vanzin commented on a change in pull request #25342: [SPARK-28571][CORE][SHUFFLE] Use the shuffle writer plugin for the SortShuffleWriter URL: https://github.com/apache/spark/pull/25342#discussion_r314393643
########## File path: core/src/main/scala/org/apache/spark/util/collection/ShufflePartitionPairsWriter.scala ########## @@ -0,0 +1,98 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.util.collection + +import java.io.{Closeable, FilterOutputStream, OutputStream} + +import org.apache.spark.serializer.{SerializationStream, SerializerInstance, SerializerManager} +import org.apache.spark.shuffle.ShuffleWriteMetricsReporter +import org.apache.spark.shuffle.api.ShufflePartitionWriter +import org.apache.spark.storage.BlockId + +/** + * A key-value writer inspired by {@link DiskBlockObjectWriter} that pushes the bytes to an + * arbitrary partition writer instead of writing to local disk through the block manager. + */ +private[spark] class ShufflePartitionPairsWriter( + partitionWriter: ShufflePartitionWriter, + serializerManager: SerializerManager, + serializerInstance: SerializerInstance, + blockId: BlockId, + writeMetrics: ShuffleWriteMetricsReporter) + extends PairsWriter with Closeable { + + private var isOpen = false + private var partitionStream: OutputStream = _ + private var wrappedStream: OutputStream = _ + private var objOut: SerializationStream = _ + private var numRecordsWritten = 0 + private var curNumBytesWritten = 0L + + override def write(key: Any, value: Any): Unit = { + if (!isOpen) { + open() + isOpen = true + } + objOut.writeKey(key) + objOut.writeValue(value) + writeMetrics.incRecordsWritten(1) + } + + private def open(): Unit = { + partitionStream = partitionWriter.openStream + wrappedStream = serializerManager.wrapStream(blockId, partitionStream) + objOut = serializerInstance.serializeStream(wrappedStream) + } + + override def close(): Unit = { + if (isOpen) { Review comment: > because wrappedStream and objOut would must be initialized successfully That's not necessarily a valid assumption. Compression codecs, e.g., may throw exceptions if the file is corrupt. ---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
