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 "Vinod K V (JIRA)" <ji...@apache.org> on 2009/10/13 08:12:31 UTC
[jira] Commented: (MAPREDUCE-1094) CapacityScheduler's
JobInitPoller shouldn't 'sleep'
[ https://issues.apache.org/jira/browse/MAPREDUCE-1094?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12764966#action_12764966 ]
Vinod K V commented on MAPREDUCE-1094:
--------------------------------------
+1 for the idea. But not sure if this is a blocker for 0.21. The sleep interval is still configurable, so if one wants faster initialization, the interval can be reduced.
> CapacityScheduler's JobInitPoller shouldn't 'sleep'
> ---------------------------------------------------
>
> Key: MAPREDUCE-1094
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-1094
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Components: contrib/capacity-sched
> Affects Versions: 0.21.0
> Reporter: Arun C Murthy
> Priority: Blocker
> Fix For: 0.21.0
>
>
> It is *really* bad for JobInitPoller to be sleeping for 5seconds before initializing jobs!
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.