hadoop-mapreduce-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Vinod K V (JIRA)" <j...@apache.org>
Subject [jira] Commented: (MAPREDUCE-1094) CapacityScheduler's JobInitPoller shouldn't 'sleep'
Date Tue, 13 Oct 2009 06:12:31 GMT

    [ 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.


Mime
View raw message