LuciferYang commented on a change in pull request #33556: URL: https://github.com/apache/spark/pull/33556#discussion_r680702762
########## File path: core/src/test/scala/org/apache/spark/storage/DiskBlockObjectWriterCloseMethodBenchmark.scala ########## @@ -0,0 +1,158 @@ +/* + * 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.storage + +import org.apache.spark.{SparkContext, SparkEnv} +import org.apache.spark.benchmark.{Benchmark, BenchmarkBase} +import org.apache.spark.executor.ShuffleWriteMetrics +import org.apache.spark.internal.config +import org.apache.spark.serializer.SerializerInstance +import org.apache.spark.util.collection.{PartitionedPairBuffer, WritablePartitionedIterator} + +/** + * Benchmark for `close` vs `revertPartialWritesAndClose` method in `DiskBlockObjectWriter`. + * To run this benchmark: + * {{{ + * 1. without sbt: + * bin/spark-submit --class <this class> <spark core test jar> + * 2. build/sbt "core/test:runMain <this class>" + * 3. generate result: + * SPARK_GENERATE_BENCHMARK_FILES=1 build/sbt "core/test:runMain <this class>" + * Results will be written to + * "benchmarks/DiskBlockObjectWriterCloseMethodBenchmark-results.txt". + * }}} + */ +object DiskBlockObjectWriterCloseMethodBenchmark extends BenchmarkBase { + + val sc = new SparkContext(master = "local", appName = "test") + + private[this] def spillWithClose( + iterator: WritablePartitionedIterator[Int, Int], + blockManager: BlockManager, + serInstance: SerializerInstance, + fileBufferSize: Int, + serializerBatchSize: Long, + revertAndClose: Boolean): Unit = { + val (blockId, file) = blockManager.diskBlockManager.createTempShuffleBlock() + + var objectsWritten: Long = 0 + val spillMetrics: ShuffleWriteMetrics = new ShuffleWriteMetrics + val writer: DiskBlockObjectWriter = + blockManager.getDiskWriter(blockId, file, serInstance, fileBufferSize, spillMetrics) + + def flush(): Unit = { + writer.commitAndGet() + objectsWritten = 0 + } + + while (iterator.hasNext) { + iterator.writeNext(writer) + objectsWritten += 1 + + if (objectsWritten == serializerBatchSize) { + flush() + } + } + if (objectsWritten > 0) { + flush() + writer.close() + } else if (revertAndClose) { + writer.revertPartialWritesAndClose() + } else { + writer.close() + } + } + + override def runBenchmarkSuite(mainArgs: Array[String]): Unit = { Review comment: It is difficult to compare benchmark directly between `writer.close()` and `writer.revertPartialWritesAndClose()`. So I extracted the main code part of `ExternalSorter.spill` to compare the performance of `writer.close()` and `writer.revertPartialWritesAndClose()` @mridulm @Ngone51 -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
