1.SparkContext类源码解析
本文基于最新spark2.0版本
本文主要讲解spark程序在new SparkContext中都做了那些工作，从程序SparkContext开始注册给Master，Master接收到注册信息。
（1）createTaskScheduler的创建，实例化TaskScheduler
// We need to register "HeartbeatReceiver" before "createTaskScheduler" because Executor will
// retrieve "HeartbeatReceiver" in the constructor. (SPARK-6640)
_heartbeatReceiver = env.rpcEnv.setupEndpoint(
HeartbeatReceiver.ENDPOINT_NAME, new HeartbeatReceiver(this))
// Create and start the scheduler
val (sched, ts) =
SparkContext.createTaskScheduler(this, master, deployMode)//创建TaskScheduler
_schedulerBackend = sched
_taskScheduler = ts
_dagScheduler =
new DAGScheduler(this) //创建DAGScheduler
_heartbeatReceiver.ask[Boolean](TaskSchedulerIsSet)
// start TaskScheduler after taskScheduler sets DAGScheduler reference in DAGScheduler's
// constructor
_taskScheduler.start()//启动TaskScheduler
（2）根据不同的提交方式创建不同的scheduler，
/**
* Create a task scheduler based on a given master URL.
* Return a 2-tuple of the scheduler backend and the task scheduler.
*/
private def createTaskScheduler(
sc: SparkContext,
master: String,
deployMode: String): (SchedulerBackend, TaskScheduler) = {
import SparkMasterRegex._
// When running locally, don't try to re-execute tasks on failure.
val MAX_LOCAL_TASK_FAILURES = 1
master match {
case "local" =>
val scheduler = new TaskSchedulerImpl(sc, MAX_LOCAL_TASK_FAILURES, isLocal = true)
val backend = new LocalSchedulerBackend(sc.getConf, scheduler, 1)
scheduler.initialize(backend)
(backend, scheduler)
case LOCAL_N_REGEX(threads) =>
def localCpuCount: Int = Runtime.getRuntime.availableProcessors()
// local[*] estimates the number of cores on the machine; local[N] uses exactly N threads.
val threadCount = if (threads == "*") localCpuCount else threads.toInt
if (threadCount <= 0) {
throw new SparkException(s"Asked to run locally with $threadCount threads")
}
val scheduler = new TaskSchedulerImpl(sc, MAX_LOCAL_TASK_FAILURES, isLocal = true)
val backend = new LocalSchedulerBackend(sc.getConf, scheduler, threadCount)
scheduler.initialize(backend)
(backend, scheduler)
case LOCAL_N_FAILURES_REGEX(threads, maxFailures) =>
def localCpuCount: Int = Runtime.getRuntime.availableProcessors()
// local[*, M] means the number of cores on the computer with M failures
// local[N, M] means exactly N threads with M failures
val threadCount = if (threads == "*") localCpuCount else threads.toInt
val scheduler = new TaskSchedulerImpl(sc, maxFailures.toInt, isLocal = true)
val backend = new LocalSchedulerBackend(sc.getConf, scheduler, threadCount)
scheduler.initialize(backend)
(backend, scheduler)
case SPARK_REGEX(sparkUrl) =>
val scheduler = new TaskSchedulerImpl(sc)
val masterUrls = sparkUrl.split(",").map("spark://" + _)
val backend = new StandaloneSchedulerBackend(scheduler, sc, masterUrls) //standalone模式
scheduler.initialize(backend)
(backend, scheduler)
case LOCAL_CLUSTER_REGEX(numSlaves, coresPerSlave, memoryPerSlave) =>
// Check to make sure memory requested <= memoryPerSlave. Otherwise Spark will just hang.
val memoryPerSlaveInt = memoryPerSlave.toInt
if (sc.executorMemory > memoryPerSlaveInt) {
throw new SparkException(
"Asked to launch cluster with %d MB RAM / worker but requested %d MB/worker".format(
memoryPerSlaveInt, sc.executorMemory))
}
val scheduler = new TaskSchedulerImpl(sc)
val localCluster = new LocalSparkCluster(
numSlaves.toInt, coresPerSlave.toInt, memoryPerSlaveInt, sc.conf)
val masterUrls = localCluster.start()
val backend = new StandaloneSchedulerBackend(scheduler, sc, masterUrls)
scheduler.initialize(backend)
backend.shutdownCallback = (backend: StandaloneSchedulerBackend) => {
localCluster.stop()
}
(backend, scheduler)
case MESOS_REGEX(mesosUrl) =>
MesosNativeLibrary.load()
val scheduler = new TaskSchedulerImpl(sc)
val coarseGrained = sc.conf.getBoolean("spark.mesos.coarse", defaultValue = true)
val backend = if (coarseGrained) {
new MesosCoarseGrainedSchedulerBackend(scheduler, sc, mesosUrl, sc.env.securityManager)
} else {
new MesosFineGrainedSchedulerBackend(scheduler, sc, mesosUrl)
}
scheduler.initialize(backend)
(backend, scheduler)
case masterUrl =>
val cm = getClusterManager(masterUrl) match {
case Some(clusterMgr) => clusterMgr
case None => throw new SparkException("Could not parse Master URL: '" + master + "'")
}
try {
val scheduler = cm.createTaskScheduler(sc, masterUrl)
val backend = cm.createSchedulerBackend(sc, masterUrl, scheduler)
cm.initialize(scheduler, backend)
(backend, scheduler)
} catch {
case se: SparkException => throw se
case NonFatal(e) =>
throw new SparkException("External scheduler cannot be instantiated", e)
}
}
}
（3）默认调度器是先进先出，类TaskSchedulerImpl中的initialize方法
def initialize(backend: SchedulerBackend) {// 传入的是
SparkDeploySchedulerBackend
this.backend = backend
// temporarily set rootPool name to empty
rootPool = new Pool("", schedulingMode, 0, 0)
schedulableBuilder = {
schedulingMode match {
case SchedulingMode.FIFO =>
new FIFOSchedulableBuilder(rootPool)
case SchedulingMode.FAIR =>
new FairSchedulableBuilder(rootPool, conf)
case _ =>
throw new IllegalArgumentException(s"Unsupported spark.scheduler.mode: $schedulingMode")
}
}
schedulableBuilder.buildPools()
}
（4）
override def start() {
backend.start()//StandaloneSchedulerBackend类的start方法
if (!isLocal && conf.getBoolean("spark.speculation", false)) {
logInfo("Starting speculative execution thread")
speculationScheduler.scheduleAtFixedRate(new Runnable {
override def run(): Unit = Utils.tryOrStopSparkContext(sc) {
checkSpeculatableTasks()
}
}, SPECULATION_INTERVAL_MS, SPECULATION_INTERVAL_MS, TimeUnit.MILLISECONDS)
}
}
（5）StandaloneSchedulerBackend类的start方法
override def start() {
super.start()
launcherBackend.connect()
// The endpoint for executors to talk to us
val driverUrl = RpcEndpointAddress(
sc.conf.get("spark.driver.host"),
sc.conf.get("spark.driver.port").toInt,
CoarseGrainedSchedulerBackend.ENDPOINT_NAME).toString
val args = Seq(
"--driver-url", driverUrl,
"--executor-id", "{{EXECUTOR_ID}}",
"--hostname", "{{HOSTNAME}}",
"--cores", "{{CORES}}",
"--app-id", "{{APP_ID}}",
"--worker-url", "{{WORKER_URL}}")
val extraJavaOpts = sc.conf.getOption("spark.executor.extraJavaOptions")
.map(Utils.splitCommandString).getOrElse(Seq.empty)
val classPathEntries = sc.conf.getOption("spark.executor.extraClassPath")
.map(_.split(java.io.File.pathSeparator).toSeq).getOrElse(Nil)
val libraryPathEntries = sc.conf.getOption("spark.executor.extraLibraryPath")
.map(_.split(java.io.File.pathSeparator).toSeq).getOrElse(Nil)
// When testing, expose the parent class path to the child. This is processed by
// compute-classpath.{cmd,sh} and makes all needed jars available to child processes
// when the assembly is built with the "*-provided" profiles enabled.
val testingClassPath =
if (sys.props.contains("spark.testing")) {
sys.props("java.class.path").split(java.io.File.pathSeparator).toSeq
} else {
Nil
}
// Start executors with a few necessary configs for registering with the scheduler
val sparkJavaOpts = Utils.sparkJavaOpts(conf, SparkConf.isExecutorStartupConf)
val javaOpts = sparkJavaOpts ++ extraJavaOpts
//创建Command对象，
val command =
Command("org.apache.spark.executor.CoarseGrainedExecutorBackend",
args, sc.executorEnvs, classPathEntries ++ testingClassPath, libraryPathEntries, javaOpts)
//当通过SparkDeploySchedulerBackend会把Command提交给Master，Master发送指令给Worker去启动Executor所在的进程的时候，加载的main方法，所在的入口类，就是command的CoarseGrainedExecutorBackend，从这里知道可以实现自己的CoarseGrainedExecutorBackend，在
CoarseGrainedExecutorBackend中启动Executor（Executor是先注册，再启动），Executor通过线程池并发执行task
val appUIAddress = sc.ui.map(_.appUIAddress).getOrElse("")
val coresPerExecutor = conf.getOption("spark.executor.cores").map(_.toInt)
// If we're using dynamic allocation, set our initial executor limit to 0 for now.
// ExecutorAllocationManager will send the real initial limit to the Master later.
val initialExecutorLimit =
if (Utils.isDynamicAllocationEnabled(conf)) {
Some(0)
} else {
None
}
//创建应用的描述信息
val appDesc = new ApplicationDescription(sc.appName, maxCores, sc.executorMemory, command,
appUIAddress, sc.eventLogDir, sc.eventLogCodec, coresPerExecutor, initialExecutorLimit)
//创建StandaloneAppClient,这里在1.6是appClient
client = new StandaloneAppClient(sc.env.rpcEnv, masters, appDesc, this, conf)
client.start()//见下面（6）会继续跟踪client启动后做了什么
launcherBackend.setState(SparkAppHandle.State.SUBMITTED)
waitForRegistration()
launcherBackend.setState(SparkAppHandle.State.RUNNING)
}
（5）CoarseGrainedSchedulerBackend类的start方法
override def start() {
val properties = new ArrayBuffer[(String, String)]
for ((key, value) <- scheduler.sc.conf.getAll) {
if (key.startsWith("spark.")) {
properties += ((key, value))
}
}
// TODO (prashant) send conf instead of properties
driverEndpoint = createDriverEndpointRef(properties)
}
（6）
StandaloneAppClient的start方法，创建了ClientEndpoint对象，ClientEndpoint是一个在文件
StandaloneAppClient中的类
def start() {
// Just launch an rpcEndpoint; it will call back into the listener.
endpoint.set(rpcEnv.setupEndpoint("AppClient",
new ClientEndpoint(rpcEnv)))
}
（7）在ClientEndpoint进行启动的时候开始进行注册给master，
这个onStart()方法在哪里进行调用？
override def onStart(): Unit = {
try {
registerWithMaster(1)
} catch {
case e: Exception =>
logWarning("Failed to connect to master", e)
markDisconnected()
stop()
}
}
（8）对所有master进行注册
/**
* Register with all masters asynchronously. It will call `registerWithMaster` every
* REGISTRATION_TIMEOUT_SECONDS seconds until exceeding REGISTRATION_RETRIES times.
* Once we connect to a master successfully, all scheduling work and Futures will be cancelled.
*
* nthRetry means this is the nth attempt to register with master.
*/
private def registerWithMaster(nthRetry: Int) {
registerMasterFutures.set(
tryRegisterAllMasters()) //实际环境中有多个master因为是HA
registrationRetryTimer.set(registrationRetryThread.schedule(new Runnable {
//用线程池进行注册
override def run(): Unit = {
if (registered.get) {
registerMasterFutures.get.foreach(_.cancel(true))
registerMasterThreadPool.shutdownNow()
} else if (nthRetry >= REGISTRATION_RETRIES) {
markDead("All masters are unresponsive! Giving up.")
} else {
registerMasterFutures.get.foreach(_.cancel(true))
registerWithMaster(nthRetry + 1)
}
}
}, REGISTRATION_TIMEOUT_SECONDS, TimeUnit.SECONDS))
}
（9）master会接收到这里的RegisterApplication对象的消息，这里就注册给了master
/**
* Register with all masters asynchronously and returns an array `Future`s for cancellation.
*/
private def tryRegisterAllMasters(): Array[JFuture[_]] = {
for (masterAddress <- masterRpcAddresses) yield {
registerMasterThreadPool.submit(new Runnable {
override def run(): Unit = try {
if (registered.get) {
return
}
logInfo("Connecting to master " + masterAddress.toSparkURL + "...")
val masterRef = rpcEnv.setupEndpointRef(masterAddress, Master.ENDPOINT_NAME)
masterRef.send(RegisterApplication(appDescription, self))
} catch {
case ie: InterruptedException => // Cancelled
case NonFatal(e) => logWarning(s"Failed to connect to master $masterAddress", e)
}
})
}
}
（10）master类中收到消息，
Master类中的receive方法
override def receive: PartialFunction[Any, Unit] = {
case ElectedLeader =>
val (storedApps, storedDrivers, storedWorkers) = persistenceEngine.readPersistedData(rpcEnv)
state = if (storedApps.isEmpty && storedDrivers.isEmpty && storedWorkers.isEmpty) {
RecoveryState.ALIVE
} else {
RecoveryState.RECOVERING
}
logInfo("I have been elected leader! New state: " + state)
if (state == RecoveryState.RECOVERING) {
beginRecovery(storedApps, storedDrivers, storedWorkers)
recoveryCompletionTask = forwardMessageThread.schedule(new Runnable {
override def run(): Unit = Utils.tryLogNonFatalError {
self.send(CompleteRecovery)
}
}, WORKER_TIMEOUT_MS, TimeUnit.MILLISECONDS)
}
case CompleteRecovery => completeRecovery()
case RevokedLeadership =>
logError("Leadership has been revoked -- master shutting down.")
System.exit(0)
case RegisterApplication(description, driver) =>
// TODO Prevent repeated registrations from some driver
if (state == RecoveryState.STANDBY) {
// ignore, don't send response
} else {
logInfo("Registering app " + description.name)
val app = createApplication(description, driver)
registerApplication(app)
logInfo("Registered app " + description.name + " with ID " + app.id)
persistenceEngine.addApplication(app)
driver.send(RegisteredApplication(app.id, self))
schedule()
}
这样一个程序在driver端向master进行注册的过程就完成了，然后master通过给worker发送指令启动Executor。
然后所有的Executor向Driver中的ScheduleBackEnd（SparkDeploy ）注册。
后面会详细讲解master接收到RegisteredApplication的工作内。
补充（1）ApplicationDescription类都包括哪些信息
private[spark] case class ApplicationDescription(
name: String,
maxCores: Option[Int],
memoryPerExecutorMB: Int,
command: Command, //创建的Command对象，这个很重要
appUiUrl: String,
eventLogDir: Option[URI] = None,
// short name of compression codec used when writing event logs, if any (e.g. lzf)
eventLogCodec: Option[String] = None,
coresPerExecutor: Option[Int] = None,
// number of executors this application wants to start with,
// only used if dynamic allocation is enabled
initialExecutorLimit: Option[Int] = None,
user: String = System.getProperty("user.name", "<unknown>")) {
override def toString: String = "ApplicationDescription(" + name + ")"
}
补充二
（1）CoarseGrainedExecutorBackend类中的main方法启动进程，然后运行run方法
def main(args: Array[String]) {
var driverUrl: String = null
var executorId: String = null
var hostname: String = null
var cores: Int = 0
var appId: String = null
var workerUrl: Option[String] = None
val userClassPath = new mutable.ListBuffer[URL]()
var argv = args.toList
while (!argv.isEmpty) {
argv match {
case ("--driver-url") :: value :: tail =>
driverUrl = value
argv = tail
case ("--executor-id") :: value :: tail =>
executorId = value
argv = tail
case ("--hostname") :: value :: tail =>
hostname = value
argv = tail
case ("--cores") :: value :: tail =>
cores = value.toInt
argv = tail
case ("--app-id") :: value :: tail =>
appId = value
argv = tail
case ("--worker-url") :: value :: tail =>
// Worker url is used in spark standalone mode to enforce fate-sharing with worker
workerUrl = Some(value)
argv = tail
case ("--user-class-path") :: value :: tail =>
userClassPath += new URL(value)
argv = tail
case Nil =>
case tail =>
// scalastyle:off println
System.err.println(s"Unrecognized options: ${tail.mkString(" ")}")
// scalastyle:on println
printUsageAndExit()
}
}
if (driverUrl == null || executorId == null || hostname == null || cores <= 0 ||
appId == null) {
printUsageAndExit()
}
run(driverUrl, executorId, hostname, cores, appId, workerUrl, userClassPath)
System.exit(0)
}
（2）调用run方法，运行CoarseGrainedExecutorBackend的run方法注册Executor，这里没有创建Executor
private def run(
driverUrl: String,
executorId: String,
hostname: String,
cores: Int,
appId: String,
workerUrl: Option[String],
userClassPath: Seq[URL]) {
Utils.initDaemon(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 = RpcEnv.create(
"driverPropsFetcher",
hostname,
port,
executorConf,
new SecurityManager(executorConf),
clientMode = true)
val driver = fetcher.setupEndpointRefByURI(driverUrl)
val props = driver.askWithRetry[Seq[(String, String)]](RetrieveSparkProps) ++
Seq[(String, String)](("spark.app.id", appId))
fetcher.shutdown()
// Create SparkEnv using properties we fetched from the driver.
val driverConf = new SparkConf()
for ((key, value) <- props) {
// this is required for SSL in standalone mode
if (SparkConf.isExecutorStartupConf(key)) {
driverConf.setIfMissing(key, value)
} else {
driverConf.set(key, value)
}
}
if (driverConf.contains("spark.yarn.credentials.file")) {
logInfo("Will periodically update credentials from: " +
driverConf.get("spark.yarn.credentials.file"))
SparkHadoopUtil.get.startExecutorDelegationTokenRenewer(driverConf)
}
val env = SparkEnv.createExecutorEnv(
driverConf, executorId, hostname, port, cores, isLocal = false)
//注意这里注册Executor，其实注册的是
CoarseGrainedExecutorBackend
env.rpcEnv.setupEndpoint("Executor", new CoarseGrainedExecutorBackend(
env.rpcEnv, driverUrl, executorId, hostname, cores, userClassPath, env))
workerUrl.foreach { url =>
env.rpcEnv.setupEndpoint("WorkerWatcher", new WorkerWatcher(env.rpcEnv, url))
}
env.rpcEnv.awaitTermination()
SparkHadoopUtil.get.stopExecutorDelegationTokenRenewer()
}
}
（3）CoarseGrainedExecutorBackend接收到注册信息后开始创建Executor，先注册成功再进行分配。
override def receive: PartialFunction[Any, Unit] = {
case RegisteredExecutor =>
logInfo("Successfully registered with driver")
try {
executor = new Executor(executorId, hostname, env, userClassPath, isLocal = false)
} catch {
case NonFatal(e) =>
exitExecutor(1, "Unable to create executor due to " + e.getMessage, e)
}
扫一扫
1073
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
