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
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
|
/*
* 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
import scala.reflect.ClassTag
import org.apache.spark.rdd.RDD
import org.apache.spark.util.Utils
/**
* An object that defines how the elements in a key-value pair RDD are partitioned by key.
* Maps each key to a partition ID, from 0 to `numPartitions - 1`.
*/
abstract class Partitioner extends Serializable {
def numPartitions: Int
def getPartition(key: Any): Int
}
object Partitioner {
/**
* Choose a partitioner to use for a cogroup-like operation between a number of RDDs.
*
* If any of the RDDs already has a partitioner, choose that one.
*
* Otherwise, we use a default HashPartitioner. For the number of partitions, if
* spark.default.parallelism is set, then we'll use the value from SparkContext
* defaultParallelism, otherwise we'll use the max number of upstream partitions.
*
* Unless spark.default.parallelism is set, He number of partitions will be the
* same as the number of partitions in the largest upstream RDD, as this should
* be least likely to cause out-of-memory errors.
*
* We use two method parameters (rdd, others) to enforce callers passing at least 1 RDD.
*/
def defaultPartitioner(rdd: RDD[_], others: RDD[_]*): Partitioner = {
val bySize = (Seq(rdd) ++ others).sortBy(_.partitions.size).reverse
for (r <- bySize if r.partitioner != None) {
return r.partitioner.get
}
if (rdd.context.conf.contains("spark.default.parallelism")) {
return new HashPartitioner(rdd.context.defaultParallelism)
} else {
return new HashPartitioner(bySize.head.partitions.size)
}
}
}
/**
* A [[org.apache.spark.Partitioner]] that implements hash-based partitioning using Java's `Object.hashCode`.
*
* Java arrays have hashCodes that are based on the arrays' identities rather than their contents,
* so attempting to partition an RDD[Array[_]] or RDD[(Array[_], _)] using a HashPartitioner will
* produce an unexpected or incorrect result.
*/
class HashPartitioner(partitions: Int) extends Partitioner {
def numPartitions = partitions
def getPartition(key: Any): Int = key match {
case null => 0
case _ => Utils.nonNegativeMod(key.hashCode, numPartitions)
}
override def equals(other: Any): Boolean = other match {
case h: HashPartitioner =>
h.numPartitions == numPartitions
case _ =>
false
}
}
/**
* A [[org.apache.spark.Partitioner]] that partitions sortable records by range into roughly equal ranges.
* Determines the ranges by sampling the RDD passed in.
*/
class RangePartitioner[K <% Ordered[K]: ClassTag, V](
partitions: Int,
@transient rdd: RDD[_ <: Product2[K,V]],
private val ascending: Boolean = true)
extends Partitioner {
// An array of upper bounds for the first (partitions - 1) partitions
private val rangeBounds: Array[K] = {
if (partitions == 1) {
Array()
} else {
val rddSize = rdd.count()
val maxSampleSize = partitions * 20.0
val frac = math.min(maxSampleSize / math.max(rddSize, 1), 1.0)
val rddSample = rdd.sample(false, frac, 1).map(_._1).collect().sortWith(_ < _)
if (rddSample.length == 0) {
Array()
} else {
val bounds = new Array[K](partitions - 1)
for (i <- 0 until partitions - 1) {
val index = (rddSample.length - 1) * (i + 1) / partitions
bounds(i) = rddSample(index)
}
bounds
}
}
}
def numPartitions = partitions
def getPartition(key: Any): Int = {
// TODO: Use a binary search here if number of partitions is large
val k = key.asInstanceOf[K]
var partition = 0
while (partition < rangeBounds.length && k > rangeBounds(partition)) {
partition += 1
}
if (ascending) {
partition
} else {
rangeBounds.length - partition
}
}
override def equals(other: Any): Boolean = other match {
case r: RangePartitioner[_,_] =>
r.rangeBounds.sameElements(rangeBounds) && r.ascending == ascending
case _ =>
false
}
}
|