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 2022/10/09 09:05:00 UTC

[jira] [Commented] (SPARK-40716) Relax the restrictions of broadcast join on bloom filter

    [ https://issues.apache.org/jira/browse/SPARK-40716?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17614661#comment-17614661 ] 

Apache Spark commented on SPARK-40716:
--------------------------------------

User 'beliefer' has created a pull request for this issue:
https://github.com/apache/spark/pull/38178

> Relax the restrictions of broadcast join on bloom filter
> --------------------------------------------------------
>
>                 Key: SPARK-40716
>                 URL: https://issues.apache.org/jira/browse/SPARK-40716
>             Project: Spark
>          Issue Type: Improvement
>          Components: SQL
>    Affects Versions: 3.4.0
>            Reporter: jiaan.geng
>            Priority: Major
>
> Currently, if the creation side of bloom filter could be broadcasted, Spark cannot inject a bloom filter or InSunquery filter into the application side.
> In fact, although we use broadcast join and improves the performance, compared with the reduction of data volume, it is still worse if the application side have many rows.
> We just need the creation side is small enough.



--
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