JkSelf commented on a change in pull request #25295: [SPARK-28560][SQL]
Optimize shuffle reader to local shuffle reader when smj converted to bhj in
adaptive execution
URL: https://github.com/apache/spark/pull/25295#discussion_r323535120
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/ReduceNumShufflePartitions.scala
##########
@@ -180,25 +180,45 @@ case class ReduceNumShufflePartitions(conf: SQLConf)
extends Rule[SparkPlan] {
case class CoalescedShuffleReaderExec(
child: QueryStageExec,
- partitionStartIndices: Array[Int]) extends UnaryExecNode {
+ partitionStartIndices: Array[Int],
+ var isLocal: Boolean = false) extends UnaryExecNode {
Review comment:
`If we change the shuffle to local shuffle reader, then the partitions
become pre-shuffle partitions, and their data size is different.`
@cloud-fan Here the local shuffle reader is still optimize the post-shuffle
partitions. And I don't understand why the partitions become pre-shuffle
partitions?
----------------------------------------------------------------
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]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
