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_r349368751
##########
File path:
core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala
##########
@@ -420,12 +446,85 @@ final class ShuffleBlockFetcherIterator(
}
}
+ private[this] def fetchHostLocalBlock(
+ blockId: BlockId,
+ mapIndex: Int,
+ localDirs: Array[String],
+ blockManagerId: BlockManagerId): Boolean = {
+ try {
+ val buf = blockManager.getHostLocalShuffleData(blockId, localDirs)
+ buf.retain()
+ results.put(SuccessFetchResult(blockId, mapIndex, blockManagerId,
buf.size(), buf,
+ isNetworkReqDone = false))
+ true
+ } catch {
+ case e: Exception =>
+ // If we see an exception, stop immediately.
+ logError(s"Error occurred while fetching local blocks", e)
+ results.put(FailureFetchResult(blockId, mapIndex, blockManagerId, e))
+ false
+ }
+ }
+
+ /**
+ * 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(hostLocalDirManager:
HostLocalDirManager): Unit = {
+ val cachedDirsByExec = hostLocalDirManager.getCachedHostLocalDirs()
+ val (hostLocalBlocksWithCachedDirs, hostLocalBlocksWithMissingDirs) =
+ hostLocalBlocksByExecutor
+ .map { case (hostLocalBmId, bmInfos) =>
+ (hostLocalBmId, bmInfos,
cachedDirsByExec.get(hostLocalBmId.executorId))
+ }.partition(_._3.isDefined)
+ val bmId = blockManager.blockManagerId
+ val immutableHostLocalBlocksWithoutDirs =
+ hostLocalBlocksWithMissingDirs.map { case (hostLocalBmId, bmInfos, _) =>
+ hostLocalBmId -> bmInfos
+ }.toMap
+ if (immutableHostLocalBlocksWithoutDirs.nonEmpty) {
+ logDebug(s"Asynchronous fetching host-local blocks without cached
executors' dir: " +
+ s"${immutableHostLocalBlocksWithoutDirs.mkString(", ")}")
+ hostLocalDirManager.getHostLocalDirs(
+ immutableHostLocalBlocksWithoutDirs.keys.map(_.executorId).toArray, {
Review comment:
minor: if you use currying, this looks slightly better (the closure doesn't
need to be inside the `()`).
This line should also be indented a little more.
----------------------------------------------------------------
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]
