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
|
/*
* 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.{NarrowDependency, SparkEnv, Partition, TaskContext}
class PartitionPruningRDDPartition(idx: Int, val parentSplit: Partition) extends Partition {
override val index = idx
}
/**
* Represents a dependency between the PartitionPruningRDD and its parent. In this
* case, the child RDD contains a subset of partitions of the parents'.
*/
class PruneDependency[T](rdd: RDD[T], @transient partitionFilterFunc: Int => Boolean)
extends NarrowDependency[T](rdd) {
@transient
val partitions: Array[Partition] = rdd.partitions
.filter(s => partitionFilterFunc(s.index)).zipWithIndex
.map { case(split, idx) => new PartitionPruningRDDPartition(idx, split) : Partition }
override def getParents(partitionId: Int) = {
List(partitions(partitionId).asInstanceOf[PartitionPruningRDDPartition].parentSplit.index)
}
}
/**
* A RDD used to prune RDD partitions/partitions so we can avoid launching tasks on
* all partitions. An example use case: If we know the RDD is partitioned by range,
* and the execution DAG has a filter on the key, we can avoid launching tasks
* on partitions that don't have the range covering the key.
*/
class PartitionPruningRDD[T: ClassTag](
@transient prev: RDD[T],
@transient partitionFilterFunc: Int => Boolean)
extends RDD[T](prev.context, List(new PruneDependency(prev, partitionFilterFunc))) {
override def compute(split: Partition, context: TaskContext) = firstParent[T].iterator(
split.asInstanceOf[PartitionPruningRDDPartition].parentSplit, context)
override protected def getPartitions: Array[Partition] =
getDependencies.head.asInstanceOf[PruneDependency[T]].partitions
}
object PartitionPruningRDD {
/**
* Create a PartitionPruningRDD. This function can be used to create the PartitionPruningRDD
* when its type T is not known at compile time.
*/
def create[T](rdd: RDD[T], partitionFilterFunc: Int => Boolean) = {
new PartitionPruningRDD[T](rdd, partitionFilterFunc)(rdd.elementClassTag)
}
}
|