Kimahriman commented on a change in pull request #35085:
URL: https://github.com/apache/spark/pull/35085#discussion_r829402416
##########
File path:
core/src/main/scala/org/apache/spark/storage/BlockManagerMasterEndpoint.scala
##########
@@ -294,33 +298,74 @@ class BlockManagerMasterEndpoint(
}
}.toSeq
- val removeRddBlockViaExtShuffleServiceFutures =
externalBlockStoreClient.map { shuffleClient =>
- blocksToDeleteByShuffleService.map { case (bmId, blockIds) =>
- Future[Int] {
- val numRemovedBlocks = shuffleClient.removeBlocks(
- bmId.host,
- bmId.port,
- bmId.executorId,
- blockIds.map(_.toString).toArray)
- numRemovedBlocks.get(defaultRpcTimeout.duration.toSeconds,
TimeUnit.SECONDS)
+ val removeRddBlockViaExtShuffleServiceFutures = if
(externalShuffleServiceRddFetchEnabled) {
+ externalBlockStoreClient.map { shuffleClient =>
+ blocksToDeleteByShuffleService.map { case (bmId, blockIds) =>
+ Future[Int] {
+ val numRemovedBlocks = shuffleClient.removeBlocks(
+ bmId.host,
+ bmId.port,
+ bmId.executorId,
+ blockIds.map(_.toString).toArray)
+ numRemovedBlocks.get(defaultRpcTimeout.duration.toSeconds,
TimeUnit.SECONDS)
+ }
}
- }
- }.getOrElse(Seq.empty)
+ }.getOrElse(Seq.empty)
+ } else {
+ Seq.empty
+ }
Future.sequence(removeRddFromExecutorsFutures ++
removeRddBlockViaExtShuffleServiceFutures)
}
private def removeShuffle(shuffleId: Int): Future[Seq[Boolean]] = {
- // Nothing to do in the BlockManagerMasterEndpoint data structures
val removeMsg = RemoveShuffle(shuffleId)
- Future.sequence(
- blockManagerInfo.values.map { bm =>
- bm.storageEndpoint.ask[Boolean](removeMsg).recover {
- // use false as default value means no shuffle data were removed
- handleBlockRemovalFailure("shuffle", shuffleId.toString,
bm.blockManagerId, false)
+ val removeShuffleFromExecutorsFutures = blockManagerInfo.values.map { bm =>
+ bm.storageEndpoint.ask[Boolean](removeMsg).recover {
+ // use false as default value means no shuffle data were removed
+ handleBlockRemovalFailure("shuffle", shuffleId.toString,
bm.blockManagerId, false)
+ }
+ }.toSeq
+
+ // Find all shuffle blocks on executors that are no longer running
+ val blocksToDeleteByShuffleService =
+ new mutable.HashMap[BlockManagerId, mutable.HashSet[BlockId]]
+ if (externalShuffleServiceRemoveShuffleEnabled) {
+ mapOutputTracker.shuffleStatuses.get(shuffleId).foreach { shuffleStatus
=>
+ shuffleStatus.mapStatuses.foreach { mapStatus =>
+ // Port should always be external shuffle port if external shuffle
is enabled so
+ // also check if the executor has been deallocated
+ if (mapStatus.location.port == externalShuffleServicePort &&
Review comment:
I think this was carried over from before this whole thing was wrapped
in a check for if shuffle service is enabled, I think I can remove
--
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]
