dongjoon-hyun commented on a change in pull request #23284: [SPARK-26337][SQL][TEST] Add benchmark for LongToUnsafeRowMap URL: https://github.com/apache/spark/pull/23284#discussion_r240802915
########## File path: sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/HashedRelationMetricsBenchmark.scala ########## @@ -0,0 +1,84 @@ +/* + * 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.sql.execution.benchmark + +import org.apache.spark.SparkConf +import org.apache.spark.benchmark.Benchmark +import org.apache.spark.internal.config.MEMORY_OFFHEAP_ENABLED +import org.apache.spark.memory.{StaticMemoryManager, TaskMemoryManager} +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.{BoundReference, UnsafeProjection} +import org.apache.spark.sql.execution.joins.LongToUnsafeRowMap +import org.apache.spark.sql.types.LongType + +/** + * Benchmark to measure metrics performance at HashedRelation. + * To run this benchmark: + * {{{ + * 1. without sbt: bin/spark-submit --class <this class> <spark sql test jar> + * 2. build/sbt "sql/test:runMain <this class>" + * 3. generate result: SPARK_GENERATE_BENCHMARK_FILES=1 build/sbt "sql/test:runMain <this class>" + * Results will be written to "benchmarks/HashedRelationMetricsBenchmark-results.txt". + * }}} + */ +object HashedRelationMetricsBenchmark extends SqlBasedBenchmark { + + def benchmarkLongToUnsafeRowMapMetrics(numRows: Int): Unit = { + runBenchmark("LongToUnsafeRowMap metrics") { + val benchmark = new Benchmark("LongToUnsafeRowMap metrics", numRows, output = output) + benchmark.addCase("LongToUnsafeRowMap") { iter => + val taskMemoryManager = new TaskMemoryManager( + new StaticMemoryManager( + new SparkConf().set(MEMORY_OFFHEAP_ENABLED.key, "false"), + Long.MaxValue, + Long.MaxValue, + 1), + 0) + val unsafeProj = UnsafeProjection.create(Seq(BoundReference(0, LongType, false))) + + val keys = Range.Long(0, numRows, 1) + val map = new LongToUnsafeRowMap(taskMemoryManager, 1) + keys.foreach { k => + map.append(k, unsafeProj(InternalRow(k))) + } + map.optimize() + + val threads = (0 to 100).map { _ => + val thread = new Thread { Review comment: So, is this the real difference from [AggregateBenchmark.LongToUnsafeRowMap](https://github.com/apache/spark/blob/master/sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/AggregateBenchmark.scala#L468-L502) benchmark case? ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on 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]
