[
https://issues.apache.org/jira/browse/YARN-1013?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16619771#comment-16619771
]
Íñigo Goiri commented on YARN-1013:
-----------------------------------
Thanks [~asuresh] for [^YARN-1013-001.branch-2.patch].
A couple general questions:
* Can we get a patch for trunk for Yetus to be able to run (branch-2 has
issues)?
* Can you give an overview comparing to the FS approach? I went through the
patch and it is hard to compare as this uses the allocator.
Comments to the patch itself:
* Some of the debug messages seem for development. Should we keep all of them?
* Can you add more comments to {{testContainerOverAllocation()}}? For example,
we setup one node without overallocation and one with it. Why those numbers and
what is the goal?
* Can we add a couple lower level unit tests? Just testing the allocator or the
scheduler?
* There are many space fixes, can we avoid most of them? Specially, pass the
null by default as second parameter to registerNode for TestAMRestart and
TestReservations.
> CS should watch resource utilization of containers and allocate speculative
> containers if appropriate
> -----------------------------------------------------------------------------------------------------
>
> Key: YARN-1013
> URL: https://issues.apache.org/jira/browse/YARN-1013
> Project: Hadoop YARN
> Issue Type: Sub-task
> Reporter: Arun C Murthy
> Assignee: Arun Suresh
> Priority: Major
> Attachments: YARN-1013-001.branch-2.patch
>
>
> CS should watch resource utilization of containers (provided by NM in
> heartbeat) and allocate speculative containers (at lower OS priority) if
> appropriate.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
