c21 commented on a change in pull request #29455:
URL: https://github.com/apache/spark/pull/29455#discussion_r472574563
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/ShuffleExchangeExec.scala
##########
@@ -83,15 +83,18 @@ trait ShuffleExchangeLike extends Exchange {
case class ShuffleExchangeExec(
override val outputPartitioning: Partitioning,
child: SparkPlan,
- noUserSpecifiedNumPartition: Boolean = true) extends ShuffleExchangeLike {
+ noUserSpecifiedNumPartition: Boolean = true,
+ isNullAwareAntiJoin: Boolean = false) extends ShuffleExchangeLike {
Review comment:
sorry I think I should be talking with data in first place. I just
checked and found in our case, less than 10% of join is using
`BroadcastNestedLoopJoin` and amount of CPU is also single digit percentage.
Our workload by no means is representative for industry, would like to hear
more of based on data.
----------------------------------------------------------------
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]
