You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@spark.apache.org by "Wenchen Fan (Jira)" <ji...@apache.org> on 2022/12/21 13:12:00 UTC

[jira] [Resolved] (SPARK-41509) Delay execution hash until after aggregation for semi-join runtime filter.

     [ https://issues.apache.org/jira/browse/SPARK-41509?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Wenchen Fan resolved SPARK-41509.
---------------------------------
    Fix Version/s: 3.4.0
       Resolution: Fixed

Issue resolved by pull request 39049
[https://github.com/apache/spark/pull/39049]

> Delay execution hash until after aggregation for semi-join runtime filter.
> --------------------------------------------------------------------------
>
>                 Key: SPARK-41509
>                 URL: https://issues.apache.org/jira/browse/SPARK-41509
>             Project: Spark
>          Issue Type: Improvement
>          Components: SQL
>    Affects Versions: 2.4.0
>            Reporter: jiaan.geng
>            Assignee: jiaan.geng
>            Priority: Major
>             Fix For: 3.4.0
>
>
> Currently, Spark runtime filter supports bloom filter and in subquery filter.
> The in subquery filter always execute Murmur3Hash before aggregate the join key.
> Because the data size before aggregate will lager than after, we can delay execute Murmur3Hash until after aggregation for semi-join runtime filter and it will reduce the number of calls to Murmur3Hash and improve performance.



--
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