[
https://issues.apache.org/jira/browse/SPARK-7877?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Hyukjin Kwon updated SPARK-7877:
--------------------------------
Labels: bulk-closed (was: )
> 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: [email protected]
For additional commands, e-mail: [email protected]
