Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance. Project price only 1 $
You can buy this project and download/modify it how often you want.
/*
* 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.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
/** Write a bunch of records to this task's output */
override def write(records: Iterator[Product2[K, V]]): Unit = {
sorter = if (dep.mapSideCombine) {
new ExternalSorter[K, V, C](
context, dep.aggregator, Some(dep.partitioner), dep.keyOrdering, dep.serializer)
} else {
// In this case we pass neither an aggregator nor an ordering to the sorter, because we don't
// care whether the keys get sorted in each partition; that will be done on the reduce side
// if the operation being run is sortByKey.
new ExternalSorter[K, V, V](
context, aggregator = None, Some(dep.partitioner), ordering = None, dep.serializer)
}
sorter.insertAll(records)
// Don't bother including the time to open the merged output file in the shuffle write time,
// because it just opens a single file, so is typically too fast to measure accurately
// (see SPARK-3570).
val output = shuffleBlockResolver.getDataFile(dep.shuffleId, mapId)
val tmp = Utils.tempFileWith(output)
try {
val blockId = ShuffleBlockId(dep.shuffleId, mapId, IndexShuffleBlockResolver.NOOP_REDUCE_ID)
val partitionLengths = sorter.writePartitionedFile(blockId, tmp)
shuffleBlockResolver.writeIndexFileAndCommit(dep.shuffleId, mapId, partitionLengths, tmp)
mapStatus = MapStatus(blockManager.shuffleServerId, partitionLengths)
} finally {
if (tmp.exists() && !tmp.delete()) {
logError(s"Error while deleting temp file ${tmp.getAbsolutePath}")
}
}
}
/** Close this writer, passing along whether the map completed */
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) {
false
} else {
val bypassMergeThreshold: Int = conf.getInt("spark.shuffle.sort.bypassMergeThreshold", 200)
dep.partitioner.numPartitions <= bypassMergeThreshold
}
}
}
