[
https://issues.apache.org/jira/browse/SPARK-44065?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Cheng Pan resolved SPARK-44065.
-------------------------------
Fix Version/s: 4.2.0
Resolution: Fixed
Issue resolved by pull request 41609
[https://github.com/apache/spark/pull/41609]
> Optimize BroadcastHashJoin skew when localShuffleReader is disabled
> -------------------------------------------------------------------
>
> Key: SPARK-44065
> URL: https://issues.apache.org/jira/browse/SPARK-44065
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Affects Versions: 3.5.0
> Reporter: Zhen Wang
> Assignee: Zhen Wang
> Priority: Major
> Labels: pull-request-available
> Fix For: 4.2.0
>
>
> In RemoteShuffleService services such as uniffle and celeborn, it is
> recommended to disable localShuffleReader by default for better performance.
> But it may make BroadcastHashJoin skewed, so I want to optimize
> BroadcastHashJoin skew in OptimizeSkewedJoin when localShuffleReader is
> disabled.
>
> Refer to:
> https://github.com/apache/incubator-celeborn#spark-configuration
> https://github.com/apache/incubator-uniffle/blob/master/docs/client_guide.md#support-spark-aqe
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
