org.apache.spark.shuffle.BaseShuffleHandle Scala Examples

package org.apache.spark.shuffle.sort

import org.apache.spark._
import org.apache.spark.internal.Logging
import org.apache.spark.scheduler.MapStatus
import org.apache.spark.shuffle.{BaseShuffleHandle, IndexShuffleBlockResolver, ShuffleWriter}
import org.apache.spark.storage.ShuffleBlockId
import org.apache.spark.util.Utils
import org.apache.spark.util.collection.ExternalSorter

private[spark] class SortShuffleWriter[K, V, C](
    shuffleBlockResolver: IndexShuffleBlockResolver,
    handle: BaseShuffleHandle[K, V, C],
    mapId: Int,
    context: TaskContext)
  extends ShuffleWriter[K, V] with Logging {

  private val dep = handle.dependency

  private val blockManager = SparkEnv.get.blockManager

  private var sorter: ExternalSorter[K, V, _] = null

  // Are we in the process of stopping? Because map tasks can call stop() with success = true
  // and then call stop() with success = false if they get an exception, we want to make sure
  // we don't try deleting files, etc twice.
  private var stopping = false

  private var mapStatus: MapStatus = null

  private val writeMetrics = context.taskMetrics().shuffleWriteMetrics

  
  override def stop(success: Boolean): Option[MapStatus] = {
    try {
      if (stopping) {
        return None
      }
      stopping = true
      if (success) {
        return Option(mapStatus)
      } else {
        return None
      }
    } finally {
      // Clean up our sorter, which may have its own intermediate files
      if (sorter != null) {
        val startTime = System.nanoTime()
        sorter.stop()
        writeMetrics.incWriteTime(System.nanoTime - startTime)
        sorter = null
      }
    }
  }
}

private[spark] object SortShuffleWriter {
  def shouldBypassMergeSort(conf: SparkConf, dep: ShuffleDependency[_, _, _]): Boolean = {
    // We cannot bypass sorting if we need to do map-side aggregation.
    if (dep.mapSideCombine) {
      require(dep.aggregator.isDefined, "Map-side combine without Aggregator specified!")
      false
    } else {
      val bypassMergeThreshold: Int = conf.getInt("spark.shuffle.sort.bypassMergeThreshold", 200)
      dep.partitioner.numPartitions <= bypassMergeThreshold
    }
  }
} 

package org.apache.spark.shuffle.remote

import org.apache.spark._
import org.apache.spark.internal.Logging
import org.apache.spark.scheduler.MapStatus
import org.apache.spark.shuffle.{BaseShuffleHandle, IndexShuffleBlockResolver, ShuffleWriter}
import org.apache.spark.storage.ShuffleBlockId
import org.apache.spark.util.collection.RemoteSorter

private[spark] class RemoteShuffleWriter[K, V, C](
    resolver: RemoteShuffleBlockResolver,
    handle: BaseShuffleHandle[K, V, C],
    mapId: Long,
    context: TaskContext)
    extends ShuffleWriter[K, V] with Logging {

  logWarning("******** General Remote Shuffle Writer is used ********")

  private lazy val fs = RemoteShuffleManager.getFileSystem

  private val blockManager = SparkEnv.get.blockManager

  private val dep = handle.dependency

  private var sorter: RemoteSorter[K, V, _] = null

  // Are we in the process of stopping? Because map tasks can call stop() with success = true
  // and then call stop() with success = false if they get an exception, we want to make sure
  // we don't try deleting files, etc twice.
  private var stopping = false

  private var mapStatus: MapStatus = null

  private val writeMetrics = context.taskMetrics().shuffleWriteMetrics

  
  override def stop(success: Boolean): Option[MapStatus] = {
    try {
      if (stopping) {
        return None
      }
      stopping = true
      if (success) {
        return Option(mapStatus)
      } else {
        return None
      }
    } finally {
      // Clean up our sorter, which may have its own intermediate files
      if (sorter != null) {
        val startTime = System.nanoTime()
        sorter.stop()
        writeMetrics.incWriteTime(System.nanoTime - startTime)
        sorter = null
      }
    }
  }
} 

package org.apache.spark.shuffle.sort

import org.apache.spark._
import org.apache.spark.internal.Logging
import org.apache.spark.scheduler.MapStatus
import org.apache.spark.shuffle.{BaseShuffleHandle, IndexShuffleBlockResolver, ShuffleWriter}
import org.apache.spark.storage.ShuffleBlockId
import org.apache.spark.util.Utils
import org.apache.spark.util.collection.ExternalSorter

private[spark] class SortShuffleWriter[K, V, C](
    shuffleBlockResolver: IndexShuffleBlockResolver,
    handle: BaseShuffleHandle[K, V, C],
    mapId: Int,
    context: TaskContext)
  extends ShuffleWriter[K, V] with Logging {

  private val dep = handle.dependency

  private val blockManager = SparkEnv.get.blockManager

  private var sorter: ExternalSorter[K, V, _] = null

  // Are we in the process of stopping? Because map tasks can call stop() with success = true
  // and then call stop() with success = false if they get an exception, we want to make sure
  // we don't try deleting files, etc twice.
  private var stopping = false

  private var mapStatus: MapStatus = null

  private val writeMetrics = context.taskMetrics().shuffleWriteMetrics

  
  override def stop(success: Boolean): Option[MapStatus] = {
    try {
      if (stopping) {
        return None
      }
      stopping = true
      if (success) {
        return Option(mapStatus)
      } else {
        return None
      }
    } finally {
      // Clean up our sorter, which may have its own intermediate files
      if (sorter != null) {
        val startTime = System.nanoTime()
        sorter.stop()
        writeMetrics.incWriteTime(System.nanoTime - startTime)
        sorter = null
      }
    }
  }
}

private[spark] object SortShuffleWriter {
  def shouldBypassMergeSort(conf: SparkConf, dep: ShuffleDependency[_, _, _]): Boolean = {
    // We cannot bypass sorting if we need to do map-side aggregation.
    if (dep.mapSideCombine) {
      require(dep.aggregator.isDefined, "Map-side combine without Aggregator specified!")
      false
    } else {
      val bypassMergeThreshold: Int = conf.getInt("spark.shuffle.sort.bypassMergeThreshold", 200)
      dep.partitioner.numPartitions <= bypassMergeThreshold
    }
  }
} 

package org.apache.spark.shuffle.hash

import org.apache.spark.{InterruptibleIterator, TaskContext}
import org.apache.spark.serializer.Serializer
import org.apache.spark.shuffle.{BaseShuffleHandle, ShuffleReader}
import org.apache.spark.util.collection.ExternalSorter

private[spark] class HashShuffleReader[K, C](
    handle: BaseShuffleHandle[K, _, C],
    startPartition: Int,
    endPartition: Int,
    context: TaskContext)
  extends ShuffleReader[K, C]
{
  require(endPartition == startPartition + 1,
    "Hash shuffle currently only supports fetching one partition")

  private val dep = handle.dependency

  
  override def read(): Iterator[Product2[K, C]] = {
    val ser = Serializer.getSerializer(dep.serializer)
    val iter = BlockStoreShuffleFetcher.fetch(handle.shuffleId, startPartition, context, ser)

    val aggregatedIter: Iterator[Product2[K, C]] = if (dep.aggregator.isDefined) {
      if (dep.mapSideCombine) {
        new InterruptibleIterator(context, dep.aggregator.get.combineCombinersByKey(iter, context))
      } else {
        new InterruptibleIterator(context, dep.aggregator.get.combineValuesByKey(iter, context))
      }
    } else {
      require(!dep.mapSideCombine, "Map-side combine without Aggregator specified!")

      // Convert the Product2s to pairs since this is what downstream RDDs currently expect
      iter.asInstanceOf[Iterator[Product2[K, C]]].map(pair => (pair._1, pair._2))
    }

    // Sort the output if there is a sort ordering defined.
    dep.keyOrdering match {
      case Some(keyOrd: Ordering[K]) =>
        // Create an ExternalSorter to sort the data. Note that if spark.shuffle.spill is disabled,
        // the ExternalSorter won't spill to disk.
        val sorter = new ExternalSorter[K, C, C](ordering = Some(keyOrd), serializer = Some(ser))
        sorter.insertAll(aggregatedIter)
        context.taskMetrics.incMemoryBytesSpilled(sorter.memoryBytesSpilled)
        context.taskMetrics.incDiskBytesSpilled(sorter.diskBytesSpilled)
        sorter.iterator
      case None =>
        aggregatedIter
    }
  }
} 

package org.apache.spark.shuffle.sort

import org.apache.spark.{MapOutputTracker, SparkEnv, Logging, TaskContext}
import org.apache.spark.executor.ShuffleWriteMetrics
import org.apache.spark.scheduler.MapStatus
import org.apache.spark.shuffle.{IndexShuffleBlockManager, ShuffleWriter, BaseShuffleHandle}
import org.apache.spark.storage.ShuffleBlockId
import org.apache.spark.util.collection.ExternalSorter

private[spark] class SortShuffleWriter[K, V, C](
    shuffleBlockManager: IndexShuffleBlockManager,
    handle: BaseShuffleHandle[K, V, C],
    mapId: Int,
    context: TaskContext)
  extends ShuffleWriter[K, V] with Logging {

  private val dep = handle.dependency

  private val blockManager = SparkEnv.get.blockManager

  private var sorter: ExternalSorter[K, V, _] = null

  // Are we in the process of stopping? Because map tasks can call stop() with success = true
  // and then call stop() with success = false if they get an exception, we want to make sure
  // we don't try deleting files, etc twice.
  private var stopping = false

  private var mapStatus: MapStatus = null

  private val writeMetrics = new ShuffleWriteMetrics()
  context.taskMetrics.shuffleWriteMetrics = Some(writeMetrics)

  
  override def stop(success: Boolean): Option[MapStatus] = {
    try {
      if (stopping) {
        return None
      }
      stopping = true
      if (success) {
        return Option(mapStatus)
      } else {
        // The map task failed, so delete our output data.
        shuffleBlockManager.removeDataByMap(dep.shuffleId, mapId)
        return None
      }
    } finally {
      // Clean up our sorter, which may have its own intermediate files
      if (sorter != null) {
        sorter.stop()
        sorter = null
      }
    }
  }
} 

package org.apache.spark.shuffle.sort

import org.apache.spark._
import org.apache.spark.internal.Logging
import org.apache.spark.scheduler.MapStatus
import org.apache.spark.shuffle.{BaseShuffleHandle, IndexShuffleBlockResolver, ShuffleWriter}
import org.apache.spark.storage.ShuffleBlockId
import org.apache.spark.util.Utils
import org.apache.spark.util.collection.ExternalSorter

private[spark] class SortShuffleWriter[K, V, C](
    shuffleBlockResolver: IndexShuffleBlockResolver,
    handle: BaseShuffleHandle[K, V, C],
    mapId: Int,
    context: TaskContext)
  extends ShuffleWriter[K, V] with Logging {

  private val user = Utils.getCurrentUserName

  private val dep = handle.dependency

  private val blockManager = SparkEnv.get(user).blockManager

  private var sorter: ExternalSorter[K, V, _] = null

  // Are we in the process of stopping? Because map tasks can call stop() with success = true
  // and then call stop() with success = false if they get an exception, we want to make sure
  // we don't try deleting files, etc twice.
  private var stopping = false

  private var mapStatus: MapStatus = null

  private val writeMetrics = context.taskMetrics().shuffleWriteMetrics

  
  override def stop(success: Boolean): Option[MapStatus] = {
    try {
      if (stopping) {
        return None
      }
      stopping = true
      if (success) {
        return Option(mapStatus)
      } else {
        return None
      }
    } finally {
      // Clean up our sorter, which may have its own intermediate files
      if (sorter != null) {
        val startTime = System.nanoTime()
        sorter.stop()
        writeMetrics.incWriteTime(System.nanoTime - startTime)
        sorter = null
      }
    }
  }
}

private[spark] object SortShuffleWriter {
  def shouldBypassMergeSort(conf: SparkConf, dep: ShuffleDependency[_, _, _]): Boolean = {
    // We cannot bypass sorting if we need to do map-side aggregation.
    if (dep.mapSideCombine) {
      require(dep.aggregator.isDefined, "Map-side combine without Aggregator specified!")
      false
    } else {
      val bypassMergeThreshold: Int = conf.getInt("spark.shuffle.sort.bypassMergeThreshold", 200)
      dep.partitioner.numPartitions <= bypassMergeThreshold
    }
  }
} 

package org.apache.spark.shuffle.hash

import org.apache.spark.{InterruptibleIterator, TaskContext}
import org.apache.spark.serializer.Serializer
import org.apache.spark.shuffle.{BaseShuffleHandle, ShuffleReader}
import org.apache.spark.util.collection.ExternalSorter

private[spark] class HashShuffleReader[K, C](
    handle: BaseShuffleHandle[K, _, C],
    startPartition: Int,
    endPartition: Int,
    context: TaskContext)
  extends ShuffleReader[K, C]
{
  require(endPartition == startPartition + 1,
    "Hash shuffle currently only supports fetching one partition")

  private val dep = handle.dependency

  
  override def read(): Iterator[Product2[K, C]] = {
    val ser = Serializer.getSerializer(dep.serializer)
    val iter = BlockStoreShuffleFetcher.fetch(handle.shuffleId, startPartition, context, ser)

    val aggregatedIter: Iterator[Product2[K, C]] = if (dep.aggregator.isDefined) {
      if (dep.mapSideCombine) {
        new InterruptibleIterator(context, dep.aggregator.get.combineCombinersByKey(iter, context))
      } else {
        new InterruptibleIterator(context, dep.aggregator.get.combineValuesByKey(iter, context))
      }
    } else {
      require(!dep.mapSideCombine, "Map-side combine without Aggregator specified!")

      // Convert the Product2s to pairs since this is what downstream RDDs currently expect
      iter.asInstanceOf[Iterator[Product2[K, C]]].map(pair => (pair._1, pair._2))
    }

    // Sort the output if there is a sort ordering defined.
    dep.keyOrdering match {
      case Some(keyOrd: Ordering[K]) =>
        // Create an ExternalSorter to sort the data. Note that if spark.shuffle.spill is disabled,
        // the ExternalSorter won't spill to disk.
        val sorter = new ExternalSorter[K, C, C](ordering = Some(keyOrd), serializer = Some(ser))
        sorter.insertAll(aggregatedIter)
        context.taskMetrics.incMemoryBytesSpilled(sorter.memoryBytesSpilled)
        context.taskMetrics.incDiskBytesSpilled(sorter.diskBytesSpilled)
        sorter.iterator
      case None =>
        aggregatedIter
    }
  }
} 

package org.apache.spark.shuffle.sort

import org.apache.spark.{MapOutputTracker, SparkEnv, Logging, TaskContext}
import org.apache.spark.executor.ShuffleWriteMetrics
import org.apache.spark.scheduler.MapStatus
import org.apache.spark.shuffle.{IndexShuffleBlockResolver, ShuffleWriter, BaseShuffleHandle}
import org.apache.spark.storage.ShuffleBlockId
import org.apache.spark.util.collection.ExternalSorter

private[spark] class SortShuffleWriter[K, V, C](
    shuffleBlockResolver: IndexShuffleBlockResolver,
    handle: BaseShuffleHandle[K, V, C],
    mapId: Int,
    context: TaskContext)
  extends ShuffleWriter[K, V] with Logging {

  private val dep = handle.dependency

  private val blockManager = SparkEnv.get.blockManager

  private var sorter: ExternalSorter[K, V, _] = null

  // Are we in the process of stopping? Because map tasks can call stop() with success = true
  // and then call stop() with success = false if they get an exception, we want to make sure
  // we don't try deleting files, etc twice.
  private var stopping = false

  private var mapStatus: MapStatus = null

  private val writeMetrics = new ShuffleWriteMetrics()
  context.taskMetrics.shuffleWriteMetrics = Some(writeMetrics)

  
  override def stop(success: Boolean): Option[MapStatus] = {
    try {
      if (stopping) {
        return None
      }
      stopping = true
      if (success) {
        return Option(mapStatus)
      } else {
        // The map task failed, so delete our output data.
        shuffleBlockResolver.removeDataByMap(dep.shuffleId, mapId)
        return None
      }
    } finally {
      // Clean up our sorter, which may have its own intermediate files
      if (sorter != null) {
        val startTime = System.nanoTime()
        sorter.stop()
        context.taskMetrics.shuffleWriteMetrics.foreach(
          _.incShuffleWriteTime(System.nanoTime - startTime))
        sorter = null
      }
    }
  }
} 

package org.apache.spark.shuffle.sort

import org.apache.spark._
import org.apache.spark.internal.Logging
import org.apache.spark.scheduler.MapStatus
import org.apache.spark.shuffle.{BaseShuffleHandle, IndexShuffleBlockResolver, ShuffleWriter}
import org.apache.spark.storage.ShuffleBlockId
import org.apache.spark.util.Utils
import org.apache.spark.util.collection.ExternalSorter

private[spark] class SortShuffleWriter[K, V, C](
    shuffleBlockResolver: IndexShuffleBlockResolver,
    handle: BaseShuffleHandle[K, V, C],
    mapId: Int,
    context: TaskContext)
  extends ShuffleWriter[K, V] with Logging {

  private val dep = handle.dependency

  private val blockManager = SparkEnv.get.blockManager

  private var sorter: ExternalSorter[K, V, _] = null

  // Are we in the process of stopping? Because map tasks can call stop() with success = true
  // and then call stop() with success = false if they get an exception, we want to make sure
  // we don't try deleting files, etc twice.
  private var stopping = false

  private var mapStatus: MapStatus = null

  private val writeMetrics = context.taskMetrics().shuffleWriteMetrics

  
  override def stop(success: Boolean): Option[MapStatus] = {
    try {
      if (stopping) {
        return None
      }
      stopping = true
      if (success) {
        return Option(mapStatus)
      } else {
        return None
      }
    } finally {
      // Clean up our sorter, which may have its own intermediate files
      if (sorter != null) {
        val startTime = System.nanoTime()
        sorter.stop()
        writeMetrics.incWriteTime(System.nanoTime - startTime)
        sorter = null
      }
    }
  }
}

private[spark] object SortShuffleWriter {
  def shouldBypassMergeSort(conf: SparkConf, dep: ShuffleDependency[_, _, _]): Boolean = {
    // We cannot bypass sorting if we need to do map-side aggregation.
    if (dep.mapSideCombine) {
      require(dep.aggregator.isDefined, "Map-side combine without Aggregator specified!")
      false
    } else {
      val bypassMergeThreshold: Int = conf.getInt("spark.shuffle.sort.bypassMergeThreshold", 200)
      dep.partitioner.numPartitions <= bypassMergeThreshold
    }
  }
} 

package org.apache.spark.shuffle.sort

import org.apache.spark._
import org.apache.spark.executor.ShuffleWriteMetrics
import org.apache.spark.scheduler.MapStatus
import org.apache.spark.shuffle.{BaseShuffleHandle, IndexShuffleBlockResolver, ShuffleWriter}
import org.apache.spark.storage.ShuffleBlockId
import org.apache.spark.util.Utils
import org.apache.spark.util.collection.ExternalSorter

private[spark] class SortShuffleWriter[K, V, C](
    shuffleBlockResolver: IndexShuffleBlockResolver,
    handle: BaseShuffleHandle[K, V, C],
    mapId: Int,
    context: TaskContext)
  extends ShuffleWriter[K, V] with Logging {

  private val dep = handle.dependency

  private val blockManager = SparkEnv.get.blockManager

  private var sorter: ExternalSorter[K, V, _] = null

  // Are we in the process of stopping? Because map tasks can call stop() with success = true
  // and then call stop() with success = false if they get an exception, we want to make sure
  // we don't try deleting files, etc twice.
  private var stopping = false

  private var mapStatus: MapStatus = null

  private val writeMetrics = new ShuffleWriteMetrics()
  context.taskMetrics.shuffleWriteMetrics = Some(writeMetrics)

  
  override def stop(success: Boolean): Option[MapStatus] = {
    try {
      if (stopping) {
        return None
      }
      stopping = true
      if (success) {
        return Option(mapStatus)
      } else {
        // The map task failed, so delete our output data.
        shuffleBlockResolver.removeDataByMap(dep.shuffleId, mapId)
        return None
      }
    } finally {
      // Clean up our sorter, which may have its own intermediate files
      if (sorter != null) {
        val startTime = System.nanoTime()
        sorter.stop()
        context.taskMetrics.shuffleWriteMetrics.foreach(
          _.incShuffleWriteTime(System.nanoTime - startTime))
        sorter = null
      }
    }
  }
}

private[spark] object SortShuffleWriter {
  def shouldBypassMergeSort(conf: SparkConf, dep: ShuffleDependency[_, _, _]): Boolean = {
    // We cannot bypass sorting if we need to do map-side aggregation.
    if (dep.mapSideCombine) {
      require(dep.aggregator.isDefined, "Map-side combine without Aggregator specified!")
      false
    } else {
      val bypassMergeThreshold: Int = conf.getInt("spark.shuffle.sort.bypassMergeThreshold", 200)
      dep.partitioner.numPartitions <= bypassMergeThreshold
    }
  }
} 

package org.apache.spark.shuffle.crail

import org.apache.spark._
import org.apache.spark.common._
import org.apache.spark.serializer.{CrailSerializer, SerializerManager}
import org.apache.spark.shuffle.{CrailShuffleSorter, BaseShuffleHandle, ShuffleReader}
import org.apache.spark.storage._


class CrailShuffleReader[K, C](
    handle: BaseShuffleHandle[K, _, C],
    startPartition: Int,
    endPartition: Int,
    context: TaskContext,
    crailSorter: CrailShuffleSorter,
    serializerManager: SerializerManager = SparkEnv.get.serializerManager,
    blockManager: BlockManager = SparkEnv.get.blockManager,
    mapOutputTracker: MapOutputTracker = SparkEnv.get.mapOutputTracker)
  extends ShuffleReader[K, C] with Logging
{
  require(endPartition == startPartition + 1, "Crail shuffle currently only supports fetching one partition")

  private val dep = handle.dependency
  private val serializerInstance = CrailDispatcher.get.getCrailSerializer().newCrailSerializer(dep.serializer)

  
  override def read(): Iterator[Product2[K, C]] = {
    val multiStream = CrailDispatcher.get.getMultiStream(handle.shuffleId, startPartition, handle.numMaps)
    val deserializationStream = serializerInstance.deserializeCrailStream(multiStream)
    dep.keyOrdering match {
      case Some(keyOrd: Ordering[K]) =>
        new CrailInputCloser(deserializationStream, crailSorter.sort(context, keyOrd, dep.serializer, deserializationStream))
      case None =>
        new CrailInputCloser(deserializationStream, deserializationStream.asKeyValueIterator.asInstanceOf[Iterator[Product2[K, C]]])
      }
  }
}