[
https://issues.apache.org/jira/browse/YARN-1368?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13986270#comment-13986270
]
Jian He commented on YARN-1368:
-------------------------------
Hi [~adhoot], sure. Thanks for sharing the prototype. I looked at the patch.
I think the prototype is doing as a scheduler-specifc fashion and only for the
FairScheduler. It'll be a maintenance overhead if we implement each scheduler
separately. The prototype recovers a portion of the FairScheduler by reusing
some existing APIs, but I think missed some other state for the scheduler
attempt, queue metrics, schedulerNode.
The patch submitted here is to experiment a generic approach for recovering
all scheduler state including all entities(metrics, schedulerNode etc,) with
no or minimum scheduler-specific changes.
> Common work to re-populate containers’ state into scheduler
> -----------------------------------------------------------
>
> Key: YARN-1368
> URL: https://issues.apache.org/jira/browse/YARN-1368
> Project: Hadoop YARN
> Issue Type: Sub-task
> Reporter: Bikas Saha
> Assignee: Anubhav Dhoot
> Attachments: YARN-1368.preliminary.patch
>
>
> YARN-1367 adds support for the NM to tell the RM about all currently running
> containers upon registration. The RM needs to send this information to the
> schedulers along with the NODE_ADDED_EVENT so that the schedulers can recover
> the current allocation state of the cluster.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
