[jboss-jira] [JBoss JIRA] Updated: (JGRP-389) Concurrent stack: performance slow in ATL lab

Bela Ban (JIRA) jira-events at jboss.com
Wed Dec 27 05:19:38 EST 2006


     [ http://jira.jboss.com/jira/browse/JGRP-389?page=all ]

Bela Ban updated JGRP-389:
--------------------------

        Summary: Concurrent stack: performance slow in ATL lab  (was: TLS: performance slow in ATL lab)
    Description: 
Setup:
- cluster 01 and 02
- 2 members, 2 senders
- send 100'000 1K messages

With use_concurrent_stack (and default udp.xml from distribution), we get 5600 msgs/sec.
With use_concurrent_stack="false", we get * 17000 msgs/sec* !

  was:
Setup:
- cluster 01 and 02
- 2 members, 2 senders
- send 100'000 1K messages

With use_threadless_stack (and default udp.xml from distribution), we get 5600 msgs/sec.
With use_threadless_stack="false", we get * 17000 msgs/sec* !


> Concurrent stack: performance slow in ATL lab
> ---------------------------------------------
>
>                 Key: JGRP-389
>                 URL: http://jira.jboss.com/jira/browse/JGRP-389
>             Project: JGroups
>          Issue Type: Task
>    Affects Versions: 2.4
>            Reporter: Bela Ban
>         Assigned To: Bela Ban
>             Fix For: 2.5
>
>
> Setup:
> - cluster 01 and 02
> - 2 members, 2 senders
> - send 100'000 1K messages
> With use_concurrent_stack (and default udp.xml from distribution), we get 5600 msgs/sec.
> With use_concurrent_stack="false", we get * 17000 msgs/sec* !

-- 
This message is automatically generated by JIRA.
-
If you think it was sent incorrectly contact one of the administrators: http://jira.jboss.com/jira/secure/Administrators.jspa
-
For more information on JIRA, see: http://www.atlassian.com/software/jira

        



More information about the jboss-jira mailing list