[
https://issues.apache.org/jira/browse/SPARK-24992?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16566249#comment-16566249
]
Apache Spark commented on SPARK-24992:
--------------------------------------
User 'hthuynh2' has created a pull request for this issue:
https://github.com/apache/spark/pull/21953
> spark should randomize yarn local dir selection
> -----------------------------------------------
>
> Key: SPARK-24992
> URL: https://issues.apache.org/jira/browse/SPARK-24992
> Project: Spark
> Issue Type: Improvement
> Components: Spark Core
> Affects Versions: 2.3.1
> Reporter: Hieu Tri Huynh
> Priority: Minor
>
> Utils.getLocalDir is used to get path of a temporary directory. However, it
> always returns the the same directory, which is the first element in the
> array _localRootDirs_. When running on YARN, this might causes the case that
> we always write to one disk, which makes it busy while other disks are free.
> We should randomize the selection to spread out the loads.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
