hadoop-yarn-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "stefanlee (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (YARN-3933) FairScheduler: Multiple calls to completedContainer are not safe
Date Thu, 08 Feb 2018 07:35:01 GMT

    [ https://issues.apache.org/jira/browse/YARN-3933?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16356599#comment-16356599
] 

stefanlee commented on YARN-3933:
---------------------------------

[~yufeigu] thanks, yesterday, i found in our cluster the utilization rate of resource  is
very low , but there is a lot of pending applications in it, and RM has no exception, then 
i found a queue has negative-usage and also has pending resource, so i doubt Whether a queue
has negative-usage resource can lead to FairScheduler do not assign containers to any other
queues. thanks for this jira[https://issues.apache.org/jira/browse/YARN-3933], it seems as
same as my scenario.

> FairScheduler: Multiple calls to completedContainer are not safe
> ----------------------------------------------------------------
>
>                 Key: YARN-3933
>                 URL: https://issues.apache.org/jira/browse/YARN-3933
>             Project: Hadoop YARN
>          Issue Type: Bug
>          Components: fairscheduler
>    Affects Versions: 2.7.1
>            Reporter: Lavkesh Lahngir
>            Assignee: Shiwei Guo
>            Priority: Major
>              Labels: oct16-medium
>             Fix For: 2.8.0, 3.0.0-alpha4
>
>         Attachments: YARN-3933.001.patch, YARN-3933.002.patch, YARN-3933.003.patch, YARN-3933.004.patch,
YARN-3933.005.patch, YARN-3933.006.patch, yarn-3933-branch-2.8.patch
>
>
> In our cluster we are seeing available memory and cores being negative. 
> Initial inspection:
> Scenario no. 1: 
> In capacity scheduler the method allocateContainersToNode() checks if 
> there are excess reservation of containers for an application, and they are no longer
needed then it calls queue.completedContainer() which causes resources being negative. And
they were never assigned in the first place. 
> I am still looking through the code. Can somebody suggest how to simulate excess containers
assignments ?



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

---------------------------------------------------------------------
To unsubscribe, e-mail: yarn-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: yarn-issues-help@hadoop.apache.org


Mime
View raw message