spark BlockRDD 源码

  • 2022-10-20
  • 浏览 (210)

spark BlockRDD 代码

文件路径:/core/src/main/scala/org/apache/spark/rdd/BlockRDD.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.errors.SparkCoreErrors
import org.apache.spark.storage.{BlockId, BlockManager}

private[spark] class BlockRDDPartition(val blockId: BlockId, idx: Int) extends Partition {
  val index = idx
}

private[spark]
class BlockRDD[T: ClassTag](sc: SparkContext, @transient val blockIds: Array[BlockId])
  extends RDD[T](sc, Nil) {

  @transient lazy val _locations = BlockManager.blockIdsToLocations(blockIds, SparkEnv.get)
  @volatile private var _isValid = true

  override def getPartitions: Array[Partition] = {
    assertValid()
    blockIds.indices.map { i =>
      new BlockRDDPartition(blockIds(i), i).asInstanceOf[Partition]
    }.toArray
  }

  override def compute(split: Partition, context: TaskContext): Iterator[T] = {
    assertValid()
    val blockManager = SparkEnv.get.blockManager
    val blockId = split.asInstanceOf[BlockRDDPartition].blockId
    blockManager.get[T](blockId) match {
      case Some(block) => block.data.asInstanceOf[Iterator[T]]
      case None =>
        throw SparkCoreErrors.rddBlockNotFoundError(blockId, id)
    }
  }

  override def getPreferredLocations(split: Partition): Seq[String] = {
    assertValid()
    _locations(split.asInstanceOf[BlockRDDPartition].blockId)
  }

  /**
   * Remove the data blocks that this BlockRDD is made from. NOTE: This is an
   * irreversible operation, as the data in the blocks cannot be recovered back
   * once removed. Use it with caution.
   */
  private[spark] def removeBlocks(): Unit = {
    blockIds.foreach { blockId =>
      sparkContext.env.blockManager.master.removeBlock(blockId)
    }
    _isValid = false
  }

  /**
   * Whether this BlockRDD is actually usable. This will be false if the data blocks have been
   * removed using `this.removeBlocks`.
   */
  private[spark] def isValid: Boolean = {
    _isValid
  }

  /** Check if this BlockRDD is valid. If not valid, exception is thrown. */
  private[spark] def assertValid(): Unit = {
    if (!isValid) {
      throw SparkCoreErrors.blockHaveBeenRemovedError(toString)
    }
  }

  protected def getBlockIdLocations(): Map[BlockId, Seq[String]] = {
    _locations
  }
}

相关信息

spark 源码目录

相关文章

spark AsyncRDDActions 源码

spark BinaryFileRDD 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

spark InputFileBlockHolder 源码

0  赞