ulysses-you commented on a change in pull request #32084:
URL: https://github.com/apache/spark/pull/32084#discussion_r610677829
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/CoalesceShufflePartitions.scala
##########
@@ -35,14 +35,25 @@ case class CoalesceShufflePartitions(session: SparkSession)
extends CustomShuffl
if (!conf.coalesceShufflePartitionsEnabled) {
return plan
}
- if (!plan.collectLeaves().forall(_.isInstanceOf[QueryStageExec])
- || plan.find(_.isInstanceOf[CustomShuffleReaderExec]).isDefined) {
- // If not all leaf nodes are query stages, it's not safe to reduce the
number of
- // shuffle partitions, because we may break the assumption that all
children of a spark plan
- // have same number of output partitions.
- return plan
+
+ if (canCoalescePartitions(plan)) {
+ coalescePartitions(plan)
+ } else {
+ plan.transformUp {
+ case u: UnionExec =>
+ u.withNewChildren(u.children.map { child =>
+ if (canCoalescePartitions(child) &&
+ child.find(_.isInstanceOf[UnionExec]).isEmpty) {
Review comment:
We should add the coalesce if it's children don't have `Union` to avoid
adding duplicate `CustomShufflerReader`.
Without `CombineUnions`, the plan can be
````
Union
Union
HashAggregate
ShuffleQueryStage
FileScan
FileScan
````
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
