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_r315833901
##########
File path:
core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala
##########
@@ -358,12 +382,65 @@ final class ShuffleBlockFetcherIterator(
}
}
+
+ /**
+ * Fetch the host-local blocks while we are fetching remote blocks. This is
ok because
+ * `ManagedBuffer`'s memory is allocated lazily when we create the input
stream, so all we
+ * track in-memory are the ManagedBuffer references themselves.
+ */
+ private[this] def fetchHostLocalBlocks() {
+ logDebug(s"Start fetching host-local blocks: ${hostLocalBlocks.mkString(",
")}")
+ val hostLocalExecutorIds =
hostLocalBlocksByExecutor.keySet.map(_.executorId)
+ val readsWithoutLocalDir = LinkedHashMap[BlockManagerId, Seq[(BlockId,
Long)]]()
+ val localDirsByExec =
blockManager.getHostLocalDirs(hostLocalExecutorIds.toArray)
+ hostLocalBlocksByExecutor.foreach { case (bmId, blockInfos) =>
+ val localDirs = localDirsByExec.get(bmId.executorId)
+ if (localDirs.isDefined) {
+ blockInfos.foreach { case (blockId, _) =>
+ try {
+ val buf = blockManager
+ .getHostLocalShuffleData(blockId.asInstanceOf[ShuffleBlockId],
localDirs.get)
+ shuffleMetrics.incLocalBlocksFetched(1)
+ shuffleMetrics.incLocalBytesRead(buf.size)
+ buf.retain()
+ results.put(SuccessFetchResult(blockId,
blockManager.blockManagerId,
+ buf.size(), buf, isNetworkReqDone = false))
+ } catch {
+ case e: Exception =>
+ // If we see an exception, stop immediately.
+ logError(s"Error occurred while fetching local blocks", e)
+ results.put(FailureFetchResult(blockId,
blockManager.blockManagerId, e))
+ return
+ }
+ }
+ } else {
+ readsWithoutLocalDir += bmId -> blockInfos
+ }
+ }
+
+ if (readsWithoutLocalDir.nonEmpty) {
+ val collectedRemoteRequests = new ArrayBuffer[FetchRequest]
+ readsWithoutLocalDir.foreach( { case (bmId, blockInfos) =>
Review comment:
`.foreach { case (bmId, blockInfos) =>`
----------------------------------------------------------------
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]
