[
https://issues.apache.org/jira/browse/SPARK-34593?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Cheng Su updated SPARK-34593:
-----------------------------
Description: `BroadcastNestedLoopJoinExec` does not preserve
`outputPartitioning` and `outputOrdering` right now. But it can preserve the
streamed side partitioning and ordering when possible. This can help avoid
shuffle and sort in later stage, if there's join and aggregation in the query.
(was: `BroadcastNestedLoopJoinExec` does not propagate `outputPartitioning` and
`outputOrdering` right now. But it can propagate the streamed side partitioning
and ordering when possible. This can help avoid shuffle and sort in later
stage, if there's join and aggregation in the query.)
> Preserve broadcast nested loop join output partitioning and ordering
> --------------------------------------------------------------------
>
> Key: SPARK-34593
> URL: https://issues.apache.org/jira/browse/SPARK-34593
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Affects Versions: 3.2.0
> Reporter: Cheng Su
> Priority: Minor
>
> `BroadcastNestedLoopJoinExec` does not preserve `outputPartitioning` and
> `outputOrdering` right now. But it can preserve the streamed side
> partitioning and ordering when possible. This can help avoid shuffle and sort
> in later stage, if there's join and aggregation in the query.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
