[ https://issues.jboss.org/browse/AS7-6778?page=com.atlassian.jira.plugin.s... ] Weixing Sun commented on AS7-6778: ---------------------------------- Hi Jaikiran, I am working on a special user case, which include one deployment jar file with several working modules: Including lots of Stateful Beans, Stateless Beans, and also MDBs, and those beans were separated into groups: such as manufacturing, supplying, and customer order, and each of those modules are under different workload, but they deployed in a single jar file. Through our continuous monitoring, we found that over 90% CPU cycles consumed in our system is the following method: org.jboss.threads.JBossThread.run() I think this might be caused by synchronized waiting or lacking of thread to execute the specific task, and even I increase all my defined threads in the configuration, this issue is always occurring (I didn't look at the EAP6.1 sourcecode yet, but if needed I will do). Your comments is highly appreciated, I know this fix may cause some other serious issues, or please let me know if you have different thought to this problem. Thanks and regards, Weixing -- 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