[
https://issues.apache.org/jira/browse/SPARK-57376?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Hongze Zhang updated SPARK-57376:
---------------------------------
Description:
When shuffle partition number is configured large, Spark could use significant
large amount of JVM heap memory just for storing the broadcasted shuffle
status, even with off-heap mode enabled.
This is a long-live issue in Apache Gluten project and is better to be fixed on
Spark side.
> Add off-heap broadcasting support for shuffle status
> ----------------------------------------------------
>
> Key: SPARK-57376
> URL: https://issues.apache.org/jira/browse/SPARK-57376
> Project: Spark
> Issue Type: Sub-task
> Components: Spark Core
> Affects Versions: 4.1.2
> Reporter: Hongze Zhang
> Priority: Major
>
> When shuffle partition number is configured large, Spark could use
> significant large amount of JVM heap memory just for storing the broadcasted
> shuffle status, even with off-heap mode enabled.
> This is a long-live issue in Apache Gluten project and is better to be fixed
> on Spark side.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
