[
https://issues.apache.org/jira/browse/MAPREDUCE-2386?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13469255#comment-13469255
]
Steve Loughran commented on MAPREDUCE-2386:
-------------------------------------------
Encountered this on the 1.x line.
# post-1.1 could be time to move up to Jetty-7 via HADOOP-8515
# I could see how the TT could itself detect this (GET self on one thread with
watcher on another), but I'm not sure if it could then react to it through a
Jetty restart. It could maybe exit with an error message & rely on other
monitoring agents to kick in. Right now it can still be heartbeating, which
stops the JT realising there are problems.
> 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.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
