greg/stasis-aries-wal
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

A few final citations (for atomic heaps), some reference clean up, latex badness < 2400 now. :)

Browse source 
Still need to check figure captions, citations, end notes.
This commit is contained in:
Sears Russell 2006-09-05 19:08:56 +00:00
parent c0773fc425
commit 73f67a2a62
2 changed files with 62 additions and 53 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

41
doc/paper3/LLADD.bib
View file

@ -14,7 +14,7 @@
@Book{camelot,
ALTauthor = {},
editor = {Jeffrey L Eppinger and Lily B Mummert and Alfred Z Spector},
editor = {Jeffrey L. Eppinger and Lily B. Mummert and Alfred Z. Spector},
title = {Camelot and Avalon, A Distributed Transaction Facility},
publisher = {Morgan Kaufmann},
year = {1991},
@ -45,19 +45,15 @@
@Book{dtp,
author = {{The Open Group}},
ALTeditor = {},
@Manual{dtp,
title = {Distributed Transaction Processing: Reference Model},
publisher = {},
year = {1996},
OPTkey = {},
OPTvolume = {},
OPTnumber = {},
OPTseries = {},
OPTauthor = {},
organization = {{The Open Group}},
OPTaddress = {},
OPTedition = {},
OPTmonth = {},
year = {1996},
OPTnote = {},
OPTannote = {}
}
@ -194,7 +190,7 @@
}
@Article{excel,
author = {B Zeeberg and J Riss and D Kane D and K Bussey and E Uchio and W Linehan and J Barret and J Weinstein},
author = {Barry R Zeeberg and Joseph Riss and David W Kane and Kimberly J Bussey and Edward Uchio and W. Marston Linehann and J. Carl Barrett and John N Weinstein},
title = {Mistaken identifiers: Gene name errors can be introduced inadvertently when using {E}xcel in bioinformatics},
journal = {BMC Bioinformatics},
year = {2004},
@ -272,7 +268,7 @@
@Misc{hibernate,
key = {hibernate},
OPTauthor = {},
title = {Hibernate: Relational Persistence for {J}ava and {.NET}},
title = {Hibernate},
OPThowpublished = {},
OPTmonth = {},
OPTyear = {},
@ -383,7 +379,7 @@
}
@Article{starburst,
author = {Guy M. Lohman and Bruce Lindsay and Hamid Pirahesh and K. Bernhard Schiefer},
author = {Guy Lohman and Bruce Lindsay and Hamid Pirahesh and K. Bernhard Schiefer},
title = {Extensions to {S}tarburst: Objects, types, functions, and rules},
journal = {Communications of the ACM},
year = {1991},
@ -484,7 +480,7 @@
}
@InProceedings{aries,
author = { C. Mohan and D. Haderle and B. Lindsay and H. Pirahesh and P Schwarz },
author = { C. Mohan and D. Haderle and B. Lindsay and H. Pirahesh and Peter M. Schwarz },
title = {{ARIES}, A Transaction Recovery Method Supporting Fine-Granularity Locking and Partial Rollbacks Using Write-Ahead Logging},
OPTcrossref = {},
OPTkey = {},
@ -503,6 +499,21 @@
OPTannote = {}
}
@inproceedings{stableHeap,
author = {Elliot K. Kolodner and
William E. Weihl},
title = {Atomic Incremental Garbage Collection and Recovery for a
Large Stable Heap.},
booktitle = {SIGMOD},
year = {1993},
pages = {177-186},
ee = {http://doi.acm.org/10.1145/170035.170068, db/conf/sigmod/KolodnerW93.html},
OPTcrossref = {DBLP:conf/sigmod/93},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
@Book{ariesIM,
author = {C Mohan and F Levine},
ALTeditor = {},
@ -543,7 +554,7 @@
OPTnumber = {},
OPTseries = {},
OPTaddress = {},
month = {Janurary},
month = {January},
OPTorganization = {},
OPTpublisher = {},
OPTnote = {},
@ -698,7 +709,7 @@
OPTeditor = {Peter Buneman and
Sushil Jajodia},
title = {The {OO7} Benchmark},
booktitle = {SIGMOD International Conference on Management of Data},
booktitle = {SIGMOD},
OPTpublisher = {ACM Press},
year = {1993},
pages = {12-21},

74
doc/paper3/LLADD.tex
View file

@ -36,8 +36,8 @@
\newcommand{\eab}[1]{\textcolor{red}{\bf EAB: #1}}
\newcommand{\rcs}[1]{\textcolor{green}{\bf RCS: #1}}
%\newcommand{\eab}[1]{}
%\newcommand{\rcs}[1]{}
%\renewcommand{\eab}[1]{}
%\renewcommand{\rcs}[1]{}
\newcommand{\eat}[1]{}
@ -63,7 +63,7 @@
\maketitle
\vspace*{-.25in}
%\vspace*{-.25in} % This was only moving the first column up. Putting it in the \author block moves the title down, and putting it before \maketitle adds a blank page...
% Use the following at camera-ready time to suppress page numbers.
% Comment it out when you first submit the paper for review.
@ -71,7 +71,7 @@
%\abstract
%\subsection*{Abstract}
\rcs{Spell check, look at end notes and figure captions. Spell check / cannonicalize bibtex. Embed graph fonts. Make sure $a < b$ when we have cites like [a, b]. Check nocite *}
%\rcs{Done, except graph fonts, but double check. Spell check, look at end notes and figure captions. Spell check / canonicalize bib TeX. Embed graph fonts. Make sure $a < b$ when we have cites like [a, b]. Check no cite *}
{\em An increasing range of applications requires robust support for atomic, durable and concurrent
transactions. Databases provide the default solution, but force
@ -297,7 +297,7 @@ Section~\ref{sec:related-work} covers these in more detail.
In some sense, our hypothesis is trivially true in that there exists a
bottom-up framework called the ``operating system'' that can implement
all of the models. A famous database paper argues that it does so
poorly (Stonebraker 1981~\cite{Stonebraker81}). Our task is really to
poorly~\cite{Stonebraker81}. Our task is really to
simplify the implementation of transactional systems through more
powerful primitives that enable concurrent transactions with a variety
of performance/robustness tradeoffs.
@ -627,7 +627,7 @@ order to implement a ``typical'' operation, the operation's
implementation must obey a few more invariants:
\begin{itemize}
\item Pages should only be updated inside physical redo/undo operation implementations.
\item Logical operation implementations may invoke other operations
\item Logical operations may invoke other operations
via {\tt Tupdate()}. Recovery does not support logical redo,
and physical operation implementations may not invoke {\tt
Tupdate()}.
@ -644,7 +644,8 @@ implementation must obey a few more invariants:
Although these restrictions are not trivial, they are not a problem in
practice. Most read-modify-write actions can be implemented as
user-defined operations, including common DBMS optimizations such as
increment operations. The power of \yad is that by following these
increment operations, and many optimizations based on
ARIES~\cite{stableHeap, ariesIM}. The power of \yad is that by following these
local restrictions, operations meet the global
invariants required by correct, concurrent transactions.
@ -671,15 +672,15 @@ way that does not deadlock. This allows higher-level code to treat
This section describes \yads latching protocols and describes two custom lock
managers that \yads allocation routines use. Applications that want
conventional transactional isolation (serializability) can make
use of a lock manager. Alternatively, applications may follow
use of a lock manager or optimistic concurrency control~\cite{optimisticConcurrencyPerformance, optimisticConcurrencyControl}. Alternatively, applications may follow
the example of \yads default data structures, and implement
deadlock prevention, or other custom lock management
schemes~\cite{hybridAtomicity, optimisticConcurrencyPerformance, optimisticConcurrencyControl}.
schemes.
Note that locking schemes may be
layered as long as no legal sequence of calls to the lower level
results in deadlock, or the higher level is prepared to handle
deadlocks reported by the lower levels~\cite{someOtherLayeringPaper}.
deadlocks reported by the lower levels.
When \yad allocates a
record, it first calls a region allocator, which allocates contiguous
@ -710,7 +711,7 @@ transparent to higher layers. General-purpose database lock managers
provide none of these features, supporting the idea that
special-purpose lock managers are a useful abstraction. Locking
schemes that interact well with object oriented programming
schemes~\cite{sharedAbstractTypes,billOOlockingProtocols} and exception
schemes~\cite{sharedAbstractTypes} and exception
handling~\cite{omtt} extend these ideas to larger systems.
Although custom locking is important for flexibility, it is largely
@ -848,7 +849,7 @@ entering metadata in the primary log.
\subsection{Concurrent RVM}
Our LSN-free pages are similar to the recovery scheme used by
LSN-free pages are similar to the recovery scheme used by
recoverable virtual memory (RVM) and Camelot~\cite{camelot}. RVM
used purely physical logging and LSN-free pages so that it
could use {\tt mmap} to map portions of the page file into application
@ -998,9 +999,9 @@ All benchmarks were run on an Intel Xeon 2.8 GHz processor with 1GB of RAM and a
types.} All results correspond to the mean of multiple runs with a
95\% confidence interval with a half-width of 5\%.
We used Berkeley DB 4.2.52
Our experiments use Berkeley DB 4.2.52
%as it existed in Debian Linux's testing branch during March of 2005,
with the flags DB\_TXN\_SYNC (sync log on commit), and
with the flags DB\_TXN\_SYNC (force log to disk on commit), and
DB\_THREAD (thread safety) enabled. We
increased Berkeley DB's buffer cache and log buffer sizes to match
\yads default sizes. If
@ -1163,13 +1164,15 @@ on top of \yad.
%model would allow us to choose the representation and transactional
%semantics that make the most sense for the system at hand.
%
The first object persistence mechanism, pobj, provides transactional updates to objects in
Titanium, a Java variant. It transparently loads and persists
entire graphs of objects, but will not be discussed in further detail.
The second variant was built on top of a C++ object
persistence library, \oasys. \oasys uses plug-in storage
modules that implement persistent storage, and includes plugins
for Berkeley DB and MySQL.
The first object persistence mechanism, pobj, provides transactional
updates to objects in Titanium, a Java variant. It transparently
loads and persists entire graphs of objects, but will not be discussed
in further detail. The second variant was built on top of a C++
object persistence library, \oasys. \oasys uses plug-in storage
modules that implement persistent storage, and includes plugins for
Berkeley DB and MySQL. Like C++ objects, \oasys objects are
explicitly freed. However, \yad could also support
concurrent and incremental atomic garbage collection~\cite{stableHeap}.
This section describes how the \yad plugin supports optimizations that reduce the
amount of data written to log and halve the amount of RAM required.
@ -1184,7 +1187,7 @@ application objects to become stale. This is safe since the system is
always able to reconstruct the appropriate page entry from the live
copy of the object. This reduces the number of times the
plugin must update serialized objects in the buffer manager, and
allows us to decrease drastically the amount of memory used by the
allows us to nearly eliminate the memory used by the
buffer manager.
We implemented the \yad buffer pool optimization by adding two new
@ -1308,10 +1311,10 @@ independently, improving locality and allowing requests to be merged.}
clip,
width=1\columnwidth]{figs/trans-closure-hotset.pdf}}
\vspace{-12pt}
\caption{\label{fig:hotGraph} Hot-set based graph traversal for random graphs with out-degrees of 3 and 9. Here
we see that the multiplexer helps when the graph has poor locality.
In the cases where depth first search performs well, the
reordering is inexpensive.}
\caption{\label{fig:hotGraph} Hot-set based graph traversal for random
graphs with out-degrees of 3 and 9. Here we see that the multiplexer
has relatively low overhead, and improves performance when the graph
has poor locality.}
\vspace{-12pt}
\end{figure}
@ -1331,7 +1334,7 @@ techniques and relational algebra operators could be used to
non-transactional memory.
To experiment with the potential of such optimizations, we implemented
a single node log-reordering scheme that increases request locality
a single-node log-reordering scheme that increases request locality
during a graph traversal. The graph traversal produces a sequence of
read requests that are partitioned according to their physical
location in the page file. Partition sizes are chosen to fit inside
@ -1355,8 +1358,8 @@ The second experiment measures the effect of graph locality
(Figure~\ref{fig:hotGraph}). Each node has a distinct hot set that
includes the 10\% of the nodes that are closest to it in ring order.
The remaining nodes are in the cold set. We do not use ring edges for
this test, so the graphs might not be connected. We use the same set
of graphs for both systems.
this test, so the graphs might not be connected. We use the same
graphs for both systems.
When the graph has good locality, a normal depth-first search
traversal and the prioritized traversal both perform well. As
@ -1577,9 +1580,9 @@ than QuickSilver, but is not designed for legacy applications.
\subsection{Data Structure Frameworks}
As mentioned in Section~\ref{sec:systems}, Berkeley DB is a system
quite similar to \yad, and provides raw access to
transactional data structures for application
programmers~\cite{libtp}. \eab{summary?}
quite similar to \yad, and gives application programmers raw access to
transactional data structures such as a single-node B-Tree and hash
table~\cite{libtp}.
Cluster hash tables provide a scalable, replicated hash table
implementation by partitioning the table's buckets across multiple
@ -1629,10 +1632,6 @@ hints~\cite{cricket}, pointer values and write order~\cite{starburst},
data type~\cite{orion}, or access
patterns~\cite{storageReorganization}.
%Other work makes use of the caller's stack to infer
%information about memory management.~\cite{xxx} \rcs{Eric, do you have
% a reference for this?}
We are interested in allowing applications to store records in
the transaction log. Assuming log fragmentation is kept to a
minimum, this is particularly attractive on a single disk system. We
@ -1659,7 +1658,7 @@ this trend to continue as development progresses.
A resource manager is a common pattern in system software design, and
manages dependencies and ordering constraints between sets of
components~\cite{resourceManager}. Over time, we hope to shrink \yads core to the point
components. Over time, we hope to shrink \yads core to the point
where it is simply a resource manager that coordinates interchangeable
implementations of the other components.
@ -1710,7 +1709,6 @@ Additional information, and \yads source code is available at:
{\footnotesize \bibliographystyle{acm}
\rcs{What's ``SIGMOD International Conference on Management of Data'' vs ``SIGMOD Record''?}
%\nocite{*}
\bibliography{LLADD}}