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
|
/*
* 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.worker
import java.io._
import java.nio.charset.StandardCharsets
import scala.collection.JavaConverters._
import com.google.common.io.Files
import org.apache.spark.{SecurityManager, SparkConf}
import org.apache.spark.deploy.{ApplicationDescription, ExecutorState}
import org.apache.spark.deploy.DeployMessages.ExecutorStateChanged
import org.apache.spark.internal.Logging
import org.apache.spark.rpc.RpcEndpointRef
import org.apache.spark.util.{ShutdownHookManager, Utils}
import org.apache.spark.util.logging.FileAppender
/**
* Manages the execution of one executor process.
* This is currently only used in standalone mode.
*/
private[deploy] class ExecutorRunner(
val appId: String,
val execId: Int,
val appDesc: ApplicationDescription,
val cores: Int,
val memory: Int,
val worker: RpcEndpointRef,
val workerId: String,
val host: String,
val webUiPort: Int,
val publicAddress: String,
val sparkHome: File,
val executorDir: File,
val workerUrl: String,
conf: SparkConf,
val appLocalDirs: Seq[String],
@volatile var state: ExecutorState.Value)
extends Logging {
private val fullId = appId + "/" + execId
private var workerThread: Thread = null
private var process: Process = null
private var stdoutAppender: FileAppender = null
private var stderrAppender: FileAppender = null
// Timeout to wait for when trying to terminate an executor.
private val EXECUTOR_TERMINATE_TIMEOUT_MS = 10 * 1000
// NOTE: This is now redundant with the automated shut-down enforced by the Executor. It might
// make sense to remove this in the future.
private var shutdownHook: AnyRef = null
private[worker] def start() {
workerThread = new Thread("ExecutorRunner for " + fullId) {
override def run() { fetchAndRunExecutor() }
}
workerThread.start()
// Shutdown hook that kills actors on shutdown.
shutdownHook = ShutdownHookManager.addShutdownHook { () =>
// It's possible that we arrive here before calling `fetchAndRunExecutor`, then `state` will
// be `ExecutorState.RUNNING`. In this case, we should set `state` to `FAILED`.
if (state == ExecutorState.RUNNING) {
state = ExecutorState.FAILED
}
killProcess(Some("Worker shutting down")) }
}
/**
* Kill executor process, wait for exit and notify worker to update resource status.
*
* @param message the exception message which caused the executor's death
*/
private def killProcess(message: Option[String]) {
var exitCode: Option[Int] = None
if (process != null) {
logInfo("Killing process!")
if (stdoutAppender != null) {
stdoutAppender.stop()
}
if (stderrAppender != null) {
stderrAppender.stop()
}
exitCode = Utils.terminateProcess(process, EXECUTOR_TERMINATE_TIMEOUT_MS)
if (exitCode.isEmpty) {
logWarning("Failed to terminate process: " + process +
". This process will likely be orphaned.")
}
}
try {
worker.send(ExecutorStateChanged(appId, execId, state, message, exitCode))
} catch {
case e: IllegalStateException => logWarning(e.getMessage(), e)
}
}
/** Stop this executor runner, including killing the process it launched */
private[worker] def kill() {
if (workerThread != null) {
// the workerThread will kill the child process when interrupted
workerThread.interrupt()
workerThread = null
state = ExecutorState.KILLED
try {
ShutdownHookManager.removeShutdownHook(shutdownHook)
} catch {
case e: IllegalStateException => None
}
}
}
/** Replace variables such as {{EXECUTOR_ID}} and {{CORES}} in a command argument passed to us */
private[worker] def substituteVariables(argument: String): String = argument match {
case "{{WORKER_URL}}" => workerUrl
case "{{EXECUTOR_ID}}" => execId.toString
case "{{HOSTNAME}}" => host
case "{{CORES}}" => cores.toString
case "{{APP_ID}}" => appId
case other => other
}
/**
* Download and run the executor described in our ApplicationDescription
*/
private def fetchAndRunExecutor() {
try {
// Launch the process
val builder = CommandUtils.buildProcessBuilder(appDesc.command, new SecurityManager(conf),
memory, sparkHome.getAbsolutePath, substituteVariables)
val command = builder.command()
val formattedCommand = command.asScala.mkString("\"", "\" \"", "\"")
logInfo(s"Launch command: $formattedCommand")
builder.directory(executorDir)
builder.environment.put("SPARK_EXECUTOR_DIRS", appLocalDirs.mkString(File.pathSeparator))
// In case we are running this from within the Spark Shell, avoid creating a "scala"
// parent process for the executor command
builder.environment.put("SPARK_LAUNCH_WITH_SCALA", "0")
// Add webUI log urls
val baseUrl =
if (conf.getBoolean("spark.ui.reverseProxy", false)) {
s"/proxy/$workerId/logPage/?appId=$appId&executorId=$execId&logType="
} else {
s"http://$publicAddress:$webUiPort/logPage/?appId=$appId&executorId=$execId&logType="
}
builder.environment.put("SPARK_LOG_URL_STDERR", s"${baseUrl}stderr")
builder.environment.put("SPARK_LOG_URL_STDOUT", s"${baseUrl}stdout")
process = builder.start()
val header = "Spark Executor Command: %s\n%s\n\n".format(
formattedCommand, "=" * 40)
// Redirect its stdout and stderr to files
val stdout = new File(executorDir, "stdout")
stdoutAppender = FileAppender(process.getInputStream, stdout, conf)
val stderr = new File(executorDir, "stderr")
Files.write(header, stderr, StandardCharsets.UTF_8)
stderrAppender = FileAppender(process.getErrorStream, stderr, conf)
// Wait for it to exit; executor may exit with code 0 (when driver instructs it to shutdown)
// or with nonzero exit code
val exitCode = process.waitFor()
state = ExecutorState.EXITED
val message = "Command exited with code " + exitCode
worker.send(ExecutorStateChanged(appId, execId, state, Some(message), Some(exitCode)))
} catch {
case interrupted: InterruptedException =>
logInfo("Runner thread for executor " + fullId + " interrupted")
state = ExecutorState.KILLED
killProcess(None)
case e: Exception =>
logError("Error running executor", e)
state = ExecutorState.FAILED
killProcess(Some(e.toString))
}
}
}
|
