zhangyue19921010 commented on code in PR #5416: URL: https://github.com/apache/hudi/pull/5416#discussion_r903357345
########## hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/spark/sql/execution/benchmark/BoundInMemoryExecutorBenchmark.scala: ########## @@ -0,0 +1,133 @@ +/* + * 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.hadoop.fs.Path +import org.apache.hudi.HoodieSparkUtils +import org.apache.spark.SparkConf +import org.apache.spark.hudi.benchmark.{HoodieBenchmark, HoodieBenchmarkBase} +import org.apache.spark.sql.hudi.HoodieSparkSessionExtension +import org.apache.spark.sql.types._ +import org.apache.spark.sql.{DataFrame, RowFactory, SaveMode, SparkSession} + +import scala.util.Random + +object BoundInMemoryExecutorBenchmark extends HoodieBenchmarkBase { + + protected val spark: SparkSession = getSparkSession + + val recordNumber = 1000000 + + def getSparkSession: SparkSession = SparkSession.builder() + .master("local[*]") + .appName(this.getClass.getCanonicalName) + .withExtensions(new HoodieSparkSessionExtension) + .config("spark.serializer", "org.apache.spark.serializer.KryoSerializer") + .config("spark.sql.session.timeZone", "CTT") + .config(sparkConf()) + .getOrCreate() + + def sparkConf(): SparkConf = { + val sparkConf = new SparkConf() + if (HoodieSparkUtils.gteqSpark3_2) { + sparkConf.set("spark.sql.catalog.spark_catalog", + "org.apache.spark.sql.hudi.catalog.HoodieCatalog") + } + sparkConf + } + + private def createDataFrame(number: Int): DataFrame = { + val schema = new StructType() + .add("c1", IntegerType) + .add("c2", StringType) + + val rdd = spark.sparkContext.parallelize(0 to number, 2).map { item => + val c1 = Integer.valueOf(item) + val c2 = s"abc" + RowFactory.create(c1, c2) + } + spark.createDataFrame(rdd, schema) + } + + /** + * Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz + * COW Ingestion: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative + * ------------------------------------------------------------------------------------------------------------------------ + * BoundInMemory Executor 5557 5607 70 0.2 5556.9 1.0X + * Disruptor Executor 2758 2778 28 0.4 2757.7 2.0X + */ + private def cowTableDisruptorExecutorBenchmark(tableName: String = "executorBenchmark"): Unit = { + val df = createDataFrame(recordNumber) Review Comment: Yeap, Changed. Also i run this benchmark several times and here are the results ``` OpenJDK 64-Bit Server VM 1.8.0_161-b14 on Linux 3.10.0-693.21.1.el7.x86_64 Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz COW Ingestion: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ BoundInMemory Executor 5629 5765 192 0.2 5628.9 1.0X Disruptor Executor 2772 2862 127 0.4 2772.2 2.0X ``` ``` OpenJDK 64-Bit Server VM 1.8.0_161-b14 on Linux 3.10.0-693.21.1.el7.x86_64 Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz COW Ingestion: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ BoundInMemory Executor 5738 5862 175 0.2 5737.8 1.0X Disruptor Executor 2742 2809 95 0.4 2742.0 2.1X ``` ``` OpenJDK 64-Bit Server VM 1.8.0_161-b14 on Linux 3.10.0-693.21.1.el7.x86_64 Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz COW Ingestion: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ BoundInMemory Executor 5348 5482 189 0.2 5348.3 1.0X Disruptor Executor 2719 2868 211 0.4 2718.9 2.0X ``` -- 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]
