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
|
/*
* 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 spark.rdd
import java.io.{ObjectOutputStream, IOException}
import spark._
private[spark]
class CartesianPartition(
idx: Int,
@transient rdd1: RDD[_],
@transient rdd2: RDD[_],
s1Index: Int,
s2Index: Int
) extends Partition {
var s1 = rdd1.partitions(s1Index)
var s2 = rdd2.partitions(s2Index)
override val index: Int = idx
@throws(classOf[IOException])
private def writeObject(oos: ObjectOutputStream) {
// Update the reference to parent split at the time of task serialization
s1 = rdd1.partitions(s1Index)
s2 = rdd2.partitions(s2Index)
oos.defaultWriteObject()
}
}
private[spark]
class CartesianRDD[T: ClassManifest, U:ClassManifest](
sc: SparkContext,
var rdd1 : RDD[T],
var rdd2 : RDD[U])
extends RDD[Pair[T, U]](sc, Nil)
with Serializable {
val numPartitionsInRdd2 = rdd2.partitions.size
override def getPartitions: Array[Partition] = {
// create the cross product split
val array = new Array[Partition](rdd1.partitions.size * rdd2.partitions.size)
for (s1 <- rdd1.partitions; s2 <- rdd2.partitions) {
val idx = s1.index * numPartitionsInRdd2 + s2.index
array(idx) = new CartesianPartition(idx, rdd1, rdd2, s1.index, s2.index)
}
array
}
override def getPreferredLocations(split: Partition): Seq[String] = {
val currSplit = split.asInstanceOf[CartesianPartition]
rdd1.preferredLocations(currSplit.s1) ++ rdd2.preferredLocations(currSplit.s2)
}
override def compute(split: Partition, context: TaskContext) = {
val currSplit = split.asInstanceOf[CartesianPartition]
for (x <- rdd1.iterator(currSplit.s1, context);
y <- rdd2.iterator(currSplit.s2, context)) yield (x, y)
}
override def getDependencies: Seq[Dependency[_]] = List(
new NarrowDependency(rdd1) {
def getParents(id: Int): Seq[Int] = List(id / numPartitionsInRdd2)
},
new NarrowDependency(rdd2) {
def getParents(id: Int): Seq[Int] = List(id % numPartitionsInRdd2)
}
)
override def clearDependencies() {
super.clearDependencies()
rdd1 = null
rdd2 = null
}
}
|