spark 2.1 LocalBackend Execute Task Process

LocalEndpoint call reviveOffers, when receive a ReviveOffers message.

  def reviveOffers() {
    val offers = IndexedSeq(new WorkerOffer(localExecutorId, localExecutorHostname, freeCores))
    for (task <- scheduler.resourceOffers(offers).flatten) {
      freeCores -= scheduler.CPUS_PER_TASK
      executor.launchTask(executorBackend, taskId = task.taskId, attemptNumber = task.attemptNumber,
        task.name, task.serializedTask)
    }
  }

Executor.launchTask

  def launchTask(
      context: ExecutorBackend,
      taskId: Long,
      attemptNumber: Int,
      taskName: String,
      serializedTask: ByteBuffer): Unit = {
    val tr = new TaskRunner(context, taskId = taskId, attemptNumber = attemptNumber, taskName,
      serializedTask)
    runningTasks.put(taskId, tr)
    threadPool.execute(tr)
  }

TaskRunner.run

override def run(): Unit = {
      val threadMXBean = ManagementFactory.getThreadMXBean
      val taskMemoryManager = new TaskMemoryManager(env.memoryManager, taskId)
      val deserializeStartTime = System.currentTimeMillis()
      val deserializeStartCpuTime = if (threadMXBean.isCurrentThreadCpuTimeSupported) {
        threadMXBean.getCurrentThreadCpuTime
      } else 0L
      Thread.currentThread.setContextClassLoader(replClassLoader)
      val ser = env.closureSerializer.newInstance()
      logInfo(s"Running $taskName (TID $taskId)")
      execBackend.statusUpdate(taskId, TaskState.RUNNING, EMPTY_BYTE_BUFFER)
      var taskStart: Long = 0
      var taskStartCpu: Long = 0
      startGCTime = computeTotalGcTime()

      try {
        val (taskFiles, taskJars, taskProps, taskBytes) =
          Task.deserializeWithDependencies(serializedTask)

        // Must be set before updateDependencies() is called, in case fetching dependencies
        // requires access to properties contained within (e.g. for access control).
        Executor.taskDeserializationProps.set(taskProps)

        updateDependencies(taskFiles, taskJars)
        task = ser.deserialize[Task[Any]](taskBytes, Thread.currentThread.getContextClassLoader)
        task.localProperties = taskProps
        task.setTaskMemoryManager(taskMemoryManager)

        // If this task has been killed before we deserialized it, let's quit now. Otherwise,
        // continue executing the task.
        if (killed) {
          // Throw an exception rather than returning, because returning within a try{} block
          // causes a NonLocalReturnControl exception to be thrown. The NonLocalReturnControl
          // exception will be caught by the catch block, leading to an incorrect ExceptionFailure
          // for the task.
          throw new TaskKilledException
        }

        logDebug("Task " + taskId + "'s epoch is " + task.epoch)
        env.mapOutputTracker.updateEpoch(task.epoch)

        // Run the actual task and measure its runtime.
        taskStart = System.currentTimeMillis()
        taskStartCpu = if (threadMXBean.isCurrentThreadCpuTimeSupported) {
          threadMXBean.getCurrentThreadCpuTime
        } else 0L
        var threwException = true
        val value = try {
          val res = task.run(
            taskAttemptId = taskId,
            attemptNumber = attemptNumber,
            metricsSystem = env.metricsSystem)
          threwException = false
          res
        } finally {
          val releasedLocks = env.blockManager.releaseAllLocksForTask(taskId)
          val freedMemory = taskMemoryManager.cleanUpAllAllocatedMemory()

          if (freedMemory > 0 && !threwException) {
            val errMsg = s"Managed memory leak detected; size = $freedMemory bytes, TID = $taskId"
            if (conf.getBoolean("spark.unsafe.exceptionOnMemoryLeak", false)) {
              throw new SparkException(errMsg)
            } else {
              logWarning(errMsg)
            }
          }

          if (releasedLocks.nonEmpty && !threwException) {
            val errMsg =
              s"${releasedLocks.size} block locks were not released by TID = $taskId:\n" +
                releasedLocks.mkString("[", ", ", "]")
            if (conf.getBoolean("spark.storage.exceptionOnPinLeak", false)) {
              throw new SparkException(errMsg)
            } else {
              logWarning(errMsg)
            }
          }
        }
        val taskFinish = System.currentTimeMillis()
        val taskFinishCpu = if (threadMXBean.isCurrentThreadCpuTimeSupported) {
          threadMXBean.getCurrentThreadCpuTime
        } else 0L

        // If the task has been killed, let's fail it.
        if (task.killed) {
          throw new TaskKilledException
        }

        val resultSer = env.serializer.newInstance()
        val beforeSerialization = System.currentTimeMillis()
        val valueBytes = resultSer.serialize(value)
        val afterSerialization = System.currentTimeMillis()

        // Deserialization happens in two parts: first, we deserialize a Task object, which
        // includes the Partition. Second, Task.run() deserializes the RDD and function to be run.
        task.metrics.setExecutorDeserializeTime(
          (taskStart - deserializeStartTime) + task.executorDeserializeTime)
        task.metrics.setExecutorDeserializeCpuTime(
          (taskStartCpu - deserializeStartCpuTime) + task.executorDeserializeCpuTime)
        // We need to subtract Task.run()'s deserialization time to avoid double-counting
        task.metrics.setExecutorRunTime((taskFinish - taskStart) - task.executorDeserializeTime)
        task.metrics.setExecutorCpuTime(
          (taskFinishCpu - taskStartCpu) - task.executorDeserializeCpuTime)
        task.metrics.setJvmGCTime(computeTotalGcTime() - startGCTime)
        task.metrics.setResultSerializationTime(afterSerialization - beforeSerialization)

        // Note: accumulator updates must be collected after TaskMetrics is updated
        val accumUpdates = task.collectAccumulatorUpdates()
        // TODO: do not serialize value twice
        val directResult = new DirectTaskResult(valueBytes, accumUpdates)
        val serializedDirectResult = ser.serialize(directResult)
        val resultSize = serializedDirectResult.limit

        // directSend = sending directly back to the driver
        val serializedResult: ByteBuffer = {
          if (maxResultSize > 0 && resultSize > maxResultSize) {
            logWarning(s"Finished $taskName (TID $taskId). Result is larger than maxResultSize " +
              s"(${Utils.bytesToString(resultSize)} > ${Utils.bytesToString(maxResultSize)}), " +
              s"dropping it.")
            ser.serialize(new IndirectTaskResult[Any](TaskResultBlockId(taskId), resultSize))
          } else if (resultSize > maxDirectResultSize) {
            val blockId = TaskResultBlockId(taskId)
            env.blockManager.putBytes(
              blockId,
              new ChunkedByteBuffer(serializedDirectResult.duplicate()),
              StorageLevel.MEMORY_AND_DISK_SER)
            logInfo(
              s"Finished $taskName (TID $taskId). $resultSize bytes result sent via BlockManager)")
            ser.serialize(new IndirectTaskResult[Any](blockId, resultSize))
          } else {
            logInfo(s"Finished $taskName (TID $taskId). $resultSize bytes result sent to driver")
            serializedDirectResult
          }
        }

        execBackend.statusUpdate(taskId, TaskState.FINISHED, serializedResult)

      } catch {
        case ffe: FetchFailedException =>
          val reason = ffe.toTaskFailedReason
          setTaskFinishedAndClearInterruptStatus()
          execBackend.statusUpdate(taskId, TaskState.FAILED, ser.serialize(reason))

        case _: TaskKilledException =>
          logInfo(s"Executor killed $taskName (TID $taskId)")
          setTaskFinishedAndClearInterruptStatus()
          execBackend.statusUpdate(taskId, TaskState.KILLED, ser.serialize(TaskKilled))

        case _: InterruptedException if task.killed =>
          logInfo(s"Executor interrupted and killed $taskName (TID $taskId)")
          setTaskFinishedAndClearInterruptStatus()
          execBackend.statusUpdate(taskId, TaskState.KILLED, ser.serialize(TaskKilled))

        case CausedBy(cDE: CommitDeniedException) =>
          val reason = cDE.toTaskFailedReason
          setTaskFinishedAndClearInterruptStatus()
          execBackend.statusUpdate(taskId, TaskState.FAILED, ser.serialize(reason))

        case t: Throwable =>
          // Attempt to exit cleanly by informing the driver of our failure.
          // If anything goes wrong (or this was a fatal exception), we will delegate to
          // the default uncaught exception handler, which will terminate the Executor.
          logError(s"Exception in $taskName (TID $taskId)", t)

          // Collect latest accumulator values to report back to the driver
          val accums: Seq[AccumulatorV2[_, _]] =
            if (task != null) {
              task.metrics.setExecutorRunTime(System.currentTimeMillis() - taskStart)
              task.metrics.setJvmGCTime(computeTotalGcTime() - startGCTime)
              task.collectAccumulatorUpdates(taskFailed = true)
            } else {
              Seq.empty
            }

          val accUpdates = accums.map(acc => acc.toInfo(Some(acc.value), None))

          val serializedTaskEndReason = {
            try {
              ser.serialize(new ExceptionFailure(t, accUpdates).withAccums(accums))
            } catch {
              case _: NotSerializableException =>
                // t is not serializable so just send the stacktrace
                ser.serialize(new ExceptionFailure(t, accUpdates, false).withAccums(accums))
            }
          }
          setTaskFinishedAndClearInterruptStatus()
          execBackend.statusUpdate(taskId, TaskState.FAILED, serializedTaskEndReason)

          // Don't forcibly exit unless the exception was inherently fatal, to avoid
          // stopping other tasks unnecessarily.
          if (Utils.isFatalError(t)) {
            SparkUncaughtExceptionHandler.uncaughtException(t)
          }

      } finally {
        runningTasks.remove(taskId)
      }
    }
  }