[
https://issues.apache.org/jira/browse/SPARK-16455?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
YangyangLiu updated SPARK-16455:
--------------------------------
Description: In our case, we are implementing restartable resource manager
mechanism which will let master executor survive when resource manager service
is temporarily down. So when resource manager service is not available,
scheduler should stop scheduling new tasks. I added a hook inside
CoarseGrainedSchedulerBackend class, in order to avoid new task scheduling
when it's necessary.
> Add a new hook in makeOffers in CoarseGrainedSchedulerBackend
> -------------------------------------------------------------
>
> Key: SPARK-16455
> URL: https://issues.apache.org/jira/browse/SPARK-16455
> Project: Spark
> Issue Type: New Feature
> Components: Scheduler
> Reporter: YangyangLiu
> Priority: Minor
>
> In our case, we are implementing restartable resource manager mechanism which
> will let master executor survive when resource manager service is temporarily
> down. So when resource manager service is not available, scheduler should
> stop scheduling new tasks. I added a hook inside
> CoarseGrainedSchedulerBackend class, in order to avoid new task scheduling
> when it's necessary.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
