vanzin commented on a change in pull request #25299: [SPARK-27651][Core] Avoid
the network when shuffle blocks are fetched from the same host
URL: https://github.com/apache/spark/pull/25299#discussion_r315826558
##########
File path: core/src/main/scala/org/apache/spark/storage/BlockManager.scala
##########
@@ -995,6 +1003,19 @@ private[spark] class BlockManager(
None
}
+ private[spark] def getHostLocalDirs(executorIds: Array[String])
+ : scala.collection.Map[String, Array[String]] = {
+ val cachedItems =
executorIdToLocalDirsCache.filterKeys(executorIds.contains(_))
+ if (cachedItems.size < executorIds.length) {
+ val notCachedItems = master
+
.getHostLocalDirs(executorIds.filterNot(executorIdToLocalDirsCache.contains))
+ executorIdToLocalDirsCache ++= notCachedItems
Review comment:
Isn't this going to grow potentially unbounded?
You added a cache to `BlockManagerMasterEndpoint` but that's something that
only exists in the driver. So it doesn't look like there's anything limiting
the number of entries cached in executors, at least directly.
----------------------------------------------------------------
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]
