cloud-fan commented on a change in pull request #32407: URL: https://github.com/apache/spark/pull/32407#discussion_r627927694
########## File path: sql/core/src/test/scala/org/apache/spark/sql/connector/functions/FunctionBenchmark.scala ########## @@ -0,0 +1,125 @@ +/* + * 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.connector.functions + +import test.org.apache.spark.sql.connector.catalog.functions.JavaLongAdd +import test.org.apache.spark.sql.connector.catalog.functions.JavaLongAdd.{JavaLongAddDefault, JavaLongAddMagic, JavaLongAddStaticMagic} + +import org.apache.spark.benchmark.Benchmark +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.CodegenObjectFactoryMode._ +import org.apache.spark.sql.connector.catalog.{Identifier, InMemoryCatalog} +import org.apache.spark.sql.connector.catalog.functions.{BoundFunction, ScalarFunction, UnboundFunction} +import org.apache.spark.sql.execution.benchmark.SqlBasedBenchmark +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.types.{DataType, LongType, StructType} + +/** + * Benchmark to measure DataSourceV2 UDF performance + * {{{ + * To run this benchmark: + * 1. without sbt: + * bin/spark-submit --class <this class> + * --jars <spark core test jar>,<spark catalyst test jar> <sql core 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/FunctionBenchmark-results.txt". + * }}} + * '''NOTE''': to update the result of this benchmark, please use Github benchmark action: + * https://spark.apache.org/developer-tools.html#github-workflow-benchmarks + */ +object FunctionBenchmark extends SqlBasedBenchmark { + val catalogName: String = "benchmark_catalog" + + override def runBenchmarkSuite(mainArgs: Array[String]): Unit = { + val N = 500L * 1000 * 1000 + Seq(true, false).foreach { codegenEnabled => + Seq(true, false).foreach { resultNullable => + scalarFunctionBenchmark(N, codegenEnabled = codegenEnabled, + resultNullable = resultNullable) + } + } + } + + private def scalarFunctionBenchmark( + N: Long, + codegenEnabled: Boolean, + resultNullable: Boolean): Unit = { + withSQLConf(s"spark.sql.catalog.$catalogName" -> classOf[InMemoryCatalog].getName) { + createFunction("java_long_add_default", + new JavaLongAdd(new JavaLongAddDefault(resultNullable))) + createFunction("java_long_add_magic", new JavaLongAdd(new JavaLongAddMagic(resultNullable))) + createFunction("java_long_add_static_magic", + new JavaLongAdd(new JavaLongAddStaticMagic(resultNullable))) + createFunction("scala_long_add_default", + LongAddUnbound(new LongAddWithProduceResult(resultNullable))) + createFunction("scala_long_add_magic", LongAddUnbound(new LongAddWithMagic(resultNullable))) + + val codeGenFactoryMode = if (codegenEnabled) FALLBACK else NO_CODEGEN + withSQLConf(SQLConf.WHOLESTAGE_CODEGEN_ENABLED.key -> codegenEnabled.toString, + SQLConf.CODEGEN_FACTORY_MODE.key -> codeGenFactoryMode.toString) { + val name = s"scalar function (long + long) -> long, result_nullable = $resultNullable " + + s"codegen = $codegenEnabled" + val benchmark = new Benchmark(name, N, output = output) + benchmark.addCase(s"with native_long_add", numIters = 3) { _ => + spark.range(N).selectExpr("id + id").noop() + } + Seq("java_long_add_default", "java_long_add_magic", "java_long_add_static_magic", + "scala_long_add_default", "scala_long_add_magic").foreach { functionName => + benchmark.addCase(s"with $functionName", numIters = 3) { _ => Review comment: nit: the `with` seems useless in the case name. -- 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: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
