cloud-fan 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_r333946016
##########
File path: core/src/main/scala/org/apache/spark/MapOutputTracker.scala
##########
@@ -749,6 +818,26 @@ private[spark] class MapOutputTrackerWorker(conf:
SparkConf) extends MapOutputTr
}
}
+ override def getMapSizesByExecutorId(
+ shuffleId: Int,
+ startPartition: Int,
+ endPartition: Int,
+ mapId: Int,
+ useOldFetchProtocol: Boolean) : Iterator[(BlockManagerId, Seq[(BlockId,
Long, Int)])] = {
+ logDebug(s"Fetching outputs for shuffle $shuffleId, mapId $mapId" +
+ s"partitions $startPartition-$endPartition")
+ val statuses = getStatuses(shuffleId)
Review comment:
Since we need to get all the shuffle status anyway, we can call the existing
`convertMapStatuses`, and do an extra filter to only collect the blocks whose
mapIndex is what we want.
----------------------------------------------------------------
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]
