[
https://issues.apache.org/jira/browse/SPARK-17365?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15504347#comment-15504347
]
Apache Spark commented on SPARK-17365:
--------------------------------------
User 'dhruve' has created a pull request for this issue:
https://github.com/apache/spark/pull/15152
> Kill multiple executors together to reduce lock contention
> ----------------------------------------------------------
>
> Key: SPARK-17365
> URL: https://issues.apache.org/jira/browse/SPARK-17365
> Project: Spark
> Issue Type: Improvement
> Components: Spark Core
> Reporter: Dhruve Ashar
>
> To regulate pending and running executors we determine the executors which
> are eligible to kill and kill them iteratively rather than a loop. This does
> an RPC call and is synchronized leading to lock contention for
> SparkListenerBus.
> Side effect - listener bus is blocked while we iteratively remove executors.
>
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
