LuciferYang commented on a change in pull request #30026: URL: https://github.com/apache/spark/pull/30026#discussion_r507304846
########## File path: sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/InsertTableWithDynamicPartitionsBenchmark.scala ########## @@ -0,0 +1,111 @@ +/* + * 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.benchmark.Benchmark +import org.apache.spark.sql.SparkSession + +/** + * Benchmark to measure insert into table with dynamic partition columns. + * 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/InsertTableWithDynamicPartitionsBenchmark-results.txt". + * }}} + */ +object InsertTableWithDynamicPartitionsBenchmark extends DataSourceWriteBenchmark { + + override def getSparkSession: SparkSession = { + SparkSession.builder().master("local[4]").getOrCreate() + } + + def prepareSourceTableAndGetTotalRows(numberRows: Long, sourceTable: String, + part1Step: Int, part2Step: Int, part3Step: Int): Long = { + val dataFrame = spark.range(0, numberRows, 1, 4) + val dataFrame1 = spark.range(0, numberRows, part1Step, 4) + val dataFrame2 = spark.range(0, numberRows, part2Step, 4) + val dataFrame3 = spark.range(0, numberRows, part3Step, 4) + + val data = dataFrame.join(dataFrame1).join(dataFrame2).join(dataFrame3) + .toDF("id", "part1", "part2", "part3") + data.write.saveAsTable(sourceTable) + data.count() + } + + def writeOnePartitionColumnTable(tableName: String, + partitionNumber: Long, benchmark: Benchmark): Unit = { + spark.sql(s"create table $tableName(i bigint, part bigint) " + + "using parquet partitioned by (part)") + benchmark.addCase(s"one partition column, $partitionNumber partitions") { _ => + spark.sql("insert overwrite table " + + s"$tableName partition(part) " + Review comment: done ########## File path: sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/InsertTableWithDynamicPartitionsBenchmark.scala ########## @@ -0,0 +1,111 @@ +/* + * 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.benchmark.Benchmark +import org.apache.spark.sql.SparkSession + +/** + * Benchmark to measure insert into table with dynamic partition columns. + * 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/InsertTableWithDynamicPartitionsBenchmark-results.txt". + * }}} + */ +object InsertTableWithDynamicPartitionsBenchmark extends DataSourceWriteBenchmark { + + override def getSparkSession: SparkSession = { + SparkSession.builder().master("local[4]").getOrCreate() + } + + def prepareSourceTableAndGetTotalRows(numberRows: Long, sourceTable: String, + part1Step: Int, part2Step: Int, part3Step: Int): Long = { + val dataFrame = spark.range(0, numberRows, 1, 4) + val dataFrame1 = spark.range(0, numberRows, part1Step, 4) + val dataFrame2 = spark.range(0, numberRows, part2Step, 4) + val dataFrame3 = spark.range(0, numberRows, part3Step, 4) + + val data = dataFrame.join(dataFrame1).join(dataFrame2).join(dataFrame3) + .toDF("id", "part1", "part2", "part3") + data.write.saveAsTable(sourceTable) + data.count() + } + + def writeOnePartitionColumnTable(tableName: String, + partitionNumber: Long, benchmark: Benchmark): Unit = { + spark.sql(s"create table $tableName(i bigint, part bigint) " + + "using parquet partitioned by (part)") + benchmark.addCase(s"one partition column, $partitionNumber partitions") { _ => + spark.sql("insert overwrite table " + + s"$tableName partition(part) " + + "select id, part1 as part from sourceTable") + } + } + + def writeTwoPartitionColumnTable(tableName: String, + partitionNumber: Long, benchmark: Benchmark): Unit = { + spark.sql(s"create table $tableName(i bigint, part1 bigint, part2 bigint) " + + "using parquet partitioned by (part1, part2)") + benchmark.addCase(s"two partition columns, $partitionNumber partitions") { _ => + spark.sql("insert overwrite table " + + s"$tableName partition(part1, part2) " + Review comment: done ########## File path: sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/InsertTableWithDynamicPartitionsBenchmark.scala ########## @@ -0,0 +1,111 @@ +/* + * 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.benchmark.Benchmark +import org.apache.spark.sql.SparkSession + +/** + * Benchmark to measure insert into table with dynamic partition columns. + * 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/InsertTableWithDynamicPartitionsBenchmark-results.txt". + * }}} + */ +object InsertTableWithDynamicPartitionsBenchmark extends DataSourceWriteBenchmark { + + override def getSparkSession: SparkSession = { + SparkSession.builder().master("local[4]").getOrCreate() + } + + def prepareSourceTableAndGetTotalRows(numberRows: Long, sourceTable: String, + part1Step: Int, part2Step: Int, part3Step: Int): Long = { + val dataFrame = spark.range(0, numberRows, 1, 4) + val dataFrame1 = spark.range(0, numberRows, part1Step, 4) + val dataFrame2 = spark.range(0, numberRows, part2Step, 4) + val dataFrame3 = spark.range(0, numberRows, part3Step, 4) + + val data = dataFrame.join(dataFrame1).join(dataFrame2).join(dataFrame3) + .toDF("id", "part1", "part2", "part3") + data.write.saveAsTable(sourceTable) + data.count() + } + + def writeOnePartitionColumnTable(tableName: String, + partitionNumber: Long, benchmark: Benchmark): Unit = { + spark.sql(s"create table $tableName(i bigint, part bigint) " + + "using parquet partitioned by (part)") + benchmark.addCase(s"one partition column, $partitionNumber partitions") { _ => + spark.sql("insert overwrite table " + + s"$tableName partition(part) " + + "select id, part1 as part from sourceTable") + } + } + + def writeTwoPartitionColumnTable(tableName: String, + partitionNumber: Long, benchmark: Benchmark): Unit = { + spark.sql(s"create table $tableName(i bigint, part1 bigint, part2 bigint) " + + "using parquet partitioned by (part1, part2)") + benchmark.addCase(s"two partition columns, $partitionNumber partitions") { _ => + spark.sql("insert overwrite table " + + s"$tableName partition(part1, part2) " + + "select id, part1, part2 from sourceTable") + } + } + + def writeThreePartitionColumnTable(tableName: String, + partitionNumber: Long, benchmark: Benchmark): Unit = { + spark.sql(s"create table $tableName(i bigint, part1 bigint, part2 bigint, part3 bigint) " + + "using parquet partitioned by (part1, part2, part3)") + benchmark.addCase(s"three partition columns, $partitionNumber partitions") { _ => + spark.sql("insert overwrite table " + + s"$tableName partition(part1, part2, part3) " + Review comment: done ---------------------------------------------------------------- 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]
