cloud-fan commented on a change in pull request #32883:
URL: https://github.com/apache/spark/pull/32883#discussion_r657935308
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/OptimizeSkewedJoin.scala
##########
@@ -90,41 +89,6 @@ object OptimizeSkewedJoin extends CustomShuffleReaderRule {
}
}
- /**
- * Get the map size of the specific reduce shuffle Id.
- */
- private def getMapSizesForReduceId(shuffleId: Int, partitionId: Int):
Array[Long] = {
- val mapOutputTracker =
SparkEnv.get.mapOutputTracker.asInstanceOf[MapOutputTrackerMaster]
-
mapOutputTracker.shuffleStatuses(shuffleId).mapStatuses.map{_.getSizeForBlock(partitionId)}
- }
-
- /**
- * Splits the skewed partition based on the map size and the target
partition size
- * after split, and create a list of `PartialMapperPartitionSpec`. Returns
None if can't split.
- */
- private def createSkewPartitionSpecs(
Review comment:
Can we make it public and just call it from the new rule?
--
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]
