You are viewing a plain text version of this content. The canonical link for it is here.
Posted to mapreduce-issues@hadoop.apache.org by "Konstantin Shvachko (JIRA)" <ji...@apache.org> on 2011/03/31 02:41:06 UTC

[jira] [Commented] (MAPREDUCE-2386) TT jetty server stuck in tight loop around epoll_wait

    [ https://issues.apache.org/jira/browse/MAPREDUCE-2386?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13013764#comment-13013764 ] 

Konstantin Shvachko commented on MAPREDUCE-2386:
------------------------------------------------

This doesn't seem to be jetty problem per se. More like a bug in nio. I see it a lot lately in the rpc layer. Lots of different use cases with the same result:
{code}
java.lang.Thread.State: RUNNABLE
	at sun.nio.ch.EPollArrayWrapper.epollWait(Native Method)
	at sun.nio.ch.EPollArrayWrapper.poll(EPollArrayWrapper.java:215)
	at sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:65)
	at sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:69)
	- locked <0x00002aaab3dd8760> (a sun.nio.ch.Util$1)
	- locked <0x00002aaab3dd83a0> (a java.util.Collections$UnmodifiableSet)
	- locked <0x00002aaab3dd82e8> (a sun.nio.ch.EPollSelectorImpl)
	at sun.nio.ch.SelectorImpl.select(SelectorImpl.java:80){code}
If anybody found a work around please share.

> TT jetty server stuck in tight loop around epoll_wait
> -----------------------------------------------------
>
>                 Key: MAPREDUCE-2386
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-2386
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: tasktracker
>    Affects Versions: 0.23.0
>         Environment: RHEL 6.0 "Santiago"
>            Reporter: Todd Lipcon
>
> In some load testing, I got a TaskTracker into a state where its Jetty server is in a tight loop calling epoll_wait, which is returning EINVAL:
> [pid 19573] epoll_wait(157, 40829000, 8192, 0) = -1 EINVAL (Invalid argument)
> It's not responding to any HTTP connections - connections are accepted and then just hang.

--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira