hadoop-mapreduce-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Arun C Murthy (JIRA)" <j...@apache.org>
Subject [jira] Commented: (MAPREDUCE-1204) Fair Scheduler preemption may preempt tasks running in slots unusable by the preempting job
Date Tue, 10 Nov 2009 23:15:27 GMT

    [ https://issues.apache.org/jira/browse/MAPREDUCE-1204?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12776149#action_12776149

Arun C Murthy commented on MAPREDUCE-1204:

I'd rather have JobInProgress.shouldRunOnTaskTracker public for now.

Long term the right direction is for schedulers to maintain all scheduling information themselves
and not rely on JobInProgress at all.

> Fair Scheduler preemption may preempt tasks running in slots unusable by the preempting
> -------------------------------------------------------------------------------------------
>                 Key: MAPREDUCE-1204
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-1204
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: contrib/fair-share
>    Affects Versions: 0.21.0
>            Reporter: Todd Lipcon
> The current preemption code works by first calculating how many tasks need to be preempted
to satisfy the min share constraints, and then killing an equal number of tasks from other
jobs, sorted to favor killing of young tasks. This works fine for the general case, but there
are some edge cases where this can cause problems.
> For example, if the preempting job has blacklisted ("marked flaky") a particular task
tracker, and that tracker is running the youngest task, preemption can still kill that task.
The preempting job will then refuse that slot, since the tracker has been blacklisted. The
same task that just got killed then gets rescheduled in that slot. This repeats ad infinitum
until a new slot opens in the cluster.
> I don't have a good test case for this, yet, but logically it is possible.
> One potential fix would be to add an API to JobInProgress that functions identically
to obtainNewMapTask but does not schedule the task. The preemption code could then use this
while iterating through the sorted preemption list to check that the preempting jobs can actually
make use of the candidate slots before killing them.

This message is automatically generated by JIRA.
You can reply to this email to add a comment to the issue online.

View raw message