ekoifman commented on a change in pull request #34464:
URL: https://github.com/apache/spark/pull/34464#discussion_r741555797
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/DynamicJoinSelection.scala
##########
@@ -50,10 +51,16 @@ object DynamicJoinSelection extends Rule[LogicalPlan] {
mapStats.bytesByPartitionId.forall(_ <=
maxShuffledHashJoinLocalMapThreshold)
}
- private def selectJoinStrategy(plan: LogicalPlan): Option[JoinStrategyHint]
= plan match {
+ private def selectJoinStrategy(plan: LogicalPlan,
+ joinType: JoinType): Option[JoinStrategyHint]
= plan match {
case LogicalQueryStage(_, stage: ShuffleQueryStageExec) if
stage.isMaterialized
&& stage.mapStats.isDefined =>
- val demoteBroadcastHash =
shouldDemoteBroadcastHashJoin(stage.mapStats.get)
+ val demoteBroadcastHash = joinType match {
+ // doesn't make sense for outer joins since one side is preserved and
join is not
+ // short circuited if the other side is empty
+ case Inner | LeftSemi | LeftAnti => shouldDemoteBroadcastHashJoin
(stage.mapStats.get)
Review comment:
changed it a bit - seems more natural
--
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.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
