[
https://issues.apache.org/jira/browse/TEZ-1369?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Thaddeus Diamond updated TEZ-1369:
----------------------------------
Attachment: (was: reuse-failed-containers.thaddeus.patch)
> Provide a configuration variable to reuse containers that had unsuccessful
> tasks
> --------------------------------------------------------------------------------
>
> Key: TEZ-1369
> URL: https://issues.apache.org/jira/browse/TEZ-1369
> Project: Apache Tez
> Issue Type: Wish
> Affects Versions: 0.5.0
> Environment: branch -> master (0.5.0)
> hadoop -> HDP 2.1/CDH 5.0
> Reporter: Thaddeus Diamond
>
> Sometimes the I/P/O is sufficiently isolated by the application developer
> that reusing the containers that had failed tasks is alright. If this is the
> case and the application developer wants extremely low latency, it may be
> worth it to reuse failed container JVMs.
> By default, this would be false to preserve the current behavior.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
