hadoop-yarn-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "nemon lou (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (YARN-276) Capacity Scheduler can hang when submit many jobs concurrently
Date Wed, 05 Jun 2013 10:31:23 GMT

    [ https://issues.apache.org/jira/browse/YARN-276?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13675778#comment-13675778
] 

nemon lou commented on YARN-276:
--------------------------------

Hi Thomas,thank you for your review.
The "used resource not showing up" issue seems like a bug that already exists.i will fire
another jira for it.(Resource.java's toString() method uses symbol "<>",which is ignored
by explorers)
The "divide by zero exception" problem has not been fixed as i haven't find which piece of
code can cause it.
Other review comments will been accepted in latest patch.Thanks.

After reconsidering user limit, i find property "maxAMResourcePerQueuePerUserPercent" added
by me is not a proper one.It will be removed and checking maxAMResourcePerQueue for each user
instead.

                
> Capacity Scheduler can hang when submit many jobs concurrently
> --------------------------------------------------------------
>
>                 Key: YARN-276
>                 URL: https://issues.apache.org/jira/browse/YARN-276
>             Project: Hadoop YARN
>          Issue Type: Bug
>          Components: capacityscheduler
>    Affects Versions: 3.0.0, 2.0.1-alpha
>            Reporter: nemon lou
>            Assignee: nemon lou
>              Labels: incompatible
>         Attachments: YARN-276.patch, YARN-276.patch, YARN-276.patch, YARN-276.patch,
YARN-276.patch, YARN-276.patch, YARN-276.patch, YARN-276.patch, YARN-276.patch, YARN-276.patch,
YARN-276.patch, YARN-276.patch, YARN-276.patch, YARN-276.patch
>
>   Original Estimate: 24h
>  Remaining Estimate: 24h
>
> In hadoop2.0.1,When i submit many jobs concurrently at the same time,Capacity scheduler
can hang with most resources taken up by AM and don't have enough resources for tasks.And
then all applications hang there.
> The cause is that "yarn.scheduler.capacity.maximum-am-resource-percent" not check directly.Instead
,this property only used for maxActiveApplications. And maxActiveApplications is computed
by minimumAllocation (not by Am actually used).

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira

Mime
View raw message