Spark内核源码解析六：worker原理解析和源码解析

1、worker里面先找到launchDriver

  case LaunchDriver(driverId, driverDesc) => {
      logInfo(s"Asked to launch driver $driverId")
      // 创建DriverRunner线程，包括在driver失败时自动重启driver
      val driver = new DriverRunner(
        conf,
        driverId,
        workDir,
        sparkHome,
        driverDesc.copy(command = Worker.maybeUpdateSSLSettings(driverDesc.command, conf)),
        self,
        akkaUrl)
      drivers(driverId) = driver
      driver.start()

      coresUsed += driverDesc.cores
      memoryUsed += driverDesc.mem
    }

DriverRunner里面的start方法

 def start() = {
    new Thread("DriverRunner for " + driverId) {
      override def run() {
        try {
          // 创建工作目录
          val driverDir = createWorkingDirectory()
          // 下载用户的jar包，下载用户jar包到工作目录，然后返回在worker中的路径
          val localJarFilename = downloadUserJar(driverDir)

          def substituteVariables(argument: String): String = argument match {
            case "{{WORKER_URL}}" => workerUrl
            case "{{USER_JAR}}" => localJarFilename
            case other => other
          }

          // TODO: If we add ability to submit multiple jars they should also be added here
          // 构建processBuilder，传入Driver启动命令和需要的cpu和内存信息
          val builder = CommandUtils.buildProcessBuilder(driverDesc.command, driverDesc.mem,
            sparkHome.getAbsolutePath, substituteVariables)
          launchDriver(builder, driverDir, driverDesc.supervise)
        }
        catch {
          case e: Exception => finalException = Some(e)
        }

        val state =
          if (killed) {
            DriverState.KILLED
          } else if (finalException.isDefined) {
            DriverState.ERROR
          } else {
            finalExitCode match {
              case Some(0) => DriverState.FINISHED
              case _ => DriverState.FAILED
            }
          }

        finalState = Some(state)

        // driver启动后向worker发送driver启动的消息
        worker ! DriverStateChanged(driverId, state, finalException)
      }
    }.start()
  }

worker接收到driver启动消息后会将消息发送给master

 case DriverStateChanged(driverId, state, exception) => {
      state match {
        case DriverState.ERROR =>
          logWarning(s"Driver $driverId failed with unrecoverable exception: ${exception.get}")
        case DriverState.FAILED =>
          logWarning(s"Driver $driverId exited with failure")
        case DriverState.FINISHED =>
          logInfo(s"Driver $driverId exited successfully")
        case DriverState.KILLED =>
          logInfo(s"Driver $driverId was killed by user")
        case _ =>
          logDebug(s"Driver $driverId changed state to $state")
      }
      master ! DriverStateChanged(driverId, state, exception)
      val driver = drivers.remove(driverId).get
      finishedDrivers(driverId) = driver
      memoryUsed -= driver.driverDesc.mem
      coresUsed -= driver.driverDesc.cores

 worker接收到启动executor消息后

首先master发送启动executor消息

 def launchExecutor(worker: WorkerInfo, exec: ExecutorDesc) {
    logInfo("Launching executor " + exec.fullId + " on worker " + worker.id)
    // 将executor加入wwoker内部的缓存
    worker.addExecutor(exec)
    // 向worker的actor发送lanchExecutor消息
    worker.actor ! LaunchExecutor(masterUrl,
      exec.application.id, exec.id, exec.application.desc, exec.cores, exec.memory)
    // 向executor对象的application的driver发送ExecutorAdded消息
    exec.application.driver ! 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
          // 首先创建Executor工作目录

          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_LOCAL_DIRS environment variable, and deleted by the Worker when the
          // application finishes.

          val appLocalDirs = appDirectories.get(appId).getOrElse {
            Utils.getOrCreateLocalRootDirs(conf).map { dir =>
              Utils.createDirectory(dir).getAbsolutePath()
            }.toSeq
          }
          appDirectories(appId) = appLocalDirs
          // 创建ExecutorRunner，然后加入本地缓存
          val manager = new ExecutorRunner(
            appId,
            execId,
            appDesc.copy(command = Worker.maybeUpdateSSLSettings(appDesc.command, conf)),
            cores_,
            memory_,
            self,
            workerId,
            host,
            webUi.boundPort,
            publicAddress,
            sparkHome,
            executorDir,
            akkaUrl,
            conf,
            appLocalDirs, ExecutorState.LOADING)
          executors(appId + "/" + execId) = manager
          manager.start()
          coresUsed += cores_
          memoryUsed += memory_
          master ! 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
            }
            master ! ExecutorStateChanged(appId, execId, ExecutorState.FAILED,
              Some(e.toString), None)
          }
        }
      }

  def start() {
    workerThread = new Thread("ExecutorRunner for " + fullId) {
      override def run() { fetchAndRunExecutor() }
    }
    workerThread.start()
    // Shutdown hook that kills actors on shutdown.
    shutdownHook = new Thread() {
      override def run() {
        killProcess(Some("Worker shutting down"))
      }
    }
    Runtime.getRuntime.addShutdownHook(shutdownHook)
  }

def fetchAndRunExecutor() {
    try {
      // Launch the process
      // 封装一个processBuilder
      val builder = CommandUtils.buildProcessBuilder(appDesc.command, memory,
        sparkHome.getAbsolutePath, substituteVariables)
      val command = builder.command()
      logInfo("Launch command: " + command.mkString("\"", "\" \"", "\""))

      builder.directory(executorDir)
      builder.environment.put("SPARK_LOCAL_DIRS", appLocalDirs.mkString(","))
      // In case we are running this from within the Spark Shell, avoid creating a "scala"
      // parent process for the executor command
      builder.environment.put("SPARK_LAUNCH_WITH_SCALA", "0")

      // Add webUI log urls
      val baseUrl =
        s"http://$publicAddress:$webUiPort/logPage/?appId=$appId&executorId=$execId&logType="
      builder.environment.put("SPARK_LOG_URL_STDERR", s"${baseUrl}stderr")
      builder.environment.put("SPARK_LOG_URL_STDOUT", s"${baseUrl}stdout")

      process = builder.start()
      val header = "Spark Executor Command: %s\n%s\n\n".format(
        command.mkString("\"", "\" \"", "\""), "=" * 40)

      // Redirect its stdout and stderr to files
      // 从定向文件流输出到文件
      val stdout = new File(executorDir, "stdout")
      stdoutAppender = FileAppender(process.getInputStream, stdout, conf)

      val stderr = new File(executorDir, "stderr")
      Files.write(header, stderr, UTF_8)
      stderrAppender = FileAppender(process.getErrorStream, stderr, conf)

      // Wait for it to exit; executor may exit with code 0 (when driver instructs it to shutdown)
      // or with nonzero exit code
      // 调用processbuilder启动executor
      val exitCode = process.waitFor()
      state = ExecutorState.EXITED
      val message = "Command exited with code " + exitCode
      // 向executor发送状态变化的消息
      worker ! ExecutorStateChanged(appId, execId, state, Some(message), Some(exitCode))
    } catch {
      case interrupted: InterruptedException => {
        logInfo("Runner thread for executor " + fullId + " interrupted")
        state = ExecutorState.KILLED
        killProcess(None)
      }
      case e: Exception => {
        logError("Error running executor", e)
        state = ExecutorState.FAILED
        killProcess(Some(e.toString))
      }
    }
  }

worker收到executor的状态变化消息后会向mastor发送executor状态变化消息

 case ExecutorStateChanged(appId, execId, state, message, exitStatus) =>
      master ! ExecutorStateChanged(appId, execId, state, message, exitStatus)
      val fullId = appId + "/" + execId
      if (ExecutorState.isFinished(state)) {
        executors.get(fullId) match {
          case Some(executor) =>
            logInfo("Executor " + fullId + " finished with state " + state +
              message.map(" message " + _).getOrElse("") +
              exitStatus.map(" exitStatus " + _).getOrElse(""))
            executors -= fullId
            finishedExecutors(fullId) = executor
            coresUsed -= executor.cores
            memoryUsed -= executor.memory
          case None =>
            logInfo("Unknown Executor " + fullId + " finished with state " + state +
              message.map(" message " + _).getOrElse("") +
              exitStatus.map(" exitStatus " + _).getOrElse(""))
        }
        maybeCleanupApplication(appId)
      }

 

def launchExecutor(worker: WorkerInfo, exec: ExecutorDesc) {
  logInfo("Launching executor " + exec.fullId + " on worker " + worker.id)
  // 将executor加入wwoker内部的缓存
worker.addExecutor(exec)
  // 向worker的actor发送lanchExecutor消息
worker.actor ! LaunchExecutor(masterUrl,
exec.application.id, exec.id, exec.application.desc, exec.cores, exec.memory)
  // 向executor对象的application的driver发送ExecutorAdded消息
exec.application.driver ! ExecutorAdded(
    exec.id, worker.id, worker.hostPort, exec.cores, exec.memory)
}