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
93
94
95
96
97
98
99
100
101
102
103
104
105
106
|
/*
* 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
override def hashCode(): 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 serializer: 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.serializer = 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[_]] = {
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 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]]
SparkEnv.get.shuffleManager.getReader(dep.shuffleHandle, split.index, split.index + 1, context)
.read()
.asInstanceOf[Iterator[(K, C)]]
}
override def clearDependencies() {
super.clearDependencies()
prev = null
}
}
|