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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
|
/*
* 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.shuffle
import java.io._
import com.google.common.io.ByteStreams
import org.apache.spark.network.buffer.{FileSegmentManagedBuffer, ManagedBuffer}
import org.apache.spark.network.netty.SparkTransportConf
import org.apache.spark.shuffle.IndexShuffleBlockResolver.NOOP_REDUCE_ID
import org.apache.spark.storage._
import org.apache.spark.util.Utils
import org.apache.spark.{SparkEnv, Logging, SparkConf}
/**
* Create and maintain the shuffle blocks' mapping between logic block and physical file location.
* Data of shuffle blocks from the same map task are stored in a single consolidated data file.
* The offsets of the data blocks in the data file are stored in a separate index file.
*
* We use the name of the shuffle data's shuffleBlockId with reduce ID set to 0 and add ".data"
* as the filename postfix for data file, and ".index" as the filename postfix for index file.
*
*/
// Note: Changes to the format in this file should be kept in sync with
// org.apache.spark.network.shuffle.ExternalShuffleBlockResolver#getSortBasedShuffleBlockData().
private[spark] class IndexShuffleBlockResolver(
conf: SparkConf,
_blockManager: BlockManager = null)
extends ShuffleBlockResolver
with Logging {
private lazy val blockManager = Option(_blockManager).getOrElse(SparkEnv.get.blockManager)
private val transportConf = SparkTransportConf.fromSparkConf(conf)
def getDataFile(shuffleId: Int, mapId: Int): File = {
blockManager.diskBlockManager.getFile(ShuffleDataBlockId(shuffleId, mapId, NOOP_REDUCE_ID))
}
private def getIndexFile(shuffleId: Int, mapId: Int): File = {
blockManager.diskBlockManager.getFile(ShuffleIndexBlockId(shuffleId, mapId, NOOP_REDUCE_ID))
}
/**
* Remove data file and index file that contain the output data from one map.
* */
def removeDataByMap(shuffleId: Int, mapId: Int): Unit = {
var file = getDataFile(shuffleId, mapId)
if (file.exists()) {
if (!file.delete()) {
logWarning(s"Error deleting data ${file.getPath()}")
}
}
file = getIndexFile(shuffleId, mapId)
if (file.exists()) {
if (!file.delete()) {
logWarning(s"Error deleting index ${file.getPath()}")
}
}
}
/**
* Check whether the given index and data files match each other.
* If so, return the partition lengths in the data file. Otherwise return null.
*/
private def checkIndexAndDataFile(index: File, data: File, blocks: Int): Array[Long] = {
// the index file should have `block + 1` longs as offset.
if (index.length() != (blocks + 1) * 8) {
return null
}
val lengths = new Array[Long](blocks)
// Read the lengths of blocks
val in = try {
new DataInputStream(new BufferedInputStream(new FileInputStream(index)))
} catch {
case e: IOException =>
return null
}
try {
// Convert the offsets into lengths of each block
var offset = in.readLong()
if (offset != 0L) {
return null
}
var i = 0
while (i < blocks) {
val off = in.readLong()
lengths(i) = off - offset
offset = off
i += 1
}
} catch {
case e: IOException =>
return null
} finally {
in.close()
}
// the size of data file should match with index file
if (data.length() == lengths.sum) {
lengths
} else {
null
}
}
/**
* Write an index file with the offsets of each block, plus a final offset at the end for the
* end of the output file. This will be used by getBlockData to figure out where each block
* begins and ends.
*
* It will commit the data and index file as an atomic operation, use the existing ones, or
* replace them with new ones.
*
* Note: the `lengths` will be updated to match the existing index file if use the existing ones.
* */
def writeIndexFileAndCommit(
shuffleId: Int,
mapId: Int,
lengths: Array[Long],
dataTmp: File): Unit = {
val indexFile = getIndexFile(shuffleId, mapId)
val indexTmp = Utils.tempFileWith(indexFile)
val out = new DataOutputStream(new BufferedOutputStream(new FileOutputStream(indexTmp)))
Utils.tryWithSafeFinally {
// We take in lengths of each block, need to convert it to offsets.
var offset = 0L
out.writeLong(offset)
for (length <- lengths) {
offset += length
out.writeLong(offset)
}
} {
out.close()
}
val dataFile = getDataFile(shuffleId, mapId)
// There is only one IndexShuffleBlockResolver per executor, this synchronization make sure
// the following check and rename are atomic.
synchronized {
val existingLengths = checkIndexAndDataFile(indexFile, dataFile, lengths.length)
if (existingLengths != null) {
// Another attempt for the same task has already written our map outputs successfully,
// so just use the existing partition lengths and delete our temporary map outputs.
System.arraycopy(existingLengths, 0, lengths, 0, lengths.length)
if (dataTmp != null && dataTmp.exists()) {
dataTmp.delete()
}
indexTmp.delete()
} else {
// This is the first successful attempt in writing the map outputs for this task,
// so override any existing index and data files with the ones we wrote.
if (indexFile.exists()) {
indexFile.delete()
}
if (dataFile.exists()) {
dataFile.delete()
}
if (!indexTmp.renameTo(indexFile)) {
throw new IOException("fail to rename file " + indexTmp + " to " + indexFile)
}
if (dataTmp != null && dataTmp.exists() && !dataTmp.renameTo(dataFile)) {
throw new IOException("fail to rename file " + dataTmp + " to " + dataFile)
}
}
}
}
override def getBlockData(blockId: ShuffleBlockId): ManagedBuffer = {
// The block is actually going to be a range of a single map output file for this map, so
// find out the consolidated file, then the offset within that from our index
val indexFile = getIndexFile(blockId.shuffleId, blockId.mapId)
val in = new DataInputStream(new FileInputStream(indexFile))
try {
ByteStreams.skipFully(in, blockId.reduceId * 8)
val offset = in.readLong()
val nextOffset = in.readLong()
new FileSegmentManagedBuffer(
transportConf,
getDataFile(blockId.shuffleId, blockId.mapId),
offset,
nextOffset - offset)
} finally {
in.close()
}
}
override def stop(): Unit = {}
}
private[spark] object IndexShuffleBlockResolver {
// No-op reduce ID used in interactions with disk store.
// The disk store currently expects puts to relate to a (map, reduce) pair, but in the sort
// shuffle outputs for several reduces are glommed into a single file.
val NOOP_REDUCE_ID = 0
}
|
