Spark执行环境

Spark对任务的计算都依托于Executor的能力，所有的Executor都有自己的Spark执行环境SparkEnv。有SparkEnv，就可以将数据存储在存储体系中；就能利用计算引擎对计算任务进行处理；在节点间进行通信等。SparkEnv还提供了多种多样的内部组件，实现不同的功能。SparkEnv是一个很重要的组件，虽然在创建SparkContext的时候也涉及它（只是因为local模式的需要），但它与Executor的关系则更为紧密。

SparkEnv的私有方法create用于创建SparkEnv，由于create方法涉及很多SparkEnv内部组件的实例化过程，如下简图：

 /**
   * Helper method to create a SparkEnv for a driver or an executor.
   */
  private def create(
      conf: SparkConf,
      executorId: String,
      hostname: String,
      port: Int,
      isDriver: Boolean,
      isLocal: Boolean,
      numUsableCores: Int,
      listenerBus: LiveListenerBus = null,
      mockOutputCommitCoordinator: Option[OutputCommitCoordinator] = None): SparkEnv = {

    // Listener bus is only used on the driver
    if (isDriver) {
      assert(listenerBus != null, "Attempted to create driver SparkEnv with null listener bus!")
    }

    val securityManager = new SecurityManager(conf)

    val systemName = if (isDriver) driverSystemName else executorSystemName
    val rpcEnv = RpcEnv.create(systemName, hostname, port, conf, securityManager,
      clientMode = !isDriver)

    // Figure out which port RpcEnv actually bound to in case the original port is 0 or occupied.
    // In the non-driver case, the RPC env's address may be null since it may not be listening
    // for incoming connections.
    if (isDriver) {
      conf.set("spark.driver.port", rpcEnv.address.port.toString)
    } else if (rpcEnv.address != null) {
      conf.set("spark.executor.port", rpcEnv.address.port.toString)
    }

    // Create an instance of the class with the given name, possibly initializing it with our conf
    def instantiateClass[T](className: String): T = {
      val cls = Utils.classForName(className)
      // Look for a constructor taking a SparkConf and a boolean isDriver, then one taking just
      // SparkConf, then one taking no arguments
      try {
        cls.getConstructor(classOf[SparkConf], java.lang.Boolean.TYPE)
          .newInstance(conf, new java.lang.Boolean(isDriver))
          .asInstanceOf[T]
      } catch {
        case _: NoSuchMethodException =>
          try {
            cls.getConstructor(classOf[SparkConf]).newInstance(conf).asInstanceOf[T]
          } catch {
            case _: NoSuchMethodException =>
              cls.getConstructor().newInstance().asInstanceOf[T]
          }
      }
    }

    // Create an instance of the class named by the given SparkConf property, or defaultClassName
    // if the property is not set, possibly initializing it with our conf
    def instantiateClassFromConf[T](propertyName: String, defaultClassName: String): T = {
      instantiateClass[T](conf.get(propertyName, defaultClassName))
    }

    val serializer = instantiateClassFromConf[Serializer](
      "spark.serializer", "org.apache.spark.serializer.JavaSerializer")
    logDebug(s"Using serializer: ${serializer.getClass}")

    val serializerManager = new SerializerManager(serializer, conf)

    val closureSerializer = new JavaSerializer(conf)

    def registerOrLookupEndpoint(
        name: String, endpointCreator: => RpcEndpoint):
      RpcEndpointRef = {
      if (isDriver) {
        logInfo("Registering " + name)
        rpcEnv.setupEndpoint(name, endpointCreator)
      } else {
        RpcUtils.makeDriverRef(name, conf, rpcEnv)
      }
    }

    val broadcastManager = new BroadcastManager(isDriver, conf, securityManager)

    val mapOutputTracker = if (isDriver) {
      new MapOutputTrackerMaster(conf, broadcastManager, isLocal)
    } else {
      new MapOutputTrackerWorker(conf)
    }

    // Have to assign trackerEndpoint after initialization as MapOutputTrackerEndpoint
    // requires the MapOutputTracker itself
    mapOutputTracker.trackerEndpoint = registerOrLookupEndpoint(MapOutputTracker.ENDPOINT_NAME,
      new MapOutputTrackerMasterEndpoint(
        rpcEnv, mapOutputTracker.asInstanceOf[MapOutputTrackerMaster], conf))

    // Let the user specify short names for shuffle managers
    val shortShuffleMgrNames = Map(
      "sort" -> classOf[org.apache.spark.shuffle.sort.SortShuffleManager].getName,
      "tungsten-sort" -> classOf[org.apache.spark.shuffle.sort.SortShuffleManager].getName)
    val shuffleMgrName = conf.get("spark.shuffle.manager", "sort")
    val shuffleMgrClass = shortShuffleMgrNames.getOrElse(shuffleMgrName.toLowerCase, shuffleMgrName)
    val shuffleManager = instantiateClass[ShuffleManager](shuffleMgrClass)

    val useLegacyMemoryManager = conf.getBoolean("spark.memory.useLegacyMode", false)
    val memoryManager: MemoryManager =
      if (useLegacyMemoryManager) {
        new StaticMemoryManager(conf, numUsableCores)
      } else {
        UnifiedMemoryManager(conf, numUsableCores)
      }

    val blockTransferService =
      new NettyBlockTransferService(conf, securityManager, hostname, numUsableCores)

    val blockManagerMaster = new BlockManagerMaster(registerOrLookupEndpoint(
      BlockManagerMaster.DRIVER_ENDPOINT_NAME,
      new BlockManagerMasterEndpoint(rpcEnv, isLocal, conf, listenerBus)),
      conf, isDriver)

    // NB: blockManager is not valid until initialize() is called later.
    val blockManager = new BlockManager(executorId, rpcEnv, blockManagerMaster,
      serializerManager, conf, memoryManager, mapOutputTracker, shuffleManager,
      blockTransferService, securityManager, numUsableCores)

    val metricsSystem = if (isDriver) {
      // Don't start metrics system right now for Driver.
      // We need to wait for the task scheduler to give us an app ID.
      // Then we can start the metrics system.
      MetricsSystem.createMetricsSystem("driver", conf, securityManager)
    } else {
      // We need to set the executor ID before the MetricsSystem is created because sources and
      // sinks specified in the metrics configuration file will want to incorporate this executor's
      // ID into the metrics they report.
      conf.set("spark.executor.id", executorId)
      val ms = MetricsSystem.createMetricsSystem("executor", conf, securityManager)
      ms.start()
      ms
    }

    val outputCommitCoordinator = mockOutputCommitCoordinator.getOrElse {
      new OutputCommitCoordinator(conf, isDriver)
    }
    val outputCommitCoordinatorRef = registerOrLookupEndpoint("OutputCommitCoordinator",
      new OutputCommitCoordinatorEndpoint(rpcEnv, outputCommitCoordinator))
    outputCommitCoordinator.coordinatorRef = Some(outputCommitCoordinatorRef)
    //构造方法
    val envInstance = new SparkEnv(
      executorId,
      rpcEnv,
      serializer,
      closureSerializer,
      serializerManager,
      mapOutputTracker,
      shuffleManager,
      broadcastManager,
      blockManager,
      securityManager,
      metricsSystem,
      memoryManager,
      outputCommitCoordinator,
      conf)

    // Add a reference to tmp dir created by driver, we will delete this tmp dir when stop() is
    // called, and we only need to do it for driver. Because driver may run as a service, and if we
    // don't delete this tmp dir when sc is stopped, then will create too many tmp dirs.
    if (isDriver) {
      val sparkFilesDir = Utils.createTempDir(Utils.getLocalDir(conf), "userFiles").getAbsolutePath
      envInstance.driverTmpDir = Some(sparkFilesDir)
    }

    envInstance
  }

以下将对部分属性进行讲解：

1. 安全管理器SecurityManager
2. RPC环境
3. 序列化管理器SerializerManager
4. 广播管理器BroadcastManager
5. map任务输出跟踪器
6. 度量系统
7. 输出提交协调器