override def onStart() {
assert(!registered)
logInfo("Starting Spark worker %s:%d with %d cores, %s RAM".format(
host, port, cores, Utils.megabytesToString(memory)))
logInfo(s"Running Spark version ${org.apache.spark.SPARK_VERSION}")
logInfo("Spark home: " + sparkHome)
createWorkDir()
shuffleService.startIfEnabled()
webUi = new WorkerWebUI(this, workDir, webUiPort)
webUi.bind()
val scheme = if (webUi.sslOptions.enabled) "https" else "http"
workerWebUiUrl = s"$scheme://$publicAddress:${webUi.boundPort}"
registerWithMaster()
metricsSystem.registerSource(workerSource)
metricsSystem.start()
// Attach the worker metrics servlet handler to the web ui after the metrics system is started.
metricsSystem.getServletHandlers.foreach(webUi.attachHandler)
}
private def registerWithMaster() {
// onDisconnected may be triggered multiple times, so don't attempt registration
// if there are outstanding registration attempts scheduled.
registrationRetryTimer match {
case None =>
registered = false
registerMasterFutures = tryRegisterAllMasters()
connectionAttemptCount = 0
registrationRetryTimer = Some(forwordMessageScheduler.scheduleAtFixedRate(
new Runnable {
override def run(): Unit = Utils.tryLogNonFatalError {
Option(self).foreach(_.send(ReregisterWithMaster))
}
},
INITIAL_REGISTRATION_RETRY_INTERVAL_SECONDS,
INITIAL_REGISTRATION_RETRY_INTERVAL_SECONDS,
TimeUnit.SECONDS))
case Some(_) =>
logInfo("Not spawning another attempt to register with the master, since there is an" +
" attempt scheduled already.")
}
}
private def tryRegisterAllMasters(): Array[JFuture[_]] = {
masterRpcAddresses.map { masterAddress =>
registerMasterThreadPool.submit(new Runnable {
override def run(): Unit = {
try {
logInfo("Connecting to master " + masterAddress + "...")
val masterEndpoint =
rpcEnv.setupEndpointRef(Master.SYSTEM_NAME, masterAddress, Master.ENDPOINT_NAME)
registerWithMaster(masterEndpoint)
} catch {
case ie: InterruptedException => // Cancelled
case NonFatal(e) => logWarning(s"Failed to connect to master $masterAddress", e)
}
}
})
}
}
private def registerWithMaster(masterEndpoint: RpcEndpointRef): Unit = {
masterEndpoint.ask[RegisterWorkerResponse](RegisterWorker(
workerId, host, port, self, cores, memory, workerWebUiUrl))
.onComplete {
// This is a very fast action so we can use "ThreadUtils.sameThread"
case Success(msg) =>
Utils.tryLogNonFatalError {
handleRegisterResponse(msg)
}
case Failure(e) =>
logError(s"Cannot register with master: ${masterEndpoint.address}", e)
System.exit(1)
}(ThreadUtils.sameThread)
}
override def receiveAndReply(context: RpcCallContext): PartialFunction[Any, Unit] = {
case RegisterWorker(
id, workerHost, workerPort, workerRef, cores, memory, workerWebUiUrl) => {
logInfo("Registering worker %s:%d with %d cores, %s RAM".format(
workerHost, workerPort, cores, Utils.megabytesToString(memory)))
if (state == RecoveryState.STANDBY) {
context.reply(MasterInStandby)
} else if (idToWorker.contains(id)) {
context.reply(RegisterWorkerFailed("Duplicate worker ID"))
} else {
val worker = new WorkerInfo(id, workerHost, workerPort, cores, memory,
workerRef, workerWebUiUrl)
if (registerWorker(worker)) {
persistenceEngine.addWorker(worker)
context.reply(RegisteredWorker(self, masterWebUiUrl))
schedule()
} else {
val workerAddress = worker.endpoint.address
logWarning("Worker registration failed. Attempted to re-register worker at same " +
"address: " + workerAddress)
context.reply(RegisterWorkerFailed("Attempted to re-register worker at same address: "
+ workerAddress))
}
}
}
private def registerWorker(worker: WorkerInfo): Boolean = {
// There may be one or more refs to dead workers on this same node (w/ different ID's),
// remove them.
workers.filter { w =>
(w.host == worker.host && w.port == worker.port) && (w.state == WorkerState.DEAD)
}.foreach { w =>
workers -= w
}
val workerAddress = worker.endpoint.address
if (addressToWorker.contains(workerAddress)) {
val oldWorker = addressToWorker(workerAddress)
if (oldWorker.state == WorkerState.UNKNOWN) {
// A worker registering from UNKNOWN implies that the worker was restarted during recovery.
// The old worker must thus be dead, so we will remove it and accept the new worker.
removeWorker(oldWorker)
} else {
logInfo("Attempted to re-register worker at same address: " + workerAddress)
return false
}
}
workers += worker
idToWorker(worker.id) = worker
addressToWorker(workerAddress) = worker
true
}