wangyum commented on code in PR #50004:
URL: https://github.com/apache/spark/pull/50004#discussion_r1970850047
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/EnsureRequirements.scala:
##########
@@ -150,10 +150,15 @@ case class EnsureRequirements(
// A: (No_Exchange, 100) <---> B: (Exchange, 120)
// it's better to pick A and change B to (Exchange, 100) instead of
picking B and insert a
// new shuffle for A.
- val candidateSpecsWithoutShuffle = candidateSpecs.filter { case (k, _)
=>
- !children(k).isInstanceOf[ShuffleExchangeLike]
+ val (candidateSpecsWithShuffle, candidateSpecsWithoutShuffle) =
candidateSpecs.partition {
+ case (k, _) => children(k).isInstanceOf[ShuffleExchangeLike]
}
- val finalCandidateSpecs = if (candidateSpecsWithoutShuffle.nonEmpty) {
+ val maxShufflePartNumOpt =
candidateSpecsWithShuffle.values.map(_.numPartitions).maxOption
+ val finalCandidateSpecs = if (candidateSpecsWithoutShuffle.nonEmpty &&
+ maxShufflePartNumOpt.forall { n =>
+ n / candidateSpecsWithoutShuffle.values.map(_.numPartitions).max <=
+ conf.coalesceBucketsInJoinMaxBucketRatio
Review Comment:
https://github.com/apache/spark/blob/498519ee6bb4b0295d1df005175e4cbcbcb051e3/sql/core/src/main/scala/org/apache/spark/sql/execution/bucketing/CoalesceBucketsInJoin.scala#L89-L90
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/EnsureRequirements.scala:
##########
@@ -150,10 +150,15 @@ case class EnsureRequirements(
// A: (No_Exchange, 100) <---> B: (Exchange, 120)
// it's better to pick A and change B to (Exchange, 100) instead of
picking B and insert a
// new shuffle for A.
Review Comment:
👌
--
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
