1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
|
/*
* 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.scheduler
import java.nio.ByteBuffer
import scala.language.existentials
import org.apache.spark._
import org.apache.spark.broadcast.Broadcast
import org.apache.spark.rdd.RDD
import org.apache.spark.shuffle.ShuffleWriter
/**
* A ShuffleMapTask divides the elements of an RDD into multiple buckets (based on a partitioner
* specified in the ShuffleDependency).
*
* See [[org.apache.spark.scheduler.Task]] for more information.
*
* @param stageId id of the stage this task belongs to
* @param taskBinary broadcast version of the RDD and the ShuffleDependency. Once deserialized,
* the type should be (RDD[_], ShuffleDependency[_, _, _]).
* @param partition partition of the RDD this task is associated with
* @param locs preferred task execution locations for locality scheduling
*/
private[spark] class ShuffleMapTask(
stageId: Int,
stageAttemptId: Int,
taskBinary: Broadcast[Array[Byte]],
partition: Partition,
@transient private var locs: Seq[TaskLocation],
internalAccumulators: Seq[Accumulator[Long]])
extends Task[MapStatus](stageId, stageAttemptId, partition.index, internalAccumulators)
with Logging {
/** A constructor used only in test suites. This does not require passing in an RDD. */
def this(partitionId: Int) {
this(0, 0, null, new Partition { override def index: Int = 0 }, null, null)
}
@transient private val preferredLocs: Seq[TaskLocation] = {
if (locs == null) Nil else locs.toSet.toSeq
}
override def runTask(context: TaskContext): MapStatus = {
// Deserialize the RDD using the broadcast variable.
val deserializeStartTime = System.currentTimeMillis()
val ser = SparkEnv.get.closureSerializer.newInstance()
val (rdd, dep) = ser.deserialize[(RDD[_], ShuffleDependency[_, _, _])](
ByteBuffer.wrap(taskBinary.value), Thread.currentThread.getContextClassLoader)
_executorDeserializeTime = System.currentTimeMillis() - deserializeStartTime
metrics = Some(context.taskMetrics)
var writer: ShuffleWriter[Any, Any] = null
try {
val manager = SparkEnv.get.shuffleManager
writer = manager.getWriter[Any, Any](dep.shuffleHandle, partitionId, context)
writer.write(rdd.iterator(partition, context).asInstanceOf[Iterator[_ <: Product2[Any, Any]]])
writer.stop(success = true).get
} catch {
case e: Exception =>
try {
if (writer != null) {
writer.stop(success = false)
}
} catch {
case e: Exception =>
log.debug("Could not stop writer", e)
}
throw e
}
}
override def preferredLocations: Seq[TaskLocation] = preferredLocs
override def toString: String = "ShuffleMapTask(%d, %d)".format(stageId, partitionId)
}
|