[
https://issues.apache.org/jira/browse/HBASE-6603?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13436538#comment-13436538
]
Lars Hofhansl commented on HBASE-6603:
--------------------------------------
The patch in HBASE-6217 is similar to the change that I had made locally. (I
did not add a try/finally block, but instead updated the metric at the spots
where the method returns. But it's the same in principle)
Damn, and I was so proud of my profiling detective work. :)
So, should I close this as dup and mark HBASE-6217 against 0.94 and 0.96 also?
Or leave HBASE-6217 against fb89 only and use this for the 0.94 and 0.96
patches?
> RegionMetricsStorage.incrNumericMetric is called too often
> ----------------------------------------------------------
>
> Key: HBASE-6603
> URL: https://issues.apache.org/jira/browse/HBASE-6603
> Project: HBase
> Issue Type: Bug
> Components: performance
> Reporter: Lars Hofhansl
> Assignee: Lars Hofhansl
> Fix For: 0.96.0, 0.94.2
>
>
> Running an HBase scan load through the profiler revealed that
> RegionMetricsStorage.incrNumericMetric is called way too often.
> It turns out that we make this call for *each* KV in StoreScanner.next(...).
> Incrementing AtomicLong requires expensive memory barriers.
> The observation here is that StoreScanner.next(...) can maintain a simple
> long in its internal loop and only update the metric upon exit. Thus the
> AtomicLong is not updated nearly as often.
> That cuts about 10% runtime from scan only load (I'll quantify this better
> soon).
--
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
