[
https://issues.apache.org/jira/browse/SPARK-15355?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Wenchen Fan resolved SPARK-15355.
---------------------------------
Resolution: Fixed
Fix Version/s: 2.2.0
Issue resolved by pull request 14412
[https://github.com/apache/spark/pull/14412]
> Pro-active block replenishment in case of node/executor failures
> ----------------------------------------------------------------
>
> Key: SPARK-15355
> URL: https://issues.apache.org/jira/browse/SPARK-15355
> Project: Spark
> Issue Type: Sub-task
> Components: Block Manager, Spark Core
> Reporter: Shubham Chopra
> Fix For: 2.2.0
>
>
> Spark currently does not replenish lost replicas. For resiliency and high
> availability, BlockManagerMasterEndpoint can proactively verify whether all
> cached RDDs have enough replicas, and replenish them, in case they don’t.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
