Github user massie commented on a diff in the pull request: https://github.com/apache/spark/pull/6423#discussion_r32074744 --- Diff: core/src/main/scala/org/apache/spark/shuffle/hash/HashShuffleReader.scala --- @@ -33,17 +34,54 @@ private[spark] class HashShuffleReader[K, C]( "Hash shuffle currently only supports fetching one partition") private val dep = handle.dependency + private val blockManager = SparkEnv.get.blockManager /** Read the combined key-values for this reduce task */ override def read(): Iterator[Product2[K, C]] = { + val blockStreams = BlockStoreShuffleFetcher.fetchBlockStreams( + handle.shuffleId, startPartition, context) + + // Wrap the streams for compression based on configuration + val wrappedStreams = blockStreams.map { case (blockId, inputStream) => + blockManager.wrapForCompression(blockId, inputStream) + } + val ser = Serializer.getSerializer(dep.serializer) - val iter = BlockStoreShuffleFetcher.fetch(handle.shuffleId, startPartition, context, ser) + val serializerInstance = ser.newInstance() + + // Create a key/value iterator for each stream + val recordIterator = wrappedStreams.flatMap { wrappedStream => + val kvIter = serializerInstance.deserializeStream(wrappedStream).asKeyValueIterator + CompletionIterator[(Any, Any), Iterator[(Any, Any)]](kvIter, { + // Close the stream once all the records have been read from it to free underlying + // ManagedBuffer as soon as possible. Note that in case of task failure, the task's + // TaskCompletionListener will make sure this is released. + wrappedStream.close() + }) + } + + // Update read metrics for each record materialized + val iter = new InterruptibleIterator[(Any, Any)](context, recordIterator) { + val readMetrics = context.taskMetrics.createShuffleReadMetricsForDependency() --- End diff -- Will fix.
--- 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