[jboss-jira] [JBoss JIRA] (JGRP-2482) Check if the largest thread pool is cluster-size + delta

Bela Ban (Jira) issues at jboss.org
Tue Jun 30 10:08:37 EDT 2020


    [ https://issues.redhat.com/browse/JGRP-2482?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14183025#comment-14183025 ] 

Bela Ban commented on JGRP-2482:
--------------------------------

If a message is internal, it will be passed to the internal thread pool, otherwise to the regular thread pool. This avoids overloading the regular pool with internal messages and thus dropping regular ones.

When fibers are mainstream, we should revisit this decision and perhaps eliminate the internal thread pool altogether...

> Check if the largest thread pool is cluster-size + delta
> --------------------------------------------------------
>
>                 Key: JGRP-2482
>                 URL: https://issues.redhat.com/browse/JGRP-2482
>             Project: JGroups
>          Issue Type: Task
>            Reporter: Bela Ban
>            Assignee: Bela Ban
>            Priority: Major
>             Fix For: 5.0.0.Final
>
>
> When running UPerf in a cluster of 4, we see {{thread_pool_size_largest=39}}. Verify that MaxOneThreadPerSender works as expected: the largest thread pool size should be 4+delta (timer threads, retransmission): ~6.
> It looks as if {{MPerf}} behaves (~6 threads), but {{UPerf}} doesn't: ~26 threads



--
This message was sent by Atlassian Jira
(v7.13.8#713008)


More information about the jboss-jira mailing list