You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "karl wang (Jira)" <ji...@apache.org> on 2020/08/05 13:28:00 UTC
[jira] [Updated] (SPARK-32542) add a batch for optimizing
logicalPlan
[ https://issues.apache.org/jira/browse/SPARK-32542?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
karl wang updated SPARK-32542:
------------------------------
Description:
Split an expand into several smallExpand,which contains the Specified number of projections.
For instance,like this sql.select a,b,c,d,count(1) from table1 group by a,b,c,d with cube. It can expand 2^4 times of original data size.
Now we specify the spark.sql.optimizer.projections.size=4.The Expand will be split into 2^4/4 smallExpand.It can reduce the shuffle pressure and improve performance in multidimensional analysis when data is huge.
> add a batch for optimizing logicalPlan
> --------------------------------------
>
> Key: SPARK-32542
> URL: https://issues.apache.org/jira/browse/SPARK-32542
> Project: Spark
> Issue Type: Improvement
> Components: Optimizer
> Affects Versions: 3.0.0
> Reporter: karl wang
> Priority: Minor
> Fix For: 3.0.0
>
>
> Split an expand into several smallExpand,which contains the Specified number of projections.
> For instance,like this sql.select a,b,c,d,count(1) from table1 group by a,b,c,d with cube. It can expand 2^4 times of original data size.
> Now we specify the spark.sql.optimizer.projections.size=4.The Expand will be split into 2^4/4 smallExpand.It can reduce the shuffle pressure and improve performance in multidimensional analysis when data is huge.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org