[ http://issues.apache.org/jira/browse/HADOOP-568?page=all ]
Owen O'Malley updated HADOOP-568:
---------------------------------
Attachment: unassigned-state.patch
I started seeing this last week and I think fundamentally it is caused my some
of the new code in localizeJob. However, the error handling is broken in that
if something goes wrong in localizeJob, it prints an error message into the log
and doesn't report the failure back to the job tracker. This patch should fix
that problem.
> small jobs benchmark fails: task is UNASSIGNED
> ----------------------------------------------
>
> Key: HADOOP-568
> URL: http://issues.apache.org/jira/browse/HADOOP-568
> Project: Hadoop
> Issue Type: Bug
> Reporter: Yoram Arnon
> Attachments: unassigned-state.patch
>
>
> the small jobs benchmark consistently failes when executed a sufficient
> number of iterations.
> It's just a matter of time before one of the jobs gets stuck, with one map
> task (out of a 100) simply doesn't get executed.
> Looking at the map list, the task is UNASSIGNED.
> Restarting the affected task tracker releases the job.
--
This message is automatically generated by JIRA.
-
If you think it was sent incorrectly contact one of the administrators:
http://issues.apache.org/jira/secure/Administrators.jspa
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
