You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Apache Spark (JIRA)" <ji...@apache.org> on 2016/09/01 20:23:20 UTC
[jira] [Assigned] (SPARK-17365) Kill multiple executors together to
reduce lock contention
[ https://issues.apache.org/jira/browse/SPARK-17365?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Apache Spark reassigned SPARK-17365:
------------------------------------
Assignee: (was: Apache Spark)
> 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-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org