[
https://issues.apache.org/jira/browse/SPARK-36645?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17503212#comment-17503212
]
Thomas Graves edited comment on SPARK-36645 at 3/8/22, 10:52 PM:
-----------------------------------------------------------------
Note it appears this only really pushes down count and min and max for some
types because:
Parquet Binary min/max could be truncated. We may get wrong result if we rely
on parquet Binary min/max.
I'm going to update the title to reflect this.
was (Author: tgraves):
Note it appears this only really pushes down count because:
Parquet Binary min/max could be truncated. We may get wrong result if we rely
on parquet Binary min/max.
I'm going to update the title to reflect this.
> Aggregate (Min/Max/Count) push down for Parquet
> -----------------------------------------------
>
> Key: SPARK-36645
> URL: https://issues.apache.org/jira/browse/SPARK-36645
> Project: Spark
> Issue Type: Sub-task
> Components: SQL
> Affects Versions: 3.3.0
> Reporter: Huaxin Gao
> Assignee: Huaxin Gao
> Priority: Major
> Fix For: 3.3.0
>
>
> Push down Aggregate (Min/Max/Count) for Parquet for performance improvement
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
