spark GroupByTest 源码

  • 2022-10-20
  • 浏览 (279)

spark GroupByTest 代码

文件路径:/examples/src/main/scala/org/apache/spark/examples/GroupByTest.scala

/*
 * 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.
 */

// scalastyle:off println
package org.apache.spark.examples

import java.util.Random

import org.apache.spark.sql.SparkSession

/**
 * Usage: GroupByTest [numMappers] [numKVPairs] [KeySize] [numReducers]
 */
object GroupByTest {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession
      .builder
      .appName("GroupBy Test")
      .getOrCreate()

    val numMappers = if (args.length > 0) args(0).toInt else 2
    val numKVPairs = if (args.length > 1) args(1).toInt else 1000
    val valSize = if (args.length > 2) args(2).toInt else 1000
    val numReducers = if (args.length > 3) args(3).toInt else numMappers

    val pairs1 = spark.sparkContext.parallelize(0 until numMappers, numMappers).flatMap { p =>
      val ranGen = new Random
      val arr1 = new Array[(Int, Array[Byte])](numKVPairs)
      for (i <- 0 until numKVPairs) {
        val byteArr = new Array[Byte](valSize)
        ranGen.nextBytes(byteArr)
        arr1(i) = (ranGen.nextInt(Int.MaxValue), byteArr)
      }
      arr1
    }.cache()
    // Enforce that everything has been calculated and in cache
    pairs1.count()

    println(pairs1.groupByKey(numReducers).count())

    spark.stop()
  }
}
// scalastyle:on println

相关信息

spark 源码目录

相关文章

spark AccumulatorMetricsTest 源码

spark BroadcastTest 源码

spark DFSReadWriteTest 源码

spark DriverSubmissionTest 源码

spark ExceptionHandlingTest 源码

spark HdfsTest 源码

spark LocalALS 源码

spark LocalFileLR 源码

spark LocalKMeans 源码

spark LocalLR 源码

0  赞