greg/stasis-bLSM
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
238 commits 1 branch 0 tags 670 KiB
Commit graph

25 commits

Author SHA1 Message Date
sears
0923cd9d96 datapage is no longer a template 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@2666 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2011-06-09 00:07:42 +00:00
sears
975410845f add empirically determined estimators of c0 size, and pessimistic ones that are the default 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@1589 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2011-01-11 22:07:39 +00:00
sears
dad55b564c Misc statistics cleanup; improved merge cost estimations during backpressure. 
Misc statistics cleanups include:
 - fixes for corner case where c0 is empty, and it would divide by zero
 - always compute number of tuples (in / out, but not base)
 - rework amount of memory allocated when --test and --newserver are passed in.



git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@1582 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2011-01-11 19:24:16 +00:00
sears
a6a0ce3f54 extended stats cleanup, verbose mode, documentation 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@1518 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-12-17 18:48:26 +00:00
sears
052508fb76 remove mergeStats->current_size field, which is derivable from other fields in mergeStats 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@1508 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-12-15 00:15:59 +00:00
sears
cd27f50baf remove ltable->tsize and ltable->tree_bytes fields 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@1507 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-12-14 23:06:21 +00:00
sears
73e72b47b2 more stats cleanups 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@1493 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-12-14 01:49:23 +00:00
sears
43425128ba clean up initialization / marshalling code. Lets some of the public mergeStat fields to be protected 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@1490 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-12-14 00:06:32 +00:00
sears
eb4446f409 readability fix: fields in mergeStats that are only used for computing extended stats for pretty print are now prefixed with "stats_", and can be optionally disabled at compile time 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@1489 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-12-13 22:27:13 +00:00
sears
a00531ae6d simplified merge_scheduler 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@1479 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-12-11 00:51:19 +00:00
sears
07b35f4e20 scattered, and poorly tested fixes. finer grained latching for tree nodes; throttle c0-c1 merge when c0 is small; fix delta computations for c0 throttling; disable short pauses for c1-c2 merge. this gets the bulk load throughput up to 8500, but workloada is still slow 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@1045 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-08-21 03:09:18 +00:00
sears
dc75f6d1f0 Implemented snowshoveling, with caveats. 
This commit includes concurrency control for datapages, the new backpressure for the c0-c1 merger, and (untested) support for defining NO_SNOWSHOVEL, and using the old approach.

There are a number of important limitations:
 - statistics gathering is somewhat messed up
 - the c0-c1 merge thread polls for new data
 - on a sequential write, if the writers stall, the merge thread could empty memory and initiate an unnecessary merge.  Instead, we should never finish a merge if c0 is less than N% full
 - this commit introduces yet another batch of nasty mutex contention issues



git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@955 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-08-05 17:43:46 +00:00
sears
9dcb624649 improved bps estimation; add "minisleeps" to update_progress; they do not belong there long term, but this is better than nothing 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@929 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-07-14 21:46:27 +00:00
sears
fded91fec6 two unrelated changes: release rb_mut before getting header_mut on read path (breaks delta tuples), and implement first-cut support for pulling in statistics when reopening logstores (required for correct recovery) 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@868 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-06-21 20:03:05 +00:00
sears
8c35a1265a fix bug in overshoot_fudge computation; reduce number of knobs 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@860 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-06-18 23:00:23 +00:00
sears
0fb644640a improved concurrency for merger. not happy with worst case write latency on my dev machine anymore (seems to be less than 2.5 seconds, up from less than 1). 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@842 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-06-17 04:49:19 +00:00
sears
0ecd7491c7 fix minor stats bugs; pull most stats computation into update_progress. The idea is that update_progress and tick, which are easily amortized, are the only stats things that need to grab latches 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@827 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-06-05 00:41:52 +00:00
sears
eda514ddaa amortize the computation of statistics (but not mutex acuqisitions) across many tuple insertions. Also, refactor stats stuff with latch contention in mind (but it still grabs too many latches...). This commit causes check_tcpclient to emit warnings on my machine. Not sure if it will happen on production hardware 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@824 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-06-02 21:47:58 +00:00
sears
fcf0dcca99 cleanup / reimplement some of the statistics calculations. dial back periodically_force 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@821 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-05-28 21:20:26 +00:00
sears
aa7f7189d6 admission control *almost* works; c1 sometimes blocks for a long time when a new c2 is created 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@809 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-05-26 00:58:17 +00:00
sears
c50c14d259 admission control is now behaving properly (but there are still no concurrent writes, or bounds on how long admission control throttles a given writer) 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@806 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-05-21 23:43:17 +00:00
sears
2a1157602a Rewrite merge thread synchronization code, update status messages, implement preliminary (and ineffective) admission control, and force write merged data every megabyte (so that prograess can be tracked by admission control. Also, refactor quite a few things. 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@805 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-05-19 23:42:06 +00:00
sears
1adb980555 added throttling policy and better stats. the throttling makes a merge policy bug painfully obvious (committing because i plan to do some refactoring...) 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@802 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-05-12 22:16:41 +00:00
sears
7b2560d906 initial merge manager (multi-merge) statistics 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@797 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-04-29 23:13:04 +00:00
sears
ce48882946 oops; forgot to add mergeStats.h; finished encapsuating its state 
git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@795 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
 2010-04-29 01:03:56 +00:00