[
https://issues.apache.org/jira/browse/HBASE-4487?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13118222#comment-13118222
]
Lars Hofhansl commented on HBASE-4487:
--------------------------------------
@ramkrishna and @dhruba. I agree with ramkrishna that the if (this.closed) is
still needed.
True, there already was a race and that was the point of HBASE-4387.
We want to sync without the updateLock held, while at the same make sure we
don't sync unless we need to (i.e. HLog not closed) and if we fail (which will
be rare) without the lock we retry with the lock.
> The increment operation can release the rowlock before sync-ing the Hlog
> ------------------------------------------------------------------------
>
> Key: HBASE-4487
> URL: https://issues.apache.org/jira/browse/HBASE-4487
> Project: HBase
> Issue Type: Improvement
> Reporter: dhruba borthakur
> Assignee: dhruba borthakur
> Fix For: 0.94.0
>
> Attachments: appendNoSync4.txt, appendNoSync5.txt, appendNoSync6.txt
>
>
> This allows for better throughput when there are hot rows.I have seen this
> change make a single row update improve from 400 increments/sec/server to
> 4000 increments/sec/server.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:
https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
