[infinispan-issues] [JBoss JIRA] (ISPN-6494) Investigate bundler performance

[Dan Berindei (Jira)]

    [ https://issues.jboss.org/browse/ISPN-6494?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13651110#comment-13651110 ] 

Dan Berindei commented on ISPN-6494:
------------------------------------

I have run a few PerfAck jobs with different bundlers and the trend is clear: tests with 100 threads are significantly faster, but tests with 10 threads are slightly slower. The trend is somewhat visible with 10kb values (throughput is down 2-6% in the tests w/ 10 threads), but much more obvious in the test with 1kb values (throughput is down 7-15% in the tests w/ 10 threads).

In fairness, the reference benchmark is pretty old, so there may be other factors: http://perfrepo.mw.lab.eng.bos.redhat.com/reports/tableComparisonReport/14144


> Investigate bundler performance
> -------------------------------
>
>                 Key: ISPN-6494
>                 URL: https://issues.jboss.org/browse/ISPN-6494
>             Project: Infinispan
>          Issue Type: Task
>          Components: Core
>    Affects Versions: 9.0.0.Alpha1
>            Reporter: Dan Berindei
>            Assignee: Dan Berindei
>            Priority: Major
>
> For ISPN-6027 we changed the default JGroups bundler to {{sender-sends-with-timer}}, because it was faster in some of the performance tests. However, IspnPerfTest shows {{transfer-queue-bundler}} to be consistently better, so we need to investigate the bundler choice again.



--
This message was sent by Atlassian Jira
(v7.12.1#712002)