上一节的sparkContext中提到了taskScheduler的启动
来看看scheduler是怎么建立的：
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" => //本地模式
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) => //spark模式
val scheduler = new TaskSchedulerImpl(sc)
val masterUrls = sparkUrl.split(",").map("spark://" + _)
val backend = new StandaloneSchedulerBackend(scheduler, sc, masterUrls)
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 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) //创建的taskeduler
val backend = cm.createSchedulerBackend(sc, masterUrl, scheduler) //创建backend
cm.initialize(scheduler, backend) //初始化
(backend, scheduler)
} catch {
case se: SparkException => throw se
case NonFatal(e) =>
throw new SparkException("External scheduler cannot be instantiated", e)
}
}
}
看看spark模式：
case SPARK_REGEX(sparkUrl) =>
val scheduler = new TaskSchedulerImpl(sc)
val masterUrls = sparkUrl.split(",").map("spark://" + _)
val backend = new StandaloneSchedulerBackend(scheduler, sc, masterUrls)
scheduler.initialize(backend)
(backend, scheduler)
standaloneschedulerBackend 看看是怎么初始化的
def initialize(backend: SchedulerBackend) {
this.backend = backend
schedulableBuilder = {
schedulingMode match {
case SchedulingMode.FIFO =>
new FIFOSchedulableBuilder(rootPool)
case SchedulingMode.FAIR =>
new FairSchedulableBuilder(rootPool, conf)
case _ =>
throw new IllegalArgumentException(s"Unsupported $SCHEDULER_MODE_PROPERTY: " +
s"$schedulingMode")
}
}
schedulableBuilder.buildPools()
}
包含了FIFO,FAIR调度方式。
接下来看看spark的 _taskScheduler.start()
override def start() {
backend.start() //backend启动
if (!isLocal && conf.getBoolean("spark.speculation", false)) {
logInfo("Starting speculative execution thread")
speculationScheduler.scheduleWithFixedDelay(new Runnable {
override def run(): Unit = Utils.tryOrStopSparkContext(sc) {
checkSpeculatableTasks()
}
}, SPECULATION_INTERVAL_MS, SPECULATION_INTERVAL_MS, TimeUnit.MILLISECONDS)
}
}
standalone的backend-start方法的实现
override def start() {
super.start()
if (sc.deployMode == "client") {
launcherBackend.connect()
}
val driverUrl = RpcEndpointAddress(
sc.conf.get("spark.driver.host"),
sc.conf.get("spark.driver.port").toInt,
CoarseGrainedSchedulerBackend.ENDPOINT_NAME).toString //driver的url
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
val command = Command("org.apache.spark.executor.CoarseGrainedExecutorBackend",
args, sc.executorEnvs, classPathEntries ++ testingClassPath, libraryPathEntries, javaOpts)
val webUrl = sc.ui.map(_.webUrl).getOrElse("")
val coresPerExecutor = conf.getOption("spark.executor.cores").map(_.toInt)
val initialExecutorLimit =
if (Utils.isDynamicAllocationEnabled(conf)) {
Some(0)
} else {
None
}
val appDesc = ApplicationDescription(sc.appName, maxCores, sc.executorMemory, command,
webUrl, sc.eventLogDir, sc.eventLogCodec, coresPerExecutor, initialExecutorLimit)
client = new StandaloneAppClient(sc.env.rpcEnv, masters, appDesc, this, conf) //前边都是相关的配置和初始化
client.start() //关键在这个里
launcherBackend.setState(SparkAppHandle.State.SUBMITTED)
waitForRegistration()
launcherBackend.setState(SparkAppHandle.State.RUNNING)
}
看看appClient在Onstart()中进行向master注册的操作
registerWithMaster(1)
registerWithMaster中有个Try操作不断重试等待master回复
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)
}
})
}
}
可以看到 masterRef.send(RegisterApplication(appDescription, self))
发送了个注册Application的消息：
master接收到这个消息后
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) //1
logInfo("Registered app " + description.name + " with ID " + app.id)
persistenceEngine.addApplication(app)
driver.send(RegisteredApplication(app.id, self))//2
schedule()//3
}
做了registerApplication的操作将app的相关信息进行记录。
关键是2、3
private def schedule(): Unit = {
if (state != RecoveryState.ALIVE) {
return
}
// Drivers take strict precedence over executors
val shuffledAliveWorkers = Random.shuffle(workers.toSeq.filter(_.state == WorkerState.ALIVE))
val numWorkersAlive = shuffledAliveWorkers.size
var curPos = 0
for (driver <- waitingDrivers.toList) { // iterate over a copy of waitingDrivers
// We assign workers to each waiting driver in a round-robin fashion. For each driver, we
// start from the last worker that was assigned a driver, and continue onwards until we have
// explored all alive workers.
var launched = false
var numWorkersVisited = 0
while (numWorkersVisited < numWorkersAlive && !launched) {
val worker = shuffledAliveWorkers(curPos)
numWorkersVisited += 1
if (worker.memoryFree >= driver.desc.mem && worker.coresFree >= driver.desc.cores) {
*launchDriver(worker, driver)*
waitingDrivers -= driver
launched = true
}
curPos = (curPos + 1) % numWorkersAlive
}
}
*startExecutorsOnWorkers()*
}
首先会寻找合适的worker节点启动Driver
然后启动Executor
lauchDriver
private def launchDriver(worker: WorkerInfo, driver: DriverInfo) {
logInfo("Launching driver " + driver.id + " on worker " + worker.id)
worker.addDriver(driver)
driver.worker = Some(worker)
worker.endpoint.send(LaunchDriver(driver.id, driver.desc))
driver.state = DriverState.RUNNING
}
发送lauDriver的消息并将Driver的状态设置为Running
看看worker接收到这样的信息怎么处理的
case LaunchDriver(driverId, driverDesc) =>
logInfo(s"Asked to launch driver $driverId")
val driver = new DriverRunner(
conf,
driverId,
workDir,
sparkHome,
driverDesc.copy(command = Worker.maybeUpdateSSLSettings(driverDesc.command, conf)),
self,
workerUri,
securityMgr)
drivers(driverId) = driver
driver.start()
coresUsed += driverDesc.cores
memoryUsed += driverDesc.mem
启动了DriverRunner
startExecutorsOnWorkers()
private def startExecutorsOnWorkers(): Unit = {
for (app <- waitingApps) {
val coresPerExecutor = app.desc.coresPerExecutor.getOrElse(1)
// If the cores left is less than the coresPerExecutor,the cores left will not be allocated
if (app.coresLeft >= coresPerExecutor) {
// Filter out workers that don't have enough resources to launch an executor
val usableWorkers = workers.toArray.filter(_.state == WorkerState.ALIVE)
.filter(worker => worker.memoryFree >= app.desc.memoryPerExecutorMB &&
worker.coresFree >= coresPerExecutor)
.sortBy(_.coresFree).reverse
val assignedCores = scheduleExecutorsOnWorkers(app, usableWorkers, spreadOutApps)
// Now that we've decided how many cores to allocate on each worker, let's allocate them
for (pos <- 0 until usableWorkers.length if assignedCores(pos) > 0) {
allocateWorkerResourceToExecutors(
app, assignedCores(pos), app.desc.coresPerExecutor, usableWorkers(pos))
}
}
}
}
先筛选能用的worker 然后在Worker上起executor
private def allocateWorkerResourceToExecutors(
app: ApplicationInfo,
assignedCores: Int,
coresPerExecutor: Option[Int],
worker: WorkerInfo): Unit = {
// If the number of cores per executor is specified, we divide the cores assigned
// to this worker evenly among the executors with no remainder.
// Otherwise, we launch a single executor that grabs all the assignedCores on this worker.
val numExecutors = coresPerExecutor.map { assignedCores / _ }.getOrElse(1)
val coresToAssign = coresPerExecutor.getOrElse(assignedCores)
for (i <- 1 to numExecutors) {
val exec = app.addExecutor(worker, coresToAssign)
launchExecutor(worker, exec)
app.state = ApplicationState.RUNNING
}
}
可以看到lauchExecutor的代码启动完成后会告诉master executor的状态已经改变
本文由 妖言君 创作，采用 知识共享署名4.0 国际许可协议进行许可
本站文章除注明转载/出处外，均为本站原创或翻译，转载前请务必署名
最后编辑时间为: Jan 10, 2021 at 02:33 pm