spark ShuffledRDD 源码

spark ShuffledRDD 代码

文件路径：/core/src/main/scala/org/apache/spark/rdd/ShuffledRDD.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.
 */

package org.apache.spark.rdd

import scala.reflect.ClassTag

import org.apache.spark._
import org.apache.spark.annotation.DeveloperApi
import org.apache.spark.serializer.Serializer

private[spark] class ShuffledRDDPartition(val idx: Int) extends Partition {
  override val index: Int = idx
}

/**
 * :: DeveloperApi ::
 * The resulting RDD from a shuffle (e.g. repartitioning of data).
 * @param prev the parent RDD.
 * @param part the partitioner used to partition the RDD
 * @tparam K the key class.
 * @tparam V the value class.
 * @tparam C the combiner class.
 */
// TODO: Make this return RDD[Product2[K, C]] or have some way to configure mutable pairs
@DeveloperApi
class ShuffledRDD[K: ClassTag, V: ClassTag, C: ClassTag](
    @transient var prev: RDD[_ <: Product2[K, V]],
    part: Partitioner)
  extends RDD[(K, C)](prev.context, Nil) {

  private var userSpecifiedSerializer: Option[Serializer] = None

  private var keyOrdering: Option[Ordering[K]] = None

  private var aggregator: Option[Aggregator[K, V, C]] = None

  private var mapSideCombine: Boolean = false

  /** Set a serializer for this RDD's shuffle, or null to use the default (spark.serializer) */
  def setSerializer(serializer: Serializer): ShuffledRDD[K, V, C] = {
    this.userSpecifiedSerializer = Option(serializer)
    this
  }

  /** Set key ordering for RDD's shuffle. */
  def setKeyOrdering(keyOrdering: Ordering[K]): ShuffledRDD[K, V, C] = {
    this.keyOrdering = Option(keyOrdering)
    this
  }

  /** Set aggregator for RDD's shuffle. */
  def setAggregator(aggregator: Aggregator[K, V, C]): ShuffledRDD[K, V, C] = {
    this.aggregator = Option(aggregator)
    this
  }

  /** Set mapSideCombine flag for RDD's shuffle. */
  def setMapSideCombine(mapSideCombine: Boolean): ShuffledRDD[K, V, C] = {
    this.mapSideCombine = mapSideCombine
    this
  }

  override def getDependencies: Seq[Dependency[_]] = {
    val serializer = userSpecifiedSerializer.getOrElse {
      val serializerManager = SparkEnv.get.serializerManager
      if (mapSideCombine) {
        serializerManager.getSerializer(implicitly[ClassTag[K]], implicitly[ClassTag[C]])
      } else {
        serializerManager.getSerializer(implicitly[ClassTag[K]], implicitly[ClassTag[V]])
      }
    }
    List(new ShuffleDependency(prev, part, serializer, keyOrdering, aggregator, mapSideCombine))
  }

  override val partitioner = Some(part)

  override def getPartitions: Array[Partition] = {
    Array.tabulate[Partition](part.numPartitions)(i => new ShuffledRDDPartition(i))
  }

  override protected def getPreferredLocations(partition: Partition): Seq[String] = {
    val tracker = SparkEnv.get.mapOutputTracker.asInstanceOf[MapOutputTrackerMaster]
    val dep = dependencies.head.asInstanceOf[ShuffleDependency[K, V, C]]
    tracker.getPreferredLocationsForShuffle(dep, partition.index)
  }

  override def compute(split: Partition, context: TaskContext): Iterator[(K, C)] = {
    val dep = dependencies.head.asInstanceOf[ShuffleDependency[K, V, C]]
    val metrics = context.taskMetrics().createTempShuffleReadMetrics()
    SparkEnv.get.shuffleManager.getReader(
      dep.shuffleHandle, split.index, split.index + 1, context, metrics)
      .read()
      .asInstanceOf[Iterator[(K, C)]]
  }

  override def clearDependencies(): Unit = {
    super.clearDependencies()
    prev = null
  }

  private[spark] override def isBarrier(): Boolean = false
}

相关信息

spark 源码目录

相关文章

spark AsyncRDDActions 源码

spark BinaryFileRDD 源码

spark BlockRDD 源码

spark CartesianRDD 源码

spark CheckpointRDD 源码

spark CoGroupedRDD 源码

spark CoalescedRDD 源码

spark DoubleRDDFunctions 源码

spark EmptyRDD 源码

spark HadoopRDD 源码