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
|
/*
* 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 org.apache.spark.annotation.DeveloperApi
import org.apache.spark.util.collection.{AppendOnlyMap, ExternalAppendOnlyMap}
/**
* :: DeveloperApi ::
* A set of functions used to aggregate data.
*
* @param createCombiner function to create the initial value of the aggregation.
* @param mergeValue function to merge a new value into the aggregation result.
* @param mergeCombiners function to merge outputs from multiple mergeValue function.
*/
@DeveloperApi
case class Aggregator[K, V, C] (
createCombiner: V => C,
mergeValue: (C, V) => C,
mergeCombiners: (C, C) => C) {
// When spilling is enabled sorting will happen externally, but not necessarily with an
// ExternalSorter.
private val isSpillEnabled = SparkEnv.get.conf.getBoolean("spark.shuffle.spill", true)
@deprecated("use combineValuesByKey with TaskContext argument", "0.9.0")
def combineValuesByKey(iter: Iterator[_ <: Product2[K, V]]): Iterator[(K, C)] =
combineValuesByKey(iter, null)
def combineValuesByKey(iter: Iterator[_ <: Product2[K, V]],
context: TaskContext): Iterator[(K, C)] = {
if (!isSpillEnabled) {
val combiners = new AppendOnlyMap[K, C]
var kv: Product2[K, V] = null
val update = (hadValue: Boolean, oldValue: C) => {
if (hadValue) mergeValue(oldValue, kv._2) else createCombiner(kv._2)
}
while (iter.hasNext) {
kv = iter.next()
combiners.changeValue(kv._1, update)
}
combiners.iterator
} else {
val combiners = new ExternalAppendOnlyMap[K, V, C](createCombiner, mergeValue, mergeCombiners)
combiners.insertAll(iter)
// Update task metrics if context is not null
// TODO: Make context non optional in a future release
Option(context).foreach { c =>
c.taskMetrics.incMemoryBytesSpilled(combiners.memoryBytesSpilled)
c.taskMetrics.incDiskBytesSpilled(combiners.diskBytesSpilled)
}
combiners.iterator
}
}
@deprecated("use combineCombinersByKey with TaskContext argument", "0.9.0")
def combineCombinersByKey(iter: Iterator[_ <: Product2[K, C]]) : Iterator[(K, C)] =
combineCombinersByKey(iter, null)
def combineCombinersByKey(iter: Iterator[_ <: Product2[K, C]], context: TaskContext)
: Iterator[(K, C)] =
{
if (!isSpillEnabled) {
val combiners = new AppendOnlyMap[K, C]
var kc: Product2[K, C] = null
val update = (hadValue: Boolean, oldValue: C) => {
if (hadValue) mergeCombiners(oldValue, kc._2) else kc._2
}
while (iter.hasNext) {
kc = iter.next()
combiners.changeValue(kc._1, update)
}
combiners.iterator
} else {
val combiners = new ExternalAppendOnlyMap[K, C, C](identity, mergeCombiners, mergeCombiners)
combiners.insertAll(iter)
// Update task metrics if context is not null
// TODO: Make context non-optional in a future release
Option(context).foreach { c =>
c.taskMetrics.incMemoryBytesSpilled(combiners.memoryBytesSpilled)
c.taskMetrics.incDiskBytesSpilled(combiners.diskBytesSpilled)
}
combiners.iterator
}
}
}
|