大数据：Spark Standalone 集群调度（一）从远程调试开始说application创建

spark-submit

提交一个spark任务

其本质就是类似下面命令

/usr/java/jdk1.8.0_111/bin/java -cp /work/spark-2.1.0-bin-hadoop2.7/conf/:/work/spark-2.1.0-bin-hadoop2.7/jars/* -Xdebug -Xrunjdwp:server=y,transport=dt_socket,address=7000,suspend=y -Xmx1g org.apache.spark.deploy.SparkSubmit --master spark://raintungmaster:7077 --class rfcexample --jars /work/spark-2.1.0-bin-hadoop2.7/examples/jars/scopt_2.11-3.3.0.jar,/work/spark-2.1.0-bin-hadoop2.7/examples/jars/spark-examples_2.11-2.1.0.jar /tmp/machinelearning.jar

1.2 master, worker 的设置调试

export SPARK_WORKER_OPTS="-Xdebug -Xrunjdwp:server=y,transport=dt_socket,address=8000,suspend=n"
export SPARK_MASTER_OPTS="-Xdebug -Xrunjdwp:server=y,transport=dt_socket,address=8001,suspend=n"

try {
      mainMethod.invoke(null, childArgs.toArray)
    } catch {
      case t: Throwable =>
        findCause(t) match {
          case SparkUserAppException(exitCode) =>
            System.exit(exitCode)

          case t: Throwable =>
            throw t
        }
    }

--class rfcexample

val sc = new SparkContext(conf)

// Create and start the scheduler
    val (sched, ts) = SparkContext.createTaskScheduler(this, master, deployMode)
    _schedulerBackend = sched
    _taskScheduler = ts
    _dagScheduler = new DAGScheduler(this)
    _heartbeatReceiver.ask[Boolean](TaskSchedulerIsSet)

    // start TaskScheduler after taskScheduler sets DAGScheduler reference in DAGScheduler‘s
    // constructor
    _taskScheduler.start()

    val appDesc = new ApplicationDescription(sc.appName, maxCores, sc.executorMemory, command,
      appUIAddress, sc.eventLogDir, sc.eventLogCodec, coresPerExecutor, initialExecutorLimit)
    client = new StandaloneAppClient(sc.env.rpcEnv, masters, appDesc, this, conf)
    client.start()
    launcherBackend.setState(SparkAppHandle.State.SUBMITTED)
    waitForRegistration()
    launcherBackend.setState(SparkAppHandle.State.RUNNING)

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()
      }

private def launchExecutor(worker: WorkerInfo, exec: ExecutorDesc): Unit = {
    logInfo("Launching executor " + exec.fullId + " on worker " + worker.id)
    worker.addExecutor(exec)
    worker.endpoint.send(LaunchExecutor(masterUrl,
      exec.application.id, exec.id, exec.application.desc, exec.cores, exec.memory))
    exec.application.driver.send(
      ExecutorAdded(exec.id, worker.id, worker.hostPort, exec.cores, exec.memory))
  }

case LaunchExecutor(masterUrl, appId, execId, appDesc, cores_, memory_) =>
      if (masterUrl != activeMasterUrl) {
        logWarning("Invalid Master (" + masterUrl + ") attempted to launch executor.")
      } else {
        try {
          logInfo("Asked to launch executor %s/%d for %s".format(appId, execId, appDesc.name))

          // Create the executor‘s working directory
          val executorDir = new File(workDir, appId + "/" + execId)
          if (!executorDir.mkdirs()) {
            throw new IOException("Failed to create directory " + executorDir)
          }

          // Create local dirs for the executor. These are passed to the executor via the
          // SPARK_EXECUTOR_DIRS environment variable, and deleted by the Worker when the
          // application finishes.
          val appLocalDirs = appDirectories.getOrElse(appId,
            Utils.getOrCreateLocalRootDirs(conf).map { dir =>
              val appDir = Utils.createDirectory(dir, namePrefix = "executor")
              Utils.chmod700(appDir)
              appDir.getAbsolutePath()
            }.toSeq)
          appDirectories(appId) = appLocalDirs
          val manager = new ExecutorRunner(
            appId,
            execId,
            appDesc.copy(command = Worker.maybeUpdateSSLSettings(appDesc.command, conf)),
            cores_,
            memory_,
            self,
            workerId,
            host,
            webUi.boundPort,
            publicAddress,
            sparkHome,
            executorDir,
            workerUri,
            conf,
            appLocalDirs, ExecutorState.RUNNING)
          executors(appId + "/" + execId) = manager
          manager.start()
          coresUsed += cores_
          memoryUsed += memory_
          sendToMaster(ExecutorStateChanged(appId, execId, manager.state, None, None))
        } catch {
          case e: Exception =>
            logError(s"Failed to launch executor $appId/$execId for ${appDesc.name}.", e)
            if (executors.contains(appId + "/" + execId)) {
              executors(appId + "/" + execId).kill()
              executors -= appId + "/" + execId
            }
            sendToMaster(ExecutorStateChanged(appId, execId, ExecutorState.FAILED,
              Some(e.toString), None))
        }
      }

private[worker] def start() {
    workerThread = new Thread("ExecutorRunner for " + fullId) {
      override def run() { fetchAndRunExecutor() }
    }
    workerThread.start()
    // Shutdown hook that kills actors on shutdown.
    shutdownHook = ShutdownHookManager.addShutdownHook { () =>
      // It‘s possible that we arrive here before calling `fetchAndRunExecutor`, then `state` will
      // be `ExecutorState.RUNNING`. In this case, we should set `state` to `FAILED`.
      if (state == ExecutorState.RUNNING) {
        state = ExecutorState.FAILED
      }
      killProcess(Some("Worker shutting down")) }
  }

private def fetchAndRunExecutor() {
    try {
      // Launch the process
      val builder = CommandUtils.buildProcessBuilder(appDesc.command, new SecurityManager(conf),
        memory, sparkHome.getAbsolutePath, substituteVariables)
      val command = builder.command()
      val formattedCommand = command.asScala.mkString("\"", "\" \"", "\"")
      .....
      process = builder.start()
      ......
      val exitCode = process.waitFor()
      state = ExecutorState.EXITED
      val message = "Command exited with code " + exitCode
      worker.send(ExecutorStateChanged(appId, execId, state, Some(message), Some(exitCode)))
    } catch {
      ......
    }
  }

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

val extraJavaOpts = sc.conf.getOption("spark.executor.extraJavaOptions")

--conf "spark.executor.extraJavaOptions=-Xdebug -Xrunjdwp:server=y,transport=dt_socket,address=7001,suspend=y"

/usr/java/jdk1.8.0_111/bin/java -cp /work/spark-2.1.0-bin-hadoop2.7/conf/:/work/spark-2.1.0-bin-hadoop2.7/jars/* -Xdebug -Xrunjdwp:server=y,transport=dt_socket,address=7000,suspend=y -Xmx1g org.apache.spark.deploy.SparkSubmit --master spark://raintungmaster:7077 --class rfcexample --jars /work/spark-2.1.0-bin-hadoop2.7/examples/jars/scopt_2.11-3.3.0.jar,/work/spark-2.1.0-bin-hadoop2.7/examples/jars/spark-examples_2.11-2.1.0.jar --conf "spark.executor.extraJavaOptions=-Xdebug -Xrunjdwp:server=y,transport=dt_socket,address=7001,suspend=y" /tmp/machinelearning.jar