Spark源码学习笔记1-SparkContext

先看一个简单的程序，代码量很少。

object PiDemo extends App {
  val conf = new SparkConf().setAppName("SparkPi").setMaster("local[4]")
  val sc = new SparkContext(conf)
  var pairs = sc.parallelize(List((1, 1), (2, 2), (3, 3)))

  for (i <- pairs) {
    println("i._1 = " + i._1 + ", i._2 = " + i._2)
  }
}

这个程序中主要初始化了3个变量：conf: SparkConf, sc: SparkContext, pairs: RDD；其中pairs是具体的数据，conf是Spark程序的配置，sc相当于是程序的上下文环境，主要包括一些初始化工作。
我们主要看看SparkContext的构造函数中做了哪些重要的事情（部分代码）：

class SparkContext(config: SparkConf) extends Logging {

/*......*/

  // In order to prevent multiple SparkContexts from being active at the same time, mark this
  // context as having started construction.
  // NOTE: this must be placed at the beginning of the SparkContext constructor.
  SparkContext.markPartiallyConstructed(this, allowMultipleContexts)
  try {
    _conf = config.clone()
    _conf.validateSettings()

    /*......*/
    // "_jobProgressListener" should be set up before creating SparkEnv because when creating
    // "SparkEnv", some messages will be posted to "listenerBus" and we should not miss them.
    _jobProgressListener = new JobProgressListener(_conf)
    listenerBus.addListener(jobProgressListener)

    // Create the Spark execution environment (cache, map output tracker, etc)
    _env = createSparkEnv(_conf, isLocal, listenerBus)

    _statusTracker = new SparkStatusTracker(this)

    // 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)
    _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()

    _applicationId = _taskScheduler.applicationId()
    ...
    _env.blockManager.initialize(_applicationId)

    _eventLogger =
      if (isEventLogEnabled) {
        val logger =
          new EventLoggingListener(_applicationId, _applicationAttemptId, _eventLogDir.get,
            _conf, _hadoopConfiguration)
        logger.start()
        listenerBus.addListener(logger)
        Some(logger)
      } else {
        None
      }

    // Optionally scale number of executors dynamically based on workload. Exposed for testing.
    val dynamicAllocationEnabled = Utils.isDynamicAllocationEnabled(_conf)
    _executorAllocationManager =
      if (dynamicAllocationEnabled) {
        schedulerBackend match {
          case b: ExecutorAllocationClient =>
            Some(new ExecutorAllocationManager(
              schedulerBackend.asInstanceOf[ExecutorAllocationClient], listenerBus, _conf))
          case _ =>
            None
        }
      } else {
        None
      }
    _executorAllocationManager.foreach(_.start())

    _cleaner =
      if (_conf.getBoolean("spark.cleaner.referenceTracking", true)) {
        Some(new ContextCleaner(this))
      } else {
        None
      }
    _cleaner.foreach(_.start())

    setupAndStartListenerBus()
    postEnvironmentUpdate()
    postApplicationStart()

    // Post init
    _taskScheduler.postStartHook()
  } catch {
    ...
  }    
}

我们从中可以发现一些重要的组成部分：

• JobProgressListener 和 LiveListenerBus

// "_jobProgressListener" should be set up before creating SparkEnv because when creating
    // "SparkEnv", some messages will be posted to "listenerBus" and we should not miss them.
    _jobProgressListener = new JobProgressListener(_conf)
    listenerBus.addListener(jobProgressListener)

• SparkEnv

// Create the Spark execution environment (cache, map output tracker, etc)
    _env = createSparkEnv(_conf, isLocal, listenerBus)

• SparkStatusTracker

_statusTracker = new SparkStatusTracker(this)

• HeartbeatReceiver

// 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))

• TaskScheduler, DAGScheduler

// 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()

• EventLoggingListener

_eventLogger =
      if (isEventLogEnabled) {
        val logger =
          new EventLoggingListener(_applicationId, _applicationAttemptId, _eventLogDir.get,
            _conf, _hadoopConfiguration)
        logger.start()
        listenerBus.addListener(logger)
        Some(logger)
      } else {
        None
      }

• ExecutorAllocationManager

// Optionally scale number of executors dynamically based on workload. Exposed for testing.
    val dynamicAllocationEnabled = Utils.isDynamicAllocationEnabled(_conf)
    _executorAllocationManager =
      if (dynamicAllocationEnabled) {
        schedulerBackend match {
          case b: ExecutorAllocationClient =>
            Some(new ExecutorAllocationManager(
              schedulerBackend.asInstanceOf[ExecutorAllocationClient], listenerBus, _conf))
          case _ =>
            None
        }
      } else {
        None
      }
    _executorAllocationManager.foreach(_.start())

• ContextCleaner

_cleaner =
      if (_conf.getBoolean("spark.cleaner.referenceTracking", true)) {
        Some(new ContextCleaner(this))
      } else {
        None
      }
    _cleaner.foreach(_.start())