_client:write_chunk(Clnt, NSInfo, File, Offset, Chunk, CSum),
+    {Res, S};
+do_pb_hl_request2({high_read_chunk=Op, File, Offset, Size, Opts},
+                  #state{high_clnt=Clnt}=S) ->
+    NSInfo = undefined,
+    todo_perhaps_remind_ns_locator_not_chosen(Op),
+    Res = machi_cr_client:read_chunk(Clnt, NSInfo, File, Offset, Size, Opts),
+    {Res, S};
+do_pb_hl_request2({high_trim_chunk=Op, File, Offset, Size},
+                  #state{high_clnt=Clnt}=S) ->
+    NSInfo = undefined,
+    todo_perhaps_remind_ns_locator_not_chosen(Op),
+    Res = machi_cr_client:trim_chunk(Clnt, NSInfo, File, Offset, Size),
+    {Res, S};
+do_pb_hl_request2({high_checksum_list, File}, #state{high_clnt=Clnt}=S) ->
+    Res = machi_cr_client:checksum_list(Clnt, File),
+    {Res, S};
+do_pb_hl_request2({high_list_files}, #state{high_clnt=Clnt}=S) ->
+    Res = machi_cr_client:list_files(Clnt),
+    {Res, S}.
+
+make_high_clnt(#state{high_clnt=undefined}=S) ->
+    {ok, Proj} = machi_projection_store:read_latest_projection(
+                   S#state.proj_store, private),
+    Ps = [P_srvr || {_, P_srvr} <- orddict:to_list(
+                                     Proj#projection_v1.members_dict)],
+    {ok, Clnt} = machi_cr_client:start_link(Ps),
+    S#state{high_clnt=Clnt};
+make_high_clnt(S) ->
+    S.
+
+todo_perhaps_remind_ns_locator_not_chosen(Op) ->
+    Key = {?MODULE, Op},
+    case get(Key) of
+        undefined ->
+            io:format(user, "TODO op ~w is using default locator value\n",
+                      [Op]),
+            put(Key, true);
+        _ ->
+            ok
+    end.
+

src/machi_flu1_subsup.erl

@@ -0,0 +1,118 @@
+%% -------------------------------------------------------------------
+%%
+%% Copyright (c) 2007-2015 Basho Technologies, Inc.  All Rights Reserved.
+%%
+%% This file is provided to you under the Apache License,
+%% Version 2.0 (the "License"); you may not use this file
+%% except in compliance with the License.  You may obtain
+%% a copy of the License at
+%%
+%%   http://www.apache.org/licenses/LICENSE-2.0
+%%
+%% Unless required by applicable law or agreed to in writing,
+%% software distributed under the License is distributed on an
+%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+%% KIND, either express or implied.  See the License for the
+%% specific language governing permissions and limitations
+%% under the License.
+%%
+%% -------------------------------------------------------------------
+
+%% @doc A supervisor to hold dynamic processes inside single
+%% FLU service, ranch listener and append server.
+
+%% TODO: This supervisor is maybe useless. First introduced for
+%% workaround to start listener dynamically in flu1 initialization
+%% phase.  Because `machi_flu_psup' is being blocked in flu1
+%% initialization time, adding a child to the supervisor leads to
+%% deadlock.  If initialization can be done only by static arguments,
+%% then this supervisor should be removed and added as a direct child
+%% of `machi_flu_psup'.
+
+-module(machi_flu1_subsup).
+-behaviour(supervisor).
+
+%% public API
+-export([start_link/1,
+         start_append_server/4,
+         stop_append_server/1,
+         start_listener/7,
+         stop_listener/1,
+         subsup_name/1,
+         listener_name/1]).
+
+%% supervisor callback
+-export([init/1]).
+
+-include("machi_projection.hrl").
+
+-define(SHUTDOWN, 5000).
+-define(BACKLOG, 8192).
+
+-spec start_link(pv1_server()) -> {ok, pid()}.
+start_link(FluName) ->
+    supervisor:start_link({local, subsup_name(FluName)}, ?MODULE, []).
+
+-spec start_append_server(pv1_server(), boolean(), boolean(),
+                          undefined | machi_dt:epoch_id()) ->
+                                 {ok, pid()}.
+start_append_server(FluName, Witness_p, Wedged_p, EpochId) ->
+    supervisor:start_child(subsup_name(FluName),
+                           append_server_spec(FluName, Witness_p, Wedged_p, EpochId)).
+
+-spec stop_append_server(pv1_server()) -> ok.
+stop_append_server(FluName) ->
+    SubSup = listener_name(FluName),
+    ok = supervisor:terminate_child(SubSup, FluName),
+    ok = supervisor:delete_child(SubSup, FluName).
+
+-spec start_listener(pv1_server(), inet:port_number(), boolean(),
+                     string(), ets:tab(), atom() | pid(),
+                     proplists:proplist()) -> {ok, pid()}.
+start_listener(FluName, TcpPort, Witness, DataDir, EpochTab, ProjStore,
+               Props) ->
+    supervisor:start_child(subsup_name(FluName),
+                           listener_spec(FluName, TcpPort, Witness, DataDir,
+                                         EpochTab, ProjStore, Props)).
+
+-spec stop_listener(pv1_server()) -> ok.
+stop_listener(FluName) ->
+    SupName = subsup_name(FluName),
+    ListenerName = listener_name(FluName),
+    ok = supervisor:terminate_child(SupName, ListenerName),
+    ok = supervisor:delete_child(SupName, ListenerName).
+
+-spec subsup_name(pv1_server()) -> atom().
+subsup_name(FluName) when is_atom(FluName) ->
+    list_to_atom(atom_to_list(FluName) ++ "_flu1_subsup").
+
+-spec listener_name(pv1_server()) -> atom().
+listener_name(FluName) ->
+    list_to_atom(atom_to_list(FluName) ++ "_listener").
+
+%% Supervisor callback
+
+init([]) ->
+    SupFlags = {one_for_all, 1000, 10},
+    {ok, {SupFlags, []}}.
+
+%% private
+
+-spec listener_spec(pv1_server(), inet:port_number(), boolean(),
+                    string(), ets:tab(), atom() | pid(),
+                    proplists:proplist()) -> supervisor:child_spec().
+listener_spec(FluName, TcpPort, Witness, DataDir, EpochTab, ProjStore, Props) ->
+    ListenerName = listener_name(FluName),
+    NbAcceptors = 10,
+    TcpOpts = [{port, TcpPort}, {backlog, ?BACKLOG}],
+    NetServerOpts = [FluName, Witness, DataDir, EpochTab, ProjStore, Props],
+    ranch:child_spec(ListenerName, NbAcceptors,
+                     ranch_tcp, TcpOpts,
+                     machi_flu1_net_server, NetServerOpts).
+
+-spec append_server_spec(pv1_server(), boolean(), boolean(),
+                         undefined | machi_dt:epoch_id()) -> supervisor:child_spec().
+append_server_spec(FluName, Witness_p, Wedged_p, EpochId) ->
+    {FluName, {machi_flu1_append_server, start_link,
+               [FluName, Witness_p, Wedged_p, EpochId]},
+     permanent, ?SHUTDOWN, worker, [machi_flu1_append_server]}.

src/machi_flu_filename_mgr.erl

@@ -51,8 +51,8 @@
 -export([
     child_spec/2,
     start_link/2,
-    find_or_make_filename_from_prefix/3,
+    find_or_make_filename_from_prefix/4,
-    increment_prefix_sequence/2,
+    increment_prefix_sequence/3,
     list_files_by_prefix/2
     ]).
 
@@ -67,12 +67,13 @@
     ]).
 
 -define(TIMEOUT, 10 * 1000).
--include("machi_projection.hrl"). %% included for pv1_epoch_n type
+-include("machi.hrl").            %% included for #ns_info record
+-include("machi_projection.hrl"). %% included for pv1_epoch type
 
 -record(state, {fluname :: atom(),
                 tid     :: ets:tid(),
-                datadir :: file:dir(),
+                datadir :: string(),
-                epoch   :: pv1_epoch_n()
+                epoch   :: pv1_epoch()
                }).
 
 %% public API
@@ -88,26 +89,30 @@ start_link(FluName, DataDir) when is_atom(FluName) andalso is_list(DataDir) ->
     gen_server:start_link({local, N}, ?MODULE, [FluName, DataDir], []).
 
 -spec find_or_make_filename_from_prefix( FluName :: atom(),
-                                         EpochId :: pv1_epoch_n(), 
+                                         EpochId :: pv1_epoch(),
-                                         Prefix :: {prefix, string()} ) ->
+                                         Prefix :: {prefix, string()},
+                                         machi_dt:ns_info()) ->
         {file, Filename :: string()} | {error, Reason :: term() } | timeout.
 % @doc Find the latest available or make a filename from a prefix. A prefix
 % should be in the form of a tagged tuple `{prefix, P}'. Returns a tagged
 % tuple in the form of `{file, F}' or an `{error, Reason}'
-find_or_make_filename_from_prefix(FluName, EpochId, {prefix, Prefix}) when is_atom(FluName) ->
+find_or_make_filename_from_prefix(FluName, EpochId,
+                                  {prefix, Prefix},
+                                  #ns_info{}=NSInfo)
+  when is_atom(FluName) ->
     N = make_filename_mgr_name(FluName),
-    gen_server:call(N, {find_filename, EpochId, Prefix}, ?TIMEOUT); 
+    gen_server:call(N, {find_filename, FluName, EpochId, NSInfo, Prefix}, ?TIMEOUT);
-find_or_make_filename_from_prefix(_FluName, _EpochId, Other) ->
+find_or_make_filename_from_prefix(_FluName, _EpochId, Other, Other2) ->
-    lager:error("~p is not a valid prefix.", [Other]),
+    lager:error("~p is not a valid prefix/locator ~p", [Other, Other2]),
     error(badarg).
 
--spec increment_prefix_sequence( FluName :: atom(), Prefix :: {prefix, string()} ) ->
+-spec increment_prefix_sequence( FluName :: atom(), NSInfo :: machi_dt:ns_info(), Prefix :: {prefix, string()} ) ->
         ok | {error, Reason :: term() } | timeout.
 % @doc Increment the sequence counter for a given prefix. Prefix should
 % be in the form of `{prefix, P}'.
-increment_prefix_sequence(FluName, {prefix, Prefix}) when is_atom(FluName) ->
+increment_prefix_sequence(FluName, #ns_info{}=NSInfo, {prefix, Prefix}) when is_atom(FluName) ->
-    gen_server:call(make_filename_mgr_name(FluName), {increment_sequence, Prefix}, ?TIMEOUT); 
+    gen_server:call(make_filename_mgr_name(FluName), {increment_sequence, NSInfo, Prefix}, ?TIMEOUT);
-increment_prefix_sequence(_FluName, Other) ->
+increment_prefix_sequence(_FluName, _NSInfo, Other) ->
     lager:error("~p is not a valid prefix.", [Other]),
     error(badarg).
 
@@ -125,7 +130,10 @@ list_files_by_prefix(_FluName, Other) ->
 %% gen_server API
 init([FluName, DataDir]) ->
     Tid = ets:new(make_filename_mgr_name(FluName), [named_table, {read_concurrency, true}]),
-    {ok, #state{ fluname = FluName, epoch = 0, datadir = DataDir, tid = Tid }}.
+    {ok, #state{fluname = FluName,
+                epoch = ?DUMMY_PV1_EPOCH,
+                datadir = DataDir,
+                tid = Tid}}.
 
 handle_cast(Req, State) ->
     lager:warning("Got unknown cast ~p", [Req]),
@@ -135,23 +143,23 @@ handle_cast(Req, State) ->
 %% the FLU has already validated that the caller's epoch id and the FLU's epoch id
 %% are the same. So we *assume* that remains the case here - that is to say, we
 %% are not wedged.
-handle_call({find_filename, EpochId, Prefix}, _From, S = #state{ datadir = DataDir, 
+handle_call({find_filename, FluName, EpochId, NSInfo, Prefix}, _From,
-                                                                 epoch = EpochId, 
+            S = #state{ datadir = DataDir, epoch = EpochId, tid = Tid }) ->
-                                                                 tid = Tid }) ->
     %% Our state and the caller's epoch ids are the same. Business as usual.
-    File = handle_find_file(Tid, Prefix, DataDir),
+    File = handle_find_file(FluName, Tid, NSInfo, Prefix, DataDir),
     {reply, {file, File}, S};
 
-handle_call({find_filename, EpochId, Prefix}, _From, S = #state{ datadir = DataDir, tid = Tid }) ->
+handle_call({find_filename, _FluName, EpochId, NSInfo, Prefix}, _From, S = #state{ datadir = DataDir, tid = Tid }) ->
     %% If the epoch id in our state and the caller's epoch id were the same, it would've
     %% matched the above clause. Since we're here, we know that they are different.
     %% If epoch ids between our state and the caller's are different, we must increment the
     %% sequence number, generate a filename and then cache it.
-    File = increment_and_cache_filename(Tid, DataDir, Prefix),
+    File = increment_and_cache_filename(Tid, DataDir, NSInfo, Prefix),
     {reply, {file, File}, S#state{epoch = EpochId}};
 
-handle_call({increment_sequence, Prefix}, _From, S = #state{ datadir = DataDir }) ->
+handle_call({increment_sequence, #ns_info{name=NS, locator=NSLocator}, Prefix}, _From, S = #state{ datadir = DataDir, tid=Tid }) ->
-    ok = machi_util:increment_max_filenum(DataDir, Prefix),
+    NSInfo = #ns_info{name=NS, locator=NSLocator},
+    _File = increment_and_cache_filename(Tid, DataDir, NSInfo, Prefix),
     {reply, ok, S};
 handle_call({list_files, Prefix}, From, S = #state{ datadir = DataDir }) ->
     spawn(fun() ->
@@ -184,65 +192,41 @@ generate_uuid_v4_str() ->
     io_lib:format("~8.16.0b-~4.16.0b-4~3.16.0b-~4.16.0b-~12.16.0b",
                         [A, B, C band 16#0fff, D band 16#3fff bor 16#8000, E]).
 
-find_file(DataDir, Prefix, N) ->
-    {_Filename, Path} = machi_util:make_data_filename(DataDir, Prefix, "*", N),
-    filelib:wildcard(Path).
-
 list_files(DataDir, Prefix) ->
-    {F, Path} = machi_util:make_data_filename(DataDir, Prefix, "*", "*"),
+    {F_bin, Path} = machi_util:make_data_filename(DataDir, "*^" ++ Prefix ++ "^*"),
-    filelib:wildcard(F, filename:dirname(Path)).
+    filelib:wildcard(binary_to_list(F_bin), filename:dirname(Path)).
 
 make_filename_mgr_name(FluName) when is_atom(FluName) ->
     list_to_atom(atom_to_list(FluName) ++ "_filename_mgr").
 
-handle_find_file(Tid, Prefix, DataDir) ->
+handle_find_file(_FluName, Tid, #ns_info{name=NS, locator=NSLocator}, Prefix, DataDir) ->
-    N = machi_util:read_max_filenum(DataDir, Prefix),
+    case ets:lookup(Tid, {NS, NSLocator, Prefix}) of
-    {File, Cleanup} = case find_file(DataDir, Prefix, N) of
          [] ->
-            {find_or_make_filename(Tid, DataDir, Prefix, N), false};
+            N = machi_util:read_max_filenum(DataDir, NS, NSLocator, Prefix),
-        [H] -> {H, true};
+            F = generate_filename(DataDir, NS, NSLocator, Prefix, N),
-        [Fn | _ ] = L -> 
+            true = ets:insert(Tid, {{NS, NSLocator, Prefix}, F}),
-            lager:warning(
-              "Searching for a matching file to prefix ~p and sequence number ~p gave multiples: ~p",
-              [Prefix, N, L]),
-            {Fn, true}
-    end,
-    maybe_cleanup(Tid, {Prefix, N}, Cleanup),
-    filename:basename(File).
-
-find_or_make_filename(Tid, DataDir, Prefix, N) ->
-    case ets:lookup(Tid, {Prefix, N}) of
-         [] ->
-            F = generate_filename(DataDir, Prefix, N),
-            true = ets:insert_new(Tid, {{Prefix, N}, F}),
             F;
         [{_Key, File}] ->
             File
     end.
 
-generate_filename(DataDir, Prefix, N) ->
+generate_filename(DataDir, NS, NSLocator, Prefix, N) ->
-    {F, _} = machi_util:make_data_filename(
+    {F, _Q} = machi_util:make_data_filename(
               DataDir,
-              Prefix,
+              NS, NSLocator, Prefix,
               generate_uuid_v4_str(),
               N),
     binary_to_list(F).
 
-maybe_cleanup(_Tid, _Key, false) ->
+increment_and_cache_filename(Tid, DataDir, #ns_info{name=NS,locator=NSLocator}, Prefix) ->
-    ok;
+    ok = machi_util:increment_max_filenum(DataDir, NS, NSLocator, Prefix),
-maybe_cleanup(Tid, Key, true) ->
+    N = machi_util:read_max_filenum(DataDir, NS, NSLocator, Prefix),
-    true = ets:delete(Tid, Key).
+    F = generate_filename(DataDir, NS, NSLocator, Prefix, N),
-
+    true = ets:insert(Tid, {{NS, NSLocator, Prefix}, F}),
-increment_and_cache_filename(Tid, DataDir, Prefix) ->
+    F.
-    ok = machi_util:increment_max_filenum(DataDir, Prefix),
-    N = machi_util:read_max_filenum(DataDir, Prefix),
-    F = generate_filename(DataDir, Prefix, N),
-    true = ets:insert_new(Tid, {{Prefix, N}, F}),
-    filename:basename(F).
 
 
 
 -ifdef(TEST).
 
 -endif.
-

src/machi_flu_metadata_mgr.erl

@@ -34,15 +34,19 @@
 -module(machi_flu_metadata_mgr).
 -behaviour(gen_server).
 
+-include("machi.hrl").
 
 -define(MAX_MGRS, 10). %% number of managers to start by default.
 -define(HASH(X), erlang:phash2(X)). %% hash algorithm to use
 -define(TIMEOUT, 10 * 1000). %% 10 second timeout
 
+-define(KNOWN_FILES_LIST_PREFIX, "known_files_").
+
 -record(state, {fluname :: atom(),
                 datadir :: string(),
                 tid     :: ets:tid(),
-                cnt     :: non_neg_integer()
+                cnt     :: non_neg_integer(),
+                trimmed_files :: machi_plist:plist()
                }).
 
 %% This record goes in the ets table where filename is the key
@@ -59,7 +63,9 @@
          lookup_proxy_pid/2,
          start_proxy_pid/2,
          stop_proxy_pid/2,
-         build_metadata_mgr_name/2
+         stop_proxy_pid_rollover/2,
+         build_metadata_mgr_name/2,
+         trim_file/2
         ]).
 
 %% gen_server callbacks
@@ -95,12 +101,29 @@ start_proxy_pid(FluName, {file, Filename}) ->
     gen_server:call(get_manager_atom(FluName, Filename), {start_proxy_pid, Filename}, ?TIMEOUT).
 
 stop_proxy_pid(FluName, {file, Filename}) ->
-    gen_server:call(get_manager_atom(FluName, Filename), {stop_proxy_pid, Filename}, ?TIMEOUT).
+    gen_server:call(get_manager_atom(FluName, Filename), {stop_proxy_pid, false, Filename}, ?TIMEOUT).
+
+stop_proxy_pid_rollover(FluName, {file, Filename}) ->
+    gen_server:call(get_manager_atom(FluName, Filename), {stop_proxy_pid, true, Filename}, ?TIMEOUT).
+
+trim_file(FluName, {file, Filename}) ->
+    gen_server:call(get_manager_atom(FluName, Filename), {trim_file, Filename}, ?TIMEOUT).
 
 %% gen_server callbacks
 init([FluName, Name, DataDir, Num]) ->
+    %% important: we'll need another persistent storage to
+    %% remember deleted (trimmed) file, to prevent resurrection after
+    %% flu restart and append.
+    FileListFileName =
+        filename:join([DataDir, ?KNOWN_FILES_LIST_PREFIX ++ atom_to_list(FluName)]),
+    {ok, PList} = machi_plist:open(FileListFileName, []),
+    %% TODO make sure all files non-existent, if any remaining files
+    %% here, just delete it. They're in the list *because* they're all
+    %% trimmed.
+
     Tid = ets:new(Name, [{keypos, 2}, {read_concurrency, true}, {write_concurrency, true}]),
-    {ok, #state{ fluname = FluName, datadir = DataDir, tid = Tid, cnt = Num}}.
+    {ok, #state{fluname = FluName, datadir = DataDir, tid = Tid, cnt = Num,
+                trimmed_files=PList}}.
 
 handle_cast(Req, State) ->
     lager:warning("Got unknown cast ~p", [Req]),
@@ -113,7 +136,11 @@ handle_call({proxy_pid, Filename}, _From, State = #state{ tid = Tid }) ->
     end,
     {reply, Reply, State};
 
-handle_call({start_proxy_pid, Filename}, _From, State = #state{ fluname = N, tid = Tid, datadir = D }) ->
+handle_call({start_proxy_pid, Filename}, _From,
+            State = #state{ fluname = N, tid = Tid, datadir = D,
+                            trimmed_files=TrimmedFiles}) ->
+    case machi_plist:find(TrimmedFiles, Filename) of
+        false ->
             NewR = case lookup_md(Tid, Filename) of
                        not_found ->
                            start_file_proxy(N, D, Filename);
@@ -124,7 +151,11 @@ handle_call({start_proxy_pid, Filename}, _From, State = #state{ fluname = N, tid
                    end,
             update_ets(Tid, NewR),
             {reply, {ok, NewR#md.proxy_pid}, State};
-handle_call({stop_proxy_pid, Filename}, _From, State = #state{ tid = Tid }) ->
+        true ->
+            {reply, {error, trimmed}, State}
+    end;
+
+handle_call({stop_proxy_pid, Rollover_p, Filename}, _From, State = #state{ tid = Tid }) ->
     case lookup_md(Tid, Filename) of
         not_found ->
             ok;
@@ -132,11 +163,25 @@ handle_call({stop_proxy_pid, Filename}, _From, State = #state{ tid = Tid }) ->
             ok;
         #md{ proxy_pid = Pid, mref = M } = R ->
             demonitor(M, [flush]),
+            if Rollover_p ->
+                    do_rollover(Filename, State);
+               true ->
                     machi_file_proxy:stop(Pid),
-            update_ets(Tid, R#md{ proxy_pid = undefined, mref = undefined })
+                    update_ets(Tid, R#md{ proxy_pid = undefined,
+                                          mref = undefined })
+            end
     end,
     {reply, ok, State};
 
+handle_call({trim_file, Filename}, _,
+            S = #state{trimmed_files = TrimmedFiles }) ->
+    case machi_plist:add(TrimmedFiles, Filename) of
+        {ok, TrimmedFiles2} ->
+            {reply, ok, S#state{trimmed_files=TrimmedFiles2}};
+        Error ->
+            {reply, Error, S}
+    end;
+
 handle_call(Req, From, State) ->
     lager:warning("Got unknown call ~p from ~p", [Req, From]),
     {reply, hoge, State}.
@@ -146,41 +191,25 @@ handle_info({'DOWN', Mref, process, Pid, normal}, State = #state{ tid = Tid }) -
     clear_ets(Tid, Mref),
     {noreply, State};
 
-handle_info({'DOWN', Mref, process, Pid, file_rollover}, State = #state{ fluname = FluName, 
-                                                                         tid = Tid }) ->
-    lager:info("file proxy ~p shutdown because of file rollover", [Pid]),
-    R = get_md_record_by_mref(Tid, Mref),
-    [Prefix | _Rest] = machi_util:parse_filename({file, R#md.filename}),
-
-    %% We only increment the counter here. The filename will be generated on the 
-    %% next append request to that prefix and since the filename will have a new
-    %% sequence number it probably will be associated with a different metadata
-    %% manager. That's why we don't want to generate a new file name immediately
-    %% and use it to start a new file proxy.
-    ok = machi_flu_filename_mgr:increment_prefix_sequence(FluName, {prefix, Prefix}),
-
-    %% purge our ets table of this entry completely since it is likely the
-    %% new filename (whenever it comes) will be in a different manager than
-    %% us.
-    purge_ets(Tid, R),
-    {noreply, State};
-
 handle_info({'DOWN', Mref, process, Pid, wedged}, State = #state{ tid = Tid }) ->
     lager:error("file proxy ~p shutdown because it's wedged", [Pid]),
     clear_ets(Tid, Mref),
     {noreply, State};
+handle_info({'DOWN', _Mref, process, Pid, trimmed}, State = #state{ tid = _Tid }) ->
+    lager:debug("file proxy ~p shutdown because the file was trimmed", [Pid]),
+    {noreply, State};
 handle_info({'DOWN', Mref, process, Pid, Error}, State = #state{ tid = Tid }) ->
     lager:error("file proxy ~p shutdown because ~p", [Pid, Error]),
     clear_ets(Tid, Mref),
     {noreply, State};
 
-
 handle_info(Info, State) ->
     lager:warning("Got unknown info ~p", [Info]),
     {noreply, State}.
 
-terminate(Reason, _State) ->
+terminate(Reason, _State = #state{trimmed_files=TrimmedFiles}) ->
     lager:info("Shutting down because ~p", [Reason]),
+    machi_plist:close(TrimmedFiles),
     ok.
 
 code_change(_OldVsn, State, _Extra) ->
@@ -228,14 +257,41 @@ clear_ets(Tid, Mref) ->
     update_ets(Tid, R#md{ proxy_pid = undefined, mref = undefined }).
 
 purge_ets(Tid, R) ->
-    ok = ets:delete_object(Tid, R).
+    true = ets:delete_object(Tid, R).
 
 get_md_record_by_mref(Tid, Mref) ->
     [R] = ets:match_object(Tid, {md, '_', '_', Mref}),
     R.
 
+get_md_record_by_filename(Tid, Filename) ->
+    [R] = ets:lookup(Tid, Filename),
+    R.
+
 get_env(Setting, Default) ->
     case application:get_env(machi, Setting) of
         undefined -> Default;
         {ok, V} -> V
     end.
+
+do_rollover(Filename, _State = #state{ fluname = FluName,
+                                       tid = Tid }) ->
+    R = get_md_record_by_filename(Tid, Filename),
+    lager:info("file ~p proxy ~p shutdown because of file rollover",
+               [Filename, R#md.proxy_pid]),
+    {Prefix, NS, NSLocator, _, _} =
+        machi_util:parse_filename(R#md.filename),
+
+    %% We only increment the counter here. The filename will be generated on the
+    %% next append request to that prefix and since the filename will have a new
+    %% sequence number it probably will be associated with a different metadata
+    %% manager. That's why we don't want to generate a new file name immediately
+    %% and use it to start a new file proxy.
+    NSInfo = #ns_info{name=NS, locator=NSLocator},
+lager:warning("INCR: ~p ~p\n", [FluName, Prefix]),
+    ok = machi_flu_filename_mgr:increment_prefix_sequence(FluName, NSInfo, {prefix, Prefix}),
+
+    %% purge our ets table of this entry completely since it is likely the
+    %% new filename (whenever it comes) will be in a different manager than
+    %% us.
+    purge_ets(Tid, R),
+    ok.

src/machi_flu_psup.erl

@@ -83,6 +83,8 @@
 %% Supervisor callbacks
 -export([init/1]).
 
+make_package_spec(#p_srvr{name=FluName, port=TcpPort, props=Props}) when is_list(Props) ->
+    make_package_spec({FluName, TcpPort, Props});
 make_package_spec({FluName, TcpPort, Props}) when is_list(Props) ->
     FluDataDir = get_env(flu_data_dir, undefined_is_invalid),
     MyDataDir = filename:join(FluDataDir, atom_to_list(FluName)),
@@ -94,7 +96,7 @@ make_package_spec(FluName, TcpPort, DataDir, Props) ->
      permanent, ?SHUTDOWN, supervisor, []}.
 
 start_flu_package(#p_srvr{name=FluName, port=TcpPort, props=Props}) ->
-    DataDir = get_data_dir(Props),
+    DataDir = get_data_dir(FluName, Props),
     start_flu_package(FluName, TcpPort, DataDir, Props).
 
 start_flu_package(FluName, TcpPort, DataDir, Props) ->
@@ -143,16 +145,19 @@ init([FluName, TcpPort, DataDir, Props0]) ->
 
     FProxySupSpec = machi_file_proxy_sup:child_spec(FluName),
 
+    Flu1SubSupSpec = {machi_flu1_subsup:subsup_name(FluName),
+                      {machi_flu1_subsup, start_link, [FluName]},
+                      permanent, ?SHUTDOWN, supervisor, []},
+
     FluSpec = {FluName,
                {machi_flu1, start_link,
                 [ [{FluName, TcpPort, DataDir}|Props] ]},
                permanent, ?SHUTDOWN, worker, []},
 
-
     {ok, {SupFlags, [
             ProjSpec, FitnessSpec, MgrSpec,
             FProxySupSpec, FNameMgrSpec, MetaSupSpec,
-            FluSpec]}}.
+            Flu1SubSupSpec, FluSpec]}}.
 
 make_flu_regname(FluName) when is_atom(FluName) ->
     FluName.
@@ -175,8 +180,11 @@ get_env(Setting, Default) ->
         {ok, V} -> V
     end.
 
-get_data_dir(Props) ->
+get_data_dir(FluName, Props) ->
     case proplists:get_value(data_dir, Props) of
         Path when is_list(Path) ->
-            Path
+            Path;
+        undefined ->
+            {ok, Dir} = application:get_env(machi, flu_data_dir),
+            Dir ++ "/" ++ atom_to_list(FluName)
     end.

src/machi_flu_sup.erl

@@ -21,6 +21,9 @@
 %% @doc Supervisor for Machi FLU servers and their related support
 %% servers.
 %%
+%% Responsibility for managing FLU and chain lifecycle after the initial
+%% application startup is delegated to {@link machi_lifecycle_mgr}.
+%%
 %% See {@link machi_flu_psup} for an illustration of the entire Machi
 %% application process structure.
 
@@ -29,8 +32,11 @@
 -behaviour(supervisor).
 
 -include("machi.hrl").
+-include("machi_projection.hrl").
 -include("machi_verbose.hrl").
 
+-ifdef(TEST).
+-compile(export_all).
 -ifdef(PULSE).
 -compile({parse_transform, pulse_instrument}).
 -include_lib("pulse_otp/include/pulse_otp.hrl").
@@ -38,9 +44,12 @@
 -else.
 -define(SHUTDOWN, 5000).
 -endif.
+-endif. %TEST
 
 %% API
--export([start_link/0]).
+-export([start_link/0,
+         get_initial_flus/0, load_rc_d_files_from_dir/1,
+         sanitize_p_srvr_records/1]).
 
 %% Supervisor callbacks
 -export([init/1]).
@@ -69,5 +78,66 @@ get_initial_flus() ->
     [].
 -else.  % PULSE
 get_initial_flus() ->
-    application:get_env(machi, initial_flus, []).
+    DoesNotExist = "/tmp/does/not/exist",
+    ConfigDir = case application:get_env(machi, flu_config_dir, DoesNotExist) of
+                    DoesNotExist ->
+                        DoesNotExist;
+                    Dir ->
+                        Dir
+                end,
+    Ps = [P || {_File, P} <- load_rc_d_files_from_dir(ConfigDir)],
+    sanitize_p_srvr_records(Ps).
 -endif. % PULSE
+
+load_rc_d_files_from_dir(Dir) ->
+    Files = filelib:wildcard(Dir ++ "/*"),
+    [case file:consult(File) of
+         {ok, [X]} ->
+             {File, X};
+         _ ->
+             lager:warning("Error parsing file '~s', ignoring",
+                           [File]),
+             {File, []}
+     end || File <- Files].
+
+sanitize_p_srvr_records(Ps) ->
+    {Sane, _} = lists:foldl(fun sanitize_p_srvr_rec/2, {[], dict:new()}, Ps),
+    Sane.
+
+sanitize_p_srvr_rec(Whole, {Acc, D}) ->
+    try
+        #p_srvr{name=Name,
+                proto_mod=PMod,
+                address=Address,
+                port=Port,
+                props=Props} = Whole,
+        true = is_atom(Name),
+        NameK = {name, Name},
+        error = dict:find(NameK, D),
+        true = is_atom(PMod),
+        case code:is_loaded(PMod) of
+            {file, _} ->
+                ok;
+            _ ->
+                {module, _} = code:load_file(PMod),
+                ok
+        end,
+        if is_list(Address)  -> ok;
+           is_tuple(Address) -> ok              % Erlang-style IPv4 or IPv6
+        end,
+        true = is_integer(Port) andalso Port >= 1024 andalso Port =< 65534,
+        PortK = {port, Port},
+        error = dict:find(PortK, D),
+        true = is_list(Props),
+
+        %% All is sane enough.
+        D2 = dict:store(NameK, Name,
+                        dict:store(PortK, Port, D)),
+        {[Whole|Acc], D2}
+    catch _:_ ->
+            _ = lager:log(error, self(),
+                          "~s: Bad (or duplicate name/port) p_srvr record, "
+                          "skipping: ~P\n",
+                          [?MODULE, Whole, 15]),
+            {Acc, D}
+    end.

src/machi_merkle_tree.erl

@@ -0,0 +1,156 @@
+%% -------------------------------------------------------------------
+%%
+%% Copyright (c) 2007-2015 Basho Technologies, Inc.  All Rights Reserved.
+%%
+%% This file is provided to you under the Apache License,
+%% Version 2.0 (the "License"); you may not use this file
+%% except in compliance with the License.  You may obtain
+%% a copy of the License at
+%%
+%%   http://www.apache.org/licenses/LICENSE-2.0
+%%
+%% Unless required by applicable law or agreed to in writing,
+%% software distributed under the License is distributed on an
+%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+%% KIND, either express or implied.  See the License for the
+%% specific language governing permissions and limitations
+%% under the License.
+%%
+%% -------------------------------------------------------------------
+
+%% @doc Creates a Merkle tree per file based on the checksum data for
+%% a given data file.
+%%
+%% The `naive' implementation representation is:
+%%
+%% `<<Length:64, Offset:32, 0>>' for unwritten bytes
+%% `<<Length:64, Offset:32, 1>>' for trimmed bytes
+%% `<<Length:64, Offset:32, Csum/binary>>' for written bytes
+%%
+%% The tree feeds these leaf nodes into hashes representing chunks of a minimum
+%% size of at least 1024 KB (1 MB), but if the file size is larger, we will try
+%% to get about 100 chunks for the first rollup "Level 1." We aim for around 10
+%% hashes at level 2, and then 2 hashes level 3 and finally the root.
+
+-module(machi_merkle_tree).
+
+-include("machi.hrl").
+-include("machi_merkle_tree.hrl").
+
+-ifdef(TEST).
+-compile(export_all).
+-else.
+-export([
+    open/2,
+    open/3,
+    tree/1,
+    filename/1,
+    diff/2
+]).
+-endif.
+
+-define(TRIMMED, <<1>>).
+-define(UNWRITTEN, <<0>>).
+-define(NAIVE_ENCODE(Offset, Size, Data), <<Offset:64/unsigned-big, Size:32/unsigned-big, Data/binary>>).
+
+-define(MINIMUM_CHUNK, 1048576). %% 1024 * 1024
+-define(LEVEL_SIZE, 10).
+-define(H, sha).
+
+%% public API
+
+open(Filename, DataDir) ->
+    open(Filename, DataDir, naive).
+
+open(Filename, DataDir, Type) ->
+    Tree = load_filename(Filename, DataDir, Type),
+    {ok, #mt{ filename = Filename, tree = Tree, backend = Type}}.
+
+tree(#mt{ tree = T, backend = naive }) ->
+    case T#naive.recalc of
+         true -> build_tree(T);
+        false -> T
+    end.
+
+filename(#mt{ filename = F }) -> F.
+
+diff(#mt{backend = naive, tree = T1}, #mt{backend = naive, tree = T2}) ->
+    case T1#naive.root == T2#naive.root of
+        true -> same;
+        false -> naive_diff(T1, T2) 
+    end;
+diff(_, _) -> error(badarg).
+
+%% private
+
+% @private
+load_filename(Filename, DataDir, naive) ->
+    {Last, M} = do_load(Filename, DataDir, fun insert_csum_naive/2, []),
+    ChunkSize = max(?MINIMUM_CHUNK, Last div 100),
+    T = #naive{ leaves = lists:reverse(M), chunk_size = ChunkSize, recalc = true },
+    build_tree(T).
+
+do_load(Filename, DataDir, FoldFun, AccInit) ->
+    CsumFile = machi_util:make_checksum_filename(DataDir, Filename),
+    {ok, T} = machi_csum_table:open(CsumFile, []),
+    Acc = machi_csum_table:foldl_chunks(FoldFun, {0, AccInit}, T),
+    ok = machi_csum_table:close(T),
+    Acc.
+
+% @private
+insert_csum_naive({Last, Size, _Csum}=In, {Last, MT}) ->
+    %% no gap
+    {Last+Size, update_acc(In, MT)};
+insert_csum_naive({Offset, Size, _Csum}=In, {Last, MT}) ->
+    Hole = Offset - Last,
+    MT0 = update_acc({Last, Hole, unwritten}, MT),
+    {Offset+Size, update_acc(In, MT0)}.
+
+% @private
+update_acc({Offset, Size, unwritten}, MT) ->
+    [ {Offset, Size, ?NAIVE_ENCODE(Offset, Size, ?UNWRITTEN)} | MT ];
+update_acc({Offset, Size, trimmed}, MT) ->
+    [ {Offset, Size, ?NAIVE_ENCODE(Offset, Size, ?TRIMMED)} | MT ];
+update_acc({Offset, Size, <<_Tag:8, Csum/binary>>}, MT) ->
+    [ {Offset, Size, ?NAIVE_ENCODE(Offset, Size, Csum)} | MT ].
+
+build_tree(MT = #naive{ leaves = L, chunk_size = ChunkSize }) ->
+    Lvl1s = build_level_1(ChunkSize, L, 1, [ crypto:hash_init(?H) ]),
+    Mod2 = length(Lvl1s) div ?LEVEL_SIZE,
+    Lvl2s = build_int_level(Mod2, Lvl1s, 1, [ crypto:hash_init(?H) ]),
+    Mod3 = length(Lvl2s) div 2,
+    Lvl3s = build_int_level(Mod3, Lvl2s, 1, [ crypto:hash_init(?H) ]),
+    Root = build_root(Lvl3s, crypto:hash_init(?H)),
+    MT#naive{ root = Root, lvl1 = Lvl1s, lvl2 = Lvl2s, lvl3 = Lvl3s, recalc = false }.
+
+build_root([], Ctx) ->
+    crypto:hash_final(Ctx);
+build_root([H|T], Ctx) ->
+    build_root(T, crypto:hash_update(Ctx, H)).
+
+build_int_level(_Mod, [], _Cnt, [ Ctx | Rest ]) ->
+    lists:reverse( [ crypto:hash_final(Ctx) | Rest ] );
+build_int_level(Mod, [H|T], Cnt, [ Ctx | Rest ]) when Cnt rem Mod == 0 ->
+    NewCtx = crypto:hash_init(?H),
+    build_int_level(Mod, T, Cnt + 1, [ crypto:hash_update(NewCtx, H), crypto:hash_final(Ctx) | Rest ]);
+build_int_level(Mod, [H|T], Cnt, [ Ctx | Rest ]) ->
+    build_int_level(Mod, T, Cnt+1, [ crypto:hash_update(Ctx, H) | Rest ]).
+
+build_level_1(_Size, [], _Multiple, [ Ctx | Rest ]) ->
+    lists:reverse([ crypto:hash_final(Ctx) | Rest ]);
+build_level_1(Size, [{Pos, Len, Hash}|T], Multiple, [ Ctx | Rest ])
+                                    when ( Pos + Len ) > ( Size * Multiple ) ->
+    NewCtx = crypto:hash_init(?H),
+    build_level_1(Size, T, Multiple+1,
+                  [ crypto:hash_update(NewCtx, Hash), crypto:hash_final(Ctx) | Rest ]);
+build_level_1(Size, [{Pos, Len, Hash}|T], Multiple, [ Ctx | Rest ])
+                                    when ( Pos + Len ) =< ( Size * Multiple ) ->
+    build_level_1(Size, T, Multiple, [ crypto:hash_update(Ctx, Hash) | Rest ]).
+
+naive_diff(#naive{lvl1 = L1}, #naive{lvl1=L2, chunk_size=CS2}) ->
+    Set1 = gb_sets:from_list(lists:zip(lists:seq(1, length(L1)), L1)),
+    Set2 = gb_sets:from_list(lists:zip(lists:seq(1, length(L2)), L2)),
+
+    %% The byte ranges in list 2 that do not match in list 1
+    %% Or should we do something else?
+    [ {(X-1)*CS2, CS2, SHA} || {X, SHA} <- gb_sets:to_list(gb_sets:subtract(Set1, Set2)) ].

src/machi_pb_high_client.erl

@@ -25,6 +25,10 @@
 %% to a single socket connection, and there is no code to deal with
 %% multiple connections/load balancing/error handling to several/all
 %% Machi cluster servers.
+%%
+%% Please see {@link machi_flu1_client} the "Client API implemntation notes"
+%% section for how this module relates to the rest of the client API
+%% implementation.
 
 -module(machi_pb_high_client).
 
@@ -40,7 +44,7 @@
          auth/3, auth/4,
          append_chunk/6, append_chunk/7,
          write_chunk/5, write_chunk/6,
-         read_chunk/4, read_chunk/5,
+         read_chunk/5, read_chunk/6,
          trim_chunk/4, trim_chunk/5,
          checksum_list/2, checksum_list/3,
          list_files/1, list_files/2
@@ -58,54 +62,114 @@
           count=0     :: non_neg_integer()
          }).
 
+%% Official error types that is specific in Machi
+-type machi_client_error_reason() :: bad_arg | wedged | bad_checksum |
+                                     partition | not_written | written |
+                                     trimmed | no_such_file | partial_read |
+                                     bad_epoch | inet:posix().
+
+%% @doc Creates a client process
+-spec start_link(p_srvr_dict()) -> {ok, pid()} | {error, machi_client_error_reason()}.
 start_link(P_srvr_list) ->
     gen_server:start_link(?MODULE, [P_srvr_list], []).
 
+%% @doc Stops a client process.
+-spec quit(pid()) -> ok.
 quit(PidSpec) ->
     gen_server:call(PidSpec, quit, infinity).
 
 connected_p(PidSpec) ->
     gen_server:call(PidSpec, connected_p, infinity).
 
+-spec echo(pid(), string()) -> {ok, string()} | {error, machi_client_error_reason()}.
 echo(PidSpec, String) ->
     echo(PidSpec, String, ?DEFAULT_TIMEOUT).
 
+-spec echo(pid(), string(), non_neg_integer()) -> {ok, string()} | {error, machi_client_error_reason()}.
 echo(PidSpec, String, Timeout) ->
     send_sync(PidSpec, {echo, String}, Timeout).
 
 %% TODO: auth() is not implemented.  Auth requires SSL, and this client
 %% doesn't support SSL yet.  This is just a placeholder and reminder.
 
+-spec auth(pid(), string(), string()) -> ok | {error, machi_client_error_reason()}.
 auth(PidSpec, User, Pass) ->
     auth(PidSpec, User, Pass, ?DEFAULT_TIMEOUT).
 
+-spec auth(pid(), string(), string(), non_neg_integer()) -> ok | {error, machi_client_error_reason()}.
 auth(PidSpec, User, Pass, Timeout) ->
     send_sync(PidSpec, {auth, User, Pass}, Timeout).
 
-append_chunk(PidSpec, PlacementKey, Prefix, Chunk, CSum, ChunkExtra) ->
+-spec append_chunk(pid(),
-    append_chunk(PidSpec, PlacementKey, Prefix, Chunk, CSum, ChunkExtra, ?DEFAULT_TIMEOUT).
+                   NS::machi_dt:namespace(), Prefix::machi_dt:file_prefix(),
+                   Chunk::machi_dt:chunk(), CSum::machi_dt:chunk_csum(),
+                   Opts::machi_dt:append_opts()) ->
+                          {ok, Filename::string(), Offset::machi_dt:file_offset()} |
+                          {error, machi_client_error_reason()}.
+append_chunk(PidSpec, NS, Prefix, Chunk, CSum, Opts) ->
+    append_chunk(PidSpec, NS, Prefix, Chunk, CSum, Opts, ?DEFAULT_TIMEOUT).
 
-append_chunk(PidSpec, PlacementKey, Prefix, Chunk, CSum, ChunkExtra, Timeout) ->
+-spec append_chunk(pid(),
-    send_sync(PidSpec, {append_chunk, PlacementKey, Prefix, Chunk, CSum, ChunkExtra}, Timeout).
+                   NS::machi_dt:namespace(), Prefix::machi_dt:file_prefix(),
+                   Chunk::machi_dt:chunk(), CSum::machi_dt:chunk_csum(),
+                   Opts::machi_dt:append_opts(),
+                   Timeout::non_neg_integer()) ->
+                          {ok, Filename::string(), Offset::machi_dt:file_offset()} |
+                          {error, machi_client_error_reason()}.
+append_chunk(PidSpec, NS, Prefix, Chunk, CSum, Opts, Timeout) ->
+    send_sync(PidSpec, {append_chunk, NS, Prefix, Chunk, CSum, Opts}, Timeout).
 
+-spec write_chunk(pid(), File::string(), machi_dt:file_offset(),
+                  Chunk::machi_dt:chunk(), CSum::machi_dt:chunk_csum()) ->
+                         ok | {error, machi_client_error_reason()}.
 write_chunk(PidSpec, File, Offset, Chunk, CSum) ->
     write_chunk(PidSpec, File, Offset, Chunk, CSum, ?DEFAULT_TIMEOUT).
 
+-spec write_chunk(pid(), File::string(), machi_dt:file_offset(),
+                  Chunk::machi_dt:chunk(), CSum::machi_dt:chunk_csum(), Timeout::non_neg_integer()) ->
+                         ok | {error, machi_client_error_reason()}.
 write_chunk(PidSpec, File, Offset, Chunk, CSum, Timeout) ->
     send_sync(PidSpec, {write_chunk, File, Offset, Chunk, CSum}, Timeout).
 
-read_chunk(PidSpec, File, Offset, Size) ->
+%% @doc Tries to read a chunk of a specified file. It returns `{ok,
-    read_chunk(PidSpec, File, Offset, Size, ?DEFAULT_TIMEOUT).
+%% {Chunks, TrimmedChunks}}' for live file while it returns `{error,
+%% trimmed}' if all bytes of the file was trimmed.
+-spec read_chunk(pid(), File::string(), machi_dt:file_offset(), machi_dt:chunk_size(),
+                 machi_dt:read_opts_x()) ->
+                        {ok, {Chunks::[{File::string(), machi_dt:file_offset(), machi_dt:chunk_size(), binary()}],
+                              Trimmed::[{File::string(), machi_dt:file_offset(), machi_dt:chunk_size()}]}} |
+                        {error, machi_client_error_reason()}.
+read_chunk(PidSpec, File, Offset, Size, Opts) ->
+    read_chunk(PidSpec, File, Offset, Size, Opts, ?DEFAULT_TIMEOUT).
 
-read_chunk(PidSpec, File, Offset, Size, Timeout) ->
+-spec read_chunk(pid(), File::string(), machi_dt:file_offset(), machi_dt:chunk_size(),
-    send_sync(PidSpec, {read_chunk, File, Offset, Size}, Timeout).
+                 machi_dt:read_opts_x(),
+                 Timeout::non_neg_integer()) ->
+                        {ok, {Chunks::[{File::string(), machi_dt:file_offset(), machi_dt:chunk_size(), binary()}],
+                              Trimmed::[{File::string(), machi_dt:file_offset(), machi_dt:chunk_size()}]}} |
+                        {error, machi_client_error_reason()}.
+read_chunk(PidSpec, File, Offset, Size, Opts0, Timeout) ->
+    Opts = machi_util:read_opts_default(Opts0),
+    send_sync(PidSpec, {read_chunk, File, Offset, Size, Opts}, Timeout).
 
+%% @doc Trims arbitrary binary range of any file. If a specified range
+%% has any byte trimmed, it fails and returns `{error, trimmed}'.
+%% Otherwise it trims all bytes in that range. If there are
+%% overlapping chunks with client-specified checksum, they will cut
+%% off and checksum are re-calculated in server side.  TODO: Add
+%% option specifying whether to trigger GC.
+-spec trim_chunk(pid(), string(), non_neg_integer(), machi_dt:chunk_size()) ->
+                        ok | {error, machi_client_error_reason()}.
 trim_chunk(PidSpec, File, Offset, Size) ->
     trim_chunk(PidSpec, File, Offset, Size, ?DEFAULT_TIMEOUT).
 
 trim_chunk(PidSpec, File, Offset, Size, Timeout) ->
     send_sync(PidSpec, {trim_chunk, File, Offset, Size}, Timeout).
 
+%% @doc Returns a binary that has checksums and chunks encoded inside
+%% (This is because encoding-decoding them are inefficient). TODO:
+%% return a structured list of them.
+-spec checksum_list(pid(), string()) -> {ok, binary()} | {error, machi_client_error_reason()}.
 checksum_list(PidSpec, File) ->
     checksum_list(PidSpec, File, ?DEFAULT_TIMEOUT).
 
@@ -225,19 +289,19 @@ do_send_sync2({auth, User, Pass}, #state{sock=Sock}=S) ->
             Res = {bummer, {X, Y, erlang:get_stacktrace()}},
             {Res, S}
     end;
-do_send_sync2({append_chunk, PlacementKey, Prefix, Chunk, CSum, ChunkExtra},
+do_send_sync2({append_chunk, NS, Prefix, Chunk, CSum, Opts},
              #state{sock=Sock, sock_id=Index, count=Count}=S) ->
     try
         ReqID = <<Index:64/big, Count:64/big>>,
-        PK = if PlacementKey == <<>> -> undefined;
-                true                 -> PlacementKey
-             end,
         CSumT = convert_csum_req(CSum, Chunk),
-        Req = #mpb_appendchunkreq{placement_key=PK,
+        {ChunkExtra, Pref, FailPref} = machi_pb_translate:conv_from_append_opts(Opts),
+        Req = #mpb_appendchunkreq{namespace=NS,
                                   prefix=Prefix,
                                   chunk=Chunk,
                                   csum=CSumT,
-                                  chunk_extra=ChunkExtra},
+                                  chunk_extra=ChunkExtra,
+                                  preferred_file_name=Pref,
+                                  flag_fail_preferred=FailPref},
         R1a = #mpb_request{req_id=ReqID, do_not_alter=1,
                            append_chunk=Req},
         Bin1a = machi_pb:encode_mpb_request(R1a),
@@ -260,10 +324,11 @@ do_send_sync2({write_chunk, File, Offset, Chunk, CSum},
     try
         ReqID = <<Index:64/big, Count:64/big>>,
         CSumT = convert_csum_req(CSum, Chunk),
-        Req = #mpb_writechunkreq{file=File,
+        Req = #mpb_writechunkreq{chunk=
+                                     #mpb_chunk{chunk=Chunk,
+                                                file_name=File,
                                                 offset=Offset,
-                                 chunk=Chunk,
+                                                csum=CSumT}},
-                                 csum=CSumT},
         R1a = #mpb_request{req_id=ReqID, do_not_alter=1,
                            write_chunk=Req},
         Bin1a = machi_pb:encode_mpb_request(R1a),
@@ -281,13 +346,19 @@ do_send_sync2({write_chunk, File, Offset, Chunk, CSum},
             Res = {bummer, {X, Y, erlang:get_stacktrace()}},
             {Res, S#state{count=Count+1}}
     end;
-do_send_sync2({read_chunk, File, Offset, Size},
+do_send_sync2({read_chunk, File, Offset, Size, Opts},
              #state{sock=Sock, sock_id=Index, count=Count}=S) ->
     try
         ReqID = <<Index:64/big, Count:64/big>>,
-        Req = #mpb_readchunkreq{file=File,
+        #read_opts{no_checksum=FlagNoChecksum,
+                   no_chunk=FlagNoChunk,
+                   needs_trimmed=NeedsTrimmed} = Opts,
+        Req = #mpb_readchunkreq{chunk_pos=#mpb_chunkpos{file_name=File,
                                                         offset=Offset,
-                                size=Size},
+                                                        chunk_size=Size},
+                                flag_no_checksum=machi_util:bool2int(FlagNoChecksum),
+                                flag_no_chunk=machi_util:bool2int(FlagNoChunk),
+                                flag_needs_trimmed=machi_util:bool2int(NeedsTrimmed)},
         R1a = #mpb_request{req_id=ReqID, do_not_alter=1,
                            read_chunk=Req},
         Bin1a = machi_pb:encode_mpb_request(R1a),
@@ -309,9 +380,9 @@ do_send_sync2({trim_chunk, File, Offset, Size},
               #state{sock=Sock, sock_id=Index, count=Count}=S) ->
     try
         ReqID = <<Index:64/big, Count:64/big>>,
-        Req = #mpb_trimchunkreq{file=File,
+        Req = #mpb_trimchunkreq{chunk_pos=#mpb_chunkpos{file_name=File,
                                                         offset=Offset,
-                                size=Size},
+                                                        chunk_size=Size}},
         R1a = #mpb_request{req_id=ReqID, do_not_alter=1,
                            trim_chunk=Req},
         Bin1a = machi_pb:encode_mpb_request(R1a),
@@ -374,9 +445,15 @@ do_send_sync2({list_files},
             {Res, S#state{count=Count+1}}
     end.
 
+%% We only convert the checksum types that make sense here:
+%% none or client_sha.  None of the other types should be sent
+%% to us via the PB high protocol.
+
 convert_csum_req(none, Chunk) ->
     #mpb_chunkcsum{type='CSUM_TAG_CLIENT_SHA',
                    csum=machi_util:checksum_chunk(Chunk)};
+convert_csum_req(<<>>, Chunk) ->
+    convert_csum_req(none, Chunk);
 convert_csum_req({client_sha, CSumBin}, _Chunk) ->
     #mpb_chunkcsum{type='CSUM_TAG_CLIENT_SHA',
                    csum=CSumBin}.
@@ -401,6 +478,8 @@ convert_general_status_code('NOT_WRITTEN') ->
     {error, not_written};
 convert_general_status_code('WRITTEN') ->
     {error, written};
+convert_general_status_code('TRIMMED') ->
+    {error, trimmed};
 convert_general_status_code('NO_SUCH_FILE') ->
     {error, no_such_file};
 convert_general_status_code('PARTIAL_READ') ->
@@ -415,8 +494,21 @@ convert_write_chunk_resp(#mpb_writechunkresp{status='OK'}) ->
 convert_write_chunk_resp(#mpb_writechunkresp{status=Status}) ->
     convert_general_status_code(Status).
 
-convert_read_chunk_resp(#mpb_readchunkresp{status='OK', chunk=Chunk}) ->
+convert_read_chunk_resp(#mpb_readchunkresp{status='OK', chunks=PB_Chunks, trimmed=PB_Trimmed}) ->
-    {ok, Chunk};
+    Chunks = lists:map(fun(#mpb_chunk{offset=Offset,
+                                      file_name=File,
+                                      chunk=Chunk,
+                                      csum=#mpb_chunkcsum{type=T, csum=Ck}}) ->
+                               %% TODO: cleanup export
+                               Csum = <<(machi_pb_translate:conv_to_csum_tag(T)):8, Ck/binary>>,
+                               {list_to_binary(File), Offset, Chunk, Csum}
+                       end, PB_Chunks),
+    Trimmed = lists:map(fun(#mpb_chunkpos{file_name=File,
+                                          offset=Offset,
+                                          chunk_size=Size}) ->
+                                {list_to_binary(File), Offset, Size}
+                        end, PB_Trimmed),
+    {ok, {Chunks, Trimmed}};
 convert_read_chunk_resp(#mpb_readchunkresp{status=Status}) ->
     convert_general_status_code(Status).
 

src/machi_pb_translate.erl

@@ -15,8 +15,8 @@
 %% KIND, either express or implied.  See the License for the
 %% specific language governing permissions and limitations
 %% under the License.
-%%
 %% -------------------------------------------------------------------
+%%
 
 -module(machi_pb_translate).
 
@@ -34,85 +34,115 @@
 -export([from_pb_request/1,
          from_pb_response/1,
          to_pb_request/2,
-         to_pb_response/3
+         to_pb_response/3,
+         conv_from_append_opts/1,
+         conv_to_append_opts/1
         ]).
 
+%% TODO: fixme cleanup
+-export([conv_to_csum_tag/1]).
+
 from_pb_request(#mpb_ll_request{
                    req_id=ReqID,
                    echo=#mpb_echoreq{message=Msg}}) ->
-    {ReqID, {low_echo, undefined, Msg}};
+    {ReqID, {low_skip_wedge, {low_echo, Msg}}};
 from_pb_request(#mpb_ll_request{
                    req_id=ReqID,
                    auth=#mpb_authreq{user=User, password=Pass}}) ->
-    {ReqID, {low_auth, undefined, User, Pass}};
+    {ReqID, {low_skip_wedge, {low_auth, User, Pass}}};
 from_pb_request(#mpb_ll_request{
                    req_id=ReqID,
-                   append_chunk=#mpb_ll_appendchunkreq{
+                   append_chunk=IR=#mpb_ll_appendchunkreq{
+                     namespace_version=NSVersion,
+                     namespace=NS_str,
+                     locator=NSLocator,
                      epoch_id=PB_EpochID,
-                     placement_key=PKey,
                      prefix=Prefix,
                      chunk=Chunk,
-                     csum=#mpb_chunkcsum{type=CSum_type, csum=CSum},
+                     csum=#mpb_chunkcsum{type=CSum_type, csum=CSum}}}) ->
-                     chunk_extra=ChunkExtra}}) ->
+    NS = list_to_binary(NS_str),
     EpochID = conv_to_epoch_id(PB_EpochID),
     CSum_tag = conv_to_csum_tag(CSum_type),
-    {ReqID, {low_append_chunk, EpochID, PKey, Prefix, Chunk, CSum_tag, CSum,
+    Opts = conv_to_append_opts(IR),
-             ChunkExtra}};
+    %% NOTE: The tuple position of NSLocator is a bit odd, because EpochID
+    %%       _must_ be in the 4th position (as NSV & NS must be in 2nd & 3rd).
+    {ReqID, {low_append_chunk, NSVersion, NS, EpochID, NSLocator,
+             Prefix, Chunk, CSum_tag, CSum, Opts}};
 from_pb_request(#mpb_ll_request{
                    req_id=ReqID,
                    write_chunk=#mpb_ll_writechunkreq{
+                     namespace_version=NSVersion,
+                     namespace=NS_str,
                      epoch_id=PB_EpochID,
-                     file=File,
+                     chunk=#mpb_chunk{file_name=File,
                                       offset=Offset,
                                       chunk=Chunk,
-                     csum=#mpb_chunkcsum{type=CSum_type, csum=CSum}}}) ->
+                                      csum=#mpb_chunkcsum{type=CSum_type, csum=CSum}}}}) ->
+    NS = list_to_binary(NS_str),
     EpochID = conv_to_epoch_id(PB_EpochID),
     CSum_tag = conv_to_csum_tag(CSum_type),
-    {ReqID, {low_write_chunk, EpochID, File, Offset, Chunk, CSum_tag, CSum}};
+    {ReqID, {low_write_chunk, NSVersion, NS, EpochID, File, Offset, Chunk, CSum_tag, CSum}};
 from_pb_request(#mpb_ll_request{
                    req_id=ReqID,
                    read_chunk=#mpb_ll_readchunkreq{
+                                 namespace_version=NSVersion,
+                                 namespace=NS_str,
+                                 epoch_id=PB_EpochID,
+                                 chunk_pos=ChunkPos,
+                                 flag_no_checksum=PB_GetNoChecksum,
+                                 flag_no_chunk=PB_GetNoChunk,
+                                 flag_needs_trimmed=PB_NeedsTrimmed}}) ->
+    NS = list_to_binary(NS_str),
+    EpochID = conv_to_epoch_id(PB_EpochID),
+    Opts = #read_opts{no_checksum=PB_GetNoChecksum,
+                      no_chunk=PB_GetNoChunk,
+                      needs_trimmed=PB_NeedsTrimmed},
+    #mpb_chunkpos{file_name=File,
+                  offset=Offset,
+                  chunk_size=Size} = ChunkPos,
+    {ReqID, {low_read_chunk, NSVersion, NS, EpochID, File, Offset, Size, Opts}};
+from_pb_request(#mpb_ll_request{
+                   req_id=ReqID,
+                   trim_chunk=#mpb_ll_trimchunkreq{
+                     namespace_version=NSVersion,
+                     namespace=NS_str,
                      epoch_id=PB_EpochID,
                      file=File,
                      offset=Offset,
                      size=Size,
-                     flag_no_checksum=PB_GetNoChecksum,
+                     trigger_gc=TriggerGC}}) ->
-                     flag_no_chunk=PB_GetNoChunk}}) ->
+    NS = list_to_binary(NS_str),
     EpochID = conv_to_epoch_id(PB_EpochID),
-    Opts = [{no_checksum, conv_to_boolean(PB_GetNoChecksum)},
+    {ReqID, {low_trim_chunk, NSVersion, NS, EpochID, File, Offset, Size, TriggerGC}};
-            {no_chunk, conv_to_boolean(PB_GetNoChunk)}],
-    {ReqID, {low_read_chunk, EpochID, File, Offset, Size, Opts}};
 from_pb_request(#mpb_ll_request{
                    req_id=ReqID,
                    checksum_list=#mpb_ll_checksumlistreq{
-                     epoch_id=PB_EpochID,
                      file=File}}) ->
-    EpochID = conv_to_epoch_id(PB_EpochID),
+    {ReqID, {low_skip_wedge, {low_checksum_list, File}}};
-    {ReqID, {low_checksum_list, EpochID, File}};
 from_pb_request(#mpb_ll_request{
                    req_id=ReqID,
                    list_files=#mpb_ll_listfilesreq{
                      epoch_id=PB_EpochID}}) ->
     EpochID = conv_to_epoch_id(PB_EpochID),
-    {ReqID, {low_list_files, EpochID}};
+    {ReqID, {low_skip_wedge, {low_list_files, EpochID}}};
 from_pb_request(#mpb_ll_request{
                    req_id=ReqID,
                    wedge_status=#mpb_ll_wedgestatusreq{}}) ->
-    {ReqID, {low_wedge_status, undefined}};
+    {ReqID, {low_skip_wedge, {low_wedge_status}}};
 from_pb_request(#mpb_ll_request{
                    req_id=ReqID,
                    delete_migration=#mpb_ll_deletemigrationreq{
                     epoch_id=PB_EpochID,
                     file=File}}) ->
     EpochID = conv_to_epoch_id(PB_EpochID),
-    {ReqID, {low_delete_migration, EpochID, File}};
+    {ReqID, {low_skip_wedge, {low_delete_migration, EpochID, File}}};
 from_pb_request(#mpb_ll_request{
                    req_id=ReqID,
                    trunc_hack=#mpb_ll_trunchackreq{
                     epoch_id=PB_EpochID,
                     file=File}}) ->
     EpochID = conv_to_epoch_id(PB_EpochID),
-    {ReqID, {low_trunc_hack, EpochID, File}};
+    {ReqID, {low_skip_wedge, {low_trunc_hack, EpochID, File}}};
 from_pb_request(#mpb_ll_request{
                    req_id=ReqID,
                    proj_gl=#mpb_ll_getlatestepochidreq{type=ProjType}}) ->
@@ -153,33 +183,39 @@ from_pb_request(#mpb_request{req_id=ReqID,
     {ReqID, {high_auth, User, Pass}};
 from_pb_request(#mpb_request{req_id=ReqID,
                              append_chunk=IR=#mpb_appendchunkreq{}}) ->
-    #mpb_appendchunkreq{placement_key=__todoPK,
+    #mpb_appendchunkreq{namespace=NS_str,
                         prefix=Prefix,
                         chunk=Chunk,
-                        csum=CSum,
+                        csum=CSum} = IR,
-                        chunk_extra=ChunkExtra} = IR,
+    NS = list_to_binary(NS_str),
     TaggedCSum = make_tagged_csum(CSum, Chunk),
-    {ReqID, {high_append_chunk, __todoPK, Prefix, Chunk, TaggedCSum,
+    Opts = conv_to_append_opts(IR),
-             ChunkExtra}};
+    {ReqID, {high_append_chunk, NS, Prefix, Chunk, TaggedCSum, Opts}};
 from_pb_request(#mpb_request{req_id=ReqID,
                              write_chunk=IR=#mpb_writechunkreq{}}) ->
-    #mpb_writechunkreq{file=File,
+    #mpb_writechunkreq{chunk=#mpb_chunk{file_name=File,
                                         offset=Offset,
                                         chunk=Chunk,
-                       csum=CSum} = IR,
+                                        csum=CSumRec}} = IR,
-    TaggedCSum = make_tagged_csum(CSum, Chunk),
+    CSum = make_tagged_csum(CSumRec, Chunk),
-    {ReqID, {high_write_chunk, File, Offset, Chunk, TaggedCSum}};
+    {ReqID, {high_write_chunk, File, Offset, Chunk, CSum}};
 from_pb_request(#mpb_request{req_id=ReqID,
                              read_chunk=IR=#mpb_readchunkreq{}}) ->
-    #mpb_readchunkreq{file=File,
+    #mpb_readchunkreq{chunk_pos=#mpb_chunkpos{file_name=File,
                                               offset=Offset,
-                      size=Size} = IR,
+                                              chunk_size=Size},
-    {ReqID, {high_read_chunk, File, Offset, Size}};
+                     flag_no_checksum=FlagNoChecksum,
+                     flag_no_chunk=FlagNoChunk,
+                     flag_needs_trimmed=NeedsTrimmed} = IR,
+    Opts = #read_opts{no_checksum=FlagNoChecksum,
+                      no_chunk=FlagNoChunk,
+                      needs_trimmed=NeedsTrimmed},
+    {ReqID, {high_read_chunk, File, Offset, Size, Opts}};
 from_pb_request(#mpb_request{req_id=ReqID,
                              trim_chunk=IR=#mpb_trimchunkreq{}}) ->
-    #mpb_trimchunkreq{file=File,
+    #mpb_trimchunkreq{chunk_pos=#mpb_chunkpos{file_name=File,
                                               offset=Offset,
-                      size=Size} = IR,
+                                              chunk_size=Size}} = IR,
     {ReqID, {high_trim_chunk, File, Offset, Size}};
 from_pb_request(#mpb_request{req_id=ReqID,
                              checksum_list=IR=#mpb_checksumlistreq{}}) ->
@@ -229,13 +265,30 @@ from_pb_response(#mpb_ll_response{
 from_pb_response(#mpb_ll_response{
                     req_id=ReqID,
                     read_chunk=#mpb_ll_readchunkresp{status=Status,
-                                                     chunk=Chunk}}) ->
+                                                     chunks=PB_Chunks,
+                                                     trimmed=PB_Trimmed}}) ->
     case Status of
         'OK' ->
-            {ReqID, {ok, Chunk}};
+            Chunks = lists:map(fun(#mpb_chunk{file_name=File,
+                                          offset=Offset,
+                                          chunk=Bytes,
+                                          csum=#mpb_chunkcsum{type=T,csum=Ck}}) ->
+                                       Csum = <<(conv_to_csum_tag(T)):8, Ck/binary>>,
+                                      {list_to_binary(File), Offset, Bytes, Csum}
+                              end, PB_Chunks),
+            Trimmed = lists:map(fun(#mpb_chunkpos{file_name=File,
+                                                  offset=Offset,
+                                                  chunk_size=Size}) ->
+                                        {list_to_binary(File), Offset, Size}
+                                end, PB_Trimmed),
+            {ReqID, {ok, {Chunks, Trimmed}}};
         _ ->
             {ReqID, machi_pb_high_client:convert_general_status_code(Status)}
     end;
+from_pb_response(#mpb_ll_response{
+                    req_id=ReqID,
+                    trim_chunk=#mpb_ll_trimchunkresp{status=Status}}) ->
+    {ReqID, machi_pb_high_client:convert_general_status_code(Status)};
 from_pb_response(#mpb_ll_response{
                     req_id=ReqID,
                     checksum_list=#mpb_ll_checksumlistresp{
@@ -262,12 +315,16 @@ from_pb_response(#mpb_ll_response{
 from_pb_response(#mpb_ll_response{
                     req_id=ReqID,
                     wedge_status=#mpb_ll_wedgestatusresp{
-                      epoch_id=PB_EpochID, wedged_flag=PB_Wedged}}) ->
+                      status=Status,
-    EpochID = conv_to_epoch_id(PB_EpochID),
+                      epoch_id=PB_EpochID, wedged_flag=Wedged_p,
-    Wedged_p = if PB_Wedged == 1 -> true;
+                      namespace_version=NSVersion, namespace=NS_str}}) ->
-                  PB_Wedged == 0 -> false
+    GeneralStatus = case machi_pb_high_client:convert_general_status_code(Status) of
+                        ok    -> ok;
+                        _Else -> {yukky, _Else}
                     end,
-    {ReqID, {ok, {Wedged_p, EpochID}}};
+    EpochID = conv_to_epoch_id(PB_EpochID),
+    NS = list_to_binary(NS_str),
+    {ReqID, {GeneralStatus, {Wedged_p, EpochID, NSVersion, NS}}};
 from_pb_response(#mpb_ll_response{
                     req_id=ReqID,
                     delete_migration=#mpb_ll_deletemigrationresp{
@@ -333,74 +390,100 @@ from_pb_response(#mpb_ll_response{
         'OK' ->
             {ReqID, {ok, Epochs}};
         _ ->
-            {ReqID< machi_pb_high_client:convert_general_status_code(Status)}
+            {ReqID, machi_pb_high_client:convert_general_status_code(Status)}
     end.
 %% No response for proj_kp/kick_projection_reaction
 
 %% TODO: move the #mbp_* record making code from
 %%       machi_pb_high_client:do_send_sync() clauses into to_pb_request().
 
-to_pb_request(ReqID, {low_echo, _BogusEpochID, Msg}) ->
+to_pb_request(ReqID, {low_skip_wedge, {low_echo, Msg}}) ->
     #mpb_ll_request{
                req_id=ReqID, do_not_alter=2,
                echo=#mpb_echoreq{message=Msg}};
-to_pb_request(ReqID, {low_auth, _BogusEpochID, User, Pass}) ->
+to_pb_request(ReqID, {low_skip_wedge, {low_auth, User, Pass}}) ->
     #mpb_ll_request{req_id=ReqID, do_not_alter=2,
                     auth=#mpb_authreq{user=User, password=Pass}};
-to_pb_request(ReqID, {low_append_chunk, EpochID, PKey, Prefix, Chunk,
+%% NOTE: The tuple position of NSLocator is a bit odd, because EpochID
-                      CSum_tag, CSum, ChunkExtra}) ->
+%%       _must_ be in the 4th position (as NSV & NS must be in 2nd & 3rd).
+to_pb_request(ReqID, {low_append_chunk, NSVersion, NS, EpochID, NSLocator,
+                      Prefix, Chunk, CSum_tag, CSum, Opts}) ->
     PB_EpochID = conv_from_epoch_id(EpochID),
     CSum_type = conv_from_csum_tag(CSum_tag),
     PB_CSum = #mpb_chunkcsum{type=CSum_type, csum=CSum},
+    {ChunkExtra, Pref, FailPref} = conv_from_append_opts(Opts),
     #mpb_ll_request{req_id=ReqID, do_not_alter=2,
                     append_chunk=#mpb_ll_appendchunkreq{
+                      namespace_version=NSVersion,
+                      namespace=NS,
+                      locator=NSLocator,
                       epoch_id=PB_EpochID,
-                      placement_key=PKey,
                       prefix=Prefix,
                       chunk=Chunk,
                       csum=PB_CSum,
-                      chunk_extra=ChunkExtra}};
+                      chunk_extra=ChunkExtra,
-to_pb_request(ReqID, {low_write_chunk, EpochID, File, Offset, Chunk, CSum_tag, CSum}) ->
+                      preferred_file_name=Pref,
+                      flag_fail_preferred=FailPref}};
+to_pb_request(ReqID, {low_write_chunk, NSVersion, NS, EpochID, File, Offset, Chunk, CSum_tag, CSum}) ->
     PB_EpochID = conv_from_epoch_id(EpochID),
     CSum_type = conv_from_csum_tag(CSum_tag),
     PB_CSum = #mpb_chunkcsum{type=CSum_type, csum=CSum},
     #mpb_ll_request{req_id=ReqID, do_not_alter=2,
                     write_chunk=#mpb_ll_writechunkreq{
+                      namespace_version=NSVersion,
+                      namespace=NS,
                       epoch_id=PB_EpochID,
-                      file=File,
+                                   chunk=#mpb_chunk{file_name=File,
                                                     offset=Offset,
                                                     chunk=Chunk,
-                      csum=PB_CSum}};
+                                                    csum=PB_CSum}}};
-to_pb_request(ReqID, {low_read_chunk, EpochID, File, Offset, Size, _Opts}) ->
+to_pb_request(ReqID, {low_read_chunk, NSVersion, NS, EpochID, File, Offset, Size, Opts}) ->
-    %% TODO: stop ignoring Opts ^_^
     PB_EpochID = conv_from_epoch_id(EpochID),
+    #read_opts{no_checksum=FNChecksum,
+               no_chunk=FNChunk,
+               needs_trimmed=NeedsTrimmed} = Opts,
     #mpb_ll_request{
                req_id=ReqID, do_not_alter=2,
                read_chunk=#mpb_ll_readchunkreq{
+                            namespace_version=NSVersion,
+                            namespace=NS,
+                            epoch_id=PB_EpochID,
+                            chunk_pos=#mpb_chunkpos{
+                                          file_name=File,
+                                          offset=Offset,
+                                          chunk_size=Size},
+                            flag_no_checksum=FNChecksum,
+                            flag_no_chunk=FNChunk,
+                            flag_needs_trimmed=NeedsTrimmed}};
+to_pb_request(ReqID, {low_trim_chunk, NSVersion, NS, EpochID, File, Offset, Size, TriggerGC}) ->
+    PB_EpochID = conv_from_epoch_id(EpochID),
+    #mpb_ll_request{req_id=ReqID, do_not_alter=2,
+                    trim_chunk=#mpb_ll_trimchunkreq{
+                                  namespace_version=NSVersion,
+                                  namespace=NS,
                                   epoch_id=PB_EpochID,
                                   file=File,
                                   offset=Offset,
-                 size=Size}};
+                                  size=Size,
-to_pb_request(ReqID, {low_checksum_list, EpochID, File}) ->
+                                  trigger_gc=TriggerGC}};
-    PB_EpochID = conv_from_epoch_id(EpochID),
+to_pb_request(ReqID, {low_skip_wedge, {low_checksum_list, File}}) ->
     #mpb_ll_request{req_id=ReqID, do_not_alter=2,
                     checksum_list=#mpb_ll_checksumlistreq{
-                      epoch_id=PB_EpochID,
                       file=File}};
-to_pb_request(ReqID, {low_list_files, EpochID}) ->
+to_pb_request(ReqID, {low_skip_wedge, {low_list_files, EpochID}}) ->
     PB_EpochID = conv_from_epoch_id(EpochID),
     #mpb_ll_request{req_id=ReqID, do_not_alter=2,
                     list_files=#mpb_ll_listfilesreq{epoch_id=PB_EpochID}};
-to_pb_request(ReqID, {low_wedge_status, _BogusEpochID}) ->
+to_pb_request(ReqID, {low_skip_wedge, {low_wedge_status}}) ->
     #mpb_ll_request{req_id=ReqID, do_not_alter=2,
                     wedge_status=#mpb_ll_wedgestatusreq{}};
-to_pb_request(ReqID, {low_delete_migration, EpochID, File}) ->
+to_pb_request(ReqID, {low_skip_wedge, {low_delete_migration, EpochID, File}}) ->
     PB_EpochID = conv_from_epoch_id(EpochID),
     #mpb_ll_request{req_id=ReqID, do_not_alter=2,
                     delete_migration=#mpb_ll_deletemigrationreq{
                      epoch_id=PB_EpochID,
                       file=File}};
-to_pb_request(ReqID, {low_trunc_hack, EpochID, File}) ->
+to_pb_request(ReqID, {low_skip_wedge, {low_trunc_hack, EpochID, File}}) ->
     PB_EpochID = conv_from_epoch_id(EpochID),
     #mpb_ll_request{req_id=ReqID, do_not_alter=2,
                     trunc_hack=#mpb_ll_trunchackreq{
@@ -436,15 +519,15 @@ to_pb_response(_ReqID, _, async_no_response=X) ->
     X;
 to_pb_response(ReqID, _, {low_error, ErrCode, ErrMsg}) ->
     make_ll_error_resp(ReqID, ErrCode, ErrMsg);
-to_pb_response(ReqID, {low_echo, _BogusEpochID, _Msg}, Resp) ->
+to_pb_response(ReqID, {low_skip_wedge, {low_echo, _Msg}}, Resp) ->
     #mpb_ll_response{
                 req_id=ReqID,
                 echo=#mpb_echoresp{message=Resp}};
-to_pb_response(ReqID, {low_auth, _, _, _}, __TODO_Resp) ->
+to_pb_response(ReqID, {low_skip_wedge, {low_auth, _, _}}, __TODO_Resp) ->
     #mpb_ll_response{req_id=ReqID,
                      generic=#mpb_errorresp{code=1,
                                             msg="AUTH not implemented"}};
-to_pb_response(ReqID, {low_append_chunk, _EID, _PKey, _Pfx, _Ch, _CST, _CS, _CE}, Resp)->
+to_pb_response(ReqID, {low_append_chunk, _NSV, _NS, _EID, _NSL, _Pfx, _Ch, _CST, _CS, _O}, Resp)->
     case Resp of
         {ok, {Offset, Size, File}} ->
             Where = #mpb_chunkpos{offset=Offset,
@@ -460,18 +543,30 @@ to_pb_response(ReqID, {low_append_chunk, _EID, _PKey, _Pfx, _Ch, _CST, _CS, _CE}
         _Else ->
             make_ll_error_resp(ReqID, 66, io_lib:format("err ~p", [_Else]))
     end;
-to_pb_response(ReqID, {low_write_chunk, _EID, _Fl, _Off, _Ch, _CST, _CS},Resp)->
+to_pb_response(ReqID, {low_write_chunk, _NSV, _NS, _EID, _Fl, _Off, _Ch, _CST, _CS},Resp)->
     Status = conv_from_status(Resp),
     #mpb_ll_response{req_id=ReqID,
                      write_chunk=#mpb_ll_writechunkresp{status=Status}};
-to_pb_response(ReqID, {low_read_chunk, _EID, _Fl, _Off, _Sz, _Opts}, Resp)->
+to_pb_response(ReqID, {low_read_chunk, _NSV, _NS, _EID, _Fl, _Off, _Sz, _Opts}, Resp)->
     case Resp of
-        {ok, Chunk} ->
+        {ok, {Chunks, Trimmed}} ->
-            CSum = undefined,                   % TODO not implemented
+            PB_Chunks = lists:map(fun({File, Offset, Bytes, Csum}) ->
+                                          {Tag, Ck} = machi_util:unmake_tagged_csum(Csum),
+                                          #mpb_chunk{file_name=File,
+                                                     offset=Offset,
+                                                     chunk=Bytes,
+                                                     csum=#mpb_chunkcsum{type=conv_from_csum_tag(Tag),
+                                                                         csum=Ck}}
+                                  end, Chunks),
+            PB_Trimmed = lists:map(fun({File, Offset, Size}) ->
+                                           #mpb_chunkpos{file_name=File,
+                                                         offset=Offset,
+                                                         chunk_size=Size}
+                                   end, Trimmed),
             #mpb_ll_response{req_id=ReqID,
                              read_chunk=#mpb_ll_readchunkresp{status='OK',
-                                                              chunk=Chunk,
+                                                              chunks=PB_Chunks,
-                                                              csum=CSum}};
+                                                              trimmed=PB_Trimmed}};
         {error, _}=Error ->
             Status = conv_from_status(Error),
             #mpb_ll_response{req_id=ReqID,
@@ -479,7 +574,19 @@ to_pb_response(ReqID, {low_read_chunk, _EID, _Fl, _Off, _Sz, _Opts}, Resp)->
         _Else ->
             make_ll_error_resp(ReqID, 66, io_lib:format("err ~p", [_Else]))
     end;
-to_pb_response(ReqID, {low_checksum_list, _EpochID, _File}, Resp) ->
+to_pb_response(ReqID, {low_trim_chunk, _, _, _, _, _, _, _}, Resp) ->
+    case Resp of
+        ok ->
+            #mpb_ll_response{req_id=ReqID,
+                             trim_chunk=#mpb_ll_trimchunkresp{status='OK'}};
+        {error, _}=Error ->
+            Status = conv_from_status(Error),
+            #mpb_ll_response{req_id=ReqID,
+                             trim_chunk=#mpb_ll_trimchunkresp{status=Status}};
+        _Else ->
+            make_ll_error_resp(ReqID, 66, io_lib:format("err ~p", [_Else]))
+    end;
+to_pb_response(ReqID, {low_skip_wedge, {low_checksum_list, _File}}, Resp) ->
     case Resp of
         {ok, Chunk} ->
             #mpb_ll_response{req_id=ReqID,
@@ -492,7 +599,7 @@ to_pb_response(ReqID, {low_checksum_list, _EpochID, _File}, Resp) ->
         _Else ->
             make_ll_error_resp(ReqID, 66, io_lib:format("err ~p", [_Else]))
     end;
-to_pb_response(ReqID, {low_list_files, _EpochID}, Resp) ->
+to_pb_response(ReqID, {low_skip_wedge, {low_list_files, _EpochID}}, Resp) ->
     case Resp of
         {ok, FileInfo} ->
             PB_Files = [#mpb_fileinfo{file_size=Size, file_name=Name} ||
@@ -507,26 +614,28 @@ to_pb_response(ReqID, {low_list_files, _EpochID}, Resp) ->
         _Else ->
             make_ll_error_resp(ReqID, 66, io_lib:format("err ~p", [_Else]))
     end;
-to_pb_response(ReqID, {low_wedge_status, _BogusEpochID}, Resp) ->
+to_pb_response(ReqID, {low_skip_wedge, {low_wedge_status}}, Resp) ->
     case Resp of
         {error, _}=Error ->
             Status = conv_from_status(Error),
             #mpb_ll_response{req_id=ReqID,
                            wedge_status=#mpb_ll_wedgestatusresp{status=Status}};
-        {Wedged_p, EpochID} ->
+        {Wedged_p, EpochID, NSVersion, NS} ->
-            PB_Wedged = conv_from_boolean(Wedged_p),
             PB_EpochID = conv_from_epoch_id(EpochID),
             #mpb_ll_response{req_id=ReqID,
                              wedge_status=#mpb_ll_wedgestatusresp{
                                status='OK',
                                epoch_id=PB_EpochID,
-                               wedged_flag=PB_Wedged}}
+                               wedged_flag=Wedged_p,
+                               namespace_version=NSVersion,
+                               namespace=NS
+                              }}
     end;
-to_pb_response(ReqID, {low_delete_migration, _EID, _Fl}, Resp)->
+to_pb_response(ReqID, {low_skip_wedge, {low_delete_migration, _EID, _Fl}}, Resp)->
     Status = conv_from_status(Resp),
     #mpb_ll_response{req_id=ReqID,
                    delete_migration=#mpb_ll_deletemigrationresp{status=Status}};
-to_pb_response(ReqID, {low_trunc_hack, _EID, _Fl}, Resp)->
+to_pb_response(ReqID, {low_skip_wedge, {low_trunc_hack, _EID, _Fl}}, Resp)->
     Status = conv_from_status(Resp),
     #mpb_ll_response{req_id=ReqID,
                      trunc_hack=#mpb_ll_trunchackresp{status=Status}};
@@ -607,7 +716,7 @@ to_pb_response(ReqID, {high_auth, _User, _Pass}, _Resp) ->
     #mpb_response{req_id=ReqID,
                   generic=#mpb_errorresp{code=1,
                                          msg="AUTH not implemented"}};
-to_pb_response(ReqID, {high_append_chunk, _TODO, _Prefix, _Chunk, _TSum, _CE}, Resp)->
+to_pb_response(ReqID, {high_append_chunk, _NS, _Prefix, _Chunk, _TSum, _O}, Resp)->
     case Resp of
         {ok, {Offset, Size, File}} ->
             Where = #mpb_chunkpos{offset=Offset,
@@ -623,7 +732,7 @@ to_pb_response(ReqID, {high_append_chunk, _TODO, _Prefix, _Chunk, _TSum, _CE}, R
         _Else ->
             make_error_resp(ReqID, 66, io_lib:format("err ~p", [_Else]))
     end;
-to_pb_response(ReqID, {high_write_chunk, _File, _Offset, _Chunk, _TaggedCSum}, Resp) ->
+to_pb_response(ReqID, {high_write_chunk, _File, _Offset, _Chunk, _CSum}, Resp) ->
     case Resp of
         {ok, {_,_,_}} ->
             %% machi_cr_client returns ok 2-tuple, convert to simple ok.
@@ -636,12 +745,26 @@ to_pb_response(ReqID, {high_write_chunk, _File, _Offset, _Chunk, _TaggedCSum}, R
         _Else ->
             make_error_resp(ReqID, 66, io_lib:format("err ~p", [_Else]))
     end;
-to_pb_response(ReqID, {high_read_chunk, _File, _Offset, _Size}, Resp) ->
+to_pb_response(ReqID, {high_read_chunk, _File, _Offset, _Size, _}, Resp) ->
     case Resp of
-        {ok, Chunk} ->
+        {ok, {Chunks, Trimmed}} ->
+            PB_Chunks = lists:map(fun({File, Offset, Bytes, Csum}) ->
+                                          {Tag, Ck} = machi_util:unmake_tagged_csum(Csum),
+                                          #mpb_chunk{
+                                             offset=Offset,
+                                             file_name=File,
+                                             chunk=Bytes,
+                                             csum=#mpb_chunkcsum{type=conv_from_csum_tag(Tag), csum=Ck}}
+                                  end, Chunks),
+            PB_Trimmed = lists:map(fun({File, Offset, Size}) ->
+                                           #mpb_chunkpos{file_name=File,
+                                                         offset=Offset,
+                                                         chunk_size=Size}
+                                   end, Trimmed),
             #mpb_response{req_id=ReqID,
                           read_chunk=#mpb_readchunkresp{status='OK',
-                                                        chunk=Chunk}};
+                                                        chunks=PB_Chunks,
+                                                        trimmed=PB_Trimmed}};
         {error, _}=Error ->
             Status = conv_from_status(Error),
             #mpb_response{req_id=ReqID,
@@ -717,6 +840,7 @@ conv_to_epoch_id(#mpb_epochid{epoch_number=Epoch,
 conv_to_projection_v1(#mpb_projectionv1{epoch_number=Epoch,
                                         epoch_csum=CSum,
                                         author_server=Author,
+                                        chain_name=ChainName,
                                         all_members=AllMembers,
                                         witnesses=Witnesses,
                                         creation_time=CTime,
@@ -730,6 +854,7 @@ conv_to_projection_v1(#mpb_projectionv1{epoch_number=Epoch,
     #projection_v1{epoch_number=Epoch,
                    epoch_csum=CSum,
                    author_server=to_atom(Author),
+                   chain_name=to_atom(ChainName),
                    all_members=[to_atom(X) || X <- AllMembers],
                    witnesses=[to_atom(X) || X <- Witnesses],
                    creation_time=conv_to_now(CTime),
@@ -850,6 +975,8 @@ conv_from_status({error, not_written}) ->
     'NOT_WRITTEN';
 conv_from_status({error, written}) ->
     'WRITTEN';
+conv_from_status({error, trimmed}) ->
+    'TRIMMED';
 conv_from_status({error, no_such_file}) ->
     'NO_SUCH_FILE';
 conv_from_status({error, partial_read}) ->
@@ -857,24 +984,34 @@ conv_from_status({error, partial_read}) ->
 conv_from_status({error, bad_epoch}) ->
     'BAD_EPOCH';
 conv_from_status(_OOPS) ->
-    io:format(user, "HEY, ~s:~w got ~w\n", [?MODULE, ?LINE, _OOPS]),
+    io:format(user, "HEY, ~s:~w got ~p\n", [?MODULE, ?LINE, _OOPS]),
     'BAD_JOSS'.
 
-conv_to_boolean(undefined) ->
+conv_from_append_opts(#append_opts{chunk_extra=ChunkExtra,
-    false;
+                                   preferred_file_name=Pref,
-conv_to_boolean(0) ->
+                                   flag_fail_preferred=FailPref}) ->
-    false;
+    {ChunkExtra, Pref, FailPref}.
-conv_to_boolean(N) when is_integer(N) ->
-    true.
 
-conv_from_boolean(false) ->
+
-    0;
+conv_to_append_opts(#mpb_appendchunkreq{
-conv_from_boolean(true) ->
+                       chunk_extra=ChunkExtra,
-    1.
+                       preferred_file_name=Pref,
+                       flag_fail_preferred=FailPref}) ->
+    #append_opts{chunk_extra=ChunkExtra,
+                 preferred_file_name=Pref,
+                 flag_fail_preferred=FailPref};
+conv_to_append_opts(#mpb_ll_appendchunkreq{
+                       chunk_extra=ChunkExtra,
+                       preferred_file_name=Pref,
+                       flag_fail_preferred=FailPref}) ->
+    #append_opts{chunk_extra=ChunkExtra,
+                 preferred_file_name=Pref,
+                 flag_fail_preferred=FailPref}.
 
 conv_from_projection_v1(#projection_v1{epoch_number=Epoch,
                                        epoch_csum=CSum,
                                        author_server=Author,
+                                       chain_name=ChainName,
                                        all_members=AllMembers,
                                        witnesses=Witnesses,
                                        creation_time=CTime,
@@ -888,6 +1025,7 @@ conv_from_projection_v1(#projection_v1{epoch_number=Epoch,
     #mpb_projectionv1{epoch_number=Epoch,
                       epoch_csum=CSum,
                       author_server=to_list(Author),
+                      chain_name=to_list(ChainName),
                       all_members=[to_list(X) || X <- AllMembers],
                       witnesses=[to_list(X) || X <- Witnesses],
                       creation_time=conv_from_now(CTime),

src/machi_plist.erl

@@ -0,0 +1,89 @@
+%% -------------------------------------------------------------------
+%%
+%% Copyright (c) 2007-2016 Basho Technologies, Inc.  All Rights Reserved.
+%%
+%% This file is provided to you under the Apache License,
+%% Version 2.0 (the "License"); you may not use this file
+%% except in compliance with the License.  You may obtain
+%% a copy of the License at
+%%
+%%   http://www.apache.org/licenses/LICENSE-2.0
+%%
+%% Unless required by applicable law or agreed to in writing,
+%% software distributed under the License is distributed on an
+%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+%% KIND, either express or implied.  See the License for the
+%% specific language governing permissions and limitations
+%% under the License.
+%%
+%% -------------------------------------------------------------------
+
+-module(machi_plist).
+
+%%% @doc persistent list of binaries
+
+-export([open/2, close/1, find/2, add/2]).
+
+-ifdef(TEST).
+-export([all/1]).
+-endif.
+
+-record(machi_plist,
+        {filename :: file:filename_all(),
+         fd :: file:io_device(),
+         list = [] :: list(string)}).
+
+-type plist() :: #machi_plist{}.
+-export_type([plist/0]).
+
+-spec open(file:filename_all(), proplists:proplist()) ->
+                  {ok, plist()} | {error, file:posix()}.
+open(Filename, _Opt) ->
+    %% TODO: This decode could fail if the file didn't finish writing
+    %% whole contents, which should be fixed by some persistent
+    %% solution.
+    List = case file:read_file(Filename) of
+               {ok, <<>>} -> [];
+               {ok, Bin} -> binary_to_term(Bin);
+               {error, enoent} -> []
+           end,
+    case file:open(Filename, [read, write, raw, binary, sync]) of
+        {ok, Fd} ->
+            {ok, #machi_plist{filename=Filename,
+                              fd=Fd,
+                              list=List}};
+        Error ->
+            Error
+    end.
+
+-spec close(plist()) -> ok.
+close(#machi_plist{fd=Fd}) ->
+    _ = file:close(Fd).
+
+-spec find(plist(), string()) -> boolean().
+find(#machi_plist{list=List}, Name) ->
+    lists:member(Name, List).
+
+-spec add(plist(), string()) -> {ok, plist()} | {error, file:posix()}.
+add(Plist = #machi_plist{list=List0, fd=Fd}, Name) ->
+    case find(Plist, Name) of
+        true ->
+            {ok, Plist};
+        false ->
+            List = lists:append(List0, [Name]),
+            %% TODO: partial write could break the file with other
+            %% persistent info (even lose data of trimmed states);
+            %% needs a solution.
+            case file:pwrite(Fd, 0, term_to_binary(List)) of
+                ok ->
+                    {ok, Plist#machi_plist{list=List}};
+                Error ->
+                    Error
+            end
+    end.
+
+-ifdef(TEST).
+-spec all(plist()) -> [file:filename()].
+all(#machi_plist{list=List}) ->
+    List.
+-endif.

src/machi_projection.erl

@@ -174,6 +174,7 @@ make_summary(#projection_v1{epoch_number=EpochNum,
                             repairing=Repairing_list,
                             dbg=Dbg, dbg2=Dbg2}) ->
     [{epoch,EpochNum}, {csum,_CSum4},
+{all, _All_list},
      {author,Author}, {mode,CMode},{witnesses, Witness_list},
      {upi,UPI_list},{repair,Repairing_list},{down,Down_list}] ++
         [{d,Dbg}, {d2,Dbg2}].

src/machi_projection_store.erl

@@ -321,7 +321,7 @@ do_proj_write3(ProjType, #projection_v1{epoch_number=Epoch,
     end.
 
 do_proj_write4(ProjType, Proj, Path, Epoch, #state{consistency_mode=CMode}=S) ->
-    {ok, FH} = file:open(Path, [write, raw, binary]),
+    {{ok, FH}, Epoch, Path} = {file:open(Path, [write, raw, binary]), Epoch, Path},
     ok = file:write(FH, term_to_binary(Proj)),
     ok = file:sync(FH),
     ok = file:close(FH),
@@ -387,7 +387,6 @@ wait_for_liveness(PidSpec, StartTime, WaitTime) ->
         undefined ->
             case timer:now_diff(os:timestamp(), StartTime) div 1000 of
                 X when X < WaitTime ->
-                    io:format(user, "\nYOO ~p ~p\n", [PidSpec, lists:sort(registered())]),
                     timer:sleep(1),
                     wait_for_liveness(PidSpec, StartTime, WaitTime)
             end;

src/machi_proxy_flu1_client.erl

@@ -22,6 +22,10 @@
 %% proxy-process style API for hiding messy details such as TCP
 %% connection/disconnection with the remote Machi server.
 %%
+%% Please see {@link machi_flu1_client} the "Client API implemntation notes"
+%% section for how this module relates to the rest of the client API
+%% implementation.
+%%
 %% Machi is intentionally avoiding using distributed Erlang for
 %% Machi's communication.  This design decision makes Erlang-side code
 %% more difficult & complex, but it's the price to pay for some
@@ -57,10 +61,9 @@
 %% FLU1 API
 -export([
          %% File API
-         append_chunk/4, append_chunk/5,
+         append_chunk/6, append_chunk/8,
-         append_chunk_extra/5, append_chunk_extra/6,
+         read_chunk/7, read_chunk/8,
-         read_chunk/5, read_chunk/6,
+         checksum_list/2, checksum_list/3,
-         checksum_list/3, checksum_list/4,
          list_files/2, list_files/3,
          wedge_status/1, wedge_status/2,
 
@@ -78,7 +81,8 @@
          quit/1,
 
          %% Internal API
-         write_chunk/5, write_chunk/6,
+         write_chunk/7, write_chunk/8,
+         trim_chunk/6, trim_chunk/7,
 
          %% Helpers
          stop_proxies/1, start_proxies/1
@@ -103,51 +107,39 @@ start_link(#p_srvr{}=I) ->
 %% @doc Append a chunk (binary- or iolist-style) of data to a file
 %% with `Prefix'.
 
-append_chunk(PidSpec, EpochID, Prefix, Chunk) ->
+append_chunk(PidSpec, NSInfo, EpochID, Prefix, Chunk, CSum) ->
-    append_chunk(PidSpec, EpochID, Prefix, Chunk, infinity).
+    append_chunk(PidSpec, NSInfo, EpochID, Prefix, Chunk, CSum,
+                 #append_opts{}, infinity).
 
 %% @doc Append a chunk (binary- or iolist-style) of data to a file
 %% with `Prefix'.
 
-append_chunk(PidSpec, EpochID, Prefix, Chunk, Timeout) ->
+append_chunk(PidSpec, NSInfo, EpochID, Prefix, Chunk, CSum, Opts,
-    gen_server:call(PidSpec, {req, {append_chunk, EpochID, Prefix, Chunk}},
+             Timeout) ->
-                    Timeout).
+    gen_server:call(PidSpec, {req, {append_chunk, NSInfo, EpochID,
-
+                                    Prefix, Chunk, CSum, Opts, Timeout}},
-%% @doc Append a chunk (binary- or iolist-style) of data to a file
-%% with `Prefix'.
-
-append_chunk_extra(PidSpec, EpochID, Prefix, Chunk, ChunkExtra)
-  when is_integer(ChunkExtra), ChunkExtra >= 0 ->
-    append_chunk_extra(PidSpec, EpochID, Prefix, Chunk, ChunkExtra, infinity).
-
-%% @doc Append a chunk (binary- or iolist-style) of data to a file
-%% with `Prefix'.
-
-append_chunk_extra(PidSpec, EpochID, Prefix, Chunk, ChunkExtra, Timeout) ->
-    gen_server:call(PidSpec, {req, {append_chunk_extra, EpochID, Prefix,
-                                    Chunk, ChunkExtra}},
                     Timeout).
 
 %% @doc Read a chunk of data of size `Size' from `File' at `Offset'.
 
-read_chunk(PidSpec, EpochID, File, Offset, Size) ->
+read_chunk(PidSpec, NSInfo, EpochID, File, Offset, Size, Opts) ->
-    read_chunk(PidSpec, EpochID, File, Offset, Size, infinity).
+    read_chunk(PidSpec, NSInfo, EpochID, File, Offset, Size, Opts, infinity).
 
 %% @doc Read a chunk of data of size `Size' from `File' at `Offset'.
 
-read_chunk(PidSpec, EpochID, File, Offset, Size, Timeout) ->
+read_chunk(PidSpec, NSInfo, EpochID, File, Offset, Size, Opts, Timeout) ->
-    gen_server:call(PidSpec, {req, {read_chunk, EpochID, File, Offset, Size}},
+    gen_server:call(PidSpec, {req, {read_chunk, NSInfo, EpochID, File, Offset, Size, Opts}},
                     Timeout).
 
 %% @doc Fetch the list of chunk checksums for `File'.
 
-checksum_list(PidSpec, EpochID, File) ->
+checksum_list(PidSpec, File) ->
-    checksum_list(PidSpec, EpochID, File, infinity).
+    checksum_list(PidSpec, File, infinity).
 
 %% @doc Fetch the list of chunk checksums for `File'.
 
-checksum_list(PidSpec, EpochID, File, Timeout) ->
+checksum_list(PidSpec, File, Timeout) ->
-    gen_server:call(PidSpec, {req, {checksum_list, EpochID, File}},
+    gen_server:call(PidSpec, {req, {checksum_list, File}},
                     Timeout).
 
 %% @doc Fetch the list of all files on the remote FLU.
@@ -288,19 +280,19 @@ quit(PidSpec) ->
 %% @doc Write a chunk (binary- or iolist-style) of data to a file
 %% with `Prefix' at `Offset'.
 
-write_chunk(PidSpec, EpochID, File, Offset, Chunk) ->
+write_chunk(PidSpec, NSInfo, EpochID, File, Offset, Chunk, CSum) ->
-    write_chunk(PidSpec, EpochID, File, Offset, Chunk, infinity).
+    write_chunk(PidSpec, NSInfo, EpochID, File, Offset, Chunk, CSum, infinity).
 
 %% @doc Write a chunk (binary- or iolist-style) of data to a file
 %% with `Prefix' at `Offset'.
 
-write_chunk(PidSpec, EpochID, File, Offset, Chunk, Timeout) ->
+write_chunk(PidSpec, NSInfo, EpochID, File, Offset, Chunk, CSum, Timeout) ->
-    case gen_server:call(PidSpec, {req, {write_chunk, EpochID, File, Offset, Chunk}},
+    case gen_server:call(PidSpec, {req, {write_chunk, NSInfo, EpochID, File, Offset, Chunk, CSum}},
                          Timeout) of
         {error, written}=Err ->
             Size = byte_size(Chunk),
-            case read_chunk(PidSpec, EpochID, File, Offset, Size, Timeout) of
+            case read_chunk(PidSpec, NSInfo, EpochID, File, Offset, Size, undefined, Timeout) of
-                {ok, Chunk2} when Chunk2 == Chunk ->
+                {ok, {[{File, Offset, Chunk2, _}], []}} when Chunk2 == Chunk ->
                     %% See equivalent comment inside write_projection().
                     ok;
                 _ ->
@@ -310,6 +302,18 @@ write_chunk(PidSpec, EpochID, File, Offset, Chunk, Timeout) ->
             Else
     end.
 
+
+trim_chunk(PidSpec, NSInfo, EpochID, File, Offset, Size) ->
+    trim_chunk(PidSpec, NSInfo, EpochID, File, Offset, Size, infinity).
+
+%% @doc Write a chunk (binary- or iolist-style) of data to a file
+%% with `Prefix' at `Offset'.
+
+trim_chunk(PidSpec, NSInfo, EpochID, File, Offset, Chunk, Timeout) ->
+    gen_server:call(PidSpec,
+                    {req, {trim_chunk, NSInfo, EpochID, File, Offset, Chunk}},
+                    Timeout).
+
 %%%%%%%%%%%%%%%%%%%%%%%%%%%
 
 init([I]) ->
@@ -371,21 +375,24 @@ do_req_retry(_Req, 2, Err, S) ->
 do_req_retry(Req, Depth, _Err, S) ->
     do_req(Req, Depth + 1, try_connect(disconnect(S))).
 
-make_req_fun({append_chunk, EpochID, Prefix, Chunk},
+make_req_fun({append_chunk, NSInfo, EpochID,
+              Prefix, Chunk, CSum, Opts, Timeout},
              #state{sock=Sock,i=#p_srvr{proto_mod=Mod}}) ->
-    fun() -> Mod:append_chunk(Sock, EpochID, Prefix, Chunk) end;
+    fun() -> Mod:append_chunk(Sock, NSInfo, EpochID,
-make_req_fun({append_chunk_extra, EpochID, Prefix, Chunk, ChunkExtra},
+                              Prefix, Chunk, CSum, Opts, Timeout)
+    end;
+make_req_fun({read_chunk, NSInfo, EpochID, File, Offset, Size, Opts},
              #state{sock=Sock,i=#p_srvr{proto_mod=Mod}}) ->
-    fun() -> Mod:append_chunk_extra(Sock, EpochID, Prefix, Chunk, ChunkExtra) end;
+    fun() -> Mod:read_chunk(Sock, NSInfo, EpochID, File, Offset, Size, Opts) end;
-make_req_fun({read_chunk, EpochID, File, Offset, Size},
+make_req_fun({write_chunk, NSInfo, EpochID, File, Offset, Chunk, CSum},
              #state{sock=Sock,i=#p_srvr{proto_mod=Mod}}) ->
-    fun() -> Mod:read_chunk(Sock, EpochID, File, Offset, Size) end;
+    fun() -> Mod:write_chunk(Sock, NSInfo, EpochID, File, Offset, Chunk, CSum) end;
-make_req_fun({write_chunk, EpochID, File, Offset, Chunk},
+make_req_fun({trim_chunk, NSInfo, EpochID, File, Offset, Size},
              #state{sock=Sock,i=#p_srvr{proto_mod=Mod}}) ->
-    fun() -> Mod:write_chunk(Sock, EpochID, File, Offset, Chunk) end;
+    fun() -> Mod:trim_chunk(Sock, NSInfo, EpochID, File, Offset, Size) end;
-make_req_fun({checksum_list, EpochID, File},
+make_req_fun({checksum_list, File},
              #state{sock=Sock,i=#p_srvr{proto_mod=Mod}}) ->
-    fun() -> Mod:checksum_list(Sock, EpochID, File) end;
+    fun() -> Mod:checksum_list(Sock, File) end;
 make_req_fun({list_files, EpochID},
              #state{sock=Sock,i=#p_srvr{proto_mod=Mod}}) ->
     fun() -> Mod:list_files(Sock, EpochID) end;

src/machi_sequencer.erl

@@ -1,194 +0,0 @@
-%% -------------------------------------------------------------------
-%%
-%% Copyright (c) 2007-2015 Basho Technologies, Inc.  All Rights Reserved.
-%%
-%% This file is provided to you under the Apache License,
-%% Version 2.0 (the "License"); you may not use this file
-%% except in compliance with the License.  You may obtain
-%% a copy of the License at
-%%
-%%   http://www.apache.org/licenses/LICENSE-2.0
-%%
-%% Unless required by applicable law or agreed to in writing,
-%% software distributed under the License is distributed on an
-%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
-%% KIND, either express or implied.  See the License for the
-%% specific language governing permissions and limitations
-%% under the License.
-%%
-%% -------------------------------------------------------------------
-
-%% @doc "Mothballed" sequencer code, perhaps to be reused sometime in
-%% the future?
-
--module(machi_sequencer).
-
--compile(export_all).
-
--include_lib("kernel/include/file.hrl").
-
--define(CONFIG_DIR, "./config").
--define(DATA_DIR, "./data").
-
-seq(Server, Prefix, Size) when is_binary(Prefix), is_integer(Size), Size > -1 ->
-    Server ! {seq, self(), Prefix, Size},
-    receive
-        {assignment, File, Offset} ->
-            {File, Offset}
-    after 1*1000 ->
-            bummer
-    end.
-
-seq_direct(Prefix, Size) when is_binary(Prefix), is_integer(Size), Size > -1 ->
-    RegName = make_regname(Prefix),
-    seq(RegName, Prefix, Size).
-
-start_server() ->
-    start_server(?MODULE).
-
-start_server(Name) ->
-    spawn_link(fun() -> run_server(Name) end).
-
-run_server(Name) ->
-    register(Name, self()),
-    ets:new(?MODULE, [named_table, public, {write_concurrency, true}]),
-    server_loop().
-
-server_loop() ->
-    receive
-        {seq, From, Prefix, Size} ->
-            spawn(fun() -> server_dispatch(From, Prefix, Size) end),
-            server_loop()
-    end.
-
-server_dispatch(From, Prefix, Size) ->
-    RegName = make_regname(Prefix),
-    case whereis(RegName) of
-        undefined ->
-            start_prefix_server(Prefix),
-            timer:sleep(1),
-            server_dispatch(From, Prefix, Size);
-        Pid ->
-            Pid ! {seq, From, Prefix, Size}
-    end,
-    exit(normal).
-
-start_prefix_server(Prefix) ->
-    spawn(fun() -> run_prefix_server(Prefix) end).
-
-run_prefix_server(Prefix) ->
-    true = register(make_regname(Prefix), self()),
-    ok = filelib:ensure_dir(?CONFIG_DIR ++ "/unused"),
-    ok = filelib:ensure_dir(?DATA_DIR ++ "/unused"),
-    FileNum = read_max_filenum(Prefix) + 1,
-    ok = increment_max_filenum(Prefix),
-    prefix_server_loop(Prefix, FileNum).
-
-prefix_server_loop(Prefix, FileNum) ->
-    File = make_data_filename(Prefix, FileNum),
-    prefix_server_loop(Prefix, File, FileNum, 0).
-
-prefix_server_loop(Prefix, File, FileNum, Offset) ->
-    receive
-        {seq, From, Prefix, Size} ->
-            From ! {assignment, File, Offset},
-            prefix_server_loop(Prefix, File, FileNum, Offset + Size)
-    after 30*1000 ->
-            io:format("timeout: ~p server stopping\n", [Prefix]),
-            exit(normal)
-    end.
-
-make_regname(Prefix) ->
-    erlang:binary_to_atom(Prefix, latin1).
-
-make_config_filename(Prefix) ->
-    lists:flatten(io_lib:format("~s/~s", [?CONFIG_DIR, Prefix])).
-
-make_data_filename(Prefix, FileNum) ->
-    erlang:iolist_to_binary(io_lib:format("~s/~s.~w",
-                                          [?DATA_DIR, Prefix, FileNum])).
-
-read_max_filenum(Prefix) ->
-    case file:read_file_info(make_config_filename(Prefix)) of
-        {error, enoent} ->
-            0;
-        {ok, FI} ->
-            FI#file_info.size
-    end.
-
-increment_max_filenum(Prefix) ->
-    {ok, FH} = file:open(make_config_filename(Prefix), [append]),
-    ok = file:write(FH, "x"),
-    %% ok = file:sync(FH),
-    ok = file:close(FH).
-
-%%%%%%%%%%%%%%%%%
-
-%% basho_bench callbacks
-
--define(SEQ, ?MODULE).
-
-new(1) ->
-    start_server(),
-    timer:sleep(100),
-    {ok, unused};
-new(_Id) ->
-    {ok, unused}.
-
-run(null, _KeyGen, _ValgueGen, State) ->
-    {ok, State};
-run(keygen_then_null, KeyGen, _ValgueGen, State) ->
-    _Prefix = KeyGen(),
-    {ok, State};
-run(seq, KeyGen, _ValgueGen, State) ->
-    Prefix = KeyGen(),
-    {_, _} = ?SEQ:seq(?SEQ, Prefix, 1),
-    {ok, State};
-run(seq_direct, KeyGen, _ValgueGen, State) ->
-    Prefix = KeyGen(),
-    Name = ?SEQ:make_regname(Prefix),
-    case get(Name) of
-        undefined ->
-            case whereis(Name) of
-                undefined ->
-                    {_, _} = ?SEQ:seq(?SEQ, Prefix, 1);
-                Pid ->
-                    put(Name, Pid),
-                    {_, _} = ?SEQ:seq(Pid, Prefix, 1)
-            end;
-        Pid ->
-            {_, _} = ?SEQ:seq(Pid, Prefix, 1)
-    end,
-    {ok, State};
-run(seq_ets, KeyGen, _ValgueGen, State) ->
-    Tab = ?MODULE,
-    Prefix = KeyGen(),
-    Res = try
-              BigNum = ets:update_counter(Tab, Prefix, 1),
-              BigBin = <<BigNum:80/big>>,
-              <<FileNum:32/big, Offset:48/big>> = BigBin,
-              %% if Offset rem 1000 == 0 ->
-              %%         io:format("~p,~p ", [FileNum, Offset]);
-              %%    true ->
-              %%         ok
-              %% end,
-              {fakefake, FileNum, Offset}
-          catch error:badarg ->
-                  FileNum2 = 1, Offset2 = 0,
-                  FileBin = <<FileNum2:32/big>>,
-                  OffsetBin = <<Offset2:48/big>>,
-                  Glop = <<FileBin/binary, OffsetBin/binary>>,
-                  <<Base:80/big>> = Glop,
-                  %% if Prefix == <<"42">> -> io:format("base:~w\n", [Base]); true -> ok end,
-                  %% Base = 0,
-                  case ets:insert_new(Tab, {Prefix, Base}) of
-                      true ->
-                          {<<"fakefakefake">>, Base};
-                      false ->
-                          Result2 = ets:update_counter(Tab, Prefix, 1),
-                          {<<"fakefakefake">>, Result2}
-                  end
-          end,
-    Res = Res,
-    {ok, State}.
-

src/machi_sup.erl

@@ -47,8 +47,6 @@ start_link() ->
     supervisor:start_link({local, ?SERVER}, ?MODULE, []).
 
 init([]) ->
-    %% {_, Ps} = process_info(self(), links),
-    %% [unlink(P) || P <- Ps],
     RestartStrategy = one_for_one,
     MaxRestarts = 1000,
     MaxSecondsBetweenRestarts = 3600,
@@ -62,9 +60,16 @@ init([]) ->
     ServerSup =
         {machi_flu_sup, {machi_flu_sup, start_link, []},
          Restart, Shutdown, Type, []},
-
+    RanchSup = {ranch_sup, {ranch_sup, start_link, []},
-    {ok, {SupFlags, [ServerSup]}}.
+                Restart, Shutdown, supervisor, [ranch_sup]},
-
+    LifecycleMgr =
-    %% AChild = {'AName', {'AModule', start_link, []},
+        {machi_lifecycle_mgr, {machi_lifecycle_mgr, start_link, []},
-    %%           Restart, Shutdown, Type, ['AModule']},
+         Restart, Shutdown, worker, []},
-    %% {ok, {SupFlags, [AChild]}}.
+    RunningApps = [A || {A,_D,_V} <- application:which_applications()],
+    Specs = case lists:member(ranch, RunningApps) of
+                true ->
+                    [ServerSup, LifecycleMgr];
+                false ->
+                    [ServerSup, RanchSup, LifecycleMgr]
+            end,
+    {ok, {SupFlags, Specs}}.

src/machi_util.erl

@@ -25,18 +25,19 @@
 -export([
          checksum_chunk/1,
          make_tagged_csum/1, make_tagged_csum/2,
+         make_client_csum/1,
          unmake_tagged_csum/1,
          hexstr_to_bin/1, bin_to_hexstr/1,
          hexstr_to_int/1, int_to_hexstr/2, int_to_hexbin/2,
          make_binary/1, make_string/1,
          make_regname/1,
-         make_config_filename/2,
+         make_config_filename/4, make_config_filename/2,
          make_checksum_filename/4, make_checksum_filename/2,
-         make_data_filename/4, make_data_filename/2,
+         make_data_filename/6, make_data_filename/2,
          make_projection_filename/2, 
          is_valid_filename/1,
          parse_filename/1,
-         read_max_filenum/2, increment_max_filenum/2,
+         read_max_filenum/4, increment_max_filenum/4,
          info_msg/2, verb/1, verb/2,
          mbytes/1, 
          pretty_time/0, pretty_time/2,
@@ -45,12 +46,15 @@
          %% List twiddling
          permutations/1, perms/1,
          combinations/1, ordered_combinations/1,
-         mk_order/2
+         mk_order/2,
+         %% Other
+         wait_for_death/2, wait_for_life/2,
+         bool2int/1,
+         int2bool/1,
+         read_opts_default/1,
+         ns_info_default/1
         ]).
 
-%% TODO: Leave this in place?
--compile(export_all).
-
 -include("machi.hrl").
 -include("machi_projection.hrl").
 -include_lib("kernel/include/file.hrl").
@@ -67,10 +71,20 @@ make_regname(Prefix) when is_list(Prefix) ->
 
 %% @doc Calculate a config file path, by common convention.
 
+-spec make_config_filename(string(), machi_dt:namespace(), machi_dt:locator(), string()) ->
+      string().
+make_config_filename(DataDir, NS, NSLocator, Prefix) ->
+    NSLocator_str = int_to_hexstr(NSLocator, 32),
+    lists:flatten(io_lib:format("~s/config/~s^~s^~s",
+                                [DataDir, Prefix, NS, NSLocator_str])).
+
+%% @doc Calculate a config file path, by common convention.
+
 -spec make_config_filename(string(), string()) ->
       string().
-make_config_filename(DataDir, Prefix) ->
+make_config_filename(DataDir, Filename) ->
-    lists:flatten(io_lib:format("~s/config/~s", [DataDir, Prefix])).
+    lists:flatten(io_lib:format("~s/config/~s",
+                                [DataDir, Filename])).
 
 %% @doc Calculate a checksum file path, by common convention.
 
@@ -91,11 +105,22 @@ make_checksum_filename(DataDir, FileName) ->
 
 %% @doc Calculate a file data file path, by common convention.
 
--spec make_data_filename(string(), string(), atom()|string()|binary(), integer()) ->
+-spec make_data_filename(string(), machi_dt:namespace(), machi_dt:locator(), string(), atom()|string()|binary(), integer()|string()) ->
       {binary(), string()}.
-make_data_filename(DataDir, Prefix, SequencerName, FileNum) ->
+make_data_filename(DataDir, NS, NSLocator, Prefix, SequencerName, FileNum)
-    File = erlang:iolist_to_binary(io_lib:format("~s^~s^~w",
+  when is_integer(FileNum) ->
-                                                 [Prefix, SequencerName, FileNum])),
+    NSLocator_str = int_to_hexstr(NSLocator, 32),
+    File = erlang:iolist_to_binary(io_lib:format("~s^~s^~s^~s^~w",
+                                                 [Prefix, NS, NSLocator_str, SequencerName, FileNum])),
+    make_data_filename2(DataDir, File);
+make_data_filename(DataDir, NS, NSLocator, Prefix, SequencerName, String)
+  when is_list(String) ->
+    NSLocator_str = int_to_hexstr(NSLocator, 32),
+    File = erlang:iolist_to_binary(io_lib:format("~s^~s^~s^~s^~s",
+                                                 [Prefix, NS, NSLocator_str, SequencerName, string])),
+    make_data_filename2(DataDir, File).
+
+make_data_filename2(DataDir, File) ->
     FullPath = lists:flatten(io_lib:format("~s/data/~s",  [DataDir, File])),
     {File, FullPath}.
 
@@ -124,34 +149,44 @@ make_projection_filename(DataDir, File) ->
 -spec is_valid_filename( Filename :: string() ) -> true | false.
 is_valid_filename(Filename) ->
     case parse_filename(Filename) of
-        [] -> false;
+        {}          -> false;
-        _ -> true
+        {_,_,_,_,_} -> true
     end.
 
 %% @doc Given a machi filename, return a set of components in a list.
 %% The components will be:
 %% <ul>
 %%      <li>Prefix</li>
+%%      <li>Cluster namespace</li>
+%%      <li>Cluster locator</li>
 %%      <li>UUID</li>
 %%      <li>Sequence number</li>
 %% </ul>
 %%
 %% Invalid filenames will return an empty list.
--spec parse_filename( Filename :: string() ) -> [ string() ].
+-spec parse_filename( Filename :: string() ) -> {} | {string(), machi_dt:namespace(), machi_dt:locator(), string(), string() }.
 parse_filename(Filename) ->
     case string:tokens(Filename, "^") of
-        [_Prefix, _UUID, _SeqNo] = L -> L;
+        [Prefix, NS, NSLocator, UUID, SeqNo] ->
-        _ -> []
+            {Prefix, NS, list_to_integer(NSLocator), UUID, SeqNo};
+        [Prefix,          NSLocator, UUID, SeqNo] ->
+            %% string:tokens() doesn't consider "foo^^bar" as 3 tokens {sigh}
+            case re:replace(Filename, "[^^]+", "x", [global,{return,binary}]) of
+                <<"x^^x^x^x">> ->
+                    {Prefix, <<"">>, list_to_integer(NSLocator), UUID, SeqNo};
+                _ ->
+                    {}
+            end;
+        _ -> {}
     end.
 
-
 %% @doc Read the file size of a config file, which is used as the
 %% basis for a minimum sequence number.
 
--spec read_max_filenum(string(), string()) ->
+-spec read_max_filenum(string(), machi_dt:namespace(), machi_dt:locator(), string()) ->
       non_neg_integer().
-read_max_filenum(DataDir, Prefix) ->
+read_max_filenum(DataDir, NS, NSLocator, Prefix) ->
-    case file:read_file_info(make_config_filename(DataDir, Prefix)) of
+    case file:read_file_info(make_config_filename(DataDir, NS, NSLocator, Prefix)) of
         {error, enoent} ->
             0;
         {ok, FI} ->
@@ -161,11 +196,11 @@ read_max_filenum(DataDir, Prefix) ->
 %% @doc Increase the file size of a config file, which is used as the
 %% basis for a minimum sequence number.
 
--spec increment_max_filenum(string(), string()) ->
+-spec increment_max_filenum(string(), machi_dt:namespace(), machi_dt:locator(), string()) ->
       ok | {error, term()}.
-increment_max_filenum(DataDir, Prefix) ->
+increment_max_filenum(DataDir, NS, NSLocator, Prefix) ->
     try
-        {ok, FH} = file:open(make_config_filename(DataDir, Prefix), [append]),
+        {ok, FH} = file:open(make_config_filename(DataDir, NS, NSLocator, Prefix), [append]),
         ok = file:write(FH, "x"),
         ok = file:sync(FH),
         ok = file:close(FH)
@@ -254,22 +289,48 @@ int_to_hexbin(I, I_size) ->
 checksum_chunk(Chunk) when is_binary(Chunk); is_list(Chunk) ->
     crypto:hash(sha, Chunk).
 
+convert_csum_tag(A) when is_atom(A)->
+    A;
+convert_csum_tag(?CSUM_TAG_NONE) ->
+    ?CSUM_TAG_NONE_ATOM;
+convert_csum_tag(?CSUM_TAG_CLIENT_SHA) ->
+    ?CSUM_TAG_CLIENT_SHA_ATOM;
+convert_csum_tag(?CSUM_TAG_SERVER_SHA) ->
+    ?CSUM_TAG_SERVER_SHA_ATOM;
+convert_csum_tag(?CSUM_TAG_SERVER_REGEN_SHA) ->
+    ?CSUM_TAG_SERVER_REGEN_SHA_ATOM.
+
 %% @doc Create a tagged checksum
 
 make_tagged_csum(none) ->
     <<?CSUM_TAG_NONE:8>>;
-make_tagged_csum({Tag, CSum}) ->
+make_tagged_csum(<<>>) ->
-    make_tagged_csum(Tag, CSum).
-
-make_tagged_csum(none, _SHA) ->
     <<?CSUM_TAG_NONE:8>>;
-make_tagged_csum(client_sha, SHA) ->
+make_tagged_csum({Tag, CSum}) ->
+    make_tagged_csum(convert_csum_tag(Tag), CSum).
+
+%% @doc Makes tagged csum. Each meanings are:
+%% none / ?CSUM_TAG_NONE
+%%  - a suspicious and nonsense checksum
+%% client_sha / ?CSUM_TAG_CLIENT_SHA
+%%  - a valid checksum given by client and stored in server
+%% server_sha / ?CSUM_TAG_SERVER_SHA
+%%  - a valid checksum generated by and stored in server
+%% server_regen_sha / ?CSUM_TAG_SERVER_REGEN_SHA
+%%  - a valid checksum generated by server in an ad hoc manner, not stored in server
+-spec make_tagged_csum(machi_dt:csum_tag(), binary()) -> machi_dt:chunk_csum().
+make_tagged_csum(?CSUM_TAG_NONE_ATOM, _SHA) ->
+    <<?CSUM_TAG_NONE:8>>;
+make_tagged_csum(?CSUM_TAG_CLIENT_SHA_ATOM, SHA) ->
     <<?CSUM_TAG_CLIENT_SHA:8, SHA/binary>>;
-make_tagged_csum(server_sha, SHA) ->
+make_tagged_csum(?CSUM_TAG_SERVER_SHA_ATOM, SHA) ->
     <<?CSUM_TAG_SERVER_SHA:8, SHA/binary>>;
-make_tagged_csum(server_regen_sha, SHA) ->
+make_tagged_csum(?CSUM_TAG_SERVER_REGEN_SHA_ATOM, SHA) ->
     <<?CSUM_TAG_SERVER_REGEN_SHA:8, SHA/binary>>.
 
+make_client_csum(BinOrList) ->
+    make_tagged_csum(?CSUM_TAG_CLIENT_SHA_ATOM, checksum_chunk(BinOrList)).
+
 unmake_tagged_csum(<<Tag:8, Rest/binary>>) ->
     {Tag, Rest}.
 
@@ -317,10 +378,21 @@ wait_for_death(Pid, Iters) when is_pid(Pid) ->
         false ->
             ok;
         true ->
-            timer:sleep(1),
+            timer:sleep(10),
             wait_for_death(Pid, Iters-1)
     end.
 
+wait_for_life(Reg, 0) ->
+    exit({not_alive_yet, Reg});
+wait_for_life(Reg, Iters) when is_atom(Reg) ->
+    case erlang:whereis(Reg) of
+        Pid when is_pid(Pid) ->
+            {ok, Pid};
+        _ ->
+            timer:sleep(1),
+            wait_for_life(Reg, Iters-1)
+    end.
+
 %%%%%%%%%%%%%%%%%
 
 %% @doc Create a TCP connection to a remote Machi server.
@@ -371,3 +443,23 @@ mk_order(UPI2, Repair1) ->
                       error     -> error
                   end || X <- UPI2],
     UPI2_order.
+
+%% C-style conversion for PB usage.
+bool2int(true) -> 1;
+bool2int(false) -> 0.
+int2bool(0) -> false;
+int2bool(I) when is_integer(I) -> true.
+
+read_opts_default(#read_opts{}=NSInfo) ->
+    NSInfo;
+read_opts_default(A) when A == 'undefined'; A == 'noopt'; A == 'none' ->
+    #read_opts{};
+read_opts_default(A) when is_atom(A) ->
+    #read_opts{}.
+
+ns_info_default(#ns_info{}=NSInfo) ->
+    NSInfo;
+ns_info_default(A) when is_atom(A) ->
+    #ns_info{}.
+
+

src/machi_yessir_client.erl

@@ -22,6 +22,8 @@
 
 -module(machi_yessir_client).
 
+-ifdef(TODO_refactoring_deferred).
+
 -include("machi.hrl").
 -include("machi_projection.hrl").
 
@@ -30,7 +32,7 @@
          append_chunk/4, append_chunk/5,
          append_chunk_extra/5, append_chunk_extra/6,
          read_chunk/5, read_chunk/6,
-         checksum_list/3, checksum_list/4,
+         checksum_list/2, checksum_list/3,
          list_files/2, list_files/3,
          wedge_status/1, wedge_status/2,
 
@@ -173,24 +175,24 @@ read_chunk(_Host, _TcpPort, EpochID, File, Offset, Size)
 
 %% @doc Fetch the list of chunk checksums for `File'.
 
-checksum_list(#yessir{name=Name,chunk_size=ChunkSize}, _EpochID, File) ->
+checksum_list(#yessir{name=Name,chunk_size=ChunkSize}, File) ->
     case get({Name,offset,File}) of
         undefined ->
             {error, no_such_file};
         MaxOffset ->
             C = machi_util:make_tagged_csum(client_sha,
                                             make_csum(Name, ChunkSize)),
-            Cs = [machi_flu1:encode_csum_file_entry_bin(Offset, ChunkSize, C) ||
+            Cs = [{Offset, ChunkSize, C} ||
                      Offset <- lists:seq(?MINIMUM_OFFSET, MaxOffset, ChunkSize)],
-            {ok, Cs}
+            {ok, term_to_binary(Cs)}
     end.
 
 %% @doc Fetch the list of chunk checksums for `File'.
 
-checksum_list(_Host, _TcpPort, EpochID, File) ->
+checksum_list(_Host, _TcpPort, File) ->
     Sock = connect(#p_srvr{proto_mod=?MODULE}),
     try
-        checksum_list(Sock, EpochID, File)
+        checksum_list(Sock, File)
     after
         disconnect(Sock)
     end.
@@ -450,7 +452,7 @@ connect(#p_srvr{name=Name, props=Props})->
                    chunk_size=ChunkSize
                   },
     %% Add fake dict entries for these files
-    [begin
+    _ = [begin
              Prefix = list_to_binary(io_lib:format("fake~w", [X])),
              {ok, _} = append_chunk_extra(Sock, {1,<<"unused">>}, Prefix, <<>>, FileSize)
          end || X <- lists:seq(1, NumFiles)],
@@ -458,10 +460,10 @@ connect(#p_srvr{name=Name, props=Props})->
     Sock.
 
 disconnect(#yessir{name=Name}) ->
-    [erase(K) || {{N,offset,_}=K, _V} <- get(), N == Name],
+    _ = [erase(K) || {{N,offset,_}=K, _V} <- get(), N == Name],
-    [erase(K) || {{N,chunk,_}=K, _V} <- get(), N == Name],
+    _ = [erase(K) || {{N,chunk,_}=K, _V} <- get(), N == Name],
-    [erase(K) || {{N,csum,_}=K, _V} <- get(), N == Name],
+    _ = [erase(K) || {{N,csum,_}=K, _V} <- get(), N == Name],
-    [erase(K) || {{N,proj,_,_}=K, _V} <- get(), N == Name],
+    _ = [erase(K) || {{N,proj,_,_}=K, _V} <- get(), N == Name],
     ok.
 
 %% Example use:
@@ -509,3 +511,5 @@ disconnect(#yessir{name=Name}) ->
 %% =INFO REPORT==== 17-May-2015::18:57:52 ===
 %% Repair success: tail a of [a] finished ap_mode repair ID {a,{1431,856671,140404}}: ok
 %% Stats [{t_in_files,0},{t_in_chunks,10413},{t_in_bytes,682426368},{t_out_files,0},{t_out_chunks,10413},{t_out_bytes,682426368},{t_bad_chunks,0},{t_elapsed_seconds,1.591}]
+
+-endif. % TODO_refactoring_deferred

test/machi_admin_util_test.erl

@@ -33,25 +33,33 @@
 -define(FLU_C, machi_flu1_client).
 
 verify_file_checksums_test_() ->
-    {timeout, 60, fun() -> verify_file_checksums_test2() end}.
+    {setup,
+     fun() -> os:cmd("rm -rf ./data") end,
+     fun(_) -> os:cmd("rm -rf ./data")  end,
+     {timeout, 60, fun() -> verify_file_checksums_test2() end}
+    }.
 
 verify_file_checksums_test2() ->
     Host = "localhost",
     TcpPort = 32958,
     DataDir = "./data",
     W_props = [{initial_wedged, false}],
-    machi_flu1_test:start_flu_package(verify1_flu, TcpPort, DataDir,
+    NSInfo = undefined,
+    NoCSum = <<>>,
+    try
+        machi_test_util:start_flu_package(verify1_flu, TcpPort, DataDir,
                                           W_props),
         Sock1 = ?FLU_C:connect(#p_srvr{address=Host, port=TcpPort}),
         try
             Prefix = <<"verify_prefix">>,
             NumChunks = 10,
-        [{ok, _} = ?FLU_C:append_chunk(Sock1, ?DUMMY_PV1_EPOCH,
+            [{ok, _} = ?FLU_C:append_chunk(Sock1, NSInfo, ?DUMMY_PV1_EPOCH,
-                                       Prefix, <<X:(X*8)/big>>) ||
+                                           Prefix, <<X:(X*8)/big>>, NoCSum) ||
                 X <- lists:seq(1, NumChunks)],
             {ok, [{_FileSize,File}]} = ?FLU_C:list_files(Sock1, ?DUMMY_PV1_EPOCH),
-        {ok, []} = machi_admin_util:verify_file_checksums_remote(
+            ?assertEqual({ok, []},
-                     Host, TcpPort, ?DUMMY_PV1_EPOCH, File),
+                         machi_admin_util:verify_file_checksums_remote(
+                           Host, TcpPort, ?DUMMY_PV1_EPOCH, File)),
 
             %% Clobber the first 3 chunks, which are sizes 1/2/3.
             {_, Path} = machi_util:make_data_filename(DataDir,binary_to_list(File)),
@@ -74,8 +82,10 @@ verify_file_checksums_test2() ->
 
             ok
         after
-        catch ?FLU_C:quit(Sock1),
+            catch ?FLU_C:quit(Sock1)
-        catch machi_flu1_test:stop_flu_package(verify1_flu)
+        end
+    after
+        catch machi_test_util:stop_flu_package()
     end.
 
 -endif. % !PULSE

test/machi_ap_repair_eqc.erl

@@ -0,0 +1,616 @@
+%% -------------------------------------------------------------------
+%%
+%% Copyright (c) 2007-2015 Basho Technologies, Inc.  All Rights Reserved.
+%%
+%% This file is provided to you under the Apache License,
+%% Version 2.0 (the "License"); you may not use this file
+%% except in compliance with the License.  You may obtain
+%% a copy of the License at
+%%
+%%   http://www.apache.org/licenses/LICENSE-2.0
+%%
+%% Unless required by applicable law or agreed to in writing,
+%% software distributed under the License is distributed on an
+%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+%% KIND, either express or implied.  See the License for the
+%% specific language governing permissions and limitations
+%% under the License.
+%%
+%% -------------------------------------------------------------------
+
+%% EQC single-threaded and concurrent test for file operations and repair
+%% under simulated network partition.
+
+%% The main purpose is to confirm no dataloss, i.e. every chunk that
+%% has been successfully written (ACK received) by append/write
+%% opration will be read after partition heals.
+%%
+%% All updating -- append, write and trim -- operations are executed
+%% through CR client, not directly by flu1 client, in order to be
+%% end-to-end test (in single chain point of veiw.) There may be churn
+%% for projections by simulated network partition.
+%%
+%% Test steps
+%% 1. Setup single chain.
+%% 2. Execute updating operations and simulated partition (by eqc_statem).
+%%    Every updating results are recorded in ETS tables.
+%% 3. When {error, timeout|partition} happens, trigger management tick for
+%%    every chain manager process.
+%% 4. After commands are executed, remove patition and wait for the chain
+%%    without down nodes nor repairing nodes.
+%% 5. Asserting written results so that each record be read from the
+%%    chain and data be the same with written one.
+
+%% Improvements to-do's
+%% - Use higher concurrency, e.g. 10+
+%% - Random length for binary to write
+%% - Operations other than append, write, trim
+%% - Use checksum instead of binary to save memory
+%% - More variety for partitioning pattern: non-constant failure
+%% - Stop and restart
+%% - Suspend and resume of some erlang processes
+
+-module(machi_ap_repair_eqc).
+
+-ifdef(TEST).
+-ifdef(EQC).
+-compile(export_all).
+-include("machi.hrl").
+-include("machi_projection.hrl").
+-include("machi_verbose.hrl").
+-include_lib("eqc/include/eqc.hrl").
+-include_lib("eqc/include/eqc_statem.hrl").
+-include_lib("eunit/include/eunit.hrl").
+
+-record(target, {verbose=false,
+                 flu_names,
+                 mgr_names}).
+
+-record(state, {num,
+                verbose=false,
+                flu_names,
+                mgr_names,
+                cr_count}).
+
+%% ETS table names
+-define(WRITTEN_TAB,  written).  % Successfully written data
+-define(ACCPT_TAB,    accpt).    % Errors with no harm, e.g. timeout
+-define(FAILED_TAB,   failed).   % Uncategorized errors, when happenes
+                                 % it should be re-categorized to accept or critical
+-define(CRITICAL_TAB, critical). % Critical errors, e.g. double write to the same key
+
+-define(QC_OUT(P),
+        eqc:on_output(fun(Str, Args) -> io:format(user, Str, Args) end, P)).
+
+%% EUNIT TEST DEFINITION
+prop_repair_test_() ->
+    {PropTO, EUnitTO} = eqc_timeout(60),
+    Verbose = eqc_verbose(),
+    {spawn,
+     [{timeout, EUnitTO,
+       ?_assertEqual(
+          true,
+          eqc:quickcheck(eqc:testing_time(
+                           PropTO, ?QC_OUT(noshrink(prop_repair(Verbose))))))}]}.
+
+prop_repair_par_test_() ->
+    {PropTO, EUnitTO} = eqc_timeout(60),
+    Verbose = eqc_verbose(),
+    {spawn,
+     [{timeout, EUnitTO,
+       ?_assertEqual(
+          true,
+          eqc:quickcheck(eqc:testing_time(
+                           PropTO, ?QC_OUT(noshrink(prop_repair_par(Verbose))))))}]}.
+
+%% Model
+
+weight(_S, change_partition) ->  20;
+weight(_S, _)                -> 100.
+
+%% Append
+
+append_args(#state{cr_count=CRCount}=S) ->
+    [choose(1, CRCount), chunk(), S].
+
+append(CRIndex, Bin, #state{verbose=V}=S) ->
+    CRList = cr_list(),
+    {_SimSelfName, C} = lists:nth(CRIndex, CRList),
+    Prefix = <<"pre">>,
+    Len = byte_size(Bin),
+    NSInfo = #ns_info{},
+    NoCSum = <<>>,
+    Opts1 = #append_opts{},
+    Res = (catch machi_cr_client:append_chunk(C, NSInfo, Prefix, Bin, NoCSum, Opts1, sec(1))),
+    case Res of
+        {ok, {_Off, Len, _FileName}=Key} ->
+            case ets:insert_new(?WRITTEN_TAB, {Key, Bin}) of
+                true ->
+                    [?V("<o>", []) || V],
+                    ok;
+                false ->
+                    %% The Key is alread written, WHY!!!????
+                    case ets:lookup(?WRITTEN_TAB, Key) of
+                        [{Key, Bin}] ->
+                            %% TODO: The identical binary is alread inserted in
+                            %%  written table. Is this acceptable??? Hmm, maybe NO...
+                            [?V("<dws:~w>", [Key]) || V],
+                            true = ets:insert_new(?ACCPT_TAB,
+                                                  {make_ref(), double_write_same, Key}),
+                            {acceptable_error, doublewrite_the_same};
+                        [{Key, OtherBin}] ->
+                            [?V("<dwd:~w:~w>", [Key, {OtherBin, Bin}]) || V],
+                            true = ets:insert_new(?CRITICAL_TAB,
+                                                  {make_ref(), double_write_diff, Key}),
+                            R = {critical_error,
+                                 {doublewrite_diff, Key, {OtherBin, Bin}}},
+                            %% TODO: when double write happens, it seems that
+                            %% repair process got stack with endless loop. To
+                            %% avoit it, return error here.
+                            %% If this error/1 will be removed, one can possibly
+                            %% know double write frequency/rate.
+                            error(R)
+                    end
+            end;
+        {error, partition} -> 
+            [?V("<pt>", []) || V],
+            true = ets:insert_new(?ACCPT_TAB, {make_ref(), timeout}),
+            _ = tick(S),
+            {acceptable_error, partition};
+        {'EXIT', {timeout, _}} ->
+            [?V("<to:~w:~w>", [_SimSelfName, C]) || V],
+            true = ets:insert_new(?ACCPT_TAB, {make_ref(), timeout}),
+            _ = tick(S),
+            {acceptable_error, timeout};
+        {ok, {_Off, UnexpectedLen, _FileName}=Key} ->
+            [?V("<XX>", []) || V],
+            true = ets:insert_new(?CRITICAL_TAB, {make_ref(), unexpected_len, Key}),
+            {critical_error, {unexpected_len, Key, Len, UnexpectedLen}};
+        {error, _Reason} = Error ->
+            [?V("<er>", []) || V],
+            true = ets:insert_new(?FAILED_TAB, {make_ref(), Error}),
+            {other_error, Error};
+        Other ->
+            [?V("<er>", []) || V],
+            true = ets:insert_new(?FAILED_TAB, {make_ref(), Other}),
+            {other_error, Other}
+    end.
+
+%% Change partition
+
+change_partition_args(#state{flu_names=FLUNames}=S) ->
+    %% [partition(FLUNames), S].
+    [partition_sym(FLUNames), S].
+
+change_partition(Partition,
+                 #state{verbose=Verbose, flu_names=FLUNames}=S) ->
+    [case Partition of
+         [] -> ?V("## Turn OFF partition: ~w~n", [Partition]);
+         _  -> ?V("## Turn ON  partition: ~w~n", [Partition])
+     end || Verbose],
+    machi_partition_simulator:always_these_partitions(Partition),
+    _ = machi_partition_simulator:get(FLUNames),
+    %% Don't wait for stable chain, tick will be executed on demand
+    %% in append oprations
+    _ = tick(S),
+
+    ok.
+
+%% Generators
+
+num() ->
+    choose(2, 5).
+
+cr_count(Num) ->
+    Num * 3.
+
+%% Returns a list like
+%% `[{#p_srvr{name=a, port=7501, ..}, "./eqc/data.eqc.a/"}, ...]'
+all_list_extra(Num) ->
+    {PortBase, DirBase} = get_port_dir_base(),
+    [begin
+         FLUNameStr = [$a + I - 1],
+         FLUName = list_to_atom(FLUNameStr),
+         MgrName = machi_flu_psup:make_mgr_supname(FLUName),
+         {#p_srvr{name=FLUName, address="localhost", port=PortBase+I,
+                  props=[{chmgr, MgrName}]},
+          DirBase ++ "/data.eqc." ++ FLUNameStr}
+     end || I <- lists:seq(1, Num)].
+
+sublist(L) ->
+    ?LET(K, nat(),
+    ?LET(L2, eqc_gen:vector(K, eqc_gen:oneof(L)),
+         lists:usort(L2))).
+
+%% Generator for possibly assymmetric partition information
+partition(FLUNames) ->
+    frequency([{10, return([])},
+               {20, non_empty(sublist(flu_ordered_pairs(FLUNames)))}]).
+
+%% Generator for symmetric partition information
+partition_sym(FLUNames) ->
+    ?LET(Pairs, non_empty(sublist(flu_pairs(FLUNames))),
+         lists:flatmap(fun({One, Another}) -> [{One, Another}, {Another, One}] end,
+                       Pairs)).
+
+flu_ordered_pairs(FLUNames) ->
+    [{From, To} || From <- FLUNames, To <- FLUNames, From =/= To].
+
+flu_pairs(FLUNames) ->
+    [{One, Another} || One <- FLUNames, Another <- FLUNames, One > Another].
+
+chunk() ->
+    non_empty(binary(10)).
+
+%% Properties
+
+prop_repair(Verbose) ->
+    error_logger:tty(false),
+    application:load(sasl),
+    application:set_env(sasl, sasl_error_logger, false),
+
+    Seed = {1445,935441,287549},
+    ?FORALL(Num, num(),
+    ?FORALL(Cmds, commands(?MODULE, initial_state(Num, Verbose)),
+            begin
+                Target = setup_target(Num, Seed, Verbose),
+                {H, S1, Res0} = run_commands(?MODULE, Cmds),
+                %% ?V("S1=~w~n", [S1]),
+                ?V("==== Start post operations, stabilize and confirm results~n", []),
+                _ = stabilize(commands_len(Cmds), Target),
+                {Dataloss, Critical} = confirm_result(Target),
+                _ = cleanup(Target),
+                pretty_commands(
+                  ?MODULE, Cmds, {H, S1, Res0},
+                  aggregate(with_title(cmds), command_names(Cmds),
+                  collect(with_title(length5), (length(Cmds) div 5) * 5,
+                          {Dataloss, Critical} =:= {0, 0})))
+            end)).
+
+prop_repair_par(Verbose) ->
+    error_logger:tty(false),
+    application:load(sasl),
+    application:set_env(sasl, sasl_error_logger, false),
+
+    Seed = {1445,935441,287549},
+    ?FORALL(Num, num(),
+    ?FORALL(Cmds,
+            %% Now try-and-err'ing, how to control command length and concurrency?
+            ?SUCHTHAT(Cmds0, ?SIZED(Size, resize(Size,
+                      parallel_commands(?MODULE, initial_state(Num, Verbose)))),
+                      commands_len(Cmds0) > 20
+                      andalso
+                      concurrency(Cmds0) > 2),
+            begin
+                CmdsLen= commands_len(Cmds),
+                Target = setup_target(Num, Seed, Verbose),
+                {Seq, Par, Res0} = run_parallel_commands(?MODULE, Cmds),
+                %% ?V("Seq=~w~n", [Seq]),
+                %% ?V("Par=~w~n", [Par]),
+                ?V("==== Start post operations, stabilize and confirm results~n", []),
+                {FinalRes, {Dataloss, Critical}} =
+                    case Res0 of
+                        ok ->
+                            Res1 = stabilize(CmdsLen, Target),
+                            {Res1, confirm_result(Target)};
+                        _ ->
+                            ?V("Res0=~w~n", [Res0]),
+                            {Res0, {undefined, undefined}}
+                end,
+                _ = cleanup(Target),
+                %% Process is leaking? This log line can be removed after fix.
+                [?V("process_count=~w~n", [erlang:system_info(process_count)]) || Verbose],
+                pretty_commands(
+                  ?MODULE, Cmds, {Seq, Par, Res0},
+                  aggregate(with_title(cmds), command_names(Cmds),
+                  collect(with_title(length5), (CmdsLen div 5) * 5,
+                  collect(with_title(conc),    concurrency(Cmds),
+                          {FinalRes, {Dataloss, Critical}} =:= {ok, {0, 0}})))
+                 )
+            end)).
+
+%% Initilization / setup
+
+%% Fake initialization function for debugging in shell like:
+%% > eqc_gen:sample(eqc_statem:commands(machi_ap_repair_eqc)).
+%% but not so helpful.
+initial_state() ->
+    #state{cr_count=3}.
+
+initial_state(Num, Verbose) ->
+    AllListE = all_list_extra(Num),
+    FLUNames = [P#p_srvr.name || {P, _Dir} <- AllListE],
+    MgrNames = [{Name, machi_flu_psup:make_mgr_supname(Name)} || Name <- FLUNames],
+    #state{num=Num, verbose=Verbose,
+           flu_names=FLUNames, mgr_names=MgrNames,
+           cr_count=cr_count(Num)}.
+
+setup_target(Num, Seed, Verbose) ->
+    %% ?V("setup_target(Num=~w, Seed=~w~nn", [Num, Seed]),
+    AllListE = all_list_extra(Num),
+    FLUNames = [P#p_srvr.name || {P, _Dir} <- AllListE],
+    MgrNames = [{Name, machi_flu_psup:make_mgr_supname(Name)} || Name <- FLUNames],
+    Dict = orddict:from_list([{P#p_srvr.name, P} || {P, _Dir} <- AllListE]),
+
+    setup_chain(Seed, AllListE, FLUNames, MgrNames, Dict),
+    _ = setup_cpool(AllListE, FLUNames, Dict),
+
+    Target = #target{flu_names=FLUNames, mgr_names=MgrNames,
+                     verbose=Verbose},
+    %% Don't wait for complete chain. Even partialy completed, the chain
+    %% should work fine. Right?
+    wait_until_stable(chain_state_all_ok(FLUNames), FLUNames, MgrNames,
+                      20, Verbose),
+    Target.
+
+setup_chain(Seed, AllListE, FLUNames, MgrNames, Dict) ->
+    ok = shutdown_hard(),
+    [begin
+         machi_test_util:clean_up_dir(Dir),
+         filelib:ensure_dir(Dir ++ "/not-used")
+     end || {_P, Dir} <- AllListE],
+    [catch ets:delete(T) || T <- tabs()],
+
+    [ets:new(T, [set, public, named_table,
+                 {write_concurrency, true}, {read_concurrency, true}]) ||
+        T <- tabs()],
+    {ok, _} = application:ensure_all_started(machi),
+
+    SimSpec = {part_sim,
+               {machi_partition_simulator, start_link, [{0,0,0}, 0, 100]},
+               permanent, 500, worker, []},
+    {ok, _PSimPid} = supervisor:start_child(machi_sup, SimSpec),
+    ok = machi_partition_simulator:set_seed(Seed),
+    _Partitions = machi_partition_simulator:get(FLUNames),
+
+    %% Start FLUs and setup the chain
+    FLUOpts = [{use_partition_simulator, true},
+               %% {private_write_verbose, true},
+               {active_mode, false},
+               {simulate_repair, false}],
+    [{ok, _} = machi_flu_psup:start_flu_package(Name, Port, Dir, FLUOpts) ||
+        {#p_srvr{name=Name, port=Port}, Dir} <- AllListE],
+    [machi_chain_manager1:set_chain_members(MgrName, Dict) || {_, MgrName} <- MgrNames],
+    ok.
+
+setup_cpool(AllListE, FLUNames, Dict) ->
+    Num = length(AllListE),
+    FCList = [begin
+                  {ok, PCPid} = machi_proxy_flu1_client:start_link(P),
+                  {Name, PCPid}
+              end || {_, #p_srvr{name=Name}=P} <- Dict],
+    %% CR clients are pooled, each has "name" which is interpreted "From"
+    %% side of simulated partition.
+    SimSelfNames = lists:append(lists:duplicate(cr_count(Num), FLUNames)),
+    CRList = [begin
+                  {ok, C} = machi_cr_client:start_link(
+                              [P || {_, P} <- Dict],
+                              [{use_partition_simulator, true},
+                               {simulator_self_name, SimSelfName},
+                               {simulator_members, FLUNames}]),
+                  {SimSelfName, C}
+              end || SimSelfName <- SimSelfNames],
+    catch ets:delete(cpool),
+    ets:new(cpool, [set, protected, named_table, {read_concurrency, true}]),
+    ets:insert(cpool, {fc_list, FCList}),
+    ets:insert(cpool, {cr_list, CRList}),
+    {CRList, FCList}.
+
+fc_list() ->
+    [{fc_list, FCList}] = ets:lookup(cpool, fc_list),
+    FCList.
+
+cr_list() ->
+    [{cr_list, CRList}] = ets:lookup(cpool, cr_list),
+    CRList.
+
+%% Post run_commands
+
+stabilize(0, _T) ->
+    ok;
+stabilize(_CmdsLen, #target{flu_names=FLUNames, mgr_names=MgrNames,
+                            verbose=Verbose}) ->
+    machi_partition_simulator:no_partitions(),
+    true = wait_until_stable(chain_state_all_ok(FLUNames), FLUNames, MgrNames,
+                             100, Verbose),
+    ok.
+
+chain_state_all_ok(FLUNames) ->
+    [{FLUName, {FLUNames, [], []}} || FLUName <- FLUNames].
+
+confirm_result(_T) ->
+    [{_, C} | _] = cr_list(),
+    [{written, _Written}, {accpt, Accpt},
+     {failed, Failed}, {critical, Critical}] = tab_counts(),
+    {OK, Dataloss} = confirm_written(C),
+    ?V("  Written=~w, DATALOSS=~w, Acceptable=~w~n", [OK, Dataloss, Accpt]),
+    ?V("  Failed=~w, Critical=~w~n~n", [Failed, Critical]),
+    DirBase = get_dir_base(),
+    Suffix = dump_file_suffix(),
+    case Failed of
+        0 -> ok;
+        _ ->
+            DumpFailed = filename:join(DirBase, "dump-failed-" ++ Suffix),
+            ?V("Dump failed ETS tab to: ~s~n", [DumpFailed]),
+            ets:tab2file(?FAILED_TAB, DumpFailed)
+    end,
+    case Critical of
+        0 -> ok;
+        _ ->
+            DumpCritical = filename:join(DirBase, "dump-critical-" ++ Suffix),
+            ?V("Dump critical ETS tab to: ~w~n", [DumpCritical]),
+            ets:tab2file(?CRITICAL_TAB, DumpCritical)
+    end,
+    {Dataloss, Critical}.
+
+confirm_written(C) ->
+    ets:foldl(
+      fun({Key, Bin}, {OK, NG}) ->
+              case assert_chunk(C, Key, Bin) of
+                  ok -> {OK+1, NG};
+                  {error, _} -> {OK, NG+1}
+              end
+      end, {0, 0}, ?WRITTEN_TAB).
+
+assert_chunk(C, {Off, Len, FileName}=Key, Bin) ->
+    %% TODO: This probably a bug, read_chunk respnds with filename of `string()' type
+    %% TODO : Use CSum instead of binary (after disuccsion about CSum is calmed down?)
+    NSInfo = undefined,
+    case (catch machi_cr_client:read_chunk(C, NSInfo, FileName, Off, Len, undefined, sec(3))) of
+        {ok, {[{FileName, Off, Bin, _}], []}} ->
+            ok;
+        {ok, Got} ->
+            ?V("read_chunk got different binary for Key=~p~n", [Key]),
+            ?V("    Expected: ~p~n", [{[{FileName, Off, Bin, <<"CSum-NYI">>}], []}]),
+            ?V("    Got:      ~p~n", [Got]),
+            {error, different_binary};
+        {error, Reason} ->
+            ?V("read_chunk error for Key=~p: ~p~n", [Key, Reason]),
+            {error, Reason};
+        Other ->
+            ?V("read_chunk other error for Key=~p: ~p~n", [Key, Other]),
+            {error, Other}
+    end.
+
+cleanup(_Target) ->
+    [begin unlink(FC), catch exit(FC, kill) end || {_, FC} <- fc_list()],
+    [begin unlink(CR), catch exit(CR, kill) end || {_, CR} <- cr_list()],
+    _ = shutdown_hard().
+
+%% Internal misc utilities
+
+eqc_verbose() ->
+    os:getenv("EQC_VERBOSE") =:= "true".
+
+eqc_timeout(Default) ->
+    PropTimeout = case os:getenv("EQC_TIME") of
+                      false -> Default;
+                      V -> list_to_integer(V)
+                  end,
+    {PropTimeout, PropTimeout * 300}.
+
+get_port_dir_base() ->
+    I = case os:getenv("EQC_BASE_PORT") of
+            false -> 0;
+            V -> list_to_integer(V)
+        end,
+    D = get_dir_base(),
+    {7400 + (I * 100), D ++ "/" ++ integer_to_list(I)}.
+
+get_dir_base() ->
+    case os:getenv("EQC_BASE_DIR") of
+        false -> "./eqc";
+        DD -> DD
+    end.
+
+shutdown_hard() ->
+    _STOP = application:stop(machi),
+    timer:sleep(100).
+
+tick(#state{flu_names=FLUNames, mgr_names=MgrNames,
+            verbose=Verbose}) ->
+    tick(FLUNames, MgrNames, Verbose).
+
+tick(FLUNames, MgrNames, Verbose) ->
+    tick(FLUNames, MgrNames, 2, 100, Verbose).
+
+tick(FLUNames, MgrNames, Iter, SleepMax, Verbose) ->
+    TickFun = tick_fun(FLUNames, MgrNames, self()),
+    TickFun(Iter, 0, SleepMax),
+    FCList = fc_list(),
+    [?V("## Chain state after tick()=~w~n", [chain_state(FCList)]) || Verbose].
+
+tick_fun(FLUNames, MgrNames, Parent) ->
+    fun(Iters, SleepMin, SleepMax) ->
+            %% ?V("^", []),
+            Trigger =
+                fun(FLUName, MgrName) ->
+                        random:seed(now()),
+                        [begin
+                             erlang:yield(),
+                             SleepMaxRand = random:uniform(SleepMax + 1),
+                             %% io:format(user, "{t}", []),
+                             Elapsed = machi_chain_manager1:sleep_ranked_order(
+                                         SleepMin, SleepMaxRand,
+                                         FLUName, FLUNames),
+                             MgrName ! tick_check_environment,
+                             %% Be more unfair by not sleeping here.
+                             timer:sleep(max(SleepMax - Elapsed, 1)),
+                             ok
+                         end || _ <- lists:seq(1, Iters)],
+                        Parent ! {done, self()}
+                end,
+            Pids = [{spawn(fun() -> Trigger(FLUName, MgrName) end), FLUName} ||
+                       {FLUName, MgrName} <- MgrNames ],
+            [receive
+                 {done, ThePid} ->
+                     ok
+             after 120*1000 ->
+                     exit({icky_timeout, M_name})
+             end || {ThePid, M_name} <- Pids]
+    end.
+
+wait_until_stable(ExpectedChainState, FLUNames, MgrNames, Verbose) ->
+    wait_until_stable(ExpectedChainState, FLUNames, MgrNames, 20, Verbose).
+
+wait_until_stable(ExpectedChainState, FLUNames, MgrNames, Retries, Verbose) ->
+    TickFun = tick_fun(FLUNames, MgrNames, self()),
+    FCList = fc_list(),
+    wait_until_stable1(ExpectedChainState, TickFun, FCList, Retries, Verbose).
+
+wait_until_stable1(ExpectedChainState, _TickFun, FCList, 0, _Verbose) ->
+    ?V("  [ERROR] _ExpectedChainState ~p\n", [ExpectedChainState]),
+    ?V("  [ERROR] wait_until_stable failed.... : ~p~n", [chain_state(FCList)]),
+    ?V("  [ERROR] norm....                     : ~p~n", [normalize_chain_state(chain_state(FCList))]),
+    false;
+wait_until_stable1(ExpectedChainState, TickFun, FCList, Reties, Verbose) ->
+    [TickFun(3, 0, 100) || _ <- lists:seq(1, 3)],
+    Normalized = normalize_chain_state(chain_state(FCList)),
+    case Normalized of
+        ExpectedChainState ->
+            [?V("  Got stable chain: ~w~n", [chain_state(FCList)]) || Verbose],
+            true;
+        _ ->
+            [?V("  NOT YET stable chain: ~w~n", [chain_state(FCList)]) || Verbose],
+            wait_until_stable1(ExpectedChainState, TickFun, FCList, Reties-1, Verbose)
+    end.
+
+normalize_chain_state(ChainState) ->
+    lists:usort([{FLUName,
+                  {lists:usort(UPI), lists:usort(Repairing), lists:usort(Down)}} ||
+                    {FLUName, {_EpochNo, UPI, Repairing, Down}} <- ChainState]).
+
+chain_state(FCList) ->
+    lists:usort(
+      [case (catch machi_proxy_flu1_client:read_latest_projection(C, private, sec(5))) of
+           {ok, #projection_v1{epoch_number=EpochNo, upi=UPI,
+                               repairing=Repairing, down=Down}} ->
+               {FLUName, {EpochNo, UPI, Repairing, Down}};
+           Other ->
+               {FLUName, Other}
+       end || {FLUName, C} <- FCList]).
+
+tabs() -> [?WRITTEN_TAB, ?ACCPT_TAB, ?FAILED_TAB, ?CRITICAL_TAB].
+
+tab_counts() ->
+    [{T, ets:info(T, size)} || T <- tabs()].
+
+sec(Sec) ->
+    timer:seconds(Sec).
+
+commands_len({SeqCmds, ParCmdsList} = _Cmds) ->
+    lists:sum([length(SeqCmds) | [length(P) || P <- ParCmdsList]]);
+commands_len(Cmds) ->
+    length(Cmds).
+
+concurrency({_SeqCmds, ParCmdsList} = _Cmds) -> length(ParCmdsList);
+concurrency(_) -> 1.
+
+dump_file_suffix() ->
+    {{Year, Month, Day}, {Hour, Min, Sec}} = calendar:local_time(),
+    lists:flatten(
+      io_lib:format("~4.10.0B-~2.10.0B-~2.10.0BT~2.10.0B:~2.10.0B:~2.10.0B.000Z",
+                    [Year, Month, Day, Hour, Min, Sec])).
+
+-endif. % EQC
+-endif. % TEST

test/machi_chain_manager1_converge_demo.erl

@@ -45,14 +45,18 @@
 
 -include_lib("eunit/include/eunit.hrl").
 
+help() ->
+    io:format("~s\n", [short_doc()]).
+
 short_doc() ->
 "
 A visualization of the convergence behavior of the chain self-management
 algorithm for Machi.
-  1. Set up 4 FLUs and chain manager pairs.
+
+  1. Set up some server and chain manager pairs.
   2. Create a number of different network partition scenarios, where
-     (simulated) partitions may be symmetric or asymmetric.  Then halt changing
+     (simulated) partitions may be symmetric or asymmetric.  Then stop changing
-     the partitions and keep the simulated network stable and broken.
+     the partitions and keep the simulated network stable (and perhaps broken).
   3. Run a number of iterations of the algorithm in parallel by poking each
      of the manager processes on a random'ish basis.
   4. Afterward, fetch the chain transition changes made by each FLU and
@@ -61,73 +65,65 @@ algorithm for Machi.
 During the iteration periods, the following is a cheatsheet for the output.
 See the internal source for interpreting the rest of the output.
 
-    'Let loose the dogs of war!'  Network instability
+    'SET partitions = '
-    'SET partitions = '           Network stability (but broken)
-    'x uses:' The FLU x has made an internal state transition.  The rest of
-              the line is a dump of internal state.
-    '{t}'     This is a tick event which triggers one of the manager processes
-              to evaluate its environment and perhaps make a state transition.
 
-A long chain of '{t}{t}{t}{t}' means that the chain state has settled
+        A pair-wise list of actors which cannot send messages.  The
-to a stable configuration, which is the goal of the algorithm.
+        list is uni-directional.  If there are three servers (a,b,c),
-Press control-c to interrupt....".
+        and if the partitions list is '[{a,b},{b,c}]' then all
+        messages from a->b and b->c will be dropped, but any other
+        sender->recipient messages will be delivered successfully.
 
-long_doc() ->
+    'x uses:'
-    "
-'Let loose the dogs of war!'
 
-    The simulated network is very unstable for a few seconds.
+        The FLU x has made an internal state transition and is using
+        this epoch's projection as operating chain configuration.  The
+        rest of the line is a summary of the projection.
 
-'x uses'
+    'CONFIRM epoch {N}'
 
-    After a single iteration, server x has determined that the chain
+        This message confirms that all of the servers listed in the
-    should be defined by the upi, repair, and down list in this record.
+        UPI and repairing lists of the projection at epoch {N} have
-    If all participants reach the same conclusion at the same epoch
+        agreed to use this projection because they all have written
-    number (and checksum, see next item below), then the chain is
+        this projection to their respective private projection stores.
-    stable, fully configured, and can provide full service.
+        The chain is now usable by/available to all clients.
 
-'epoch,E'
+    'Sweet, private projections are stable'
 
-    The epoch number for this decision is E.  The checksum of the full
+        This report announces that this iteration of the test cycle
-    record is not shown.  For purposes of the protocol, a server will
+        has passed successfully.  The report that follows briefly
-    'wedge' itself and refuse service (until a new config is chosen)
+        summarizes the latest private projection used by each
-    whenever: a). it sees a bigger epoch number mentioned somewhere, or
+        participating server.  For example, when in strong consistency
-    b). it sees the same epoch number but a different checksum.  In case
+        mode with 'a' as a witness and 'b' and 'c' as real servers:
-    of b), there was a network partition that has healed, and both sides
-    had chosen to operate with an identical epoch number but different
-    chain configs.
 
-'upi', 'repair', and 'down'
+        %% Legend:
+        %% server name, epoch ID, UPI list, repairing list, down list, ...
+        %%                         ... witness list, 'false' (a constant value)
 
-    Members in the chain that are fully in sync and thus preserving the
+        [{a,{{1116,<<23,143,246,55>>},[a,b],[],[c],[a],false}},
-    Update Propagation Invariant, up but under repair (simulated), and
+         {b,{{1116,<<23,143,246,55>>},[a,b],[],[c],[a],false}}]
-    down, respectively.
 
-'ps,[some list]'
+        Both servers 'a' and 'b' agree on epoch 1116 with epoch ID
+        {1116,<<23,143,246,55>>} where UPI=[a,b], repairing=[],
+        down=[c], and witnesses=[a].
 
-    The list of asymmetric network partitions.  {a,b} means that a
+        Server 'c' is not shown because 'c' has wedged itself OOS (out
-    cannot send to b, but b can send to a.
+        of service) by configuring a chain length of zero.
 
-    This partition list is recorded for debugging purposes but is *not*
+        If no servers are listed in the report (i.e. only '[]' is
-    used by the algorithm.  The algorithm only 'feels' its effects via
+        displayed), then all servers have wedged themselves OOS, and
-    simulated timeout whenever there's a partition in one of the
+        the chain is unavailable.
-    messaging directions.
 
-'nodes_up,[list]'
+    'DoIt,' 
 
-    The best guess right now of which ndoes are up, relative to the
+        This marks a group of tick events which trigger the manager
-    author node, specified by '{author,X}'
+        processes to evaluate their environment and perhaps make a
+        state transition.
 
-'SET partitions = [some list]'
+A long chain of 'DoIt,DoIt,DoIt,' means that the chain state has
+(probably) settled to a stable configuration, which is the goal of the
+algorithm.
 
-    All subsequent iterations should have a stable list of partitions,
+Press control-c to interrupt the test....".
-    i.e. the 'ps' list described should be stable.
-
-'{FLAP: x flaps n}!'
-
-    Server x has detected that it's flapping/oscillating after iteration
-    n of a naive/1st draft detection algorithm.
-".
 
 %% ' silly Emacs syntax highlighting....
 
@@ -138,6 +134,7 @@ long_doc() ->
 %%     convergence_demo_testfun(3).
 
 -define(DEFAULT_MGR_OPTS, [{private_write_verbose, false},
+                           {private_write_verbose_confirm, true},
                            {active_mode,false},
                            {use_partition_simulator, true}]).
 
@@ -154,7 +151,8 @@ convergence_demo_testfun(NumFLUs, MgrOpts0) ->
     %% Faster test startup, commented: io:format(user, short_doc(), []),
     %% Faster test startup, commented: timer:sleep(3000),
 
-    application:start(sasl),
+    Apps = [sasl, ranch],
+    [application:start(App) || App <- Apps],
 
     MgrOpts = MgrOpts0 ++ ?DEFAULT_MGR_OPTS,
     TcpPort = proplists:get_value(port_base, MgrOpts, 62877),
@@ -191,15 +189,18 @@ convergence_demo_testfun(NumFLUs, MgrOpts0) ->
              end || #p_srvr{name=Name}=P <- Ps],
     MembersDict = machi_projection:make_members_dict(Ps),
     Witnesses = proplists:get_value(witnesses, MgrOpts, []),
+    CMode = case {Witnesses, proplists:get_value(consistency_mode, MgrOpts,
+                                                 ap_mode)} of
+                {[_|_], _}   -> cp_mode;
+                {_, cp_mode} -> cp_mode;
+                {_, ap_mode} -> ap_mode
+            end,
     MgrNamez = [begin
                     MgrName = machi_flu_psup:make_mgr_supname(Name),
-                    ok = ?MGR:set_chain_members(MgrName,MembersDict,Witnesses),
+                    ok = ?MGR:set_chain_members(MgrName, ch_demo, 0, CMode,
+                                                MembersDict,Witnesses),
                     {Name, MgrName}
                 end || #p_srvr{name=Name} <- Ps],
-    CpApMode = case Witnesses /= [] of
-                   true  -> cp_mode;
-                   false -> ap_mode
-               end,
 
     try
       [{_, Ma}|_] = MgrNamez,
@@ -295,7 +296,7 @@ convergence_demo_testfun(NumFLUs, MgrOpts0) ->
                             private_projections_are_stable(Namez, DoIt)
                     end, false, lists:seq(0, MaxIters)),
            io:format(user, "\n~s Sweet, private projections are stable\n", [machi_util:pretty_time()]),
-           io:format(user, "\t~P\n", [get(stable), 14]),
+           io:format(user, "\t~P\n", [get(stable), 24]),
            io:format(user, "Rolling sanity check ... ", []),
            PrivProjs = [{Name, begin
                                    {ok, Ps8} = ?FLU_PC:get_all_projections(
@@ -307,9 +308,9 @@ convergence_demo_testfun(NumFLUs, MgrOpts0) ->
                [{FLU, true} = {FLU, ?MGR:projection_transitions_are_sane_retrospective(Psx, FLU)} ||
                    {FLU, Psx} <- PrivProjs]
            catch
-               _Err:_What when CpApMode == cp_mode ->
+               _Err:_What when CMode == cp_mode ->
                    io:format(user, "none proj skip detected, TODO? ", []);
-               _Err:_What when CpApMode == ap_mode ->
+               _Err:_What when CMode == ap_mode ->
                    io:format(user, "PrivProjs ~p\n", [PrivProjs]),
                    exit({line, ?LINE, _Err, _What})
            end,
@@ -375,9 +376,9 @@ timer:sleep(1234),
               {FLU, Psx} <- PrivProjs],
           io:format(user, "\nAll sanity checks pass, hooray!\n", [])
       catch
-          _Err:_What when CpApMode == cp_mode ->
+          _Err:_What when CMode == cp_mode ->
               io:format(user, "none proj skip detected, TODO? ", []);
-          _Err:_What when CpApMode == ap_mode ->
+          _Err:_What when CMode == ap_mode ->
               io:format(user, "Report ~p\n", [Report]),
               io:format(user, "PrivProjs ~p\n", [PrivProjs]),
               exit({line, ?LINE, _Err, _What})
@@ -394,7 +395,8 @@ timer:sleep(1234),
         exit(SupPid, normal),
         ok = machi_partition_simulator:stop(),
         [ok = ?FLU_PC:quit(PPid) || {_, PPid} <- Namez],
-        machi_util:wait_for_death(SupPid, 100)
+        machi_util:wait_for_death(SupPid, 100),
+        [application:start(App) || App <- lists:reverse(Apps)]
     end.
 
 %% Many of the static partition lists below have been problematic at one
@@ -719,7 +721,7 @@ private_projections_are_stable(Namez, PollFunc) ->
                 true
         end,
 
-    io:format(user, "\nPriv1 ~p\nPriv2 ~p\n1==2 ~w ap_disjoint ~w u_all_peers ~w cp_mode_agree ~w\n", [lists:sort(Private1), lists:sort(Private2), Private1 == Private2, AP_mode_disjoint_test_p, Unanimous_with_all_peers_p, CP_mode_agree_test_p]),
+    %% io:format(user, "\nPriv1 ~p\nPriv2 ~p\n1==2 ~w ap_disjoint ~w u_all_peers ~w cp_mode_agree ~w\n", [lists:sort(Private1), lists:sort(Private2), Private1 == Private2, AP_mode_disjoint_test_p, Unanimous_with_all_peers_p, CP_mode_agree_test_p]),
     Private1 == Private2 andalso
         AP_mode_disjoint_test_p andalso
         (

test/machi_chain_manager1_test.erl

@@ -273,78 +273,80 @@ make_prop_ets() ->
 
 -endif. % EQC
 
+make_advance_fun(FitList, FLUList, MgrList, Num) ->
+    fun() ->
+            [begin
+                 [catch machi_fitness:trigger_early_adjustment(Fit, Tgt) ||
+                     Fit <- FitList,
+                     Tgt <- FLUList ],
+                 [catch ?MGR:trigger_react_to_env(Mgr) || Mgr <- MgrList],
+                 ok
+             end || _ <- lists:seq(1, Num)]
+    end.
+
 smoke0_test() ->
-    {ok, _} = machi_partition_simulator:start_link({1,2,3}, 50, 50),
-    Host = "localhost",
     TcpPort = 6623,
-    {ok, FLUa} = machi_flu1:start_link([{a,TcpPort,"./data.a"}]),
+    {[Pa], [M0], _Dirs} = machi_test_util:start_flu_packages(
-    Pa = #p_srvr{name=a, address=Host, port=TcpPort},
+                            1, TcpPort, "./data.", []),
-    Members_Dict = machi_projection:make_members_dict([Pa]),
-    %% Egadz, more racing on startup, yay.  TODO fix.
-    timer:sleep(1),
     {ok, FLUaP} = ?FLU_PC:start_link(Pa),
-    {ok, M0} = ?MGR:start_link(a, Members_Dict, [{active_mode, false}]),
-    _SockA = machi_util:connect(Host, TcpPort),
     try
         pong = ?MGR:ping(M0)
     after
-        ok = ?MGR:stop(M0),
-        ok = machi_flu1:stop(FLUa),
         ok = ?FLU_PC:quit(FLUaP),
-        ok = machi_partition_simulator:stop()
+        machi_test_util:stop_flu_packages()
     end.
 
-smoke1_test() ->
+smoke1_test_() ->
-    machi_partition_simulator:start_link({1,2,3}, 100, 0),
+    {timeout, 1*60, fun() -> smoke1_test2() end}.
-    TcpPort = 62777,
-    FluInfo = [{a,TcpPort+0,"./data.a"}, {b,TcpPort+1,"./data.b"}, {c,TcpPort+2,"./data.c"}],
-    P_s = [#p_srvr{name=Name, address="localhost", port=Port} ||
-              {Name,Port,_Dir} <- FluInfo],
 
-    [machi_flu1_test:clean_up_data_dir(Dir) || {_,_,Dir} <- FluInfo],
+smoke1_test2() ->
-    FLUs = [element(2, machi_flu1:start_link([{Name,Port,Dir}])) ||
+    TcpPort = 62777,
-               {Name,Port,Dir} <- FluInfo],
+    MgrOpts = [{active_mode,false}],
-    MembersDict = machi_projection:make_members_dict(P_s),
-    {ok, M0} = ?MGR:start_link(a, MembersDict, [{active_mode,false}]),
     try
-        {ok, P1} = ?MGR:test_calc_projection(M0, false),
+        {Ps, MgrNames, _Dirs} = machi_test_util:start_flu_packages(
+                                  3, TcpPort, "./data.", MgrOpts),
+        MembersDict = machi_projection:make_members_dict(Ps),
+        [machi_chain_manager1:set_chain_members(M, MembersDict) || M <- MgrNames],
+        Ma = hd(MgrNames),
+
+        {ok, P1} = ?MGR:test_calc_projection(Ma, false),
         % DERP! Check for race with manager's proxy vs. proj listener
-        case ?MGR:test_read_latest_public_projection(M0, false) of
+        ok = lists:foldl(
-            {error, partition} -> timer:sleep(500);
+                    fun(_, {_,{true,[{c,ok},{b,ok},{a,ok}]}}) ->
-            _                  -> ok
+                            ok;             % Short-circuit remaining attempts
-        end,
+                       (_, ok) ->
-        {remote_write_results,{true,[{c,ok},{b,ok},{a,ok}]}} =
+                            ok;             % Skip remaining!
-            ?MGR:test_write_public_projection(M0, P1),
+                       (_, _Else) ->
-        {unanimous, P1, Extra1} = ?MGR:test_read_latest_public_projection(M0, false),
+                            timer:sleep(10),
+                            ?MGR:test_write_public_projection(Ma, P1)
+                    end, not_ok, lists:seq(1, 1000)),
+        %% Writing the exact same projection multiple times returns ok:
+        %% no change!
+        {_,{true,[{c,ok},{b,ok},{a,ok}]}} =  ?MGR:test_write_public_projection(Ma, P1),
+        {unanimous, P1, Extra1} = ?MGR:test_read_latest_public_projection(Ma, false),
 
         ok
     after
-        ok = ?MGR:stop(M0),
+        machi_test_util:stop_flu_packages()
-        [ok = machi_flu1:stop(X) || X <- FLUs],
-        ok = machi_partition_simulator:stop()
     end.
 
-nonunanimous_setup_and_fix_test() ->
+nonunanimous_setup_and_fix_test_() ->
-    machi_partition_simulator:start_link({1,2,3}, 100, 0),
+    os:cmd("rm -f /tmp/moomoo.*"),
-    TcpPort = 62877,
+    {timeout, 1*60, fun() -> nonunanimous_setup_and_fix_test2() end}.
-    FluInfo = [{a,TcpPort+0,"./data.a"}, {b,TcpPort+1,"./data.b"}],
+
-    P_s = [#p_srvr{name=Name, address="localhost", port=Port} ||
+nonunanimous_setup_and_fix_test2() ->
-              {Name,Port,_Dir} <- FluInfo],
+    TcpPort = 62877,
+    MgrOpts = [{active_mode,false}],
+    {Ps, [Ma,Mb,Mc], Dirs} = machi_test_util:start_flu_packages(
+                             3, TcpPort, "./data.", MgrOpts),
+    MembersDict = machi_projection:make_members_dict(Ps),
+    ChainName = my_little_chain,
+    [machi_chain_manager1:set_chain_members(M, ChainName, 0, ap_mode,
+                                            MembersDict, []) || M <- [Ma, Mb]],
+
+    [Proxy_a, Proxy_b, Proxy_c] = Proxies =
+        [element(2, ?FLU_PC:start_link(P)) || P <- Ps],
 
-    [machi_flu1_test:clean_up_data_dir(Dir) || {_,_,Dir} <- FluInfo],
-    {ok, SupPid} = machi_flu_sup:start_link(),
-    Opts = [{active_mode, false}],
-    %% {ok, Mb} = ?MGR:start_link(b, MembersDict, [{active_mode, false}]++XX),
-    [{ok,_}=machi_flu_psup:start_flu_package(Name, Port, Dir, Opts) ||
-               {Name,Port,Dir} <- FluInfo],
-    FLUs = [machi_flu_psup:make_flu_regname(Name) ||
-               {Name,_Port,_Dir} <- FluInfo],
-    [Proxy_a, Proxy_b] = Proxies =
-        [element(2,?FLU_PC:start_link(P)) || P <- P_s],
-    MembersDict = machi_projection:make_members_dict(P_s),
-    [Ma,Mb] = [a_chmgr, b_chmgr],
-    ok = machi_chain_manager1:set_chain_members(Ma, MembersDict, []),
-    ok = machi_chain_manager1:set_chain_members(Mb, MembersDict, []),
     try
         {ok, P1} = ?MGR:test_calc_projection(Ma, false),
 
@@ -381,16 +383,114 @@ nonunanimous_setup_and_fix_test() ->
         {ok, P2pb} = ?FLU_PC:read_latest_projection(Proxy_b, private),
         P2 = P2pb#projection_v1{dbg2=[]},
 
-        %% Pspam = machi_projection:update_checksum(
+        Mgrs = [a_chmgr, b_chmgr, c_chmgr],
-        %%           P1b#projection_v1{epoch_number=?SPAM_PROJ_EPOCH,
+        Advance = make_advance_fun([a_fitness,b_fitness,c_fitness],
-        %%                             dbg=[hello_spam]}),
+                                   [a,b,c],
-        %% ok = ?FLU_PC:write_projection(Proxy_b, public, Pspam),
+                                   Mgrs,
+                                   3),
+        Advance(),
+        {_, _, TheEpoch_3} = ?MGR:trigger_react_to_env(Ma),
+        {_, _, TheEpoch_3} = ?MGR:trigger_react_to_env(Mb),
+        {_, _, TheEpoch_3} = ?MGR:trigger_react_to_env(Mc),
 
+        %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+        io:format("STEP: Remove 'a' from the chain.\n", []),
+
+        MembersDict4 = machi_projection:make_members_dict(tl(Ps)),
+        ok = machi_chain_manager1:set_chain_members(
+               Mb, ChainName, TheEpoch_3, ap_mode, MembersDict4, []),
+
+        Advance(),
+        {ok, {true, _,_,_}} = ?FLU_PC:wedge_status(Proxy_a),
+        {_, _, TheEpoch_4} = ?MGR:trigger_react_to_env(Mb),
+        {_, _, TheEpoch_4} = ?MGR:trigger_react_to_env(Mc),
+        [{ok, #projection_v1{upi=[b,c], repairing=[]}} =
+             ?FLU_PC:read_latest_projection(Pxy, private) || Pxy <- tl(Proxies)],
+
+        %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+        io:format("STEP: Add a to the chain again (a is running).\n", []),
+
+        MembersDict5 = machi_projection:make_members_dict(Ps),
+        ok = machi_chain_manager1:set_chain_members(
+               Mb, ChainName, TheEpoch_4, ap_mode, MembersDict5, []),
+
+        Advance(),
+        {_, _, TheEpoch_5} = ?MGR:trigger_react_to_env(Ma),
+        {_, _, TheEpoch_5} = ?MGR:trigger_react_to_env(Mb),
+        {_, _, TheEpoch_5} = ?MGR:trigger_react_to_env(Mc),
+        [{ok, #projection_v1{upi=[b,c], repairing=[a]}} =
+             ?FLU_PC:read_latest_projection(Pxy, private) || Pxy <- Proxies],
+
+        %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+        io:format("STEP: Stop a while a chain member, advance b&c.\n", []),
+
+        ok = machi_flu_psup:stop_flu_package(a),
+        Advance(),
+        {_, _, TheEpoch_6} = ?MGR:trigger_react_to_env(Mb),
+        {_, _, TheEpoch_6} = ?MGR:trigger_react_to_env(Mc),
+        [{ok, #projection_v1{upi=[b,c], repairing=[]}} =
+             ?FLU_PC:read_latest_projection(Pxy, private) || Pxy <- tl(Proxies)],
+
+        %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+        io:format("STEP: Remove 'a' from the chain.\n", []),
+
+        MembersDict7 = machi_projection:make_members_dict(tl(Ps)),
+        ok = machi_chain_manager1:set_chain_members(
+               Mb, ChainName, TheEpoch_6, ap_mode, MembersDict7, []),
+
+        Advance(),
+        {_, _, TheEpoch_7} = ?MGR:trigger_react_to_env(Mb),
+        {_, _, TheEpoch_7} = ?MGR:trigger_react_to_env(Mc),
+        [{ok, #projection_v1{upi=[b,c], repairing=[]}} =
+             ?FLU_PC:read_latest_projection(Pxy, private) || Pxy <- tl(Proxies)],
+
+        %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+        io:format("STEP: Start a, advance.\n", []),
+
+        Opts = [{active_mode, false}, {initial_wedged, true}],
+        #p_srvr{name=NameA} = hd(Ps),
+        {ok,_}=machi_flu_psup:start_flu_package(NameA, TcpPort+1, hd(Dirs), Opts),
+        Advance(),
+        {ok, {true, _,_,_}} = ?FLU_PC:wedge_status(Proxy_a),
+        {ok, {false, EpochID_8,_,_}} = ?FLU_PC:wedge_status(Proxy_b),
+        {ok, {false, EpochID_8,_,_}} = ?FLU_PC:wedge_status(Proxy_c),
+        [{ok, #projection_v1{upi=[b,c], repairing=[]}} =
+             ?FLU_PC:read_latest_projection(Pxy, private) || Pxy <- tl(Proxies)],
+
+        %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+        io:format("STEP: Stop a, delete a's data, leave it stopped\n", []),
+
+        ok = machi_flu_psup:stop_flu_package(a),
+        Advance(),
+        machi_flu1_test:clean_up_data_dir(hd(Dirs)),
+        {ok, {false, _,_,_}} = ?FLU_PC:wedge_status(Proxy_b),
+        {ok, {false, _,_,_}} = ?FLU_PC:wedge_status(Proxy_c),
+
+        %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+        io:format("STEP: Add a to the chain again (a is stopped).\n", []),
+
+        MembersDict9 = machi_projection:make_members_dict(Ps),
+        {_, _, TheEpoch_9} = ?MGR:trigger_react_to_env(Mb),
+        ok = machi_chain_manager1:set_chain_members(
+               Mb, ChainName, TheEpoch_9, ap_mode, MembersDict9, []),
+        Advance(),
+        {_, _, TheEpoch_9b} = ?MGR:trigger_react_to_env(Mb),
+        true = (TheEpoch_9b > TheEpoch_9),
+
+        %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+        io:format("STEP: Start a, and it joins like it ought to\n", []),
+
+        {ok,_}=machi_flu_psup:start_flu_package(NameA, TcpPort+1, hd(Dirs), Opts),
+        Advance(),
+        {ok, {false, {TheEpoch10,_},_,_}} = ?FLU_PC:wedge_status(Proxy_a),
+        {ok, {false, {TheEpoch10,_},_,_}} = ?FLU_PC:wedge_status(Proxy_b),
+        {ok, {false, {TheEpoch10,_},_,_}} = ?FLU_PC:wedge_status(Proxy_c),
+        [{ok, #projection_v1{upi=[b,c], repairing=[a]}} =
+             ?FLU_PC:read_latest_projection(Pxy, private) || Pxy <- Proxies],
         ok
     after
-        exit(SupPid, normal),
         [ok = ?FLU_PC:quit(X) || X <- Proxies],
-        ok = machi_partition_simulator:stop()
+        machi_test_util:stop_flu_packages()
     end.
 
 unanimous_report_test() ->

test/machi_cinfo_test.erl

@@ -0,0 +1,68 @@
+%% -------------------------------------------------------------------
+%%
+%% Copyright (c) 2007-2015 Basho Technologies, Inc.  All Rights Reserved.
+%%
+%% This file is provided to you under the Apache License,
+%% Version 2.0 (the "License"); you may not use this file
+%% except in compliance with the License.  You may obtain
+%% a copy of the License at
+%%
+%%   http://www.apache.org/licenses/LICENSE-2.0
+%%
+%% Unless required by applicable law or agreed to in writing,
+%% software distributed under the License is distributed on an
+%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+%% KIND, either express or implied.  See the License for the
+%% specific language governing permissions and limitations
+%% under the License.
+%%
+%% -------------------------------------------------------------------
+
+-module(machi_cinfo_test).
+
+-ifdef(TEST).
+-ifndef(PULSE).
+
+-include_lib("eunit/include/eunit.hrl").
+
+-include("machi_projection.hrl").
+
+%% smoke_test() will try just dump cluster_info and call each functions
+
+smoke_test_() ->
+    {setup,
+     fun setup/0,
+     fun cleanup/1,
+     [
+      fun() -> machi_cinfo:public_projection(a) end,
+      fun() -> machi_cinfo:private_projection(a) end,
+      fun() -> machi_cinfo:fitness(a) end,
+      fun() -> machi_cinfo:chain_manager(a) end,
+      fun() -> machi_cinfo:flu1(a) end,
+      fun() -> machi_cinfo:dump() end
+     ]}.
+
+setup() ->
+    machi_cinfo:register(),
+    Ps = [{a,#p_srvr{name=a, address="localhost", port=5555, props="./data.a"}},
+          {b,#p_srvr{name=b, address="localhost", port=5556, props="./data.b"}},
+          {c,#p_srvr{name=c, address="localhost", port=5557, props="./data.c"}}
+         ],
+    [os:cmd("rm -rf " ++ P#p_srvr.props) || {_,P} <- Ps],
+    {ok, SupPid} = machi_sup:start_link(),
+    %% Only run a, don't run b & c so we have 100% failures talking to them
+    [begin
+         #p_srvr{name=Name, port=Port, props=Dir} = P,
+         {ok, _} = machi_flu_psup:start_flu_package(Name, Port, Dir, [])
+     end || {_,P} <- [hd(Ps)]],
+    machi_chain_manager1:set_chain_members(a_chmgr, orddict:from_list(Ps)),
+    {SupPid, Ps}.
+
+cleanup({SupPid, Ps}) ->
+    exit(SupPid, normal),
+    [os:cmd("rm -rf " ++ P#p_srvr.props) || {_,P} <- Ps],
+    machi_util:wait_for_death(SupPid, 100),
+    ok.
+
+-endif. % !PULSE
+-endif. % TEST

test/machi_cr_client_test.erl

@@ -32,6 +32,7 @@ smoke_test_() -> {timeout, 1*60, fun() -> smoke_test2() end}.
 
 setup_smoke_test(Host, PortBase, Os, Witness_list) ->
     os:cmd("rm -rf ./data.a ./data.b ./data.c"),
+    {ok, _} = machi_util:wait_for_life(machi_flu_sup, 100),
 
     F = fun(X) -> case lists:member(X, Witness_list) of
                       true ->
@@ -57,9 +58,15 @@ setup_smoke_test(Host, PortBase, Os, Witness_list) ->
     %% 4. Wait until all others are using epoch id from #3.
     %%
     %% Damn, this is a pain to make 100% deterministic, bleh.
-    ok = machi_chain_manager1:set_chain_members(a_chmgr, D, Witness_list),
+    CMode = if Witness_list == [] -> ap_mode;
-    ok = machi_chain_manager1:set_chain_members(b_chmgr, D, Witness_list),
+               Witness_list /= [] -> cp_mode
-    ok = machi_chain_manager1:set_chain_members(c_chmgr, D, Witness_list),
+            end,
+    ok = machi_chain_manager1:set_chain_members(a_chmgr, ch0, 0, CMode,
+                                                D, Witness_list),
+    ok = machi_chain_manager1:set_chain_members(b_chmgr, ch0, 0, CMode,
+                                                D, Witness_list),
+    ok = machi_chain_manager1:set_chain_members(c_chmgr, ch0, 0, CMode,
+                                                D, Witness_list),
     run_ticks([a_chmgr,b_chmgr,c_chmgr]),
     %% Everyone is settled on the same damn epoch id.
     {ok, EpochID} = machi_flu1_client:get_latest_epochid(Host, PortBase+0,
@@ -95,11 +102,13 @@ run_ticks(MgrList) ->
     ok.
 
 smoke_test2() ->
-    {ok, SupPid} = machi_flu_sup:start_link(),
+    {ok, SupPid} = machi_sup:start_link(),
     error_logger:tty(false),
     try
         Prefix = <<"pre">>,
         Chunk1 = <<"yochunk">>,
+        NSInfo = undefined,
+        NoCSum = <<>>,
         Host = "localhost",
         PortBase = 64454,
         Os = [{ignore_stability_time, true}, {active_mode, false}],
@@ -107,99 +116,119 @@ smoke_test2() ->
 
         %% Whew ... ok, now start some damn tests.
         {ok, C1} = machi_cr_client:start_link([P || {_,P}<-orddict:to_list(D)]),
-        machi_cr_client:append_chunk(C1, Prefix, Chunk1),
+        machi_cr_client:append_chunk(C1, NSInfo, Prefix, Chunk1, NoCSum),
         {ok, {Off1,Size1,File1}} =
-            machi_cr_client:append_chunk(C1, Prefix, Chunk1),
+            machi_cr_client:append_chunk(C1, NSInfo, Prefix, Chunk1, NoCSum),
-        Chunk1_badcs = {<<?CSUM_TAG_CLIENT_SHA:8, 0:(8*20)>>, Chunk1},
+        BadCSum = {?CSUM_TAG_CLIENT_SHA, crypto:hash(sha, "foo")},
         {error, bad_checksum} =
-            machi_cr_client:append_chunk(C1, Prefix, Chunk1_badcs),
+            machi_cr_client:append_chunk(C1, NSInfo, Prefix, Chunk1, BadCSum),
-        {ok, Chunk1} = machi_cr_client:read_chunk(C1, File1, Off1, Size1),
+        {ok, {[{_, Off1, Chunk1, _}], []}} =
+            machi_cr_client:read_chunk(C1, NSInfo, File1, Off1, Size1, undefined),
         {ok, PPP} = machi_flu1_client:read_latest_projection(Host, PortBase+0,
                                                              private),
         %% Verify that the client's CR wrote to all of them.
-        [{ok, Chunk1} = machi_flu1_client:read_chunk(
+        [{ok, {[{_, Off1, Chunk1, _}], []}} =
-                          Host, PortBase+X, EpochID, File1, Off1, Size1) ||
+             machi_flu1_client:read_chunk(
+               Host, PortBase+X, NSInfo, EpochID, File1, Off1, Size1, undefined) ||
             X <- [0,1,2] ],
 
         %% Test read repair: Manually write to head, then verify that
         %% read-repair fixes all.
         FooOff1 = Off1 + (1024*1024),
         [{error, not_written} = machi_flu1_client:read_chunk(
-                                  Host, PortBase+X, EpochID,
+                                  Host, PortBase+X, NSInfo, EpochID,
-                                  File1, FooOff1, Size1) || X <- [0,1,2] ],
+                                  File1, FooOff1, Size1, undefined) || X <- [0,1,2] ],
-        ok = machi_flu1_client:write_chunk(Host, PortBase+0, EpochID,
+        ok = machi_flu1_client:write_chunk(Host, PortBase+0, NSInfo, EpochID,
-                                           File1, FooOff1, Chunk1),
+                                           File1, FooOff1, Chunk1, NoCSum),
-        {ok, Chunk1} = machi_cr_client:read_chunk(C1, File1, FooOff1, Size1),
+        {ok, {[{File1, FooOff1, Chunk1, _}=_YY], []}} =
-        [{X,{ok, Chunk1}} = {X,machi_flu1_client:read_chunk(
+            machi_flu1_client:read_chunk(Host, PortBase+0, NSInfo, EpochID,
-                                 Host, PortBase+X, EpochID,
+                                         File1, FooOff1, Size1, undefined),
-                                 File1, FooOff1, Size1)} || X <- [0,1,2] ],
+        {ok, {[{File1, FooOff1, Chunk1, _}], []}} =
+            machi_cr_client:read_chunk(C1, NSInfo, File1, FooOff1, Size1, undefined),
+        [?assertMatch({X,{ok, {[{_, FooOff1, Chunk1, _}], []}}},
+                      {X,machi_flu1_client:read_chunk(
+                                 Host, PortBase+X, NSInfo, EpochID,
+                                 File1, FooOff1, Size1, undefined)})
+         || X <- [0,1,2] ],
 
         %% Test read repair: Manually write to middle, then same checking.
         FooOff2 = Off1 + (2*1024*1024),
         Chunk2 = <<"Middle repair chunk">>,
         Size2 = size(Chunk2),
-        ok = machi_flu1_client:write_chunk(Host, PortBase+1, EpochID,
+        ok = machi_flu1_client:write_chunk(Host, PortBase+1, NSInfo, EpochID,
-                                           File1, FooOff2, Chunk2),
+                                           File1, FooOff2, Chunk2, NoCSum),
-        {ok, Chunk2} = machi_cr_client:read_chunk(C1, File1, FooOff2, Size2),
+        {ok, {[{File1, FooOff2, Chunk2, _}], []}} =
-        [{X,{ok, Chunk2}} = {X,machi_flu1_client:read_chunk(
+            machi_cr_client:read_chunk(C1, NSInfo, File1, FooOff2, Size2, undefined),
-                                 Host, PortBase+X, EpochID,
+        [{X,{ok, {[{File1, FooOff2, Chunk2, _}], []}}} =
-                                 File1, FooOff2, Size2)} || X <- [0,1,2] ],
+             {X,machi_flu1_client:read_chunk(
+                  Host, PortBase+X, NSInfo, EpochID,
+                  File1, FooOff2, Size2, undefined)} || X <- [0,1,2] ],
 
         %% Misc API smoke & minor regression checks
-        {error, bad_arg} = machi_cr_client:read_chunk(C1, <<"no">>,
+        {error, bad_arg} = machi_cr_client:read_chunk(C1, NSInfo, <<"no">>,
-                                                          999999999, 1),
+                                                      999999999, 1, undefined),
-        {error, not_written} = machi_cr_client:read_chunk(C1, File1,
+        {ok, {[{File1,Off1,Chunk1,_}, {File1,FooOff1,Chunk1,_}, {File1,FooOff2,Chunk2,_}],
-                                                           Off1, 88888888),
+              []}} =
+            machi_cr_client:read_chunk(C1, NSInfo, File1, Off1, 88888888, undefined),
         %% Checksum list return value is a primitive binary().
         {ok, KludgeBin} = machi_cr_client:checksum_list(C1, File1),
         true = is_binary(KludgeBin),
 
         {error, bad_arg} = machi_cr_client:checksum_list(C1, <<"!!!!">>),
-        %% Exactly one file right now
+        io:format(user, "\nFiles = ~p\n", [machi_cr_client:list_files(C1)]),
+        %% Exactly one file right now, e.g.,
+        %% {ok,[{2098202,<<"pre^b144ef13-db4d-4c9f-96e7-caff02dc754f^1">>}]}
         {ok, [_]} = machi_cr_client:list_files(C1),
 
-        %% Go back and test append_chunk_extra() and write_chunk()
+        %% Go back and test append_chunk() + extra and write_chunk()
         Chunk10 = <<"It's a different chunk!">>,
         Size10 = byte_size(Chunk10),
         Extra10 = 5,
+        Opts1 = #append_opts{chunk_extra=Extra10*Size10},
         {ok, {Off10,Size10,File10}} =
-            machi_cr_client:append_chunk_extra(C1, Prefix, Chunk10,
+            machi_cr_client:append_chunk(C1, NSInfo, Prefix, Chunk10,
-                                               Extra10 * Size10),
+                                         NoCSum, Opts1),
-        {ok, Chunk10} = machi_cr_client:read_chunk(C1, File10, Off10, Size10),
+        {ok, {[{_, Off10, Chunk10, _}], []}} =
+            machi_cr_client:read_chunk(C1, NSInfo, File10, Off10, Size10, undefined),
         [begin
              Offx = Off10 + (Seq * Size10),
              %% TODO: uncomment written/not_written enforcement is available.
-             %% {error,not_written} = machi_cr_client:read_chunk(C1, File10,
+             %% {error,not_written} = machi_cr_client:read_chunk(C1, NSInfo, File10,
              %%                                                  Offx, Size10),
              {ok, {Offx,Size10,File10}} =
-                 machi_cr_client:write_chunk(C1, File10, Offx, Chunk10),
+                 machi_cr_client:write_chunk(C1, NSInfo, File10, Offx, Chunk10, NoCSum),
-             {ok, Chunk10} = machi_cr_client:read_chunk(C1, File10, Offx,
+             {ok, {[{_, Offx, Chunk10, _}], []}} =
-                                                        Size10)
+                 machi_cr_client:read_chunk(C1, NSInfo, File10, Offx, Size10, undefined)
          end || Seq <- lists:seq(1, Extra10)],
         {ok, {Off11,Size11,File11}} =
-            machi_cr_client:append_chunk(C1, Prefix, Chunk10),
+            machi_cr_client:append_chunk(C1, NSInfo, Prefix, Chunk10, NoCSum),
-        %% Double-check that our reserved extra bytes were really honored!
+        %% %% Double-check that our reserved extra bytes were really honored!
-        true = (Off11 > (Off10 + (Extra10 * Size10))),
+        %% true = (Off11 > (Off10 + (Extra10 * Size10))),
+io:format(user, "\nFiles = ~p\n", [machi_cr_client:list_files(C1)]),
 
         ok
     after
+        exit(SupPid, normal),
+        machi_util:wait_for_death(SupPid, 100),
         error_logger:tty(true),
-        catch application:stop(machi),
+        catch application:stop(machi)
-        exit(SupPid, normal)
     end.
 
 witness_smoke_test_() -> {timeout, 1*60, fun() -> witness_smoke_test2() end}.
 
 witness_smoke_test2() ->
-    SupPid = case machi_flu_sup:start_link() of 
+    SupPid = case machi_sup:start_link() of
                 {ok, P} -> P;
                 {error, {already_started, P1}} -> P1;
                 Other -> error(Other)
     end,
-    error_logger:tty(false),
+    %% TODO: I wonder why commenting this out makes this test pass
+    %% error_logger:tty(true),
     try
         Prefix = <<"pre">>,
         Chunk1 = <<"yochunk">>,
+        NSInfo = undefined,
+        NoCSum = <<>>,
         Host = "localhost",
         PortBase = 64444,
         Os = [{ignore_stability_time, true}, {active_mode, false},
@@ -209,13 +238,15 @@ witness_smoke_test2() ->
 
         %% Whew ... ok, now start some damn tests.
         {ok, C1} = machi_cr_client:start_link([P || {_,P}<-orddict:to_list(D)]),
-        {ok, _} = machi_cr_client:append_chunk(C1, Prefix, Chunk1),
+        {ok, _} = machi_cr_client:append_chunk(C1, NSInfo, Prefix,
+                                               Chunk1, NoCSum),
         {ok, {Off1,Size1,File1}} =
-            machi_cr_client:append_chunk(C1, Prefix, Chunk1),
+            machi_cr_client:append_chunk(C1, NSInfo, Prefix, Chunk1, NoCSum),
-        Chunk1_badcs = {<<?CSUM_TAG_CLIENT_SHA:8, 0:(8*20)>>, Chunk1},
+        BadCSum = {?CSUM_TAG_CLIENT_SHA, crypto:hash(sha, "foo")},
         {error, bad_checksum} =
-            machi_cr_client:append_chunk(C1, Prefix, Chunk1_badcs),
+            machi_cr_client:append_chunk(C1, NSInfo, Prefix, Chunk1, BadCSum),
-        {ok, Chunk1} = machi_cr_client:read_chunk(C1, File1, Off1, Size1),
+        {ok, {[{_, Off1, Chunk1, _}], []}} =
+            machi_cr_client:read_chunk(C1, NSInfo, File1, Off1, Size1, undefined),
 
         %% Stop 'b' and let the chain reset.
         ok = machi_flu_psup:stop_flu_package(b),
@@ -228,23 +259,25 @@ witness_smoke_test2() ->
         %% Let's wedge OurWitness and see what happens: timeout/partition.
         #p_srvr{name=WitName, address=WitA, port=WitP} =
             orddict:fetch(OurWitness, D),
-        {ok, {false, EpochID2}} = machi_flu1_client:wedge_status(WitA, WitP),
+        {ok, {false, EpochID2,_,_}} = machi_flu1_client:wedge_status(WitA, WitP),
         machi_flu1:wedge_myself(WitName, EpochID2),
         case machi_flu1_client:wedge_status(WitA, WitP) of
-            {ok, {true,  EpochID2}} ->
+            {ok, {true,  EpochID2,_,_}} ->
                 ok;
-            {ok, {false,  EpochID2}} ->
+            {ok, {false,  EpochID2,_,_}} ->
                 %% This is racy.  Work around it by sleeping a while.
                 timer:sleep(6*1000),
-                {ok, {true,  EpochID2}} =
+                {ok, {true,  EpochID2,_,_}} =
                     machi_flu1_client:wedge_status(WitA, WitP)
         end,
 
         %% Chunk1 is still readable: not affected by wedged witness head.
-        {ok, Chunk1} = machi_cr_client:read_chunk(C1, File1, Off1, Size1),
+        {ok, {[{_, Off1, Chunk1, _}], []}} =
+            machi_cr_client:read_chunk(C1, NSInfo, File1, Off1, Size1, undefined),
         %% But because the head is wedged, an append will fail.
         {error, partition} =
-            machi_cr_client:append_chunk(C1, Prefix, Chunk1, 1*1000),
+            machi_cr_client:append_chunk(C1, NSInfo, Prefix, Chunk1, NoCSum,
+                                         #append_opts{}, 1*1000),
 
         %% The witness's wedge status should cause timeout/partition
         %% for write_chunk also.
@@ -253,7 +286,7 @@ witness_smoke_test2() ->
         File10 = File1,
         Offx = Off1 + (1 * Size10),
         {error, partition} =
-            machi_cr_client:write_chunk(C1, File10, Offx, Chunk10, 1*1000),
+            machi_cr_client:write_chunk(C1, NSInfo, File10, Offx, Chunk10, NoCSum, 1*1000),
 
         ok
     after

test/machi_csum_table_test.erl

@@ -1,31 +1,131 @@
 -module(machi_csum_table_test).
 -compile(export_all).
 
+-include_lib("eunit/include/eunit.hrl").
+-define(HDR, {0, 1024, none}).
+
+cleanup(Dir) ->
+    os:cmd("rm -rf " ++ Dir).
+
 smoke_test() ->
     Filename = "./temp-checksum-dumb-file",
-    _ = file:delete(Filename),
+    _ = cleanup(Filename),
     {ok, MC} = machi_csum_table:open(Filename, []),
-    {Offset, Size, Checksum} = {64, 34, <<"deadbeef">>},
+    ?assertEqual([{1024, infinity}],
-    {error, unknown_chunk} = machi_csum_table:find(MC, Offset, Size),
+                 machi_csum_table:calc_unwritten_bytes(MC)),
+    Entry = {Offset, Size, Checksum} = {1064, 34, <<"deadbeef">>},
+    [] = machi_csum_table:find(MC, Offset, Size),
     ok = machi_csum_table:write(MC, Offset, Size, Checksum),
-    {ok, Checksum} = machi_csum_table:find(MC, Offset, Size),
+    [{1024, 40}, {1098, infinity}] = machi_csum_table:calc_unwritten_bytes(MC),
-    ok = machi_csum_table:trim(MC, Offset, Size),
+    ?assertEqual([Entry], machi_csum_table:find(MC, Offset, Size)),
-    {error, trimmed} = machi_csum_table:find(MC, Offset, Size),
+    ok = machi_csum_table:trim(MC, Offset, Size, undefined, undefined),
+    ?assertEqual([{Offset, Size, trimmed}],
+                 machi_csum_table:find(MC, Offset, Size)),
     ok = machi_csum_table:close(MC),
     ok = machi_csum_table:delete(MC).
 
 close_test() ->
     Filename = "./temp-checksum-dumb-file-2",
-    _ = file:delete(Filename),
+    _ = cleanup(Filename),
     {ok, MC} = machi_csum_table:open(Filename, []),
-    {Offset, Size, Checksum} = {64, 34, <<"deadbeef">>},
+    Entry = {Offset, Size, Checksum} = {1064, 34, <<"deadbeef">>},
-    {error, unknown_chunk} = machi_csum_table:find(MC, Offset, Size),
+    [] = machi_csum_table:find(MC, Offset, Size),
     ok = machi_csum_table:write(MC, Offset, Size, Checksum),
-    {ok, Checksum} = machi_csum_table:find(MC, Offset, Size),
+    [Entry] = machi_csum_table:find(MC, Offset, Size),
     ok = machi_csum_table:close(MC),
 
     {ok, MC2} = machi_csum_table:open(Filename, []),
-    {ok, Checksum} = machi_csum_table:find(MC2, Offset, Size),
+    [Entry] = machi_csum_table:find(MC2, Offset, Size),
-    ok = machi_csum_table:trim(MC2, Offset, Size),
+    ok = machi_csum_table:trim(MC2, Offset, Size, undefined, undefined),
-    {error, trimmed} = machi_csum_table:find(MC2, Offset, Size),
+    [{Offset, Size, trimmed}] = machi_csum_table:find(MC2, Offset, Size),
     ok = machi_csum_table:delete(MC2).
+
+smoke2_test() ->
+    Filename = "./temp-checksum-dumb-file-3",
+    _ = cleanup(Filename),
+    {ok, MC} = machi_csum_table:open(Filename, []),
+    Entry = {Offset, Size, Checksum} = {1025, 10, <<"deadbeef">>},
+    ok = machi_csum_table:write(MC, Offset, Size, Checksum),
+    ?assertEqual([], machi_csum_table:find(MC, 0, 0)),
+    ?assertEqual([?HDR], machi_csum_table:find(MC, 0, 1)),
+    [Entry] = machi_csum_table:find(MC, Offset, Size),
+    [?HDR] = machi_csum_table:find(MC, 1, 1024),
+    ?assertEqual([?HDR, Entry],
+                 machi_csum_table:find(MC, 1023, 1024)),
+    [Entry] = machi_csum_table:find(MC, 1024, 1024),
+    [Entry] = machi_csum_table:find(MC, 1025, 1024),
+
+    ok = machi_csum_table:trim(MC, Offset, Size, undefined, undefined),
+    [{Offset, Size, trimmed}] = machi_csum_table:find(MC, Offset, Size),
+    ok = machi_csum_table:close(MC),
+    ok = machi_csum_table:delete(MC).
+
+smoke3_test() ->
+    Filename = "./temp-checksum-dumb-file-4",
+    _ = cleanup(Filename),
+    {ok, MC} = machi_csum_table:open(Filename, []),
+    Scenario =
+        [%% Command, {Offset, Size, Csum}, LeftNeighbor, RightNeibor
+         {?LINE, write, {2000, 10, <<"heh">>}, undefined, undefined},
+         {?LINE, write, {3000, 10, <<"heh">>}, undefined, undefined},
+         {?LINE, write, {4000, 10, <<"heh2">>}, undefined, undefined},
+         {?LINE, write, {4000, 10, <<"heh2">>}, undefined, undefined},
+         {?LINE, write, {4005, 10, <<"heh3">>}, {4000, 5, <<"heh2">>}, undefined},
+         {?LINE, write, {4005, 10, <<"heh3">>}, undefined, undefined},
+         {?LINE, trim, {3005, 10, <<>>}, {3000, 5, <<"heh">>}, undefined},
+         {?LINE, trim, {2000, 10, <<>>}, undefined, undefined},
+         {?LINE, trim, {2005, 5, <<>>}, {2000, 5, trimmed}, undefined},
+         {?LINE, trim, {3000, 5, <<>>}, undefined, undefined},
+         {?LINE, trim, {4000, 10, <<>>}, undefined, {4010, 5, <<"heh3">>}},
+         {?LINE, trim, {4010, 5, <<>>}, undefined, undefined},
+         {?LINE, trim, {0, 1024, <<>>}, undefined, undefined}
+        ],
+    [ begin
+          %% ?debugVal({_Line, Chunk}),
+          {Offset, Size, Csum} = Chunk,
+          ?assertEqual(LeftN0,
+                       machi_csum_table:find_leftneighbor(MC, Offset)),
+          ?assertEqual(RightN0,
+                       machi_csum_table:find_rightneighbor(MC, Offset+Size)),
+          LeftN = case LeftN0 of
+                      {OffsL, SizeL, trimmed} -> {OffsL, SizeL, trimmed};
+                      {OffsL, SizeL, _} -> {OffsL, SizeL, <<"boom">>};
+                      OtherL -> OtherL
+                  end,
+          RightN = case RightN0 of
+                       {OffsR, SizeR, _} -> {OffsR, SizeR, <<"boot">>};
+                       OtherR -> OtherR
+                   end,
+          case Cmd of
+              write ->
+                  ok = machi_csum_table:write(MC, Offset, Size, Csum,
+                                              LeftN, RightN);
+              trim ->
+                  ok = machi_csum_table:trim(MC, Offset, Size,
+                                             LeftN, RightN)
+          end
+      end || {_Line, Cmd, Chunk, LeftN0, RightN0} <- Scenario ],
+    ?assert(not machi_csum_table:all_trimmed(MC, 10000)),
+    machi_csum_table:trim(MC, 0, 10000, undefined, undefined),
+    ?assert(machi_csum_table:all_trimmed(MC, 10000)),
+
+    ok = machi_csum_table:close(MC),
+    ok = machi_csum_table:delete(MC).
+
+%% TODO: add quickcheck test here
+
+%% Previous implementation
+-spec all_trimmed2(machi_csum_table:table(),
+                   non_neg_integer(), non_neg_integer()) -> boolean().
+all_trimmed2(CsumT, Left, Right) ->
+    Chunks = machi_csum_table:find(CsumT, Left, Right),
+    runthru(Chunks, Left, Right).
+
+%% @doc make sure all trimmed chunks are continously chained
+%% TODO: test with EQC
+runthru([], Pos, Pos) -> true;
+runthru([], Pos0, Pos) when Pos0 < Pos -> false;
+runthru([{Offset0, Size0, trimmed}|T], Offset, Pos) when Offset0 =< Offset ->
+    runthru(T, Offset0+Size0, Pos);
+runthru(_L, _O, _P) ->
+    false.

test/machi_file_proxy_eqc.erl

@@ -31,13 +31,18 @@
 -define(QC_OUT(P),
         eqc:on_output(fun(Str, Args) -> io:format(user, Str, Args) end, P)).
 
+-define(TESTDIR, "./eqc").
 
 %% EUNIT TEST DEFINITION
 eqc_test_() ->
-    {timeout, 60,
+    PropTimeout = case os:getenv("EQC_TIME") of
+                      false -> 30;
+                      V     -> list_to_integer(V)
+                  end,
+    {timeout, PropTimeout*2 + 30,
      {spawn,
       [
-        {timeout, 30, ?_assertEqual(true, eqc:quickcheck(eqc:testing_time(15, ?QC_OUT(prop_ok()))))}
+       ?_assertEqual(true, eqc:quickcheck(eqc:testing_time(PropTimeout, ?QC_OUT(prop_ok()))))
       ]
      }}.
 
@@ -88,12 +93,14 @@ data_with_csum(Limit) ->
 intervals([]) ->
     [];
 intervals([N]) ->
-    [{N, choose(1,150)}];
+    [{N, choose(1,1)}];
 intervals([A,B|T]) ->
-    [{A, choose(1, B-A)}|intervals([B|T])].
+    [{A, oneof([choose(1, B-A), B-A])}|intervals([B|T])].
 
 interval_list() ->
-    ?LET(L, list(choose(1024, 4096)), intervals(lists:usort(L))).
+    ?LET(L,
+         oneof([list(choose(1025, 1033)), list(choose(1024, 4096))]),
+         intervals(lists:usort(L))).
 
 shuffle_interval() ->
     ?LET(L, interval_list(), shuffle(L)).
@@ -103,40 +110,100 @@ get_written_interval(L) ->
 
 %% INITIALIZATION
 
--record(state, {pid, prev_extra = 0, planned_writes=[], written=[]}).
+-record(state, {pid, prev_extra = 0,
+                filename = undefined,
+                planned_writes=[],
+                planned_trims=[],
+                written=[],
+                trimmed=[]}).
 
-initial_state() -> #state{written=[{0,1024}]}.
+initial_state() ->
-initial_state(I) -> #state{written=[{0,1024}], planned_writes=I}.
+    {_, _, MS} = os:timestamp(),
+    Filename = test_server:temp_name("eqc_data") ++ "." ++ integer_to_list(MS),
+    #state{filename=Filename, written=[{0,1024}]}.
+
+initial_state(I, T) ->
+    S=initial_state(),
+    S#state{written=[{0,1024}],
+            planned_writes=I,
+            planned_trims=T}.
 
 weight(_S, rewrite) -> 1;
 weight(_S, _) -> 2.
 
 %% HELPERS
 
-%% check if an operation is permitted based on whether a write has
+get_overlaps(_Offset, _Len, [], Acc) -> lists:reverse(Acc);
-%% occurred
+get_overlaps(Offset, Len, [{Pos, Sz} = Ck|T], Acc0)
-check_writes(_Op, [], _Off, _L) ->
+%% Overlap judgement differnt from the one in machi_csum_table
-    false;
+%% [a=Offset, b), [x=Pos, y) ...
-check_writes(_Op, [{Pos, Sz}|_T], Off, L) when Pos == Off 
+  when
-                                          andalso Sz == L ->
+      %% a =< x && x < b && b =< y
-    mostly_true;
+      (Offset =< Pos andalso Pos < Offset + Len andalso Offset + Len =< Pos + Sz) orelse
-check_writes(read, [{Pos, Sz}|_T], Off, L) when Off >= Pos 
+      %% a =< x          && y < b
-                                          andalso Off < (Pos + Sz) 
+      (Offset =< Pos andalso Pos + Sz < Offset + Len) orelse
-                                          andalso Sz >= ( L - ( Off - Pos ) ) ->
+      %% x < a && a < y  && y =< b
-    true;
+      (Pos < Offset andalso Offset < Pos + Sz andalso Pos + Sz =< Offset + Len) orelse
-check_writes(write, [{Pos, Sz}|_T], Off, L) when ( Off + L ) > Pos 
+      %% x < a           && b < y
-                                                 andalso Off < (Pos + Sz) ->
+      (Pos < Offset + Len andalso Offset + Len < Pos + Sz) ->
-    true;
+    get_overlaps(Offset, Len, T, [Ck|Acc0]);
-check_writes(Op, [_H|T], Off, L) ->
+get_overlaps(Offset, Len, [_Ck|T], Acc0) ->
-    check_writes(Op, T, Off, L).
+    get_overlaps(Offset, Len, T, Acc0).
+
+%% Inefficient but simple easy code to verify by eyes - returns all
+%% bytes that fits in (Offset, Len)
+chop(Offset, Len, List) ->
+    ChopLeft = fun({Pos, Sz}) when Pos < Offset andalso Offset =< Pos + Sz ->
+                       {Offset, Sz + Pos - Offset};
+                  ({Pos, Sz}) when Offset =< Pos andalso Pos + Sz < Offset + Len ->
+                       {Pos, Sz};
+                  ({Pos, _Sz}) when Offset =< Pos ->
+                       {Pos, Offset + Len - Pos}
+               end,
+    ChopRight = fun({Pos, Sz}) when Offset + Len < Pos + Sz ->
+                        {Pos, Offset + Len - Pos};
+                   ({Pos, Sz}) ->
+                        {Pos, Sz}
+                end,
+    Filter0 = fun({_, 0}) -> false;
+                 (Other) -> {true, Other} end,
+    lists:filtermap(fun(E) -> Filter0(ChopRight(ChopLeft(E))) end,
+                    List).
+
+%% Returns all bytes that are at left side of the Offset
+chopped_left(_Offset, []) -> undefined;
+chopped_left(Offset, [{Pos,_Sz}|_]) when Pos < Offset ->
+    {Pos, Offset - Pos};
+chopped_left(_, _) ->
+    undefined.
+
+chopped_right(_Offset, []) -> undefined;
+chopped_right(Offset, List) ->
+    {Pos, Sz} = lists:last(List),
+    if Offset < Pos + Sz ->
+            {Offset, Pos + Sz - Offset};
+       true ->
+            undefined
+    end.
+
+cleanup_chunk(Offset, Length, ChunkList) ->
+    Overlaps = get_overlaps(Offset, Length, ChunkList, []),
+    NewCL0 = lists:foldl(fun lists:delete/2,
+                         ChunkList, Overlaps),
+    NewCL1 = case chopped_left(Offset, Overlaps) of
+                 undefined -> NewCL0;
+                 LeftRemain -> [LeftRemain|NewCL0]
+             end,
+    NewCL2 = case chopped_right(Offset+Length, Overlaps) of
+                 undefined -> NewCL1;
+                 RightRemain -> [RightRemain|NewCL1]
+             end,
+    lists:sort(NewCL2).
 
 is_error({error, _}) -> true;
 is_error({error, _, _}) -> true;
 is_error(Other) -> {expected_ERROR, Other}.
 
-probably_error(ok) -> true;
-probably_error(V) -> is_error(V).
-
 is_ok({ok, _, _}) -> true;
 is_ok(ok) -> true;
 is_ok(Other) -> {expected_OK, Other}.
@@ -144,11 +211,10 @@ is_ok(Other) -> {expected_OK, Other}.
 get_offset({ok, _Filename, Offset}) -> Offset;
 get_offset(_) -> error(badarg).
 
-offset_valid(Offset, Extra, L) ->
+last_byte([]) -> 0;
-    {Pos, Sz} = lists:last(L),
+last_byte(L0) ->
-    Offset == Pos + Sz + Extra.
+    L1 = lists:map(fun({Pos, Sz}) -> Pos + Sz end, L0),
-
+    lists:last(lists:sort(L1)).
--define(TESTDIR, "./eqc").
 
 cleanup() ->
     [begin
@@ -162,19 +228,17 @@ cleanup() ->
 %% start
 
 start_pre(S) ->
-    S#state.pid == undefined.
+    S#state.pid =:= undefined.
 
 start_command(S) ->
     {call, ?MODULE, start, [S]}.
 
-start(_S) ->
+start(#state{filename=File}) ->
-    {_, _, MS} = os:timestamp(),
+    {ok, Pid} = machi_file_proxy:start_link(some_flu, File, ?TESTDIR),
-    File = test_server:temp_name("eqc_data") ++ "." ++ integer_to_list(MS),
-    {ok, Pid} = machi_file_proxy:start_link(File, ?TESTDIR),
     unlink(Pid),
     Pid.
 
-start_next(S, Pid, _Args) ->
+start_next(S, Pid, _) ->
     S#state{pid = Pid}.
 
 %% read
@@ -183,25 +247,34 @@ read_pre(S) ->
     S#state.pid /= undefined.
 
 read_args(S) ->
-    [S#state.pid, offset(), len()].
+    [S#state.pid, oneof([offset(), big_offset()]), len()].
-
-read_ok(S, Off, L) ->
-    case S#state.written of
-        [{0, 1024}] -> false;
-        W -> check_writes(read, W, Off, L)
-    end.
 
 read_post(S, [_Pid, Off, L], Res) ->
-    case read_ok(S, Off, L) of
+    Written = get_overlaps(Off, L, S#state.written, []),
-        true -> is_ok(Res);
+    Chopped = chop(Off, L, Written),
-        mostly_true -> is_ok(Res);
+    Trimmed = get_overlaps(Off, L, S#state.trimmed, []),
-        false -> is_error(Res)
+    Eof = lists:max([Pos+Sz||{Pos,Sz}<-S#state.written]),
+    case Res of
+        {ok, {Written0, Trimmed0}} ->
+            Written1 = lists:map(fun({_, Pos, Chunk, _}) ->
+                                         {Pos, iolist_size(Chunk)}
+                                 end, Written0),
+            Trimmed1 = lists:map(fun({_, Pos, Sz}) -> {Pos, Sz} end, Trimmed0),
+            Chopped =:= Written1
+                andalso Trimmed =:= Trimmed1;
+        %% TODO: such response are ugly, rethink the SPEC
+        {error, not_written} when Eof < Off + L ->
+            true;
+        {error, not_written} when Chopped =:= [] andalso Trimmed =:= [] ->
+            true;
+        _Other ->
+            is_error(Res)
     end.
 
 read_next(S, _Res, _Args) -> S.
 
 read(Pid, Offset, Length) ->
-    machi_file_proxy:read(Pid, Offset, Length).
+    machi_file_proxy:read(Pid, Offset, Length, [{needs_trimmed, true}]).
 
 %% write
 
@@ -210,6 +283,7 @@ write_pre(S) ->
 
 %% do not allow writes with empty data
 write_pre(_S, [_Pid, _Extra, {<<>>, _Tag, _Csum}]) ->
+    ?assert(false),
     false;
 write_pre(_S, _Args) ->
     true.
@@ -218,28 +292,18 @@ write_args(S) ->
     {Off, Len} = hd(S#state.planned_writes),
     [S#state.pid, Off, data_with_csum(Len)].
 
-write_ok(_S, [_Pid, Off, _Data]) when Off < 1024 -> false;
+write_post(S, [_Pid, Off, {Bin, _Tag, _Csum}] = _Args, Res) ->
-write_ok(S, [_Pid, Off, {Bin, _Tag, _Csum}]) ->
     Size = iolist_size(Bin),
-    %% Check writes checks if a byte range is *written*
+    case {get_overlaps(Off, Size, S#state.written, []),
-    %% So writes are ok IFF they are NOT written, so
+          get_overlaps(Off, Size, S#state.trimmed, [])} of
-    %% we want not check_writes/3 to be true.
+        {[], []} ->
-    check_writes(write, S#state.written, Off, Size).
+            %% No overlap neither with written ranges nor trimmed
-
+            %% ranges; OK to write things.
-write_post(S, Args, Res) ->
+            eq(Res, ok);
-    case write_ok(S, Args) of
+        {_, _} ->
-        %% false means this range has NOT been written before, so
+            %% overlap found in either or both at written or at
-        %% it should succeed
+            %% trimmed ranges; can't write.
-        false -> eq(Res, ok);
+            is_error(Res)
-        %% mostly true means we've written this range before BUT
-        %% as a special case if we get a call to write the EXACT
-        %% same data that's already on the disk, we return "ok"
-        %% instead of {error, written}.
-        mostly_true -> probably_error(Res); 
-        %% If we get true, then we've already written this section 
-        %% or a portion of this range to disk and should return an 
-        %% error.
-        true -> is_error(Res)
     end.
 
 write_next(S, Res, [_Pid, Offset, {Bin, _Tag, _Csum}]) ->
@@ -280,24 +344,40 @@ append_next(S, Res, [_Pid, Extra, {Bin, _Tag, _Csum}]) ->
     case is_ok(Res) of
         true ->
             Offset = get_offset(Res),
-            true = offset_valid(Offset, S#state.prev_extra, S#state.written),
+            S#state{prev_extra = Extra,
-            S#state{prev_extra = Extra, written = lists:sort(S#state.written ++ [{Offset, iolist_size(Bin)}])};
+                    written = lists:sort(S#state.written ++ [{Offset, iolist_size(Bin)}])};
-        _ ->
+        _Other ->
             S
     end.
 
 %% appends should always succeed unless the disk is full
 %% or there's a hardware failure.
-append_post(_S, _Args, Res) ->
+append_post(S, _Args, Res) ->
-    true == is_ok(Res).
+    case is_ok(Res) of
+        true ->
+            Offset = get_offset(Res),
+            case erlang:max(last_byte(S#state.written),
+                            last_byte(S#state.trimmed)) + S#state.prev_extra of
+                Offset ->
+                    true;
+                UnexpectedByte ->
+                    {wrong_offset_after_append,
+                     {Offset, UnexpectedByte},
+                     {S#state.written, S#state.prev_extra}}
+            end;
+        Error ->
+            Error
+    end.
 
 %% rewrite
 
 rewrite_pre(S) ->
-    S#state.pid /= undefined andalso S#state.written /= [].
+    S#state.pid /= undefined andalso
+        (S#state.written ++ S#state.trimmed) /= [] .
 
 rewrite_args(S) ->
-    ?LET({Off, Len}, get_written_interval(S#state.written),
+    ?LET({Off, Len},
+         get_written_interval(S#state.written ++ S#state.trimmed),
          [S#state.pid, Off, data_with_csum(Len)]).
 
 rewrite(Pid, Offset, {Bin, Tag, Csum}) ->
@@ -311,18 +391,88 @@ rewrite_post(_S, _Args, Res) ->
 rewrite_next(S, _Res, _Args) ->
     S#state{prev_extra = 0}.
 
+%% trim
+
+trim_pre(S) ->
+    S#state.pid /= undefined andalso S#state.planned_trims /= [].
+
+trim_args(S) ->
+    {Offset, Length} = hd(S#state.planned_trims),
+    [S#state.pid, Offset, Length].
+
+trim(Pid, Offset, Length) ->
+    machi_file_proxy:trim(Pid, Offset, Length, false).
+
+trim_post(_S, [_Pid, _Offset, _Length], ok) ->
+    true;
+trim_post(_S, [_Pid, _Offset, _Length], _Res) ->
+    false.
+
+trim_next(S, Res, [_Pid, Offset, Length]) ->
+    S1 = case is_ok(Res) of
+             true ->
+                 NewWritten = cleanup_chunk(Offset, Length, S#state.written),
+                 Trimmed1 = cleanup_chunk(Offset, Length, S#state.trimmed),
+                 NewTrimmed = lists:sort([{Offset, Length}|Trimmed1]),
+                 S#state{trimmed=NewTrimmed,
+                         written=NewWritten};
+             _Other ->
+                 S
+         end,
+    S1#state{prev_extra=0,
+             planned_trims=tl(S#state.planned_trims)}.
+
+stop_pre(S) ->
+    S#state.pid /= undefined.
+
+stop_args(S) ->
+    [S#state.pid].
+
+stop(Pid) ->
+    catch machi_file_proxy:stop(Pid).
+
+stop_post(_, _, _) -> true.
+
+stop_next(S, _, _) ->
+    S#state{pid=undefined, prev_extra=0}.
+
 %% Property
 
 prop_ok() ->
     cleanup(),
-  ?FORALL(I, shuffle_interval(),
+    ?FORALL({I, T},
-    ?FORALL(Cmds, parallel_commands(?MODULE, initial_state(I)),
+            {shuffle_interval(), shuffle_interval()},
+            ?FORALL(Cmds, parallel_commands(?MODULE, initial_state(I, T)),
                     begin
                         {H, S, Res} = run_parallel_commands(?MODULE, Cmds),
+                        cleanup(),
                         pretty_commands(?MODULE, Cmds, {H, S, Res},
                                         aggregate(command_names(Cmds), Res == ok))
-    end)
+                    end)).
-  ).
+
+%% Test for tester functions
+chopper_test_() ->
+    [?_assertEqual([{0, 1024}],
+                   get_overlaps(1, 1, [{0, 1024}], [])),
+     ?_assertEqual([],
+                   get_overlaps(10, 5, [{9, 1}, {15, 1}], [])),
+     ?_assertEqual([{9,2},{14,1}],
+                   get_overlaps(10, 5, [{9, 2}, {14, 1}], [])),
+     ?_assertEqual([],       chop(0, 0, [{0,2}])),
+     ?_assertEqual([{0, 1}], chop(0, 1, [{0,2}])),
+     ?_assertEqual([],       chop(1, 0, [{0,2}])),
+     ?_assertEqual([{1, 1}], chop(1, 1, [{0,2}])),
+     ?_assertEqual([{1, 1}], chop(1, 2, [{0,2}])),
+     ?_assertEqual([],       chop(2, 1, [{0,2}])),
+     ?_assertEqual([],       chop(2, 2, [{0,2}])),
+     ?_assertEqual([{1, 1}], chop(1, 3, [{0,2}])),
+     ?_assertError(_,  chop(3, 1, [{0,2}])),
+     ?_assertEqual([], chop(2, 3, [{0,2}])),
+     ?_assertEqual({0, 1}, chopped_left(1, [{0, 1024}])),
+     ?_assertEqual([{0, 1}, {2, 1022}], cleanup_chunk(1, 1, [{0, 1024}])),
+     ?_assertEqual([{2, 1022}], cleanup_chunk(0, 2, [{0, 1}, {2, 1022}])),
+     ?_assert(true)
+    ].
 
 -endif. % EQC
 -endif. % TEST

test/machi_file_proxy_test.erl

@@ -38,7 +38,7 @@ clean_up_data_dir(DataDir) ->
 -ifndef(PULSE).
 
 -define(TESTDIR, "./t").
--define(HYOOGE, 1 * 1024 * 1024 * 1024). % 1 long GB
+-define(HYOOGE, 75 * 1024 * 1024). % 75 MBytes
 
 random_binary_single() ->
     %% OK, I guess it's not that random...
@@ -76,28 +76,67 @@ random_binary(Start, End) ->
             binary:part(random_binary_single(), Start, End)
     end.
 
+setup() ->
+    {ok, Pid} = machi_file_proxy:start_link(fluname, "test", ?TESTDIR),
+    Pid.
+
+teardown(Pid) ->
+    catch machi_file_proxy:stop(Pid).
+
 machi_file_proxy_test_() ->
     clean_up_data_dir(?TESTDIR),
-    {ok, Pid} = machi_file_proxy:start_link("test", ?TESTDIR),
+    {setup,
+     fun setup/0,
+     fun teardown/1,
+     fun(Pid) ->
              [
               ?_assertEqual({error, bad_arg}, machi_file_proxy:read(Pid, -1, -1)),
               ?_assertEqual({error, bad_arg}, machi_file_proxy:write(Pid, -1, <<"yo">>)),
               ?_assertEqual({error, bad_arg}, machi_file_proxy:append(Pid, [], -1, <<"krep">>)),
-	?_assertEqual({error, not_written}, machi_file_proxy:read(Pid, 1, 1)),
+              ?_assertMatch({ok, {_, []}}, machi_file_proxy:read(Pid, 1, 1)),
               ?_assertEqual({error, not_written}, machi_file_proxy:read(Pid, 1024, 1)),
-        ?_assertEqual({error, not_written}, machi_file_proxy:read(Pid, 1, 1024)),
+              ?_assertMatch({ok, {_, []}}, machi_file_proxy:read(Pid, 1, 1024)),
               ?_assertEqual({error, not_written}, machi_file_proxy:read(Pid, 1024, ?HYOOGE)),
               ?_assertEqual({error, not_written}, machi_file_proxy:read(Pid, ?HYOOGE, 1)),
-	?_assertEqual({error, written}, machi_file_proxy:write(Pid, 1, random_binary(0, ?HYOOGE))),
+              {timeout, 10,
+               ?_assertEqual({error, written}, machi_file_proxy:write(Pid, 1, random_binary(0, ?HYOOGE)))},
               ?_assertMatch({ok, "test", _}, machi_file_proxy:append(Pid, random_binary(0, 1024))),
               ?_assertEqual({error, written}, machi_file_proxy:write(Pid, 1024, <<"fail">>)),
               ?_assertEqual({error, written}, machi_file_proxy:write(Pid, 1, <<"fail">>)),
-	?_assertMatch({ok, _, _}, machi_file_proxy:read(Pid, 1025, 1000)),
+              ?_assertMatch({ok, {[{_, _, _, _}], []}}, machi_file_proxy:read(Pid, 1025, 1000)),
               ?_assertMatch({ok, "test", _}, machi_file_proxy:append(Pid, [], 1024, <<"mind the gap">>)),
-	?_assertEqual(ok, machi_file_proxy:write(Pid, 2060, [], random_binary(0, 1024))),
+              ?_assertEqual(ok, machi_file_proxy:write(Pid, 2060, [], random_binary(0, 1024)))
-        ?_assertException(exit, {normal, _}, machi_file_proxy:stop(Pid))
+             ]
-    ].
+     end}.
+
+multiple_chunks_read_test_() ->
+    clean_up_data_dir(?TESTDIR),
+    {setup,
+     fun setup/0,
+     fun teardown/1,
+     fun(Pid) ->
+             [
+              ?_assertEqual(ok, machi_file_proxy:trim(Pid, 0, 1, false)),
+              ?_assertMatch({ok, {[], [{"test", 0, 1}]}},
+                            machi_file_proxy:read(Pid, 0, 1,
+                                                  #read_opts{needs_trimmed=true})),
+              ?_assertMatch({ok, "test", _}, machi_file_proxy:append(Pid, random_binary(0, 1024))),
+              ?_assertEqual(ok, machi_file_proxy:write(Pid, 10000, <<"fail">>)),
+              ?_assertEqual(ok, machi_file_proxy:write(Pid, 20000, <<"fail">>)),
+              ?_assertEqual(ok, machi_file_proxy:write(Pid, 30000, <<"fail">>)),
+              %% Freeza
+              ?_assertEqual(ok, machi_file_proxy:write(Pid, 530000, <<"fail">>)),
+              ?_assertMatch({ok, {[{"test", 1024, _, _},
+                                   {"test", 10000, <<"fail">>, _},
+                                   {"test", 20000, <<"fail">>, _},
+                                   {"test", 30000, <<"fail">>, _},
+                                   {"test", 530000, <<"fail">>, _}], []}},
+                            machi_file_proxy:read(Pid, 1024, 530000)),
+              ?_assertMatch({ok, {[{"test", 1, _, _}], [{"test", 0, 1}]}},
+                            machi_file_proxy:read(Pid, 0, 1024,
+                                                  #read_opts{needs_trimmed=true}))
+             ]
+     end}.
 
 -endif. % !PULSE
 -endif. % TEST.
-

test/machi_flu1_test.erl

@@ -30,6 +30,22 @@
 -define(FLU, machi_flu1).
 -define(FLU_C, machi_flu1_client).
 
+get_env_vars(App, Ks) ->
+    Raw = [application:get_env(App, K) || K <- Ks],
+    Old = lists:zip(Ks, Raw),
+    {App, Old}.
+
+clean_up_env_vars({App, Old}) ->
+    [case Res of
+         undefined ->
+             application:unset_env(App, K);
+         {ok, V} ->
+             application:set_env(App, K, V)
+     end || {K, Res} <- Old].
+
+filter_env_var({ok, V}) -> V;
+filter_env_var(Else)    -> Else.
+
 clean_up_data_dir(DataDir) ->
     [begin
          Fs = filelib:wildcard(DataDir ++ Glob),
@@ -69,47 +85,46 @@ maybe_start_sup() ->
         Pid -> Pid
     end.
 
-
 -ifndef(PULSE).
 
 flu_smoke_test() ->
     Host = "localhost",
-    TcpPort = 32957,
+    TcpPort = 12957,
     DataDir = "./data",
+    NSInfo = undefined,
+    NoCSum = <<>>,
     Prefix = <<"prefix!">>,
     BadPrefix = BadFile = "no/good",
-
     W_props = [{initial_wedged, false}],
-    start_flu_package(smoke_flu, TcpPort, DataDir, W_props),
+    {_, _, _} = machi_test_util:start_flu_package(smoke_flu, TcpPort, DataDir, W_props),
     try
         Msg = "Hello, world!",
         Msg = ?FLU_C:echo(Host, TcpPort, Msg),
-        {error, bad_arg} = ?FLU_C:checksum_list(Host, TcpPort,
+        {error, bad_arg} = ?FLU_C:checksum_list(Host, TcpPort,"does-not-exist"),
-                                                     ?DUMMY_PV1_EPOCH,
+        {error, bad_arg} = ?FLU_C:checksum_list(Host, TcpPort, BadFile),
-                                                     "does-not-exist"),
-        {error, bad_arg} = ?FLU_C:checksum_list(Host, TcpPort,
-                                                ?DUMMY_PV1_EPOCH, BadFile),
 
         {ok, []} = ?FLU_C:list_files(Host, TcpPort, ?DUMMY_PV1_EPOCH),
-        {ok, {false, _}} = ?FLU_C:wedge_status(Host, TcpPort),
+        {ok, {false, _,_,_}} = ?FLU_C:wedge_status(Host, TcpPort),
 
         Chunk1 = <<"yo!">>,
-        {ok, {Off1,Len1,File1}} = ?FLU_C:append_chunk(Host, TcpPort,
+        {ok, {Off1,Len1,File1}} = ?FLU_C:append_chunk(Host, TcpPort, NSInfo,
                                                       ?DUMMY_PV1_EPOCH,
-                                                      Prefix, Chunk1),
+                                                      Prefix, Chunk1, NoCSum),
-        {ok, Chunk1} = ?FLU_C:read_chunk(Host, TcpPort, ?DUMMY_PV1_EPOCH,
+        {ok, {[{_, Off1, Chunk1, _}], _}} = ?FLU_C:read_chunk(Host, TcpPort,
-                                         File1, Off1, Len1),
+                                                       NSInfo, ?DUMMY_PV1_EPOCH,
-        {ok, KludgeBin} = ?FLU_C:checksum_list(Host, TcpPort,
+                                                       File1, Off1, Len1,
-                                               ?DUMMY_PV1_EPOCH, File1),
+                                                       noopt),
+        {ok, KludgeBin} = ?FLU_C:checksum_list(Host, TcpPort, File1),
         true = is_binary(KludgeBin),
-        {error, bad_arg} = ?FLU_C:append_chunk(Host, TcpPort,
+        {error, bad_arg} = ?FLU_C:append_chunk(Host, TcpPort, NSInfo,
                                                ?DUMMY_PV1_EPOCH,
-                                               BadPrefix, Chunk1),
+                                               BadPrefix, Chunk1, NoCSum),
         {ok, [{_,File1}]} = ?FLU_C:list_files(Host, TcpPort, ?DUMMY_PV1_EPOCH),
         Len1 = size(Chunk1),
         {error, not_written} = ?FLU_C:read_chunk(Host, TcpPort,
-                                                  ?DUMMY_PV1_EPOCH,
+                                                 NSInfo, ?DUMMY_PV1_EPOCH,
-                                                  File1, Off1*983829323, Len1),
+                                                 File1, Off1*983829323, Len1,
+                                                 noopt),
         %% XXX FIXME
         %%
         %% This is failing because the read extends past the end of the file.
@@ -118,19 +133,22 @@ flu_smoke_test() ->
         %% of the read will cause it to fail.
         %%
         %% {error, partial_read} = ?FLU_C:read_chunk(Host, TcpPort,
-        %%                                           ?DUMMY_PV1_EPOCH,
+        %%                                           NSInfo, ?DUMMY_PV1_EPOCH,
         %%                                           File1, Off1, Len1*9999),
 
-        {ok, {Off1b,Len1b,File1b}} = ?FLU_C:append_chunk(Host, TcpPort,
+        {ok, {Off1b,Len1b,File1b}} = ?FLU_C:append_chunk(Host, TcpPort, NSInfo,
                                                          ?DUMMY_PV1_EPOCH,
-                                                         Prefix, Chunk1),
+                                                         Prefix, Chunk1,NoCSum),
         Extra = 42,
-        {ok, {Off1c,Len1c,File1c}} = ?FLU_C:append_chunk_extra(Host, TcpPort,
+        Opts1 = #append_opts{chunk_extra=Extra},
+        {ok, {Off1c,Len1c,File1c}} = ?FLU_C:append_chunk(Host, TcpPort, NSInfo,
                                                          ?DUMMY_PV1_EPOCH,
-                                                         Prefix, Chunk1, Extra),
+                                                         Prefix, Chunk1, NoCSum,
+                                                         Opts1, infinity),
         {ok, {Off1d,Len1d,File1d}} = ?FLU_C:append_chunk(Host, TcpPort,
+                                                         NSInfo,
                                                          ?DUMMY_PV1_EPOCH,
-                                                         Prefix, Chunk1),
+                                                         Prefix, Chunk1,NoCSum),
         if File1b == File1c, File1c == File1d ->
                 true = (Off1c == Off1b + Len1b),
                 true = (Off1d == Off1c + Len1c + Extra);
@@ -138,27 +156,44 @@ flu_smoke_test() ->
                 exit(not_mandatory_but_test_expected_same_file_fixme)
         end,
 
-        Chunk1_cs = {<<?CSUM_TAG_NONE:8, 0:(8*20)>>, Chunk1},
-        {ok, {Off1e,Len1e,File1e}} = ?FLU_C:append_chunk(Host, TcpPort,
-                                                         ?DUMMY_PV1_EPOCH,
-                                                         Prefix, Chunk1_cs),
-
         Chunk2 = <<"yo yo">>,
         Len2 = byte_size(Chunk2),
         Off2 = ?MINIMUM_OFFSET + 77,
-        File2 = "smoke-whole-file^1^1",
+        File2 = "smoke-whole-file^^0^1^1",
-        ok = ?FLU_C:write_chunk(Host, TcpPort, ?DUMMY_PV1_EPOCH,
+        ok = ?FLU_C:write_chunk(Host, TcpPort, NSInfo, ?DUMMY_PV1_EPOCH,
-                                File2, Off2, Chunk2),
+                                File2, Off2, Chunk2, NoCSum),
-        {error, bad_arg} = ?FLU_C:write_chunk(Host, TcpPort, ?DUMMY_PV1_EPOCH,
+        {error, bad_arg} = ?FLU_C:write_chunk(Host, TcpPort, NSInfo, ?DUMMY_PV1_EPOCH,
-                                              BadFile, Off2, Chunk2),
+                                              BadFile, Off2, Chunk2, NoCSum),
-        {ok, Chunk2} = ?FLU_C:read_chunk(Host, TcpPort, ?DUMMY_PV1_EPOCH,
+        {ok, {[{_, Off2, Chunk2, _}], _}} =
-                                         File2, Off2, Len2),
+            ?FLU_C:read_chunk(Host, TcpPort, NSInfo, ?DUMMY_PV1_EPOCH, File2, Off2, Len2, noopt),
         {error, bad_arg} = ?FLU_C:read_chunk(Host, TcpPort,
-                                                 ?DUMMY_PV1_EPOCH,
+                                                 NSInfo, ?DUMMY_PV1_EPOCH,
-                                                 "no!!", Off2, Len2),
+                                                 "no!!", Off2, Len2, noopt),
         {error, bad_arg} = ?FLU_C:read_chunk(Host, TcpPort,
-                                             ?DUMMY_PV1_EPOCH,
+                                             NSInfo, ?DUMMY_PV1_EPOCH,
-                                             BadFile, Off2, Len2),
+                                             BadFile, Off2, Len2, noopt),
+
+        %% Make a connected socket.
+        Sock1 = ?FLU_C:connect(#p_srvr{address=Host, port=TcpPort}),
+
+        %% Let's test some cluster version enforcement.
+        Good_EpochNum = 0,
+        Good_NSVersion = 0,
+        Good_NS = <<>>,
+        {ok, {false, {Good_EpochNum,_}, Good_NSVersion, GoodNS}} =
+            ?FLU_C:wedge_status(Sock1),
+        NS_good = #ns_info{version=Good_NSVersion, name=Good_NS},
+        {ok, {[{_, Off2, Chunk2, _}], _}} =
+            ?FLU_C:read_chunk(Sock1, NS_good, ?DUMMY_PV1_EPOCH,
+                              File2, Off2, Len2, noopt),
+        NS_bad_version = #ns_info{version=1, name=Good_NS},
+        NS_bad_name = #ns_info{version=Good_NSVersion, name= <<"foons">>},
+        {error, bad_epoch} =
+            ?FLU_C:read_chunk(Sock1, NS_bad_version, ?DUMMY_PV1_EPOCH,
+                              File2, Off2, Len2, noopt),
+        {error, bad_arg} =
+            ?FLU_C:read_chunk(Sock1, NS_bad_name, ?DUMMY_PV1_EPOCH,
+                              File2, Off2, Len2, noopt),
 
         %% We know that File1 still exists.  Pretend that we've done a
         %% migration and exercise the delete_migration() API.
@@ -175,25 +210,23 @@ flu_smoke_test() ->
         {error, bad_arg} = ?FLU_C:trunc_hack(Host, TcpPort,
                                              ?DUMMY_PV1_EPOCH, BadFile),
 
-        ok = ?FLU_C:quit(?FLU_C:connect(#p_srvr{address=Host,
+        ok = ?FLU_C:quit(Sock1)
-                                                port=TcpPort}))
     after
-        stop_flu_package(smoke_flu)
+        machi_test_util:stop_flu_package()
     end.
 
 flu_projection_smoke_test() ->
     Host = "localhost",
-    TcpPort = 32959,
+    TcpPort = 12959,
     DataDir = "./data.projst",
-
+    {_,_,_} = machi_test_util:start_flu_package(projection_test_flu, TcpPort, DataDir),
-    start_flu_package(projection_test_flu, TcpPort, DataDir),
     try
         [ok = flu_projection_common(Host, TcpPort, T) ||
             T <- [public, private] ]
-%% ,        {ok, {false, EpochID1}} = ?FLU_C:wedge_status(Host, TcpPort),
+%% ,        {ok, {false, EpochID1,_,_}} = ?FLU_C:wedge_status(Host, TcpPort),
 %% io:format(user, "EpochID1 ~p\n", [EpochID1])
     after
-        stop_flu_package(projection_test_flu)
+        machi_test_util:stop_flu_package()
     end.
 
 flu_projection_common(Host, TcpPort, T) ->
@@ -221,30 +254,32 @@ flu_projection_common(Host, TcpPort, T) ->
 
 bad_checksum_test() ->
     Host = "localhost",
-    TcpPort = 32960,
+    TcpPort = 12960,
     DataDir = "./data.bct",
-
     Opts = [{initial_wedged, false}],
-    start_flu_package(projection_test_flu, TcpPort, DataDir, Opts),
+    {_,_,_} = machi_test_util:start_flu_package(projection_test_flu, TcpPort, DataDir, Opts),
+    NSInfo = undefined,
     try
         Prefix = <<"some prefix">>,
         Chunk1 = <<"yo yo yo">>,
-        Chunk1_badcs = {<<?CSUM_TAG_CLIENT_SHA:8, 0:(8*20)>>, Chunk1},
+        BadCSum = {?CSUM_TAG_CLIENT_SHA, crypto:hash(sha, ".................")},
-        {error, bad_checksum} = ?FLU_C:append_chunk(Host, TcpPort,
+        {error, bad_checksum} = ?FLU_C:append_chunk(Host, TcpPort, NSInfo,
                                                     ?DUMMY_PV1_EPOCH,
-                                                    Prefix, Chunk1_badcs),
+                                                    Prefix,
+                                                    Chunk1, BadCSum),
         ok
     after
-        stop_flu_package(projection_test_flu)
+        machi_test_util:stop_flu_package()
     end.
 
 witness_test() ->
     Host = "localhost",
-    TcpPort = 32961,
+    TcpPort = 12961,
     DataDir = "./data.witness",
-
     Opts = [{initial_wedged, false}, {witness_mode, true}],
-    start_flu_package(projection_test_flu, TcpPort, DataDir, Opts),
+    {_,_,_} = machi_test_util:start_flu_package(projection_test_flu, TcpPort, DataDir, Opts),
+    NSInfo = undefined,
+    NoCSum = <<>>,
     try
         Prefix = <<"some prefix">>,
         Chunk1 = <<"yo yo yo">>,
@@ -257,15 +292,14 @@ witness_test() ->
         {ok, EpochID1} = ?FLU_C:get_latest_epochid(Host, TcpPort, private),
 
         %% Witness-protected ops all fail
-        {error, bad_arg} = ?FLU_C:append_chunk(Host, TcpPort, EpochID1,
+        {error, bad_arg} = ?FLU_C:append_chunk(Host, TcpPort, NSInfo, EpochID1,
-                                               Prefix, Chunk1),
+                                               Prefix, Chunk1, NoCSum),
         File = <<"foofile">>,
-        {error, bad_arg} = ?FLU_C:read_chunk(Host, TcpPort, EpochID1,
+        {error, bad_arg} = ?FLU_C:read_chunk(Host, TcpPort, NSInfo, EpochID1,
-                                             File, 9999, 9999),
+                                             File, 9999, 9999, noopt),
-        {error, bad_arg} = ?FLU_C:checksum_list(Host, TcpPort, EpochID1,
+        {error, bad_arg} = ?FLU_C:checksum_list(Host, TcpPort, File),
-                                                File),
         {error, bad_arg} = ?FLU_C:list_files(Host, TcpPort, EpochID1),
-        {ok, {false, EpochID1}} = ?FLU_C:wedge_status(Host, TcpPort),
+        {ok, {false, EpochID1,_,_}} = ?FLU_C:wedge_status(Host, TcpPort),
         {ok, _} = ?FLU_C:get_latest_epochid(Host, TcpPort, public),
         {ok, _} = ?FLU_C:read_latest_projection(Host, TcpPort, public),
         {error, not_written} = ?FLU_C:read_projection(Host, TcpPort,
@@ -276,7 +310,7 @@ witness_test() ->
 
         ok
     after
-        stop_flu_package(projection_test_flu)
+        machi_test_util:stop_flu_package()
     end.
 
 %% The purpose of timing_pb_encoding_test_ and timing_bif_encoding_test_ is

test/machi_flu_psup_test.erl

@@ -38,12 +38,12 @@ smoke_test_() ->
     {timeout, 5*60, fun() -> smoke_test2() end}.
 
 smoke_test2() ->
-    Ps = [{a,#p_srvr{name=a, address="localhost", port=5555, props="./data.a"}},
+    Ps = [{a,#p_srvr{name=a, address="localhost", port=5550, props="./data.a"}},
-          {b,#p_srvr{name=b, address="localhost", port=5556, props="./data.b"}},
+          {b,#p_srvr{name=b, address="localhost", port=5551, props="./data.b"}},
-          {c,#p_srvr{name=c, address="localhost", port=5557, props="./data.c"}}
+          {c,#p_srvr{name=c, address="localhost", port=5552, props="./data.c"}}
          ],
     [os:cmd("rm -rf " ++ P#p_srvr.props) || {_,P} <- Ps],
-    {ok, SupPid} = machi_flu_sup:start_link(),
+    {ok, SupPid} = machi_sup:start_link(),
     try
         %% Only run a, don't run b & c so we have 100% failures talking to them
         [begin
@@ -66,15 +66,15 @@ partial_stop_restart_test_() ->
     {timeout, 5*60, fun() -> partial_stop_restart2() end}.
 
 partial_stop_restart2() ->
-    Ps = [{a,#p_srvr{name=a, address="localhost", port=5555, props="./data.a"}},
+    Ps = [{a,#p_srvr{name=a, address="localhost", port=5560, props="./data.a"}},
-          {b,#p_srvr{name=b, address="localhost", port=5556, props="./data.b"}},
+          {b,#p_srvr{name=b, address="localhost", port=5561, props="./data.b"}},
-          {c,#p_srvr{name=c, address="localhost", port=5557, props="./data.c"}}
+          {c,#p_srvr{name=c, address="localhost", port=5562, props="./data.c"}}
          ],
     ChMgrs = [machi_flu_psup:make_mgr_supname(P#p_srvr.name) || {_,P} <-Ps],
     PStores = [machi_flu_psup:make_proj_supname(P#p_srvr.name) || {_,P} <-Ps],
     Dict = orddict:from_list(Ps),
     [os:cmd("rm -rf " ++ P#p_srvr.props) || {_,P} <- Ps],
-    {ok, SupPid} = machi_flu_sup:start_link(),
+    {ok, SupPid} = machi_sup:start_link(),
     DbgProps = [{initial_wedged, true}],
     Start = fun({_,P}) ->
                     #p_srvr{name=Name, port=Port, props=Dir} = P,
@@ -84,20 +84,23 @@ partial_stop_restart2() ->
     WedgeStatus = fun({_,#p_srvr{address=Addr, port=TcpPort}}) ->
                           machi_flu1_client:wedge_status(Addr, TcpPort)
                   end,
+    NSInfo = undefined,
     Append = fun({_,#p_srvr{address=Addr, port=TcpPort}}, EpochID) ->
+                     NoCSum = <<>>,
                      machi_flu1_client:append_chunk(Addr, TcpPort,
-                                                    EpochID,
+                                                    NSInfo, EpochID,
-                                                    <<"prefix">>, <<"data">>)
+                                                    <<"prefix">>,
+                                                    <<"data">>, NoCSum)
                   end,
     try
         [Start(P) || P <- Ps],
-        [{ok, {true, _}} = WedgeStatus(P) || P <- Ps], % all are wedged
+        [{ok, {true, _,_,_}} = WedgeStatus(P) || P <- Ps], % all are wedged
         [{error,wedged} = Append(P, ?DUMMY_PV1_EPOCH) || P <- Ps], % all are wedged
 
         [machi_chain_manager1:set_chain_members(ChMgr, Dict) ||
             ChMgr <- ChMgrs ],
-        {ok, {false, EpochID1}} = WedgeStatus(hd(Ps)),
+        {ok, {false, EpochID1,_,_}} = WedgeStatus(hd(Ps)),
-        [{ok, {false, EpochID1}} = WedgeStatus(P) || P <- Ps], % *not* wedged
+        [{ok, {false, EpochID1,_,_}} = WedgeStatus(P) || P <- Ps], % *not* wedged
         [{ok,_} = Append(P, EpochID1) || P <- Ps],             % *not* wedged
         {ok, {_,_,File1}} = Append(hd(Ps), EpochID1),
 
@@ -123,9 +126,9 @@ partial_stop_restart2() ->
         Epoch_m = Proj_m#projection_v1.epoch_number,
         %% Confirm that all FLUs are *not* wedged, with correct proj & epoch
         Proj_mCSum = Proj_m#projection_v1.epoch_csum,
-        [{ok, {false, {Epoch_m, Proj_mCSum}}} = WedgeStatus(P) || % *not* wedged
+        [{ok, {false, {Epoch_m, Proj_mCSum},_,_}} = WedgeStatus(P) || % *not* wedged
              P <- Ps], 
-        {ok, {false, EpochID1}} = WedgeStatus(hd(Ps)),
+        {ok, {false, EpochID1,_,_}} = WedgeStatus(hd(Ps)),
         [{ok,_} = Append(P, EpochID1) || P <- Ps],            % *not* wedged
 
         %% Stop all but 'a'.
@@ -145,10 +148,10 @@ partial_stop_restart2() ->
         {error, wedged} = Append(hd(Ps), EpochID1),
         {_, #p_srvr{address=Addr_a, port=TcpPort_a}} = hd(Ps),
         {error, wedged} = machi_flu1_client:read_chunk(
-                            Addr_a, TcpPort_a, ?DUMMY_PV1_EPOCH,
+                            Addr_a, TcpPort_a, NSInfo, ?DUMMY_PV1_EPOCH,
-                            <<>>, 99999999, 1),
+                            <<>>, 99999999, 1, undefined),
-        {error, wedged} = machi_flu1_client:checksum_list(
+        {error, bad_arg} = machi_flu1_client:checksum_list(
-                            Addr_a, TcpPort_a, ?DUMMY_PV1_EPOCH, <<>>),
+                             Addr_a, TcpPort_a, <<>>),
         %% list_files() is permitted despite wedged status
         {ok, _} = machi_flu1_client:list_files(
                             Addr_a, TcpPort_a, ?DUMMY_PV1_EPOCH),
@@ -157,7 +160,7 @@ partial_stop_restart2() ->
         {now_using,_,Epoch_n} = machi_chain_manager1:trigger_react_to_env(
                                   hd(ChMgrs)),
         true = (Epoch_n > Epoch_m),
-        {ok, {false, EpochID3}} = WedgeStatus(hd(Ps)),
+        {ok, {false, EpochID3,_,_}} = WedgeStatus(hd(Ps)),
         %% The file we're assigned should be different with the epoch change.
         {ok, {_,_,File3}} = Append(hd(Ps), EpochID3),
         true = (File1 /= File3),
@@ -173,6 +176,19 @@ partial_stop_restart2() ->
         ok
     end.
 
+p_srvr_rec_test() ->
+    P = #p_srvr{name=a, address="localhost", port=1024, props=[yo]},
+    [P] = machi_flu_sup:sanitize_p_srvr_records([P]),
+    [P] = machi_flu_sup:sanitize_p_srvr_records([P,P]),
+    [] = machi_flu_sup:sanitize_p_srvr_records([nope]),
+    [] = machi_flu_sup:sanitize_p_srvr_records([#p_srvr{proto_mod=does_not_exist}]),
+    [] = machi_flu_sup:sanitize_p_srvr_records([#p_srvr{proto_mod="lists"}]),
+    [] = machi_flu_sup:sanitize_p_srvr_records([#p_srvr{address=7}]),
+    [] = machi_flu_sup:sanitize_p_srvr_records([#p_srvr{port=5}]),
+    [] = machi_flu_sup:sanitize_p_srvr_records([#p_srvr{port=foo}]),
+    [] = machi_flu_sup:sanitize_p_srvr_records([#p_srvr{props=foo}]),
+    ok.
+
 -endif. % !PULSE
 -endif. % TEST
 

test/machi_lifecycle_mgr_test.erl

@@ -0,0 +1,307 @@
+%% -------------------------------------------------------------------
+%%
+%% Copyright (c) 2007-2014 Basho Technologies, Inc.  All Rights Reserved.
+%%
+%% This file is provided to you under the Apache License,
+%% Version 2.0 (the "License"); you may not use this file
+%% except in compliance with the License.  You may obtain
+%% a copy of the License at
+%%
+%%   http://www.apache.org/licenses/LICENSE-2.0
+%%
+%% Unless required by applicable law or agreed to in writing,
+%% software distributed under the License is distributed on an
+%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+%% KIND, either express or implied.  See the License for the
+%% specific language governing permissions and limitations
+%% under the License.
+%%
+%% -------------------------------------------------------------------
+
+-module(machi_lifecycle_mgr_test).
+-compile(export_all).
+
+-ifdef(TEST).
+-ifndef(PULSE).
+
+-include_lib("eunit/include/eunit.hrl").
+
+-include("machi.hrl").
+-include("machi_projection.hrl").
+
+-define(MGR, machi_chain_manager1).
+
+setup() ->
+    catch application:stop(machi),
+    {ok, SupPid} = machi_sup:start_link(),
+    error_logger:tty(false),
+    Dir = "./" ++ atom_to_list(?MODULE) ++ ".datadir",
+    machi_flu1_test:clean_up_data_dir(Dir ++ "/*/*"),
+    machi_flu1_test:clean_up_data_dir(Dir),
+    Envs = [{flu_data_dir, Dir ++ "/data/flu"},
+            {flu_config_dir, Dir ++ "/etc/flu-config"},
+            {chain_config_dir, Dir ++ "/etc/chain-config"},
+            {platform_data_dir, Dir ++ "/data"},
+            {platform_etc_dir, Dir ++ "/etc"},
+            {not_used_pending, Dir ++ "/etc/pending"}
+           ],
+    EnvKeys = [K || {K,_V} <- Envs],
+    undefined = application:get_env(machi, yo),
+    Cleanup = machi_flu1_test:get_env_vars(machi, EnvKeys ++ [yo]),
+    [begin
+         filelib:ensure_dir(V ++ "/unused"),
+         application:set_env(machi, K, V)
+     end || {K, V} <- Envs],
+    {SupPid, Dir, Cleanup}.
+
+cleanup({SupPid, Dir, Cleanup}) ->
+    exit(SupPid, normal),
+    machi_util:wait_for_death(SupPid, 100),
+    error_logger:tty(true),
+    catch application:stop(machi),
+    machi_flu1_test:clean_up_data_dir(Dir ++ "/*/*"),
+    machi_flu1_test:clean_up_data_dir(Dir),
+    machi_flu1_test:clean_up_env_vars(Cleanup),
+    undefined = application:get_env(machi, yo),
+    ok.
+
+smoke_test_() ->
+    {timeout, 60, fun() -> smoke_test2() end}.
+
+smoke_test2() ->
+    YoCleanup = setup(),
+    try
+        Prefix = <<"pre">>,
+        Chunk1 = <<"yochunk">>,
+        Host = "localhost",
+        PortBase = 60120,
+
+        Pa = #p_srvr{name=a,address="localhost",port=PortBase+0},
+        Pb = #p_srvr{name=b,address="localhost",port=PortBase+1},
+        Pc = #p_srvr{name=c,address="localhost",port=PortBase+2},
+        %% Pstore_a = machi_flu1:make_projection_server_regname(a),
+        %% Pstore_b = machi_flu1:make_projection_server_regname(b),
+        %% Pstore_c = machi_flu1:make_projection_server_regname(c),
+        Pstores = [Pstore_a, Pstore_b, Pstore_c] =
+            [machi_flu1:make_projection_server_regname(a),
+             machi_flu1:make_projection_server_regname(b),
+             machi_flu1:make_projection_server_regname(c)],
+        ChMgrs = [ChMgr_a, ChMgr_b, ChMgr_c] =
+            [machi_chain_manager1:make_chmgr_regname(a),
+             machi_chain_manager1:make_chmgr_regname(b),
+             machi_chain_manager1:make_chmgr_regname(c)],
+        Fits = [Fit_a, Fit_b, Fit_c] =
+            [machi_flu_psup:make_fitness_regname(a),
+             machi_flu_psup:make_fitness_regname(b),
+             machi_flu_psup:make_fitness_regname(c)],
+        Advance = machi_chain_manager1_test:make_advance_fun(
+                    Fits, [a,b,c], ChMgrs, 3),
+
+        %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+        io:format("\nSTEP: Start 3 FLUs, no chain.\n", []),
+
+        [machi_lifecycle_mgr:make_pending_config(P) || P <- [Pa,Pb,Pc] ],
+        {[_,_,_],[]} = machi_lifecycle_mgr:process_pending(),
+        [{ok, #projection_v1{epoch_number=0}} =
+             machi_projection_store:read_latest_projection(PSTORE, private)
+         || PSTORE <- Pstores],
+
+        %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+        io:format("\nSTEP: Start chain = [a,b,c]\n", []),
+
+        C1 = #chain_def_v1{name=cx, mode=ap_mode, full=[Pa,Pb,Pc],
+                           local_run=[a,b,c]},
+        machi_lifecycle_mgr:make_pending_config(C1),
+        {[],[_]} = machi_lifecycle_mgr:process_pending(),
+        Advance(),
+        [{ok, #projection_v1{all_members=[a,b,c]}} =
+             machi_projection_store:read_latest_projection(PSTORE, private)
+         || PSTORE <- Pstores],
+
+        %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+        io:format("\nSTEP: Reset chain = [b,c]\n", []),
+
+        C2 = #chain_def_v1{name=cx, mode=ap_mode, full=[Pb,Pc],
+                           old_full=[a,b,c], old_witnesses=[],
+                           local_stop=[a], local_run=[b,c]},
+        machi_lifecycle_mgr:make_pending_config(C2),
+        {[],[_]} = machi_lifecycle_mgr:process_pending(),
+        Advance(),
+        %% a should be down
+        {'EXIT', _} = (catch machi_projection_store:read_latest_projection(
+                               hd(Pstores), private)),
+        [{ok, #projection_v1{all_members=[b,c]}} =
+             machi_projection_store:read_latest_projection(PSTORE, private)
+         || PSTORE <- tl(Pstores)],
+
+        %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+        io:format("\nSTEP: Reset chain = []\n", []),
+
+        C3 = #chain_def_v1{name=cx, mode=ap_mode, full=[],
+                           old_full=[b,c], old_witnesses=[],
+                           local_stop=[b,c], local_run=[]},
+        machi_lifecycle_mgr:make_pending_config(C3),
+        {[],[_]} = machi_lifecycle_mgr:process_pending(),
+        Advance(),
+        %% a,b,c should be down
+        [{'EXIT', _} = (catch machi_projection_store:read_latest_projection(
+                                PSTORE, private))
+         || PSTORE <- Pstores],
+
+        ok
+    after
+        cleanup(YoCleanup)
+    end.
+
+ast_tuple_syntax_test() ->
+    T = fun(L) -> machi_lifecycle_mgr:check_ast_tuple_syntax(L) end,
+    Canon1 = [ {host, "localhost", []},
+               {host, "localhost", [{client_interface, "1.2.3.4"},
+                                    {admin_interface, "5.6.7.8"}]},
+               {flu, 'fx', "foohost", 4000, []},
+               switch_old_and_new,
+               {chain, 'cy', ['fx', 'fy'], [{foo,"yay"},{bar,baz}]} ],
+
+    {_Good,[]=_Bad} = T(Canon1),
+    Canon1_norm = machi_lifecycle_mgr:normalize_ast_tuple_syntax(Canon1),
+    true = (length(Canon1) == length(Canon1_norm)),
+    {Canon1_norm_b, []} = T(Canon1_norm),
+    true = (length(Canon1_norm) == length(Canon1_norm_b)),
+
+    {[],[_,_,_,_]} =
+        T([ {host, 'localhost', []},
+            {host, 'localhost', yo},
+            {host, "localhost", [{client_interface, 77.88293829832}]},
+            {host, "localhost", [{client_interface, "1.2.3.4"},
+                                 {bummer, "5.6.7.8"}]} ]),
+    {[],[_,_,_,_,_,_]} =
+        T([ {flu, 'fx', 'foohost', 4000, []},
+            {flu, 'fx', <<"foohost">>, 4000, []},
+            {flu, 'fx', "foohost", -4000, []},
+            {flu, 'fx', "foohost", 40009999, []},
+            {flu, 'fx', "foohost", 4000, gack},
+            {flu, 'fx', "foohost", 4000, [22]} ]),
+    {[],[_,_,_]} =
+        T([ {chain, 'cy', ["fx", "fy"], [foo,{bar,baz}]},
+            yoloyolo,
+            {chain, "cy", ["fx", 27], oops,arity,way,way,way,too,big,x}
+          ]).
+
+ast_run_test() ->
+    PortBase = 20300,
+    R1 = [
+          {host, "localhost", "localhost", "localhost", []},
+          {flu, 'f0', "localhost", PortBase+0, []},
+          {flu, 'f1', "localhost", PortBase+1, []},
+          {chain, 'ca', ['f0'], []},
+          {chain, 'cb', ['f1'], []},
+          switch_old_and_new,
+          {flu, 'f2', "localhost", PortBase+2, []},
+          {flu, 'f3', "localhost", PortBase+3, []},
+          {flu, 'f4', "localhost", PortBase+4, []},
+          {chain, 'ca', ['f0', 'f2'], []},
+          {chain, 'cc', ['f3', 'f4'], []}
+         ],
+
+    {ok, Env1} = machi_lifecycle_mgr:run_ast(R1),
+    %% Uncomment to examine the Env trees.
+    %% Y1 = {lists:sort(gb_trees:to_list(element(1, Env1))),
+    %%       lists:sort(gb_trees:to_list(element(2, Env1))),
+    %%       element(3, Env1)},
+    %% io:format(user, "\nY1 ~p\n", [Y1]),
+
+    Negative_after_R1 =
+        [
+          {host, "localhost", "foo", "foo", []}, % dupe host
+          {flu, 'f1', "other", PortBase+9999999, []}, % bogus port # (syntax)
+          {flu, 'f1', "other", PortBase+888, []}, % dupe flu name
+          {flu, 'f7', "localhost", PortBase+1, []}, % dupe host+port
+          {chain, 'ca', ['f7'], []}, % unknown flu
+          {chain, 'cc', ['f0'], []}, % flu previously assigned
+          {chain, 'ca', cp_mode, ['f0', 'f1', 'f2'], [], []} % mode change
+        ],
+    [begin
+         %% io:format(user, "dbg: Neg ~p\n", [Neg]),
+         {error, _} = machi_lifecycle_mgr:run_ast(R1 ++ [Neg])
+     end || Neg <- Negative_after_R1],
+
+    %% The 'run' phase doesn't blow smoke.  What about 'diff'?
+    {X1a, X1b} = machi_lifecycle_mgr:diff_env(Env1, "localhost"),
+    %% There's only one host, "localhost", so 'all' should be exactly equal.
+    {X1a, X1b} = machi_lifecycle_mgr:diff_env(Env1, all),
+    %% io:format(user, "X1b: ~p\n", [X1b]),
+
+    %% Append to the R1 scenario: for chain cc: add f5, remove f4
+    %% Expect: see pattern matching below on X2b.
+    R2 = (R1 -- [switch_old_and_new]) ++
+        [switch_old_and_new,
+         {flu, 'f5', "localhost", PortBase+5, []},
+         {chain, 'cc', ['f3','f5'], []}],
+    {ok, Env2} = machi_lifecycle_mgr:run_ast(R2),
+    {_X2a, X2b} = machi_lifecycle_mgr:diff_env(Env2, "localhost"),
+    %% io:format(user, "X2b: ~p\n", [X2b]),
+    F5_port = PortBase+5,
+    [#p_srvr{name='f5',address="localhost",port=F5_port},
+     #chain_def_v1{name='cc',
+                   full=[#p_srvr{name='f3'},#p_srvr{name='f5'}], witnesses=[],
+                   old_full=[f3,f4], old_witnesses=[],
+                   local_run=[f5], local_stop=[f4]}] = X2b,
+
+    ok.
+
+ast_then_apply_test_() ->
+    {timeout, 60, fun() -> ast_then_apply_test2() end}.
+
+ast_then_apply_test2() ->
+    YoCleanup = setup(),
+    try
+        PortBase = 20400,
+        NumChains = 4,
+        ChainLen = 3,
+        FLU_num = NumChains * ChainLen,
+        FLU_defs = [{flu, list_to_atom("f"++integer_to_list(X)),
+                     "localhost", PortBase+X, []} || X <- lists:seq(1,FLU_num)],
+        FLU_names = [FLU || {flu,FLU,_,_,_} <- FLU_defs],
+        Ch_defs = [{chain, list_to_atom("c"++integer_to_list(X)),
+                    lists:sublist(FLU_names, X, 3),
+                    []} || X <- lists:seq(1, FLU_num, 3)],
+
+        R1 = [switch_old_and_new,
+              {host, "localhost", "localhost", "localhost", []}]
+             ++ FLU_defs ++ Ch_defs,
+        {ok, Env1} = machi_lifecycle_mgr:run_ast(R1),
+        {_X1a, X1b} = machi_lifecycle_mgr:diff_env(Env1, "localhost"),
+        %% io:format(user, "X1b ~p\n", [X1b]),
+        [machi_lifecycle_mgr:make_pending_config(X) || X <- X1b],
+        {PassFLUs, PassChains} = machi_lifecycle_mgr:process_pending(),
+        true = (length(PassFLUs) == length(FLU_defs)),
+        true = (length(PassChains) == length(Ch_defs)),
+             
+        %% Kick the chain managers into doing something useful right now.
+        Pstores = [list_to_atom(atom_to_list(X) ++ "_pstore") || X <- FLU_names],
+        Fits = [list_to_atom(atom_to_list(X) ++ "_fitness") || X <- FLU_names],
+        ChMgrs = [list_to_atom(atom_to_list(X) ++ "_chmgr") || X <- FLU_names],
+        Advance = machi_chain_manager1_test:make_advance_fun(
+                    Fits, FLU_names, ChMgrs, 3),
+        Advance(),
+
+        %% Sanity check: everyone is configured properly.
+        [begin
+             {ok, #projection_v1{epoch_number=Epoch, all_members=All,
+                                 chain_name=ChainName, upi=UPI}} =
+                 machi_projection_store:read_latest_projection(PStore, private),
+             %% io:format(user, "~p: epoch ~p all ~p\n", [PStore, Epoch, All]),
+             true = Epoch > 0,
+             ChainLen = length(All),
+             true = (length(UPI) > 0),
+             {chain, _, Full, []} = lists:keyfind(ChainName, 2, Ch_defs),
+             true = lists:sort(Full) == lists:sort(All)
+         end || PStore <- Pstores],
+        
+        ok
+    after
+        cleanup(YoCleanup)
+    end.
+
+-endif. % !PULSE
+-endif. % TEST

test/machi_merkle_tree_test.erl

@@ -0,0 +1,200 @@
+%% -------------------------------------------------------------------
+%%
+%% Copyright (c) 2007-2015 Basho Technologies, Inc.  All Rights Reserved.
+%%
+%% This file is provided to you under the Apache License,
+%% Version 2.0 (the "License"); you may not use this file
+%% except in compliance with the License.  You may obtain
+%% a copy of the License at
+%%
+%%   http://www.apache.org/licenses/LICENSE-2.0
+%%
+%% Unless required by applicable law or agreed to in writing,
+%% software distributed under the License is distributed on an
+%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+%% KIND, either express or implied.  See the License for the
+%% specific language governing permissions and limitations
+%% under the License.
+%%
+%% -------------------------------------------------------------------
+
+-module(machi_merkle_tree_test).
+-compile([export_all]).
+
+-include("machi_merkle_tree.hrl").
+
+-include_lib("eunit/include/eunit.hrl").
+-include_lib("kernel/include/file.hrl").
+
+-define(GAP_CHANCE, 0.10).
+
+%% unit tests
+basic_test() ->
+    random:seed(os:timestamp()),
+    Fsz = choose_size() * 1024,
+    Filesize = max(Fsz, 10*1024*1024),
+    ChunkSize = max(1048576, Filesize div 100),
+    N = make_leaf_nodes(Filesize),
+    D0 = #naive{ leaves = N, chunk_size = ChunkSize, recalc = true },
+    T1 = machi_merkle_tree:build_tree(D0),
+
+    D1 = #naive{ leaves = tl(N), chunk_size = ChunkSize, recalc = true },
+    T2 = machi_merkle_tree:build_tree(D1),
+
+    ?assertNotEqual(T1#naive.root, T2#naive.root),
+    ?assertEqual(true, length(machi_merkle_tree:naive_diff(T1, T2)) == 1
+                       orelse
+                       Filesize > ChunkSize).
+
+
+make_leaf_nodes(Filesize) ->
+    lists:reverse(
+      lists:foldl(fun(T, Acc) -> machi_merkle_tree:update_acc(T, Acc) end, 
+                  [], 
+                  generate_offsets(Filesize, 1024, []))
+     ).
+
+choose_int(Factor) ->
+    random:uniform(1024*Factor).
+
+small_int() ->
+    choose_int(10).
+
+medium_int() ->
+    choose_int(1024).
+
+large_int() ->
+    choose_int(4096).
+
+generate_offsets(Filesize, Current, Acc) when Current < Filesize ->
+    Length0 = choose_size(),
+
+    Length = case Length0 + Current > Filesize of
+                 false -> Length0;
+                  true -> Filesize - Current
+    end,
+    Data = term_to_binary(os:timestamp()),
+    Checksum = machi_util:make_tagged_csum(client_sha, machi_util:checksum_chunk(Data)),
+    Gap = maybe_gap(random:uniform()),
+    generate_offsets(Filesize, Current + Length + Gap, [ {Current, Length, Checksum} | Acc ]);
+generate_offsets(_Filesize, _Current, Acc) ->
+    lists:reverse(Acc).
+
+
+random_from_list(L) ->
+    N = random:uniform(length(L)),
+    lists:nth(N, L).
+
+choose_size() ->
+    F = random_from_list([fun small_int/0, fun medium_int/0, fun large_int/0]),
+    F().
+
+maybe_gap(Chance) when Chance < ?GAP_CHANCE ->
+    choose_size();
+maybe_gap(_) -> 0.
+
+%% Define or remove these ifdefs if benchmarking is desired.
+-ifdef(BENCH).
+generate_offsets(FH, Filesize, Current, Acc) when Current < Filesize ->
+    Length0 = choose_size(),
+
+    Length = case Length0 + Current > Filesize of
+                 false -> Length0;
+                  true -> Filesize - Current
+    end,
+    {ok, Data} = file:pread(FH, Current, Length),
+    Checksum = machi_util:make_tagged_csum(client_sha, machi_util:checksum_chunk(Data)),
+    Gap = maybe_gap(random:uniform()),
+    generate_offsets(FH, Filesize, Current + Length + Gap, [ {Current, Length, Checksum} | Acc ]);
+generate_offsets(_FH, _Filesize, _Current, Acc) ->
+    lists:reverse(Acc).
+
+make_offsets_from_file(Filename) ->
+    {ok, Info} = file:read_file_info(Filename),
+    Filesize = Info#file_info.size,
+    {ok, FH} = file:open(Filename, [read, raw, binary]),
+    Offsets = generate_offsets(FH, Filesize, 1024, []),
+    file:close(FH),
+    Offsets.
+
+choose_filename() ->
+    random_from_list([
+        "def^c5ea7511-d649-47d6-a8c3-2b619379c237^1",
+        "jkl^b077eff7-b2be-4773-a73f-fea4acb8a732^1",
+        "stu^553fa47a-157c-4fac-b10f-2252c7d8c37a^1",
+        "vwx^ae015d68-7689-4c9f-9677-926c6664f513^1",
+        "yza^4c784dc2-19bf-4ac6-91f6-58bbe5aa88e0^1"
+                     ]).
+
+
+make_csum_file(DataDir, Filename, Offsets) ->
+    Path = machi_util:make_checksum_filename(DataDir, Filename),
+    filelib:ensure_dir(Path),
+    {ok, MC} = machi_csum_table:open(Path, []),
+    lists:foreach(fun({Offset, Size, Checksum}) -> 
+                    machi_csum_table:write(MC, Offset, Size, Checksum) end,
+                  Offsets),
+    machi_csum_table:close(MC).
+
+
+test() -> 
+    test(100).
+
+test(N) ->
+    {ok, F} = file:open("results.txt", [raw, write]),
+    lists:foreach(fun(X) -> format_and_store(F, run_test(X)) end, lists:seq(1, N)).
+
+format_and_store(F, {OffsetNum, {MTime, MSize}, {NTime, NSize}}) ->
+    S = io_lib:format("~w\t~w\t~w\t~w\t~w\n", [OffsetNum, MTime, MSize, NTime, NSize]),
+    ok = file:write(F, S).
+
+run_test(C) ->
+    random:seed(os:timestamp()),
+    OffsetFn = "test/" ++ choose_filename(),
+    O = make_offsets_from_file(OffsetFn),
+    Fn = "csum_" ++ integer_to_list(C),
+    make_csum_file(".", Fn, O),
+
+    Osize = length(O),
+
+    {MTime, {ok, M}} = timer:tc(fun() -> machi_merkle_tree:open(Fn, ".", merklet) end),
+    {NTime, {ok, N}} = timer:tc(fun() -> machi_merkle_tree:open(Fn, ".", naive) end),
+
+    ?assertEqual(Fn, machi_merkle_tree:filename(M)),
+    ?assertEqual(Fn, machi_merkle_tree:filename(N)),
+
+    MTree = machi_merkle_tree:tree(M),
+    MSize = byte_size(term_to_binary(MTree)),
+
+    NTree = machi_merkle_tree:tree(N),
+    NSize = byte_size(term_to_binary(NTree)),
+
+    ?assertEqual(same, machi_merkle_tree:diff(N, N)),
+    ?assertEqual(same, machi_merkle_tree:diff(M, M)),
+    {Osize, {MTime, MSize}, {NTime, NSize}}.
+
+torture_test(C) ->
+    Results = [ run_torture_test() || _ <- lists:seq(1, C) ],
+    {ok, F} = file:open("torture_results.txt", [raw, write]),
+    lists:foreach(fun({MSize, MTime, NSize, NTime}) ->
+                      file:write(F, io_lib:format("~p\t~p\t~p\t~p\n",
+                                                [MSize, MTime, NSize, NTime]))
+                  end, Results),
+    ok = file:close(F).
+
+run_torture_test() ->
+    {NTime, N} = timer:tc(fun() -> naive_torture() end), 
+
+    MSize = byte_size(term_to_binary(M)),
+    NSize = byte_size(term_to_binary(N)),
+
+    {MSize, MTime, NSize, NTime}.
+
+naive_torture() ->
+    N = lists:foldl(fun(T, Acc) -> machi_merkle_tree:update_acc(T, Acc) end, [], torture_generator()),
+    T = #naive{ leaves = lists:reverse(N), chunk_size = 10010, recalc = true },
+    machi_merkle_tree:build_tree(T).
+
+torture_generator() ->
+    [ {O, 1, crypto:hash(sha, term_to_binary(now()))} || O <- lists:seq(1024, 1000000) ].
+-endif. % BENCH

test/machi_pb_high_client_test.erl

@@ -24,6 +24,7 @@
 -ifdef(TEST).
 -ifndef(PULSE).
 
+-include("machi.hrl").
 -include("machi_pb.hrl").
 -include("machi_projection.hrl").
 -include_lib("eunit/include/eunit.hrl").
@@ -34,20 +35,15 @@ smoke_test_() ->
     {timeout, 5*60, fun() -> smoke_test2() end}.
 
 smoke_test2() ->
-    Port = 5720,
+    PortBase = 5720,
-    Ps = [#p_srvr{name=a, address="localhost", port=Port, props="./data.a"}
+    ok = application:set_env(machi, max_file_size, 1024*1024),
-         ],
-    D = orddict:from_list([{P#p_srvr.name, P} || P <- Ps]),
-    
-    [os:cmd("rm -rf " ++ P#p_srvr.props) || P <- Ps],
-    {ok, SupPid} = machi_flu_sup:start_link(),
     try
-        [begin
+        {Ps, MgrNames, Dirs} = machi_test_util:start_flu_packages(
-             #p_srvr{name=Name, port=Port, props=Dir} = P,
+                                 1, PortBase, "./data.", []),
-             {ok, _} = machi_flu_psup:start_flu_package(Name, Port, Dir, [])
+        D = orddict:from_list([{P#p_srvr.name, P} || P <- Ps]),
-         end || P <- Ps],
+        M0 = hd(MgrNames),
-        ok = machi_chain_manager1:set_chain_members(a_chmgr, D),
+        ok = machi_chain_manager1:set_chain_members(M0, D),
-        [machi_chain_manager1:trigger_react_to_env(a_chmgr) || _ <-lists:seq(1,5)],
+        [machi_chain_manager1:trigger_react_to_env(M0) || _ <-lists:seq(1,5)],
 
         {ok, Clnt} = ?C:start_link(Ps),
         try
@@ -60,16 +56,18 @@ smoke_test2() ->
             %% a separate test module?  Or separate test func?
             {error, _} = ?C:auth(Clnt, "foo", "bar"),
 
-            PK = <<>>,
             Prefix = <<"prefix">>,
             Chunk1 = <<"Hello, chunk!">>,
+            NS = "",
+            NoCSum = <<>>,
+            Opts1 = #append_opts{},
             {ok, {Off1, Size1, File1}} =
-                ?C:append_chunk(Clnt, PK, Prefix, Chunk1, none, 0),
+                ?C:append_chunk(Clnt, NS, Prefix, Chunk1, NoCSum, Opts1),
             true = is_binary(File1),
             Chunk2 = "It's another chunk",
             CSum2 = {client_sha, machi_util:checksum_chunk(Chunk2)},
             {ok, {Off2, Size2, File2}} =
-                ?C:append_chunk(Clnt, PK, Prefix, Chunk2, CSum2, 1024),
+                ?C:append_chunk(Clnt, NS, Prefix, Chunk2, CSum2, Opts1),
             Chunk3 = ["This is a ", <<"test,">>, 32, [["Hello, world!"]]],
             File3 = File2,
             Off3 = Off2 + iolist_size(Chunk2),
@@ -80,7 +78,9 @@ smoke_test2() ->
                      {iolist_to_binary(Chunk2), File2, Off2, Size2},
                      {iolist_to_binary(Chunk3), File3, Off3, Size3}],
             [begin
-                 {ok, Ch} = ?C:read_chunk(Clnt, Fl, Off, Sz)
+                 File = Fl,
+                 ?assertMatch({ok, {[{File, Off, Ch, _}], []}},
+                              ?C:read_chunk(Clnt, Fl, Off, Sz, undefined))
              end || {Ch, Fl, Off, Sz} <- Reads],
 
             {ok, KludgeBin} = ?C:checksum_list(Clnt, File1),
@@ -88,25 +88,56 @@ smoke_test2() ->
             {ok, [{File1Size,File1}]} = ?C:list_files(Clnt),
             true = is_integer(File1Size),
 
+            File1Bin = binary_to_list(File1),
             [begin
-                 %% ok = ?C:trim_chunk(Clnt, Fl, Off, Sz)
+                 #p_srvr{name=Name, props=Props} = P,
-                 %% This gets an error as trim API is still a stub
+                 Dir = proplists:get_value(data_dir, Props),
-                 ?assertMatch({bummer,
+                 ?assertEqual({ok, [File1Bin]},
-                               {throw,
+                              file:list_dir(filename:join([Dir, "data"]))),
-                                {error, bad_joss_taipan_fixme},
+                 FileListFileName = filename:join([Dir, "known_files_" ++ atom_to_list(Name)]),
-                                _Boring_stack_trace}},
+                 {ok, Plist} = machi_plist:open(FileListFileName, []),
-                              ?C:trim_chunk(Clnt, Fl, Off, Sz))
+                 ?assertEqual([], machi_plist:all(Plist))
-             end || {Ch, Fl, Off, Sz} <- Reads],
+             end || P <- Ps],
 
+            [begin
+                 ok = ?C:trim_chunk(Clnt, Fl, Off, Sz)
+             end || {_Ch, Fl, Off, Sz} <- Reads],
+            [begin
+                 {ok, {[], Trimmed}} =
+                        ?C:read_chunk(Clnt, Fl, Off, Sz, #read_opts{needs_trimmed=true}),
+                 Filename = Fl,
+                 ?assertEqual([{Filename, Off, Sz}], Trimmed)
+             end || {_Ch, Fl, Off, Sz} <- Reads],
+
+            LargeBytes = binary:copy(<<"x">>, 1024*1024),
+            LBCsum = {client_sha, machi_util:checksum_chunk(LargeBytes)},
+            {ok, {Offx, Sizex, Filex}} =
+                ?C:append_chunk(Clnt, NS,
+                                Prefix, LargeBytes, LBCsum, Opts1),
+            ok = ?C:trim_chunk(Clnt, Filex, Offx, Sizex),
+
+            %% Make sure everything was trimmed
+            File = binary_to_list(Filex),
+            [begin
+                 #p_srvr{name=Name, props=Props} = P,
+                 Dir = proplists:get_value(data_dir, Props),
+                 ?assertEqual({ok, []},
+                              file:list_dir(filename:join([Dir, "data"]))),
+                 FileListFileName = filename:join([Dir, "known_files_" ++ atom_to_list(Name)]),
+                 {ok, Plist} = machi_plist:open(FileListFileName, []),
+                 ?assertEqual([File], machi_plist:all(Plist))
+             end || P <- Ps],
+
+            [begin
+                 {error, trimmed} =
+                        ?C:read_chunk(Clnt, Fl, Off, Sz, undefined)
+             end || {_Ch, Fl, Off, Sz} <- Reads],
             ok
         after
             (catch ?C:quit(Clnt))
         end
     after
-        exit(SupPid, normal),
+        machi_test_util:stop_flu_packages()
-       [os:cmd("rm -rf " ++ P#p_srvr.props) || P <- Ps],
-        machi_util:wait_for_death(SupPid, 100),
-        ok
     end.
 
 -endif. % !PULSE

test/machi_plist_test.erl

@@ -0,0 +1,17 @@
+-module(machi_plist_test).
+
+-include_lib("eunit/include/eunit.hrl").
+
+open_close_test() ->
+    FileName = "bark-bark-one",
+    file:delete(FileName),
+    {ok, PList0} = machi_plist:open(FileName, []),
+    {ok, PList1} = machi_plist:add(PList0, "boomar"),
+    ?assertEqual(["boomar"], machi_plist:all(PList1)),
+    ok = machi_plist:close(PList1),
+
+    {ok, PList2} = machi_plist:open(FileName, []),
+    ?assertEqual(["boomar"], machi_plist:all(PList2)),
+    ok = machi_plist:close(PList2),
+    file:delete(FileName),
+    ok.

test/machi_projection_store_test.erl

@@ -33,7 +33,7 @@ smoke_test() ->
     Dir = "./data.a",
     Os = [{ignore_stability_time, true}, {active_mode, false}],
     os:cmd("rm -rf " ++ Dir),
-    machi_flu1_test:start_flu_package(a, PortBase, "./data.a", Os),
+    machi_test_util:start_flu_package(a, PortBase, "./data.a", Os),
 
     try
         P1 = machi_projection:new(1, a, [], [], [], [], []),
@@ -58,7 +58,7 @@ smoke_test() ->
 
         ok
     after
-        machi_flu1_test:stop_flu_package(a)
+        machi_test_util:stop_flu_package()
     end.
 
 -endif. % !PULSE

test/machi_proxy_flu1_client_test.erl

@@ -32,46 +32,55 @@
 
 api_smoke_test() ->
     RegName = api_smoke_flu,
-    Host = "localhost",
+    TcpPort = 17124,
-    TcpPort = 57124,
     DataDir = "./data.api_smoke_flu",
     W_props = [{active_mode, false},{initial_wedged, false}],
     Prefix = <<"prefix">>,
-
+    NSInfo = undefined,
-    machi_flu1_test:start_flu_package(RegName, TcpPort, DataDir, W_props),
+    NoCSum = <<>>,
 
     try
-        I = #p_srvr{name=RegName, address=Host, port=TcpPort},
+        {[I], _, _} = machi_test_util:start_flu_package(
+                        RegName, TcpPort, DataDir, W_props),
         {ok, Prox1} = ?MUT:start_link(I),
         try
             FakeEpoch = ?DUMMY_PV1_EPOCH,
-            [{ok, {_,_,_}} = ?MUT:append_chunk(Prox1,
+            [{ok, {_,_,_}} = ?MUT:append_chunk(
-                                          FakeEpoch, Prefix, <<"data">>,
+                                          Prox1, NSInfo, FakeEpoch,
-                                          infinity) || _ <- lists:seq(1,5)],
+                                          Prefix, <<"data">>, NoCSum) ||
+                _ <- lists:seq(1,5)],
             %% Stop the FLU, what happens?
-            machi_flu1_test:stop_flu_package(RegName),
+            machi_test_util:stop_flu_package(),
-            [{error,partition} = ?MUT:append_chunk(Prox1,
+            [{error,partition} = ?MUT:append_chunk(Prox1, NSInfo,
                                 FakeEpoch, Prefix, <<"data-stopped1">>,
-                                infinity) || _ <- lists:seq(1,3)],
+                                NoCSum) || _ <- lists:seq(1,3)],
             %% Start the FLU again, we should be able to do stuff immediately
-            machi_flu1_test:start_flu_package(RegName, TcpPort, DataDir,
+            machi_test_util:start_flu_package(RegName, TcpPort, DataDir,
-                                                   [save_data_dir|W_props]),
+                                              [no_cleanup|W_props]),
             MyChunk = <<"my chunk data">>,
             {ok, {MyOff,MySize,MyFile}} =
-                ?MUT:append_chunk(Prox1, FakeEpoch, Prefix, MyChunk,
+                ?MUT:append_chunk(Prox1, NSInfo, FakeEpoch, Prefix, MyChunk,
-                                  infinity),
+                                  NoCSum),
-            {ok, MyChunk} = ?MUT:read_chunk(Prox1, FakeEpoch, MyFile, MyOff, MySize),
+            {ok, {[{_, MyOff, MyChunk, _MyChunkCSUM}], []}} =
-            MyChunk2 = <<"my chunk data, yeah, again">>,
+                ?MUT:read_chunk(Prox1, NSInfo, FakeEpoch, MyFile, MyOff, MySize, undefined),
+            MyChunk2_parts = [<<"my chunk ">>, "data", <<", yeah, again">>],
+            MyChunk2 = iolist_to_binary(MyChunk2_parts),
+            Opts1 = #append_opts{chunk_extra=4242},
             {ok, {MyOff2,MySize2,MyFile2}} =
-                ?MUT:append_chunk_extra(Prox1, FakeEpoch, Prefix,
+                ?MUT:append_chunk(Prox1, NSInfo, FakeEpoch, Prefix,
-                                        MyChunk2, 4242, infinity),
+                                  MyChunk2_parts, NoCSum, Opts1, infinity),
-            {ok, MyChunk2} = ?MUT:read_chunk(Prox1, FakeEpoch, MyFile2, MyOff2, MySize2),
+            [{ok, {[{_, MyOff2, MyChunk2, _}], []}} =
-            MyChunk_badcs = {<<?CSUM_TAG_CLIENT_SHA:8, 0:(8*20)>>, MyChunk},
+                ?MUT:read_chunk(Prox1, NSInfo, FakeEpoch, MyFile2, MyOff2, MySize2, DefaultOptions) ||
-            {error, bad_checksum} = ?MUT:append_chunk(Prox1, FakeEpoch,
+                DefaultOptions <- [undefined, noopt, none, any_atom_at_all] ],
-                                                      Prefix, MyChunk_badcs),
+
-            {error, bad_checksum} = ?MUT:write_chunk(Prox1, FakeEpoch,
+            BadCSum = {?CSUM_TAG_CLIENT_SHA, crypto:hash(sha, "...................")},
-                                                     <<"foo-file^1^1">>, 99832,
+            {error, bad_checksum} = ?MUT:append_chunk(Prox1, NSInfo, FakeEpoch,
-                                                     MyChunk_badcs),
+                                                      Prefix, MyChunk, BadCSum),
+            {error, bad_checksum} = ?MUT:write_chunk(Prox1, NSInfo, FakeEpoch,
+                                                     MyFile2,
+                                                     MyOff2 + size(MyChunk2),
+                                                     MyChunk, BadCSum,
+                                                     infinity),
 
             %% Put kick_projection_reaction() in the middle of the test so
             %% that any problems with its async nature will (hopefully)
@@ -80,9 +89,9 @@ api_smoke_test() ->
 
             %% Alright, now for the rest of the API, whee
             BadFile = <<"no-such-file">>,
-            {error, bad_arg} = ?MUT:checksum_list(Prox1, FakeEpoch, BadFile),
+            {error, bad_arg} = ?MUT:checksum_list(Prox1, BadFile),
             {ok, [_|_]} = ?MUT:list_files(Prox1, FakeEpoch),
-            {ok, {false, _}} = ?MUT:wedge_status(Prox1),
+            {ok, {false, _,_,_}} = ?MUT:wedge_status(Prox1),
             {ok, {0, _SomeCSum}} = ?MUT:get_latest_epochid(Prox1, public),
             {ok, #projection_v1{epoch_number=0}} =
                  ?MUT:read_latest_projection(Prox1, public),
@@ -100,27 +109,30 @@ api_smoke_test() ->
             _ = (catch ?MUT:quit(Prox1))
         end
     after
-        (catch machi_flu1_test:stop_flu_package(RegName))
+        (catch machi_test_util:stop_flu_package())
     end.
 
-flu_restart_test() ->
+flu_restart_test_() ->
+    {timeout, 1*60, fun() -> flu_restart_test2() end}.
+
+flu_restart_test2() ->
     RegName = a,
-    Host = "localhost",
+    TcpPort = 17125,
-    TcpPort = 57125,
     DataDir = "./data.api_smoke_flu2",
     W_props = [{initial_wedged, false}, {active_mode, false}],
-    machi_flu1_test:start_flu_package(RegName, TcpPort, DataDir, W_props),
+    NSInfo = undefined,
+    NoCSum = <<>>,
 
     try
-        I = #p_srvr{name=RegName, address=Host, port=TcpPort},
+        {[I], _, _} = machi_test_util:start_flu_package(
+                        RegName, TcpPort, DataDir, W_props),
         {ok, Prox1} = ?MUT:start_link(I),
         try
             FakeEpoch = ?DUMMY_PV1_EPOCH,
             Data   = <<"data!">>,
             Dataxx = <<"Fake!">>,
-            {ok, {Off1,Size1,File1}} = ?MUT:append_chunk(Prox1,
+            {ok, {Off1,Size1,File1}} = ?MUT:append_chunk(Prox1, NSInfo,
-                                          FakeEpoch, <<"prefix">>, Data,
+                                         FakeEpoch, <<"prefix">>, Data, NoCSum),
-                                          infinity),
             P_a = #p_srvr{name=a, address="localhost", port=6622},
             P1   = machi_projection:new(1, RegName, [P_a], [], [RegName], [], []),
             P1xx = P1#projection_v1{dbg2=["dbg2 changes are ok"]},
@@ -132,7 +144,7 @@ flu_restart_test() ->
             {ok, EpochID} = ?MUT:get_epoch_id(Prox1),
             {ok, EpochID} = ?MUT:get_latest_epochid(Prox1, public),
             {ok, EpochID} = ?MUT:get_latest_epochid(Prox1, private),
-            ok = machi_flu1_test:stop_flu_package(RegName), timer:sleep(50),
+            ok = machi_test_util:stop_flu_package(), timer:sleep(50),
 
             %% Now that the last proxy op was successful and only
             %% after did we stop the FLU, let's check that both the
@@ -144,9 +156,10 @@ flu_restart_test() ->
             %% makes the code a bit convoluted.  (No LFE or
             %% Elixir macros here, alas, they'd be useful.)
 
+            AppendOpts1 = #append_opts{chunk_extra=42},
             ExpectedOps = 
                 [
-                 fun(run) -> {ok, EpochID} = ?MUT:get_epoch_id(Prox1),
+                 fun(run) -> ?assertEqual({ok, EpochID}, ?MUT:get_epoch_id(Prox1)),
                              ok;
                     (line) -> io:format("line ~p, ", [?LINE]);
                     (stop) -> ?MUT:get_epoch_id(Prox1) end,
@@ -225,35 +238,37 @@ flu_restart_test() ->
                     (stop) -> ?MUT:get_all_projections(Prox1, private)
                  end,
                  fun(run) -> {ok, {_,_,_}} =
-                                 ?MUT:append_chunk(Prox1, FakeEpoch,
+                                 ?MUT:append_chunk(Prox1, NSInfo, FakeEpoch,
-                                                <<"prefix">>, Data, infinity),
+                                                <<"prefix">>, Data, NoCSum),
                              ok;
                     (line) -> io:format("line ~p, ", [?LINE]);
-                    (stop) -> ?MUT:append_chunk(Prox1, FakeEpoch,
+                    (stop) -> ?MUT:append_chunk(Prox1, NSInfo, FakeEpoch,
-                                                <<"prefix">>, Data, infinity)
+                                                <<"prefix">>, Data, NoCSum)
                  end,
                  fun(run) -> {ok, {_,_,_}} =
-                                 ?MUT:append_chunk_extra(Prox1, FakeEpoch,
+                                 ?MUT:append_chunk(Prox1, NSInfo, FakeEpoch,
-                                             <<"prefix">>, Data, 42, infinity),
+                                                   <<"prefix">>, Data, NoCSum,
+                                                   AppendOpts1, infinity),
                              ok;
                     (line) -> io:format("line ~p, ", [?LINE]);
-                    (stop) -> ?MUT:append_chunk_extra(Prox1, FakeEpoch,
+                    (stop) -> ?MUT:append_chunk(Prox1, NSInfo, FakeEpoch,
-                                             <<"prefix">>, Data, 42, infinity)
+                                                   <<"prefix">>, Data, NoCSum,
+                                                   AppendOpts1, infinity)
                  end,
-                 fun(run) -> {ok, Data} =
+                 fun(run) -> {ok, {[{_, Off1, Data, _}], []}} =
-                                 ?MUT:read_chunk(Prox1, FakeEpoch,
+                                 ?MUT:read_chunk(Prox1, NSInfo, FakeEpoch,
-                                                 File1, Off1, Size1),
+                                                 File1, Off1, Size1, undefined),
                              ok;
                     (line) -> io:format("line ~p, ", [?LINE]);
-                    (stop) -> ?MUT:read_chunk(Prox1, FakeEpoch,
+                    (stop) -> ?MUT:read_chunk(Prox1, NSInfo, FakeEpoch,
-                                                 File1, Off1, Size1)
+                                              File1, Off1, Size1, undefined)
                  end,
                  fun(run) -> {ok, KludgeBin} =
-                                 ?MUT:checksum_list(Prox1, FakeEpoch, File1),
+                                 ?MUT:checksum_list(Prox1, File1),
                              true = is_binary(KludgeBin),
                              ok;
                     (line) -> io:format("line ~p, ", [?LINE]);
-                    (stop) -> ?MUT:checksum_list(Prox1, FakeEpoch, File1)
+                    (stop) -> ?MUT:checksum_list(Prox1, File1)
                  end,
                  fun(run) -> {ok, _} =
                                  ?MUT:list_files(Prox1, FakeEpoch),
@@ -269,32 +284,32 @@ flu_restart_test() ->
                  end,
                  fun(run) ->
                              ok =
-                                 ?MUT:write_chunk(Prox1, FakeEpoch, File1, Off1,
+                                 ?MUT:write_chunk(Prox1, NSInfo, FakeEpoch, File1, Off1,
-                                                  Data, infinity),
+                                                  Data, NoCSum, infinity),
                              ok;
                     (line) -> io:format("line ~p, ", [?LINE]);
-                    (stop) -> ?MUT:write_chunk(Prox1, FakeEpoch, File1, Off1,
+                    (stop) -> ?MUT:write_chunk(Prox1, NSInfo, FakeEpoch, File1, Off1,
-                                               Data, infinity)
+                                               Data, NoCSum, infinity)
                  end,
                  fun(run) -> 
                          {error, written} =
-                                 ?MUT:write_chunk(Prox1, FakeEpoch, File1, Off1,
+                                 ?MUT:write_chunk(Prox1, NSInfo, FakeEpoch, File1, Off1,
-                                                  Dataxx, infinity),
+                                                  Dataxx, NoCSum, infinity),
                              ok;
                     (line) -> io:format("line ~p, ", [?LINE]);
-                    (stop) -> ?MUT:write_chunk(Prox1, FakeEpoch, File1, Off1,
+                    (stop) -> ?MUT:write_chunk(Prox1, NSInfo, FakeEpoch, File1, Off1,
-                                               Dataxx, infinity)
+                                               Dataxx, NoCSum, infinity)
                  end
                 ],
 
             [begin
-                 machi_flu1_test:start_flu_package(
+                 machi_test_util:start_flu_package(
                           RegName, TcpPort, DataDir,
-                          [save_data_dir|W_props]),
+                          [no_cleanup|W_props]),
                  _ = Fun(line),
                  ok = Fun(run),
                  ok = Fun(run),
-                 ok = machi_flu1_test:stop_flu_package(RegName),
+                 ok = machi_test_util:stop_flu_package(),
                  {error, partition} = Fun(stop),
                  {error, partition} = Fun(stop),
                  ok
@@ -304,7 +319,7 @@ flu_restart_test() ->
             _ = (catch ?MUT:quit(Prox1))
         end
     after
-        (catch machi_flu1_test:stop_flu_package(RegName))
+        (catch machi_test_util:stop_flu_package())
     end.
 
 -endif. % !PULSE

test/machi_test_util.erl

@@ -0,0 +1,111 @@
+%% -------------------------------------------------------------------
+%%
+%% Copyright (c) 2007-2015 Basho Technologies, Inc.  All Rights Reserved.
+%%
+%% This file is provided to you under the Apache License,
+%% Version 2.0 (the "License"); you may not use this file
+%% except in compliance with the License.  You may obtain
+%% a copy of the License at
+%%
+%%   http://www.apache.org/licenses/LICENSE-2.0
+%%
+%% Unless required by applicable law or agreed to in writing,
+%% software distributed under the License is distributed on an
+%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+%% KIND, either express or implied.  See the License for the
+%% specific language governing permissions and limitations
+%% under the License.
+%%
+%% -------------------------------------------------------------------
+
+-module(machi_test_util).
+-compile(export_all).
+
+-ifdef(TEST).
+-ifndef(PULSE).
+
+-include_lib("eunit/include/eunit.hrl").
+
+-include("machi.hrl").
+-include("machi_projection.hrl").
+
+-define(FLU, machi_flu1).
+-define(FLU_C, machi_flu1_client).
+
+-spec start_flu_package(atom(), inet:port_number(), string()) ->
+                               {Ps::[#p_srvr{}], MgrNames::[atom()], Dirs::[string()]}.
+start_flu_package(FluName, TcpPort, DataDir) ->
+    start_flu_package(FluName, TcpPort, DataDir, []).
+
+-spec start_flu_package(atom(), inet:port_number(), string(), list()) ->
+                               {Ps::[#p_srvr{}], MgrNames::[atom()], Dirs::[string()]}.
+start_flu_package(FluName, TcpPort, DataDir, Props) ->
+    MgrName = machi_flu_psup:make_mgr_supname(FluName),
+    FluInfo = [{#p_srvr{name=FluName, address="localhost", port=TcpPort,
+                        props=[{chmgr, MgrName}, {data_dir, DataDir} | Props]},
+                DataDir, MgrName}],
+    start_flu_packages(FluInfo).
+
+-spec start_flu_packages(pos_integer(), inet:port_number(), string(), list()) ->
+                                {Ps::[#p_srvr{}], MgrNames::[atom()], Dirs::[string()]}.
+start_flu_packages(FluCount, BaseTcpPort, DirPrefix, Props) ->
+    FluInfo = flu_info(FluCount, BaseTcpPort, DirPrefix, Props),
+    start_flu_packages(FluInfo).
+
+start_flu_packages(FluInfo) ->
+    _ = stop_machi_sup(),
+    clean_up(FluInfo),
+    {ok, _SupPid} = machi_sup:start_link(),
+    [{ok, _} = machi_flu_psup:start_flu_package(Name, Port, Dir, Props) ||
+        {#p_srvr{name=Name, port=Port, props=Props}, Dir, _} <- FluInfo],
+    {Ps, Dirs, MgrNames} = lists:unzip3(FluInfo),
+    {Ps, MgrNames, Dirs}.
+
+stop_flu_package() ->
+    stop_flu_packages().
+
+stop_flu_packages() ->
+    stop_machi_sup().
+
+flu_info(FluCount, BaseTcpPort, DirPrefix, Props) ->
+    [begin
+         FLUNameStr = [$a + I - 1],
+         FLUName = list_to_atom(FLUNameStr),
+         MgrName = machi_flu_psup:make_mgr_supname(FLUName),
+         DataDir = DirPrefix ++ "/data.eqc." ++ FLUNameStr,
+         {#p_srvr{name=FLUName, address="localhost", port=BaseTcpPort + I,
+                  props=[{chmgr, MgrName}, {data_dir, DataDir} | Props]},
+          DataDir, MgrName}
+     end || I <- lists:seq(1, FluCount)].
+
+stop_machi_sup() ->
+    case whereis(machi_sup) of
+        undefined -> ok;
+        Pid ->
+            catch exit(whereis(machi_sup), normal),
+            machi_util:wait_for_death(Pid, 100)
+    end.
+
+clean_up(FluInfo) ->
+    _ = [begin
+             case proplists:get_value(no_cleanup, Props) of
+                 true -> ok;
+                 _ ->
+                     _ = machi_flu1:stop(FLUName),
+                     clean_up_dir(Dir)
+             end
+         end || {#p_srvr{name=FLUName, props=Props}, Dir, _} <- FluInfo],
+    ok.
+
+clean_up_dir(Dir) ->
+    [begin
+         Fs = filelib:wildcard(Dir ++ Glob),
+         [file:delete(F) || F <- Fs],
+         [file:del_dir(F) || F <- Fs]
+     end || Glob <- ["*/*/*/*", "*/*/*", "*/*", "*"] ],
+    _ = file:del_dir(Dir),
+    ok.
+
+-endif. % !PULSE
+-endif. % TEST
+

tools.mk

@@ -0,0 +1,176 @@
+#  -------------------------------------------------------------------
+#
+#  Copyright (c) 2014 Basho Technologies, Inc.
+#
+#  This file is provided to you under the Apache License,
+#  Version 2.0 (the "License"); you may not use this file
+#  except in compliance with the License.  You may obtain
+#  a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing,
+#  software distributed under the License is distributed on an
+#  "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+#  KIND, either express or implied.  See the License for the
+#  specific language governing permissions and limitations
+#  under the License.
+#
+#  -------------------------------------------------------------------
+
+#  -------------------------------------------------------------------
+#  NOTE: This file is is from https://github.com/basho/tools.mk.
+#  It should not be edited in a project. It should simply be updated
+#  wholesale when a new version of tools.mk is released.
+#  -------------------------------------------------------------------
+
+REBAR ?= ./rebar
+REVISION ?= $(shell git rev-parse --short HEAD)
+PROJECT ?= $(shell basename `find src -name "*.app.src"` .app.src)
+EUNIT_OPTS ?=
+
+.PHONY: compile-no-deps test docs xref dialyzer-run dialyzer-quick dialyzer \
+		cleanplt upload-docs
+
+compile-no-deps:
+	${REBAR} compile skip_deps=true
+
+test: compile
+	${REBAR} ${EUNIT_OPTS} eunit skip_deps=true
+
+upload-docs: docs
+	@if [ -z "${BUCKET}" -o -z "${PROJECT}" -o -z "${REVISION}" ]; then \
+		echo "Set BUCKET, PROJECT, and REVISION env vars to upload docs"; \
+	        exit 1; fi
+	@cd doc; s3cmd put -P * "s3://${BUCKET}/${PROJECT}/${REVISION}/" > /dev/null
+	@echo "Docs built at: http://${BUCKET}.s3-website-us-east-1.amazonaws.com/${PROJECT}/${REVISION}"
+
+docs:
+	${REBAR} doc skip_deps=true
+
+xref: compile
+	${REBAR} xref skip_deps=true
+
+PLT ?= $(HOME)/.combo_dialyzer_plt
+LOCAL_PLT = .local_dialyzer_plt
+DIALYZER_FLAGS ?= -Wunmatched_returns
+NATIVE_EBIN ?= ./.ebin.native
+DIALYZER_BIN ?= dialyzer
+# Always include -pa arg in DIALYZER_CMD for speed
+DIALYZER_CMD ?= $(DIALYZER_BIN) -pa $(NATIVE_EBIN)
+DIALYZER_VERSION = $(shell $(DIALYZER_BIN) --version | sed 's/.* //')
+ERL_LIB_DIR = $(shell erl -eval '{io:format("~s\n", [code:lib_dir()]), erlang:halt(0)}.' | tail -1)
+
+native-ebin:
+	mkdir -p $(NATIVE_EBIN)
+	rm -f $(NATIVE_EBIN)/*.erl $(NATIVE_EBIN)/*.hrl $(NATIVE_EBIN)/*.beam
+	@for mod in lists dict digraph digraph_utils ets gb_sets gb_trees ordsets sets sofs; do \
+		cp $(ERL_LIB_DIR)/stdlib-*/src/"$$mod".erl $(NATIVE_EBIN); \
+	done
+	@for mod in cerl cerl_trees core_parse; do \
+		cp $(ERL_LIB_DIR)/compiler-*/src/"$$mod".?rl  $(NATIVE_EBIN); \
+	done
+	@for mod in dialyzer_analysis_callgraph dialyzer dialyzer_behaviours dialyzer_codeserver dialyzer_contracts dialyzer_coordinator dialyzer_dataflow dialyzer_dep dialyzer_plt dialyzer_succ_typings dialyzer_typesig dialyzer_worker; do \
+		cp $(ERL_LIB_DIR)/dialyzer-*/src/"$$mod".?rl  $(NATIVE_EBIN); \
+	done
+	@for mod in erl_types erl_bif_types; do \
+		cp $(ERL_LIB_DIR)/hipe-*/*/"$$mod".?rl  $(NATIVE_EBIN); \
+	done
+	erlc -o $(NATIVE_EBIN) -smp +native -DVSN='"$(DIALYZER_VERSION)"' $(NATIVE_EBIN)/*erl
+
+${PLT}: compile
+	@mkdir -p $(NATIVE_EBIN)
+	@if [ -f $(PLT) ]; then \
+		$(DIALYZER_CMD) --check_plt --plt $(PLT) --apps $(DIALYZER_APPS) && \
+		$(DIALYZER_CMD) --add_to_plt --plt $(PLT) --output_plt $(PLT) --apps $(DIALYZER_APPS) ; test $$? -ne 1; \
+	else \
+		$(DIALYZER_CMD) --build_plt --output_plt $(PLT) --apps $(DIALYZER_APPS); test $$? -ne 1; \
+	fi
+
+${LOCAL_PLT}: compile
+	@mkdir -p $(NATIVE_EBIN)
+	@if [ -d deps ]; then \
+		if [ -f $(LOCAL_PLT) ]; then \
+			$(DIALYZER_CMD) --check_plt --plt $(LOCAL_PLT) deps/*/ebin  && \
+			$(DIALYZER_CMD) --add_to_plt --plt $(LOCAL_PLT) --output_plt $(LOCAL_PLT) deps/*/ebin ; test $$? -ne 1; \
+		else \
+			$(DIALYZER_CMD) --build_plt --output_plt $(LOCAL_PLT) deps/*/ebin ; test $$? -ne 1; \
+		fi \
+	fi
+
+dialyzer-run:
+	@mkdir -p $(NATIVE_EBIN)
+	@echo "==> $(shell basename $(shell pwd)) (dialyzer)"
+# The bulk of the code below deals with the dialyzer.ignore-warnings file
+# which contains strings to ignore if output by dialyzer.
+# Typically the strings include line numbers. Using them exactly is hard
+# to maintain as the code changes. This approach instead ignores the line
+# numbers, but takes into account the number of times a string is listed
+# for a given file. So if one string is listed once, for example, and it
+# appears twice in the warnings, the user is alerted. It is possible but
+# unlikely that this approach could mask a warning if one ignored warning
+# is removed and two warnings of the same kind appear in the file, for
+# example. But it is a trade-off that seems worth it.
+# Details of the cryptic commands:
+#   - Remove line numbers from dialyzer.ignore-warnings
+#   - Pre-pend duplicate count to each warning with sort | uniq -c
+#   - Remove annoying white space around duplicate count
+#   - Save in dialyer.ignore-warnings.tmp
+#   - Do the same to dialyzer_warnings
+#   - Remove matches from dialyzer.ignore-warnings.tmp from output
+#   - Remove duplicate count
+#   - Escape regex special chars to use lines as regex patterns
+#   - Add pattern to match any line number (file.erl:\d+:)
+#   - Anchor to match the entire line (^entire line$)
+#   - Save in dialyzer_unhandled_warnings
+#   - Output matches for those patterns found in the original warnings
+	@if [ -f $(LOCAL_PLT) ]; then \
+		PLTS="$(PLT) $(LOCAL_PLT)"; \
+	else \
+		PLTS=$(PLT); \
+	fi; \
+	if [ -f dialyzer.ignore-warnings ]; then \
+		if [ $$(grep -cvE '[^[:space:]]' dialyzer.ignore-warnings) -ne 0 ]; then \
+			echo "ERROR: dialyzer.ignore-warnings contains a blank/empty line, this will match all messages!"; \
+			exit 1; \
+		fi; \
+		$(DIALYZER_CMD) $(DIALYZER_FLAGS) --plts $${PLTS} -c ebin > dialyzer_warnings ; \
+		cat dialyzer.ignore-warnings \
+		| sed -E 's/^([^:]+:)[^:]+:/\1/' \
+		| sort \
+		| uniq -c \
+		| sed -E '/.*\.erl: /!s/^[[:space:]]*[0-9]+[[:space:]]*//' \
+		> dialyzer.ignore-warnings.tmp ; \
+		egrep -v "^[[:space:]]*(done|Checking|Proceeding|Compiling)" dialyzer_warnings \
+		| sed -E 's/^([^:]+:)[^:]+:/\1/' \
+		| sort \
+		| uniq -c \
+		| sed -E '/.*\.erl: /!s/^[[:space:]]*[0-9]+[[:space:]]*//' \
+		| grep -F -f dialyzer.ignore-warnings.tmp -v \
+		| sed -E 's/^[[:space:]]*[0-9]+[[:space:]]*//' \
+		| sed -E 's/([]\^:+?|()*.$${}\[])/\\\1/g' \
+		| sed -E 's/(\\\.erl\\\:)/\1[[:digit:]]+:/g' \
+		| sed -E 's/^(.*)$$/^[[:space:]]*\1$$/g' \
+		> dialyzer_unhandled_warnings ; \
+		rm dialyzer.ignore-warnings.tmp; \
+		if [ $$(cat dialyzer_unhandled_warnings | egrep -v 'Unknown functions\\:' | wc -l) -gt 0 ]; then \
+		    egrep -f dialyzer_unhandled_warnings dialyzer_warnings ; \
+			found_warnings=1; \
+	    fi; \
+		[ "$$found_warnings" != 1 ] ; \
+	else \
+		$(DIALYZER_CMD) $(DIALYZER_FLAGS) --plts $${PLTS} -c ebin; \
+	fi
+
+dialyzer-quick: compile-no-deps dialyzer-run
+
+dialyzer: ${PLT} ${LOCAL_PLT} dialyzer-run
+
+cleanplt:
+	@echo
+	@echo "Are you sure?  It takes several minutes to re-build."
+	@echo Deleting $(PLT) and $(LOCAL_PLT) in 5 seconds.
+	@echo
+	sleep 5
+	rm $(PLT)
+	rm $(LOCAL_PLT)