[ 
https://issues.apache.org/jira/browse/YARN-2604?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14147899#comment-14147899
 ] 

Jason Lowe commented on YARN-2604:
----------------------------------

How is this different from YARN-56?  Also wondering about the case of a 
heterogeneous cluster where only a few nodes are big enough to satisfy the 
request and they are temporarily unavailable.  Do we outright fail the request 
or hang around a bit to see if they return before failing?  The discussion in 
YARN-56 covers some of this.

> Scheduler should consider max-allocation-* in conjunction with the largest 
> node
> -------------------------------------------------------------------------------
>
>                 Key: YARN-2604
>                 URL: https://issues.apache.org/jira/browse/YARN-2604
>             Project: Hadoop YARN
>          Issue Type: Improvement
>          Components: scheduler
>    Affects Versions: 2.5.1
>            Reporter: Karthik Kambatla
>            Assignee: Karthik Kambatla
>
> If the scheduler max-allocation-* values are larger than the resources 
> available on the largest node in the cluster, an application requesting 
> resources between the two values will be accepted by the scheduler but the 
> requests will never be satisfied. The app essentially hangs forever. 



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Reply via email to