[jboss-jira] [JBoss JIRA] (JGRP-1716) The UDP receiver thread parsing messages causes performance regression
Radim Vansa (JIRA)
jira-events at lists.jboss.org
Wed Oct 16 05:01:02 EDT 2013
[ https://issues.jboss.org/browse/JGRP-1716?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Radim Vansa updated JGRP-1716:
------------------------------
Attachment: benchmark-jgroups.xml
jgroups-udp.xml
Yes, the chart is based on results obtained with RadarGun. I am attaching the benchmark and JGroups configuration (just rename it to jgroups-udp-custom.xml) used to show the difference.
RadarGun can be checked out from https://github.com/radargun/radargun (you may want to change JGroups version in jgroups34 plugin's pom.xml from Beta1 to Final).
> The UDP receiver thread parsing messages causes performance regression
> ----------------------------------------------------------------------
>
> Key: JGRP-1716
> URL: https://issues.jboss.org/browse/JGRP-1716
> Project: JGroups
> Issue Type: Bug
> Affects Versions: 3.4
> Reporter: Dan Berindei
> Assignee: Bela Ban
> Fix For: 3.5
>
> Attachments: benchmark-jgroups.xml, jgroups-udp.pdf, jgroups-udp.xml
>
>
> Comparing JGroups 3.2/3.3/3.4 performance with Radargun, the throughput went down by ~10%. (See the attached chart. "getall" means the get requests are sent to 2 nodes, "getfirst" means they are sent to only 1 node.)
> Erik Salter profiled his application and noticed that the message parsing in the UDP receiver thread seemed to slow things down. He wrote a patch that brought his throughput back to 3.2 levels: https://github.com/an1310/JGroups/compare/t_perfhack
> The UDP receiver thread may not tell the whole story, however: in the Radargun tests, performance with his patch was even lower.
--
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
More information about the jboss-jira
mailing list