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
141
142
143
144
145
146
147
148
149
|
/*
* 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.serializer
import java.io.{BufferedInputStream, BufferedOutputStream, InputStream, OutputStream}
import java.nio.ByteBuffer
import scala.reflect.ClassTag
import org.apache.spark.SparkConf
import org.apache.spark.io.CompressionCodec
import org.apache.spark.storage._
import org.apache.spark.util.io.{ChunkedByteBuffer, ChunkedByteBufferOutputStream}
/**
* Component which configures serialization and compression for various Spark components, including
* automatic selection of which [[Serializer]] to use for shuffles.
*/
private[spark] class SerializerManager(defaultSerializer: Serializer, conf: SparkConf) {
private[this] val kryoSerializer = new KryoSerializer(conf)
private[this] val stringClassTag: ClassTag[String] = implicitly[ClassTag[String]]
private[this] val primitiveAndPrimitiveArrayClassTags: Set[ClassTag[_]] = {
val primitiveClassTags = Set[ClassTag[_]](
ClassTag.Boolean,
ClassTag.Byte,
ClassTag.Char,
ClassTag.Double,
ClassTag.Float,
ClassTag.Int,
ClassTag.Long,
ClassTag.Null,
ClassTag.Short
)
val arrayClassTags = primitiveClassTags.map(_.wrap)
primitiveClassTags ++ arrayClassTags
}
// Whether to compress broadcast variables that are stored
private[this] val compressBroadcast = conf.getBoolean("spark.broadcast.compress", true)
// Whether to compress shuffle output that are stored
private[this] val compressShuffle = conf.getBoolean("spark.shuffle.compress", true)
// Whether to compress RDD partitions that are stored serialized
private[this] val compressRdds = conf.getBoolean("spark.rdd.compress", false)
// Whether to compress shuffle output temporarily spilled to disk
private[this] val compressShuffleSpill = conf.getBoolean("spark.shuffle.spill.compress", true)
/* The compression codec to use. Note that the "lazy" val is necessary because we want to delay
* the initialization of the compression codec until it is first used. The reason is that a Spark
* program could be using a user-defined codec in a third party jar, which is loaded in
* Executor.updateDependencies. When the BlockManager is initialized, user level jars hasn't been
* loaded yet. */
private lazy val compressionCodec: CompressionCodec = CompressionCodec.createCodec(conf)
private def canUseKryo(ct: ClassTag[_]): Boolean = {
primitiveAndPrimitiveArrayClassTags.contains(ct) || ct == stringClassTag
}
def getSerializer(ct: ClassTag[_]): Serializer = {
if (canUseKryo(ct)) {
kryoSerializer
} else {
defaultSerializer
}
}
/**
* Pick the best serializer for shuffling an RDD of key-value pairs.
*/
def getSerializer(keyClassTag: ClassTag[_], valueClassTag: ClassTag[_]): Serializer = {
if (canUseKryo(keyClassTag) && canUseKryo(valueClassTag)) {
kryoSerializer
} else {
defaultSerializer
}
}
private def shouldCompress(blockId: BlockId): Boolean = {
blockId match {
case _: ShuffleBlockId => compressShuffle
case _: BroadcastBlockId => compressBroadcast
case _: RDDBlockId => compressRdds
case _: TempLocalBlockId => compressShuffleSpill
case _: TempShuffleBlockId => compressShuffle
case _ => false
}
}
/**
* Wrap an output stream for compression if block compression is enabled for its block type
*/
def wrapForCompression(blockId: BlockId, s: OutputStream): OutputStream = {
if (shouldCompress(blockId)) compressionCodec.compressedOutputStream(s) else s
}
/**
* Wrap an input stream for compression if block compression is enabled for its block type
*/
def wrapForCompression(blockId: BlockId, s: InputStream): InputStream = {
if (shouldCompress(blockId)) compressionCodec.compressedInputStream(s) else s
}
/** Serializes into a stream. */
def dataSerializeStream[T: ClassTag](
blockId: BlockId,
outputStream: OutputStream,
values: Iterator[T]): Unit = {
val byteStream = new BufferedOutputStream(outputStream)
val ser = getSerializer(implicitly[ClassTag[T]]).newInstance()
ser.serializeStream(wrapForCompression(blockId, byteStream)).writeAll(values).close()
}
/** Serializes into a chunked byte buffer. */
def dataSerialize[T: ClassTag](blockId: BlockId, values: Iterator[T]): ChunkedByteBuffer = {
val bbos = new ChunkedByteBufferOutputStream(1024 * 1024 * 4, ByteBuffer.allocate)
dataSerializeStream(blockId, bbos, values)
bbos.toChunkedByteBuffer
}
/**
* Deserializes a InputStream into an iterator of values and disposes of it when the end of
* the iterator is reached.
*/
def dataDeserializeStream[T: ClassTag](
blockId: BlockId,
inputStream: InputStream): Iterator[T] = {
val stream = new BufferedInputStream(inputStream)
getSerializer(implicitly[ClassTag[T]])
.newInstance()
.deserializeStream(wrapForCompression(blockId, stream))
.asIterator.asInstanceOf[Iterator[T]]
}
}
|
