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
|
package spark.deploy.worker
import scala.collection.mutable.{ArrayBuffer, HashMap}
import akka.actor.{ActorRef, Props, Actor}
import spark.{Logging, Utils}
import spark.util.AkkaUtils
import spark.deploy._
import akka.remote.RemoteClientLifeCycleEvent
import java.text.SimpleDateFormat
import java.util.Date
import akka.remote.RemoteClientShutdown
import akka.remote.RemoteClientDisconnected
import spark.deploy.RegisterWorker
import spark.deploy.LaunchExecutor
import spark.deploy.RegisterWorkerFailed
import akka.actor.Terminated
import java.io.File
private[spark] class Worker(
ip: String,
port: Int,
webUiPort: Int,
cores: Int,
memory: Int,
masterUrl: String,
workDirPath: String = null)
extends Actor with Logging {
val DATE_FORMAT = new SimpleDateFormat("yyyyMMddHHmmss") // For worker and executor IDs
val MASTER_REGEX = "spark://([^:]+):([0-9]+)".r
var master: ActorRef = null
var masterWebUiUrl : String = ""
val workerId = generateWorkerId()
var sparkHome: File = null
var workDir: File = null
val executors = new HashMap[String, ExecutorRunner]
val finishedExecutors = new HashMap[String, ExecutorRunner]
val publicAddress = {
val envVar = System.getenv("SPARK_PUBLIC_DNS")
if (envVar != null) envVar else ip
}
var coresUsed = 0
var memoryUsed = 0
def coresFree: Int = cores - coresUsed
def memoryFree: Int = memory - memoryUsed
def createWorkDir() {
workDir = if (workDirPath != null) {
new File(workDirPath)
} else {
new File(sparkHome, "work")
}
try {
if (!workDir.exists() && !workDir.mkdirs()) {
logError("Failed to create work directory " + workDir)
System.exit(1)
}
} catch {
case e: Exception =>
logError("Failed to create work directory " + workDir, e)
System.exit(1)
}
}
override def preStart() {
logInfo("Starting Spark worker %s:%d with %d cores, %s RAM".format(
ip, port, cores, Utils.memoryMegabytesToString(memory)))
val envVar = System.getenv("SPARK_HOME")
sparkHome = new File(if (envVar == null) "." else envVar)
logInfo("Spark home: " + sparkHome)
createWorkDir()
connectToMaster()
startWebUi()
}
def connectToMaster() {
masterUrl match {
case MASTER_REGEX(masterHost, masterPort) => {
logInfo("Connecting to master spark://" + masterHost + ":" + masterPort)
val akkaUrl = "akka://spark@%s:%s/user/Master".format(masterHost, masterPort)
try {
master = context.actorFor(akkaUrl)
master ! RegisterWorker(workerId, ip, port, cores, memory, webUiPort, publicAddress)
context.system.eventStream.subscribe(self, classOf[RemoteClientLifeCycleEvent])
context.watch(master) // Doesn't work with remote actors, but useful for testing
} catch {
case e: Exception =>
logError("Failed to connect to master", e)
System.exit(1)
}
}
case _ =>
logError("Invalid master URL: " + masterUrl)
System.exit(1)
}
}
def startWebUi() {
val webUi = new WorkerWebUI(context.system, self)
try {
AkkaUtils.startSprayServer(context.system, "0.0.0.0", webUiPort, webUi.handler)
} catch {
case e: Exception =>
logError("Failed to create web UI", e)
System.exit(1)
}
}
override def receive = {
case RegisteredWorker(url) =>
masterWebUiUrl = url
logInfo("Successfully registered with master")
case RegisterWorkerFailed(message) =>
logError("Worker registration failed: " + message)
System.exit(1)
case LaunchExecutor(jobId, execId, jobDesc, cores_, memory_) =>
logInfo("Asked to launch executor %s/%d for %s".format(jobId, execId, jobDesc.name))
val manager = new ExecutorRunner(
jobId, execId, jobDesc, cores_, memory_, self, workerId, ip, sparkHome, workDir)
executors(jobId + "/" + execId) = manager
manager.start()
coresUsed += cores_
memoryUsed += memory_
master ! ExecutorStateChanged(jobId, execId, ExecutorState.RUNNING, None)
case ExecutorStateChanged(jobId, execId, state, message) =>
master ! ExecutorStateChanged(jobId, execId, state, message)
val fullId = jobId + "/" + execId
if (ExecutorState.isFinished(state)) {
val executor = executors(fullId)
logInfo("Executor " + fullId + " finished with state " + state)
finishedExecutors(fullId) = executor
executors -= fullId
coresUsed -= executor.cores
memoryUsed -= executor.memory
}
case KillExecutor(jobId, execId) =>
val fullId = jobId + "/" + execId
val executor = executors(fullId)
logInfo("Asked to kill executor " + fullId)
executor.kill()
case Terminated(_) | RemoteClientDisconnected(_, _) | RemoteClientShutdown(_, _) =>
masterDisconnected()
case RequestWorkerState => {
sender ! WorkerState(ip + ":" + port, workerId, executors.values.toList,
finishedExecutors.values.toList, masterUrl, cores, memory,
coresUsed, memoryUsed, masterWebUiUrl)
}
}
def masterDisconnected() {
// TODO: It would be nice to try to reconnect to the master, but just shut down for now.
// (Note that if reconnecting we would also need to assign IDs differently.)
logError("Connection to master failed! Shutting down.")
executors.values.foreach(_.kill())
System.exit(1)
}
def generateWorkerId(): String = {
"worker-%s-%s-%d".format(DATE_FORMAT.format(new Date), ip, port)
}
override def postStop() {
executors.values.foreach(_.kill())
}
}
private[spark] object Worker {
def main(argStrings: Array[String]) {
val args = new WorkerArguments(argStrings)
val (actorSystem, boundPort) = AkkaUtils.createActorSystem("spark", args.ip, args.port)
val actor = actorSystem.actorOf(
Props(new Worker(args.ip, boundPort, args.webUiPort, args.cores, args.memory,
args.master, args.workDir)),
name = "Worker")
actorSystem.awaitTermination()
}
}
|