ulysses-you commented on code in PR #41609:
URL: https://github.com/apache/spark/pull/41609#discussion_r1253829679
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/OptimizeSkewedJoin.scala:
##########
@@ -198,6 +199,42 @@ case class OptimizeSkewedJoin(ensureRequirements:
EnsureRequirements)
}
}
+ /**
+ * Split the skewed partition of the BroadcastHashJoin streamPlan.
+ */
+ private def tryOptimizeBroadcastHashJoinStreamedPlan(
+ shuffle: ShuffleQueryStageExec): Option[SparkPlan] = {
+ val mapStats = shuffle.mapStats.get
+ val bytesByPartitionId = mapStats.bytesByPartitionId
+ val medSize = Utils.median(bytesByPartitionId, false)
+ val skewThreshold = getSkewThreshold(medSize)
+ val streamedPlanTargetSize = targetSize(bytesByPartitionId, skewThreshold)
+
+ val newPartitionsSpec = bytesByPartitionId.indices.flatMap { reduceIndex =>
Review Comment:
Is there have existed code can be reused ? We can put it to
`ShufflePartitionsUtil`
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
