[
https://issues.apache.org/jira/browse/HBASE-5826?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13633980#comment-13633980
]
Matteo Bertozzi commented on HBASE-5826:
----------------------------------------
I've played a bit with it days ago but I don't see improvements
the only advantage of this patch is removing one atomic operation
"unflushedEntries" by using the "logSeqNum" that we've already.
By running HLogPerformanceEvaluation this patch results slower than the current
version
https://github.com/matteobertozzi/hbase/commit/5a608a8eee3c1d5a88149132cc782d64f8b6441a
and by reverting back the synchronize (this) to the current status, the
performance seems more or less the same
https://github.com/matteobertozzi/hbase/commit/cb5cc2034bd10ad990a22589dc2a80a93180e358
I don't think that this should stay as critical
> Improve sync of HLog edits
> --------------------------
>
> Key: HBASE-5826
> URL: https://issues.apache.org/jira/browse/HBASE-5826
> Project: HBase
> Issue Type: Improvement
> Reporter: Ted Yu
> Assignee: Todd Lipcon
> Priority: Critical
> Fix For: 0.95.1
>
> Attachments: 5826.txt, 5826-v2.txt, 5826-v3.txt, 5826-v4.txt,
> 5826-v5.txt
>
>
> HBASE-5782 solved the correctness issue for the sync of HLog edits.
> Todd provided a patch that would achieve higher throughput.
> This JIRA is a continuation of Todd's work submitted there.
--
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
