[infinispan-issues] [JBoss JIRA] (ISPN-1918) Benchmark UNICAST vs UNICAST2 vs NAKACK2 with JGroups 3.0.x
Dan Berindei (JIRA)
jira-events at lists.jboss.org
Tue Mar 20 11:07:48 EDT 2012
[ https://issues.jboss.org/browse/ISPN-1918?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12678022#comment-12678022 ]
Dan Berindei commented on ISPN-1918:
------------------------------------
It turns out I had TRACE logging enabled and that slowed the test a lot.
These are the throughputs in the JGroups DIST mode simulation:
|| || || || 2|| 3|| 4||
|jgroups-udp.xml| 1| n| 20.94| 15.44| 14.6|
| | | y| 20.13| 15.4| 14.48|
|jgroups-udp-unicast2.xml| 2| n| 25.7| 23.08| 22.39|
| | | y| 25.79| 23.7| 23.16|
UNICAST starts a little slower than UNICAST2 with 2 nodes, but its performance degrades much quicker as the number of nodes increases.
> Benchmark UNICAST vs UNICAST2 vs NAKACK2 with JGroups 3.0.x
> -----------------------------------------------------------
>
> Key: ISPN-1918
> URL: https://issues.jboss.org/browse/ISPN-1918
> Project: Infinispan
> Issue Type: Task
> Components: RPC
> Affects Versions: 5.1.2.FINAL
> Reporter: Dan Berindei
> Assignee: Dan Berindei
> Labels: jgroups_tuning
> Fix For: 5.1.3.CR1, 5.1.3.FINAL
>
>
> Recent changes seem to have brought performance a bit down, so we need to check whether this is caused by reverting to UNICAST instead of UNICAST2 (ISPN-1892).
> Performance has decreased most in the 2-node scenario, where we were actually sending multicasts instead of unicasts. So we need to check whether there is a performance difference between UNICAST2 and NAKACK2 as well.
> If we find UNICAST2 to perform better, we can proceed with ISPN-1879 on the 5.1.x branch as well as on the master branch.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.jboss.org/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
More information about the infinispan-issues
mailing list