Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/16989#discussion_r115248267 --- Diff: core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala --- @@ -175,33 +195,47 @@ final class ShuffleBlockFetcherIterator( val sizeMap = req.blocks.map { case (blockId, size) => (blockId.toString, size) }.toMap val remainingBlocks = new HashSet[String]() ++= sizeMap.keys val blockIds = req.blocks.map(_._1.toString) - val address = req.address - shuffleClient.fetchBlocks(address.host, address.port, address.executorId, blockIds.toArray, - new BlockFetchingListener { - override def onBlockFetchSuccess(blockId: String, buf: ManagedBuffer): Unit = { - // Only add the buffer to results queue if the iterator is not zombie, - // i.e. cleanup() has not been called yet. - ShuffleBlockFetcherIterator.this.synchronized { - if (!isZombie) { - // Increment the ref count because we need to pass this to a different thread. - // This needs to be released after use. - buf.retain() - remainingBlocks -= blockId - results.put(new SuccessFetchResult(BlockId(blockId), address, sizeMap(blockId), buf, - remainingBlocks.isEmpty)) - logDebug("remainingBlocks: " + remainingBlocks) - } + + val blockFetchingListener = new BlockFetchingListener { + override def onBlockFetchSuccess(blockId: String, buf: ManagedBuffer): Unit = { + // Only add the buffer to results queue if the iterator is not zombie, + // i.e. cleanup() has not been called yet. + ShuffleBlockFetcherIterator.this.synchronized { + if (!isZombie) { + // Increment the ref count because we need to pass this to a different thread. + // This needs to be released after use. + buf.retain() + remainingBlocks -= blockId + results.put(new SuccessFetchResult(BlockId(blockId), address, sizeMap(blockId), buf, + remainingBlocks.isEmpty)) + logDebug("remainingBlocks: " + remainingBlocks) } - logTrace("Got remote block " + blockId + " after " + Utils.getUsedTimeMs(startTime)) } + logTrace("Got remote block " + blockId + " after " + Utils.getUsedTimeMs(startTime)) + } - override def onBlockFetchFailure(blockId: String, e: Throwable): Unit = { - logError(s"Failed to get block(s) from ${req.address.host}:${req.address.port}", e) - results.put(new FailureFetchResult(BlockId(blockId), address, e)) - } + override def onBlockFetchFailure(blockId: String, e: Throwable): Unit = { + logError(s"Failed to get block(s) from ${req.address.host}:${req.address.port}", e) + results.put(new FailureFetchResult(BlockId(blockId), address, e)) } - ) + } + val acquired = acquireMemory(req.size) + // Shuffle remote blocks to disk when local memory shortage or the request is too large. + if (acquired < req.size || bytesInFlight > maxBytesInFlight) { --- End diff -- if `bytesInFlight > maxBytesInFlight`, we don't need to bother the memory manager at all.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org