[
https://issues.apache.org/jira/browse/MAPREDUCE-2324?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13073677#comment-13073677
]
Robert Joseph Evans commented on MAPREDUCE-2324:
------------------------------------------------
I have been able to run gridmix on a 10 node cluster, and everything looks
stable. I have not been able to run it on anything larger because the
processes here are really not set up to do that very easily. The process in
the past has been to run gridmix at scale after the branch is in QA not before
then so the tools are not setup to deploy from a dev branch. Plus I have to
get approval from lots of people to make that happen. I am trying to see if I
can still do it, but I am not very hopeful that it will happen any time soon.
> Job should fail if a reduce task can't be scheduled anywhere
> ------------------------------------------------------------
>
> Key: MAPREDUCE-2324
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-2324
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Affects Versions: 0.20.2, 0.20.205.0
> Reporter: Todd Lipcon
> Assignee: Robert Joseph Evans
> Fix For: 0.20.205.0
>
> Attachments: MR-2324-security-v1.txt, MR-2324-security-v2.txt,
> MR-2324-security-v3.patch, MR-2324-secutiry-just-log-v1.patch
>
>
> If there's a reduce task that needs more disk space than is available on any
> mapred.local.dir in the cluster, that task will stay pending forever. For
> example, we produced this in a QA cluster by accidentally running terasort
> with one reducer - since no mapred.local.dir had 1T free, the job remained in
> pending state for several days. The reason for the "stuck" task wasn't clear
> from a user perspective until we looked at the JT logs.
> Probably better to just fail the job if a reduce task goes through all TTs
> and finds that there isn't enough space.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
