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
|
/*
* 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.deploy
import java.lang.reflect.Method
import java.security.PrivilegedExceptionAction
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.{FileSystem, Path}
import org.apache.hadoop.fs.FileSystem.Statistics
import org.apache.hadoop.mapred.JobConf
import org.apache.hadoop.security.Credentials
import org.apache.hadoop.security.UserGroupInformation
import org.apache.spark.{Logging, SparkContext, SparkConf, SparkException}
import org.apache.spark.annotation.DeveloperApi
import org.apache.spark.util.Utils
import scala.collection.JavaConversions._
/**
* :: DeveloperApi ::
* Contains util methods to interact with Hadoop from Spark.
*/
@DeveloperApi
class SparkHadoopUtil extends Logging {
val conf: Configuration = newConfiguration(new SparkConf())
UserGroupInformation.setConfiguration(conf)
/**
* Runs the given function with a Hadoop UserGroupInformation as a thread local variable
* (distributed to child threads), used for authenticating HDFS and YARN calls.
*
* IMPORTANT NOTE: If this function is going to be called repeated in the same process
* you need to look https://issues.apache.org/jira/browse/HDFS-3545 and possibly
* do a FileSystem.closeAllForUGI in order to avoid leaking Filesystems
*/
def runAsSparkUser(func: () => Unit) {
val user = Option(System.getenv("SPARK_USER")).getOrElse(SparkContext.SPARK_UNKNOWN_USER)
if (user != SparkContext.SPARK_UNKNOWN_USER) {
logDebug("running as user: " + user)
val ugi = UserGroupInformation.createRemoteUser(user)
transferCredentials(UserGroupInformation.getCurrentUser(), ugi)
ugi.doAs(new PrivilegedExceptionAction[Unit] {
def run: Unit = func()
})
} else {
logDebug("running as SPARK_UNKNOWN_USER")
func()
}
}
def transferCredentials(source: UserGroupInformation, dest: UserGroupInformation) {
for (token <- source.getTokens()) {
dest.addToken(token)
}
}
@Deprecated
def newConfiguration(): Configuration = newConfiguration(null)
/**
* Return an appropriate (subclass) of Configuration. Creating config can initializes some Hadoop
* subsystems.
*/
def newConfiguration(conf: SparkConf): Configuration = {
val hadoopConf = new Configuration()
// Note: this null check is around more than just access to the "conf" object to maintain
// the behavior of the old implementation of this code, for backwards compatibility.
if (conf != null) {
// Explicitly check for S3 environment variables
if (System.getenv("AWS_ACCESS_KEY_ID") != null &&
System.getenv("AWS_SECRET_ACCESS_KEY") != null) {
hadoopConf.set("fs.s3.awsAccessKeyId", System.getenv("AWS_ACCESS_KEY_ID"))
hadoopConf.set("fs.s3n.awsAccessKeyId", System.getenv("AWS_ACCESS_KEY_ID"))
hadoopConf.set("fs.s3.awsSecretAccessKey", System.getenv("AWS_SECRET_ACCESS_KEY"))
hadoopConf.set("fs.s3n.awsSecretAccessKey", System.getenv("AWS_SECRET_ACCESS_KEY"))
}
// Copy any "spark.hadoop.foo=bar" system properties into conf as "foo=bar"
conf.getAll.foreach { case (key, value) =>
if (key.startsWith("spark.hadoop.")) {
hadoopConf.set(key.substring("spark.hadoop.".length), value)
}
}
val bufferSize = conf.get("spark.buffer.size", "65536")
hadoopConf.set("io.file.buffer.size", bufferSize)
}
hadoopConf
}
/**
* Add any user credentials to the job conf which are necessary for running on a secure Hadoop
* cluster.
*/
def addCredentials(conf: JobConf) {}
def isYarnMode(): Boolean = { false }
def getCurrentUserCredentials(): Credentials = { null }
def addCurrentUserCredentials(creds: Credentials) {}
def addSecretKeyToUserCredentials(key: String, secret: String) {}
def getSecretKeyFromUserCredentials(key: String): Array[Byte] = { null }
def loginUserFromKeytab(principalName: String, keytabFilename: String) {
UserGroupInformation.loginUserFromKeytab(principalName, keytabFilename)
}
/**
* Returns a function that can be called to find Hadoop FileSystem bytes read. If
* getFSBytesReadOnThreadCallback is called from thread r at time t, the returned callback will
* return the bytes read on r since t. Reflection is required because thread-level FileSystem
* statistics are only available as of Hadoop 2.5 (see HADOOP-10688).
* Returns None if the required method can't be found.
*/
private[spark] def getFSBytesReadOnThreadCallback(path: Path, conf: Configuration)
: Option[() => Long] = {
try {
val threadStats = getFileSystemThreadStatistics(path, conf)
val getBytesReadMethod = getFileSystemThreadStatisticsMethod("getBytesRead")
val f = () => threadStats.map(getBytesReadMethod.invoke(_).asInstanceOf[Long]).sum
val baselineBytesRead = f()
Some(() => f() - baselineBytesRead)
} catch {
case e: NoSuchMethodException => {
logDebug("Couldn't find method for retrieving thread-level FileSystem input data", e)
None
}
}
}
/**
* Returns a function that can be called to find Hadoop FileSystem bytes written. If
* getFSBytesWrittenOnThreadCallback is called from thread r at time t, the returned callback will
* return the bytes written on r since t. Reflection is required because thread-level FileSystem
* statistics are only available as of Hadoop 2.5 (see HADOOP-10688).
* Returns None if the required method can't be found.
*/
private[spark] def getFSBytesWrittenOnThreadCallback(path: Path, conf: Configuration)
: Option[() => Long] = {
try {
val threadStats = getFileSystemThreadStatistics(path, conf)
val getBytesWrittenMethod = getFileSystemThreadStatisticsMethod("getBytesWritten")
val f = () => threadStats.map(getBytesWrittenMethod.invoke(_).asInstanceOf[Long]).sum
val baselineBytesWritten = f()
Some(() => f() - baselineBytesWritten)
} catch {
case e: NoSuchMethodException => {
logDebug("Couldn't find method for retrieving thread-level FileSystem output data", e)
None
}
}
}
private def getFileSystemThreadStatistics(path: Path, conf: Configuration): Seq[AnyRef] = {
val qualifiedPath = path.getFileSystem(conf).makeQualified(path)
val scheme = qualifiedPath.toUri().getScheme()
val stats = FileSystem.getAllStatistics().filter(_.getScheme().equals(scheme))
stats.map(Utils.invoke(classOf[Statistics], _, "getThreadStatistics"))
}
private def getFileSystemThreadStatisticsMethod(methodName: String): Method = {
val statisticsDataClass =
Class.forName("org.apache.hadoop.fs.FileSystem$Statistics$StatisticsData")
statisticsDataClass.getDeclaredMethod(methodName)
}
}
object SparkHadoopUtil {
private val hadoop = {
val yarnMode = java.lang.Boolean.valueOf(
System.getProperty("SPARK_YARN_MODE", System.getenv("SPARK_YARN_MODE")))
if (yarnMode) {
try {
Class.forName("org.apache.spark.deploy.yarn.YarnSparkHadoopUtil")
.newInstance()
.asInstanceOf[SparkHadoopUtil]
} catch {
case e: Exception => throw new SparkException("Unable to load YARN support", e)
}
} else {
new SparkHadoopUtil
}
}
def get: SparkHadoopUtil = {
hadoop
}
}
|
