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 "Arun C Murthy (JIRA)" <ji...@apache.org> on 2010/02/11 20:52:27 UTC

[jira] Created: (MAPREDUCE-1485) CapacityScheduler should have prevent a single job taking over large parts of a cluster

CapacityScheduler should have prevent a single job taking over large parts of a cluster
---------------------------------------------------------------------------------------

                 Key: MAPREDUCE-1485
                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-1485
             Project: Hadoop Map/Reduce
          Issue Type: Improvement
          Components: contrib/capacity-sched
            Reporter: Arun C Murthy
            Assignee: Arun C Murthy
             Fix For: 0.22.0


The proposal is to have a per-queue limit on the number of concurrent tasks a job can run on a cluster. 

We've seen cases where a single, large, job took over a majority of the cluster - worse, it meant that any bug in it caused issues for both the NameNode _and_ the JobTracker.

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

[jira] Commented: (MAPREDUCE-1485) CapacityScheduler should have prevent a single job taking over large parts of a cluster

Posted by "David Ciemiewicz (JIRA)" <ji...@apache.org>.
    [ https://issues.apache.org/jira/browse/MAPREDUCE-1485?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12854609#action_12854609 ] 

David Ciemiewicz commented on MAPREDUCE-1485:
---------------------------------------------

I would also be good if any single user was limited to as to the total number of tasks.

This way it doesn't matter if a user has a single job with 20,000 tasks or many 20 jobs with 1,000 tasks.


> CapacityScheduler should have prevent a single job taking over large parts of a cluster
> ---------------------------------------------------------------------------------------
>
>                 Key: MAPREDUCE-1485
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-1485
>             Project: Hadoop Map/Reduce
>          Issue Type: Improvement
>          Components: contrib/capacity-sched
>            Reporter: Arun C Murthy
>            Assignee: Arun C Murthy
>             Fix For: 0.22.0
>
>
> The proposal is to have a per-queue limit on the number of concurrent tasks a job can run on a cluster. 
> We've seen cases where a single, large, job took over a majority of the cluster - worse, it meant that any bug in it caused issues for both the NameNode _and_ the JobTracker.

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