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
|
/*
* 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.executor
import java.nio.ByteBuffer
import scala.concurrent.Await
import akka.actor.{Actor, ActorSelection, Props}
import akka.pattern.Patterns
import akka.remote.{RemotingLifecycleEvent, DisassociatedEvent}
import org.apache.spark.{Logging, SecurityManager, SparkConf, SparkEnv}
import org.apache.spark.TaskState.TaskState
import org.apache.spark.deploy.SparkHadoopUtil
import org.apache.spark.deploy.worker.WorkerWatcher
import org.apache.spark.scheduler.TaskDescription
import org.apache.spark.scheduler.cluster.CoarseGrainedClusterMessages._
import org.apache.spark.util.{ActorLogReceive, AkkaUtils, SignalLogger, Utils}
private[spark] class CoarseGrainedExecutorBackend(
driverUrl: String,
executorId: String,
hostPort: String,
cores: Int,
env: SparkEnv)
extends Actor with ActorLogReceive with ExecutorBackend with Logging {
Utils.checkHostPort(hostPort, "Expected hostport")
var executor: Executor = null
var driver: ActorSelection = null
override def preStart() {
logInfo("Connecting to driver: " + driverUrl)
driver = context.actorSelection(driverUrl)
driver ! RegisterExecutor(executorId, hostPort, cores)
context.system.eventStream.subscribe(self, classOf[RemotingLifecycleEvent])
}
override def receiveWithLogging = {
case RegisteredExecutor =>
logInfo("Successfully registered with driver")
val (hostname, _) = Utils.parseHostPort(hostPort)
executor = new Executor(executorId, hostname, env, isLocal = false)
case RegisterExecutorFailed(message) =>
logError("Slave registration failed: " + message)
System.exit(1)
case LaunchTask(data) =>
if (executor == null) {
logError("Received LaunchTask command but executor was null")
System.exit(1)
} else {
val ser = env.closureSerializer.newInstance()
val taskDesc = ser.deserialize[TaskDescription](data.value)
logInfo("Got assigned task " + taskDesc.taskId)
executor.launchTask(this, taskId = taskDesc.taskId, attemptNumber = taskDesc.attemptNumber,
taskDesc.name, taskDesc.serializedTask)
}
case KillTask(taskId, _, interruptThread) =>
if (executor == null) {
logError("Received KillTask command but executor was null")
System.exit(1)
} else {
executor.killTask(taskId, interruptThread)
}
case x: DisassociatedEvent =>
logError(s"Driver $x disassociated! Shutting down.")
System.exit(1)
case StopExecutor =>
logInfo("Driver commanded a shutdown")
executor.stop()
context.stop(self)
context.system.shutdown()
}
override def statusUpdate(taskId: Long, state: TaskState, data: ByteBuffer) {
driver ! StatusUpdate(executorId, taskId, state, data)
}
}
private[spark] object CoarseGrainedExecutorBackend extends Logging {
private def run(
driverUrl: String,
executorId: String,
hostname: String,
cores: Int,
appId: String,
workerUrl: Option[String]) {
SignalLogger.register(log)
SparkHadoopUtil.get.runAsSparkUser { () =>
// Debug code
Utils.checkHost(hostname)
// Bootstrap to fetch the driver's Spark properties.
val executorConf = new SparkConf
val port = executorConf.getInt("spark.executor.port", 0)
val (fetcher, _) = AkkaUtils.createActorSystem(
"driverPropsFetcher", hostname, port, executorConf, new SecurityManager(executorConf))
val driver = fetcher.actorSelection(driverUrl)
val timeout = AkkaUtils.askTimeout(executorConf)
val fut = Patterns.ask(driver, RetrieveSparkProps, timeout)
val props = Await.result(fut, timeout).asInstanceOf[Seq[(String, String)]] ++
Seq[(String, String)](("spark.app.id", appId))
fetcher.shutdown()
// Create SparkEnv using properties we fetched from the driver.
val driverConf = new SparkConf().setAll(props)
val env = SparkEnv.createExecutorEnv(
driverConf, executorId, hostname, port, cores, isLocal = false)
// SparkEnv sets spark.driver.port so it shouldn't be 0 anymore.
val boundPort = env.conf.getInt("spark.executor.port", 0)
assert(boundPort != 0)
// Start the CoarseGrainedExecutorBackend actor.
val sparkHostPort = hostname + ":" + boundPort
env.actorSystem.actorOf(
Props(classOf[CoarseGrainedExecutorBackend],
driverUrl, executorId, sparkHostPort, cores, env),
name = "Executor")
workerUrl.foreach { url =>
env.actorSystem.actorOf(Props(classOf[WorkerWatcher], url), name = "WorkerWatcher")
}
env.actorSystem.awaitTermination()
}
}
def main(args: Array[String]) {
args.length match {
case x if x < 5 =>
System.err.println(
// Worker url is used in spark standalone mode to enforce fate-sharing with worker
"Usage: CoarseGrainedExecutorBackend <driverUrl> <executorId> <hostname> " +
"<cores> <appid> [<workerUrl>] ")
System.exit(1)
// NB: These arguments are provided by SparkDeploySchedulerBackend (for standalone mode)
// and CoarseMesosSchedulerBackend (for mesos mode).
case 5 =>
run(args(0), args(1), args(2), args(3).toInt, args(4), None)
case x if x > 5 =>
run(args(0), args(1), args(2), args(3).toInt, args(4), Some(args(5)))
}
}
}
|
