Spark里面的任务调度：离SparkContext开始

看一下如今支持的部署方法：

 /** Creates a task scheduler based on a given master URL. Extracted for testing. */
  private def createTaskScheduler(sc: SparkContext, master: String): TaskScheduler = {
    // Regular expression used for local[N] and local[*] master formats
    val LOCAL_N_REGEX = """local\[([0-9]+|\*)\]""".r
    // Regular expression for local[N, maxRetries], used in tests with failing tasks
    val LOCAL_N_FAILURES_REGEX = """local\[([0-9]+|\*)\s*,\s*([0-9]+)\]""".r
    // Regular expression for simulating a Spark cluster of [N, cores, memory] locally
    val LOCAL_CLUSTER_REGEX = """local-cluster\[\s*([0-9]+)\s*,\s*([0-9]+)\s*,\s*([0-9]+)\s*]""".r
    // Regular expression for connecting to Spark deploy clusters
    val SPARK_REGEX = """spark://(.*)""".r
    // Regular expression for connection to Mesos cluster by mesos:// or zk:// url
    val MESOS_REGEX = """(mesos|zk)://.*""".r
    // Regular expression for connection to Simr cluster
    val SIMR_REGEX = """simr://(.*)""".r

    // When running locally, don‘t try to re-execute tasks on failure.
    val MAX_LOCAL_TASK_FAILURES = 1

    master match {
      case "local" =>
        val scheduler = new TaskSchedulerImpl(sc, MAX_LOCAL_TASK_FAILURES, isLocal = true)
        val backend = new LocalBackend(scheduler, 1)
        scheduler.initialize(backend)
        scheduler

      case LOCAL_N_REGEX(threads) =>
        def localCpuCount = 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
        val scheduler = new TaskSchedulerImpl(sc, MAX_LOCAL_TASK_FAILURES, isLocal = true)
        val backend = new LocalBackend(scheduler, threadCount)
        scheduler.initialize(backend)
        scheduler

      case LOCAL_N_FAILURES_REGEX(threads, maxFailures) =>
        def localCpuCount = 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 LocalBackend(scheduler, threadCount)
        scheduler.initialize(backend)
        scheduler

      case SPARK_REGEX(sparkUrl) =>
        val scheduler = new TaskSchedulerImpl(sc)
        val masterUrls = sparkUrl.split(",").map("spark://" + _)
        val backend = new SparkDeploySchedulerBackend(scheduler, sc, masterUrls)
        scheduler.initialize(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)
        val masterUrls = localCluster.start()
        val backend = new SparkDeploySchedulerBackend(scheduler, sc, masterUrls)
        scheduler.initialize(backend)
        backend.shutdownCallback = (backend: SparkDeploySchedulerBackend) => {
          localCluster.stop()
        }
        scheduler

      case "yarn-standalone" | "yarn-cluster" =>
        if (master == "yarn-standalone") {
          logWarning(
            "\"yarn-standalone\" is deprecated as of Spark 1.0. Use \"yarn-cluster\" instead.")
        }
        val scheduler = try {
          val clazz = Class.forName("org.apache.spark.scheduler.cluster.YarnClusterScheduler")
          val cons = clazz.getConstructor(classOf[SparkContext])
          cons.newInstance(sc).asInstanceOf[TaskSchedulerImpl]
        } catch {
          // TODO: Enumerate the exact reasons why it can fail
          // But irrespective of it, it means we cannot proceed !
          case e: Exception => {
            throw new SparkException("YARN mode not available ?", e)
          }
        }
        val backend = try {
          val clazz =
            Class.forName("org.apache.spark.scheduler.cluster.YarnClusterSchedulerBackend")
          val cons = clazz.getConstructor(classOf[TaskSchedulerImpl], classOf[SparkContext])
          cons.newInstance(scheduler, sc).asInstanceOf[CoarseGrainedSchedulerBackend]
        } catch {
          case e: Exception => {
            throw new SparkException("YARN mode not available ?", e)
          }
        }
        scheduler.initialize(backend)
        scheduler

      case "yarn-client" =>
        val scheduler = try {
          val clazz =
            Class.forName("org.apache.spark.scheduler.cluster.YarnClientClusterScheduler")
          val cons = clazz.getConstructor(classOf[SparkContext])
          cons.newInstance(sc).asInstanceOf[TaskSchedulerImpl]

        } catch {
          case e: Exception => {
            throw new SparkException("YARN mode not available ?
", e)
          }
        }

        val backend = try {
          val clazz =
            Class.forName("org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend")
          val cons = clazz.getConstructor(classOf[TaskSchedulerImpl], classOf[SparkContext])
          cons.newInstance(scheduler, sc).asInstanceOf[CoarseGrainedSchedulerBackend]
        } catch {
          case e: Exception => {
            throw new SparkException("YARN mode not available ?", e)
          }
        }

        scheduler.initialize(backend)
        scheduler

      case mesosUrl @ MESOS_REGEX(_) =>
        MesosNativeLibrary.load()
        val scheduler = new TaskSchedulerImpl(sc)
        val coarseGrained = sc.conf.getBoolean("spark.mesos.coarse", false)
        val url = mesosUrl.stripPrefix("mesos://") // strip scheme from raw Mesos URLs
        val backend = if (coarseGrained) {
          new CoarseMesosSchedulerBackend(scheduler, sc, url)
        } else {
          new MesosSchedulerBackend(scheduler, sc, url)
        }
        scheduler.initialize(backend)
        scheduler

      case SIMR_REGEX(simrUrl) =>
        val scheduler = new TaskSchedulerImpl(sc)
        val backend = new SimrSchedulerBackend(scheduler, sc, simrUrl)
        scheduler.initialize(backend)
        scheduler

      case _ =>
        throw new SparkException("Could not parse Master URL: ‘" + master + "‘")
    }
  }
}

      case SPARK_REGEX(sparkUrl) =>
        val scheduler = new TaskSchedulerImpl(sc)
        val masterUrls = sparkUrl.split(",").map("spark://" + _)
        val backend = new SparkDeploySchedulerBackend(scheduler, sc, masterUrls)
        scheduler.initialize(backend)
        scheduler

这个也是在SparkContext初始化时调用的：

  def initialize(backend: SchedulerBackend) {
    this.backend = backend
    // temporarily set rootPool name to empty
    rootPool = new Pool("", schedulingMode, 0, 0)
    schedulableBuilder = {
      schedulingMode match {
        case SchedulingMode.FIFO =>
          new FIFOSchedulableBuilder(rootPool)
        case SchedulingMode.FAIR =>
          new FairSchedulableBuilder(rootPool, conf)
      }
    }
    schedulableBuilder.buildPools()
  }

// default scheduler is FIFO
  private val schedulingModeConf = conf.get("spark.scheduler.mode", "FIFO")
  val schedulingMode: SchedulingMode = try {
    SchedulingMode.withName(schedulingModeConf.toUpperCase)
  } catch {
    case e: java.util.NoSuchElementException =>
      throw new SparkException(s"Unrecognized spark.scheduler.mode: $schedulingModeConf")
  }

start的实现例如以下：

  override def start() {
    backend.start()

    if (!isLocal && conf.getBoolean("spark.speculation", false)) {
      logInfo("Starting speculative execution thread")
      import sc.env.actorSystem.dispatcher
      sc.env.actorSystem.scheduler.schedule(SPECULATION_INTERVAL milliseconds,
            SPECULATION_INTERVAL milliseconds) {
        Utils.tryOrExit { checkSpeculatableTasks() }
      }
    }
  }

主要是backend的启动。对于非本地模式。而且设置了spark.speculation为true，那么对于指定时间未返回的task将会启动另外的task来运行。事实上对于一般的应用，这个的确可能会降低任务的运行时间，可是也浪费了集群的计算资源。

因此对于离线应用来说，这个设置是不推荐的。

org.apache.spark.scheduler.cluster.SparkDeploySchedulerBackend是Standalone模式的SchedulerBackend。它的定义例如以下：

private[spark] class SparkDeploySchedulerBackend(
    scheduler: TaskSchedulerImpl,
    sc: SparkContext,
    masters: Array[String])
  extends CoarseGrainedSchedulerBackend(scheduler, sc.env.actorSystem)
  with AppClientListener
  with Logging {

 override def start() {
    super.start()

    // The endpoint for executors to talk to us
    val driverUrl = "akka.tcp://%s@%s:%s/user/%s".format(
      SparkEnv.driverActorSystemName,
      conf.get("spark.driver.host"),
      conf.get("spark.driver.port"),
      CoarseGrainedSchedulerBackend.ACTOR_NAME)
    val args = Seq(driverUrl, "{{EXECUTOR_ID}}", "{{HOSTNAME}}", "{{CORES}}", "{{WORKER_URL}}")
    val extraJavaOpts = sc.conf.getOption("spark.executor.extraJavaOptions")
      .map(Utils.splitCommandString).getOrElse(Seq.empty)
    val classPathEntries = sc.conf.getOption("spark.executor.extraClassPath").toSeq.flatMap { cp =>
      cp.split(java.io.File.pathSeparator)
    }
    val libraryPathEntries =
      sc.conf.getOption("spark.executor.extraLibraryPath").toSeq.flatMap { cp =>
        cp.split(java.io.File.pathSeparator)
      }

    // 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, libraryPathEntries, javaOpts)
    val appDesc = new ApplicationDescription(sc.appName, maxCores, sc.executorMemory, command,
      sc.ui.appUIAddress, sc.eventLogger.map(_.logDir))

    client = new AppClient(sc.env.actorSystem, masters, appDesc, this, conf)
    client.start()

    waitForRegistration()
  }

接下来，我们将对TaskScheduler。SchedulerBackend和DAG Scheduler进行具体解释。来逐步揭开他们的神奇面纱。