[ https://issues.jboss.org/browse/AS7-6583?page=com.atlassian.jira.plugin.s... ] Tomas Remes commented on AS7-6583: ---------------------------------- Well yes, It's quite weird. The example isn't using any logging. The tests as well as results are available at http://jenkins.mw.lab.eng.bos.redhat.com/hudson/view/Weld/view/Weld-Perfo.... IMHO this is bringing the regression https://github.com/jbossas/jboss-as/commit/526c2ae7a4194dc6b787c32c5218ce... (but it could be anything else). Results are following (2000 parallel sessions load): {noformat} 7.1.3.Final: throughput 1,901.4 samples/s, mean response: 48 ms 7.2.0.Final(prerelease): throughput 1,537.0 samples/s, mean response: 293 ms 7.2.0.Final(prerelease) with logging cb2a3c15cb4a50c41032d27ea560a4f92d6e2b7d: throughput 1,937.9 samples/s, mean response: 27 ms 7.2.0.Final(prerelease) with logging 526c2ae7a4194dc6b787c32c5218cea003276900: throughput 1,537.5 samples/s, mean response: 308 ms {noformat} Of course that I could be wrong, but now it seems to me that mentioned commit is the problem (it's not easy to profile such load). -- 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