[jira] [Comment Edited] (HBASE-8755) A new write thread model for HLog to improve the overall HBase write throughput

["Lars Hofhansl (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/HBASE-8755?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13688003#comment-13688003 ] 

Lars Hofhansl edited comment on HBASE-8755 at 6/19/13 1:47 PM:
---------------------------------------------------------------

I guess that makes sense. More handoff required between threads, which would impact latency, but better throughput in high pressure cases because of fewer threads contenting for locks.

Any chance to measure context switches during the test with/without the patch? I wonder if those increase due to thread handoffs, until the ctx switches from contended locks outweigh those.

                
      was (Author: lhofhansl):
    I guess that makes sense. More handoff required between threads, which would impact latency, but better throughput in high pressure cases because of fewer threads contenting for locks.

Any chance to measure context switches during the test with/without the patch? I wonder if those increase due to thread handoffs.

                  
> A new write thread model for HLog to improve the overall HBase write throughput
> -------------------------------------------------------------------------------
>
>                 Key: HBASE-8755
>                 URL: https://issues.apache.org/jira/browse/HBASE-8755
>             Project: HBase
>          Issue Type: Improvement
>          Components: wal
>            Reporter: Feng Honghua
>         Attachments: HBASE-8755-0.94-V0.patch, HBASE-8755-0.94-V1.patch, HBASE-8755-trunk-V0.patch
>
>
> In current write model, each write handler thread (executing put()) will individually go through a full 'append (hlog local buffer) => HLog writer append (write to hdfs) => HLog writer sync (sync hdfs)' cycle for each write, which incurs heavy race condition on updateLock and flushLock.
> The only optimization where checking if current syncTillHere > txid in expectation for other thread help write/sync its own txid to hdfs and omitting the write/sync actually help much less than expectation.
> Three of my colleagues(Ye Hangjun / Wu Zesheng / Zhang Peng) at Xiaomi proposed a new write thread model for writing hdfs sequence file and the prototype implementation shows a 4X improvement for throughput (from 17000 to 70000+). 
> I apply this new write thread model in HLog and the performance test in our test cluster shows about 3X throughput improvement (from 12150 to 31520 for 1 RS, from 22000 to 70000 for 5 RS), the 1 RS write throughput (1K row-size) even beats the one of BigTable (Precolator published in 2011 says Bigtable's write throughput then is 31002). I can provide the detailed performance test results if anyone is interested.
> The change for new write thread model is as below:
>  1> All put handler threads append the edits to HLog's local pending buffer; (it notifies AsyncWriter thread that there is new edits in local buffer)
>  2> All put handler threads wait in HLog.syncer() function for underlying threads to finish the sync that contains its txid;
>  3> An single AsyncWriter thread is responsible for retrieve all the buffered edits in HLog's local pending buffer and write to the hdfs (hlog.writer.append); (it notifies AsyncFlusher thread that there is new writes to hdfs that needs a sync)
>  4> An single AsyncFlusher thread is responsible for issuing a sync to hdfs to persist the writes by AsyncWriter; (it notifies the AsyncNotifier thread that sync watermark increases)
>  5> An single AsyncNotifier thread is responsible for notifying all pending put handler threads which are waiting in the HLog.syncer() function
>  6> No LogSyncer thread any more (since there is always AsyncWriter/AsyncFlusher threads do the same job it does)

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira