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
|
/*
* 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.hash
import java.io.IOException
import org.apache.spark._
import org.apache.spark.internal.Logging
import org.apache.spark.scheduler.MapStatus
import org.apache.spark.shuffle._
import org.apache.spark.storage.DiskBlockObjectWriter
private[spark] class HashShuffleWriter[K, V](
shuffleBlockResolver: FileShuffleBlockResolver,
handle: BaseShuffleHandle[K, V, _],
mapId: Int,
context: TaskContext)
extends ShuffleWriter[K, V] with Logging {
private val dep = handle.dependency
private val numOutputSplits = dep.partitioner.numPartitions
private val metrics = context.taskMetrics
// Are we in the process of stopping? Because map tasks can call stop() with success = true
// and then call stop() with success = false if they get an exception, we want to make sure
// we don't try deleting files, etc twice.
private var stopping = false
private val writeMetrics = metrics.registerShuffleWriteMetrics()
private val blockManager = SparkEnv.get.blockManager
private val shuffle = shuffleBlockResolver.forMapTask(dep.shuffleId, mapId, numOutputSplits,
dep.serializer, writeMetrics)
/** Write a bunch of records to this task's output */
override def write(records: Iterator[Product2[K, V]]): Unit = {
val iter = if (dep.aggregator.isDefined) {
if (dep.mapSideCombine) {
dep.aggregator.get.combineValuesByKey(records, context)
} else {
records
}
} else {
require(!dep.mapSideCombine, "Map-side combine without Aggregator specified!")
records
}
for (elem <- iter) {
val bucketId = dep.partitioner.getPartition(elem._1)
shuffle.writers(bucketId).write(elem._1, elem._2)
}
}
/** Close this writer, passing along whether the map completed */
override def stop(initiallySuccess: Boolean): Option[MapStatus] = {
var success = initiallySuccess
try {
if (stopping) {
return None
}
stopping = true
if (success) {
try {
Some(commitWritesAndBuildStatus())
} catch {
case e: Exception =>
success = false
revertWrites()
throw e
}
} else {
revertWrites()
None
}
} finally {
// Release the writers back to the shuffle block manager.
if (shuffle != null && shuffle.writers != null) {
try {
shuffle.releaseWriters(success)
} catch {
case e: Exception => logError("Failed to release shuffle writers", e)
}
}
}
}
private def commitWritesAndBuildStatus(): MapStatus = {
// Commit the writes. Get the size of each bucket block (total block size).
val sizes: Array[Long] = shuffle.writers.map { writer: DiskBlockObjectWriter =>
writer.commitAndClose()
writer.fileSegment().length
}
// rename all shuffle files to final paths
// Note: there is only one ShuffleBlockResolver in executor
shuffleBlockResolver.synchronized {
shuffle.writers.zipWithIndex.foreach { case (writer, i) =>
val output = blockManager.diskBlockManager.getFile(writer.blockId)
if (sizes(i) > 0) {
if (output.exists()) {
// Use length of existing file and delete our own temporary one
sizes(i) = output.length()
writer.file.delete()
} else {
// Commit by renaming our temporary file to something the fetcher expects
if (!writer.file.renameTo(output)) {
throw new IOException(s"fail to rename ${writer.file} to $output")
}
}
} else {
if (output.exists()) {
output.delete()
}
}
}
}
MapStatus(blockManager.shuffleServerId, sizes)
}
private def revertWrites(): Unit = {
if (shuffle != null && shuffle.writers != null) {
for (writer <- shuffle.writers) {
writer.revertPartialWritesAndClose()
}
}
}
}
|
