maropu commented on a change in pull request #30379: URL: https://github.com/apache/spark/pull/30379#discussion_r523473622
########## File path: sql/core/src/test/scala/org/apache/spark/sql/execution/SubExprEliminationBenchmark.scala ########## @@ -0,0 +1,119 @@ +/* + * 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 + +import org.apache.spark.benchmark.Benchmark +import org.apache.spark.sql.execution.benchmark.SqlBasedBenchmark +import org.apache.spark.sql.functions._ +import org.apache.spark.sql.internal.SQLConf + +/** + * The benchmarks aims to measure performance of the queries where there are subexpression + * elimination or not. + * To run this benchmark: + * {{{ + * 1. without sbt: + * bin/spark-submit --class <this class> --jars <spark core test jar>, + * <spark catalyst test jar> <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/SubExprEliminationBenchmark-results.txt". + * }}} + */ + Review comment: nit: The other benchmark codes don't seem to have this blank between the comment and the object. ########## File path: sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/SqlBasedBenchmark.scala ########## @@ -66,4 +68,26 @@ trait SqlBasedBenchmark extends BenchmarkBase with SQLHelper { ds.write.format("noop").mode(Overwrite).save() } } + + protected def prepareDataInfo(benchmark: Benchmark): Unit = { + // scalastyle:off println + benchmark.out.println("Preparing data for benchmarking ...") + // scalastyle:on println + } + + /** + * Prepares a table with wide row for benchmarking. The table will be written into + * the given path. + */ + protected def writeWideRow(path: String, rowsNum: Int, numCols: Int): StructType = { + val fields = Seq.tabulate(numCols)(i => StructField(s"col$i", IntegerType)) + val schema = StructType(fields) + + spark.range(rowsNum) + .select(Seq.tabulate(numCols)(i => lit(i).as(s"col$i")): _*) + .write.json(path) + + schema + } + Review comment: nit: remove this. ---------------------------------------------------------------- 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 --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
