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 2022/08/05 01:28:00 UTC

[jira] [Commented] (SPARK-39983) Should not cache unserialized broadcast relations on the driver

    [ https://issues.apache.org/jira/browse/SPARK-39983?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17575506#comment-17575506 ] 

Apache Spark commented on SPARK-39983:
--------------------------------------

User 'alex-balikov' has created a pull request for this issue:
https://github.com/apache/spark/pull/37413

> Should not cache unserialized broadcast relations on the driver
> ---------------------------------------------------------------
>
>                 Key: SPARK-39983
>                 URL: https://issues.apache.org/jira/browse/SPARK-39983
>             Project: Spark
>          Issue Type: Improvement
>          Components: Spark Core
>    Affects Versions: 3.3.0
>            Reporter: Alex Balikov
>            Priority: Minor
>
> In TorrentBroadcast.writeBlocks we store the unserialized broadcast object in addition to the serialized version of it - 
> {code:java}
> private def writeBlocks(value: T): Int = {
>     import StorageLevel._
>     // Store a copy of the broadcast variable in the driver so that tasks run on the driver
>     // do not create a duplicate copy of the broadcast variable's value.
>     val blockManager = SparkEnv.get.blockManager
>     if (!blockManager.putSingle(broadcastId, value, MEMORY_AND_DISK, tellMaster = false)) {
>       throw new SparkException(s"Failed to store $broadcastId in BlockManager")
>     }
>  {code}
> In case of broadcast relations, these objects can be fairly large (60MB in one observed case) and are not strictly necessary on the driver.
> Add the option to not keep the unserialized versions of the objects.
>  



--
This message was sent by Atlassian Jira
(v8.20.10#820010)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org