cloud-fan commented on code in PR #45930:
URL: https://github.com/apache/spark/pull/45930#discussion_r1575684967
##########
core/src/main/scala/org/apache/spark/shuffle/IndexShuffleBlockResolver.scala:
##########
@@ -76,13 +78,21 @@ private[spark] class IndexShuffleBlockResolver(
override def getStoredShuffles(): Seq[ShuffleBlockInfo] = {
val allBlocks = blockManager.diskBlockManager.getAllBlocks()
allBlocks.flatMap {
- case ShuffleIndexBlockId(shuffleId, mapId, _) =>
+ case ShuffleIndexBlockId(shuffleId, mapId, _)
+ if Option(shuffleIdsToSkip.getIfPresent(shuffleId)).isEmpty =>
Some(ShuffleBlockInfo(shuffleId, mapId))
case _ =>
None
}
}
+ private val shuffleIdsToSkip =
+ CacheBuilder.newBuilder().maximumSize(1000).build[java.lang.Integer,
java.lang.Boolean]()
Review Comment:
if the value does not matter, shall we just use `Object` type and always
pass null?
--
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]
