You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@spark.apache.org by "Hyukjin Kwon (JIRA)" <ji...@apache.org> on 2019/05/21 04:35:11 UTC

[jira] [Resolved] (SPARK-7877) Support non-persistent cluster mode

     [ https://issues.apache.org/jira/browse/SPARK-7877?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Hyukjin Kwon resolved SPARK-7877.
---------------------------------
    Resolution: Incomplete

> Support non-persistent cluster mode
> -----------------------------------
>
>                 Key: SPARK-7877
>                 URL: https://issues.apache.org/jira/browse/SPARK-7877
>             Project: Spark
>          Issue Type: Improvement
>          Components: Mesos
>            Reporter: Timothy Chen
>            Priority: Major
>              Labels: bulk-closed
>
> Currently mesos cluster mode framework by default won't be removed even when it's shutdown since it's assumed to be a long running framework can register and reattach to all the running tasks.
> However, there might be cases users want to make the framework more empheral, which when the framework dies all the tasks stops and mesos doesn't keep the framework state at all.
> Besides making the state be in memory, we also need to make the framework failover timeout to be a small amount, which should be configurable.



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

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