[
https://issues.apache.org/jira/browse/MAPREDUCE-1030?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12758746#action_12758746
]
Arun C Murthy commented on MAPREDUCE-1030:
------------------------------------------
bq. This happens when using capacity-scheduler with TTs in the cluster
configured with more number of map slots than reduce slots, for e.g. in 5:2
ratio.
This has more to do with the ratio of maps to reduces in the system and less to
do with slot ratios. If we had 500k maps (across all jobs) versus a few
thousand reduces (across all jobs) this behaviour would be prevalent too.
> Reduce tasks are getting starved in capacity scheduler
> ------------------------------------------------------
>
> Key: MAPREDUCE-1030
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-1030
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Components: contrib/capacity-sched
> Affects Versions: 0.21.0
> Reporter: rahul k singh
> Assignee: rahul k singh
> Priority: Blocker
> Fix For: 0.21.0
>
>
> reduce tasks are getting starved in capacity scheduler.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
