Spark Core源码精读计划9 | Spark RPC环境中的消息调度逻辑

  private val endpoints: ConcurrentMap[String, EndpointData] =
    new ConcurrentHashMap[String, EndpointData]

  private val endpointRefs: ConcurrentMap[RpcEndpoint, RpcEndpointRef] =
    new ConcurrentHashMap[RpcEndpoint, RpcEndpointRef]

  private val receivers = new LinkedBlockingQueue[EndpointData]

  private val threadpool: ThreadPoolExecutor = {
    val availableCores =
      if (numUsableCores > 0) numUsableCores else Runtime.getRuntime.availableProcessors()
    val numThreads = nettyEnv.conf.getInt("spark.rpc.netty.dispatcher.numThreads",
      math.max(2, availableCores))
    val pool = ThreadUtils.newDaemonFixedThreadPool(numThreads, "dispatcher-event-loop")
    for (i <- 0 until numThreads) {
      pool.execute(new MessageLoop)
    }
    pool
  }

  private class EndpointData(
      val name: String,
      val endpoint: RpcEndpoint,
      val ref: NettyRpcEndpointRef) {
    val inbox = new Inbox(ref, endpoint)
  }

  private class MessageLoop extends Runnable {
    override def run(): Unit = {
      try {
        while (true) {
          try {
            val data = receivers.take()
            if (data == PoisonPill) {
              receivers.offer(PoisonPill)
              return
            }
            data.inbox.process(Dispatcher.this)
          } catch {
            case NonFatal(e) => logError(e.getMessage, e)
          }
        }
      } catch {
        case ie: InterruptedException =>
      }
    }
  }

  private val PoisonPill = new EndpointData(null, null, null)

  @GuardedBy("this")
  protected val messages = new java.util.LinkedList[InboxMessage]()
 
  def process(dispatcher: Dispatcher): Unit = {
    var message: InboxMessage = null
    inbox.synchronized {
      if (!enableConcurrent && numActiveThreads != 0) {
        return
      }
      message = messages.poll()
      if (message != null) {
        numActiveThreads += 1
      } else {
        return
      }
    }
    while (true) {
      safelyCall(endpoint) {
        message match {
          case RpcMessage(_sender, content, context) =>
            try {
              endpoint.receiveAndReply(context).applyOrElse[Any, Unit](content, { msg =>
                throw new SparkException(s"Unsupported message $message from ${_sender}")
              })
            } catch {
              case NonFatal(e) =>
                context.sendFailure(e)
                throw e
            }

          case OneWayMessage(_sender, content) =>
            endpoint.receive.applyOrElse[Any, Unit](content, { msg =>
              throw new SparkException(s"Unsupported message $message from ${_sender}")
            })

          case OnStart =>
            endpoint.onStart()
            if (!endpoint.isInstanceOf[ThreadSafeRpcEndpoint]) {
              inbox.synchronized {
                if (!stopped) {
                  enableConcurrent = true
                }
              }
            }

          case OnStop =>
            val activeThreads = inbox.synchronized {
              inbox.numActiveThreads
            }
            assert(activeThreads == 1,
              s"There should be only a single active thread but found $activeThreads threads.")
            dispatcher.removeRpcEndpointRef(endpoint)
            endpoint.onStop()
            assert(isEmpty, "OnStop should be the last message")

          case RemoteProcessConnected(remoteAddress) =>
            endpoint.onConnected(remoteAddress)

          case RemoteProcessDisconnected(remoteAddress) =>
            endpoint.onDisconnected(remoteAddress)

          case RemoteProcessConnectionError(cause, remoteAddress) =>
            endpoint.onNetworkError(cause, remoteAddress)
        }
      }

      inbox.synchronized {
        if (!enableConcurrent && numActiveThreads != 1) {
          numActiveThreads -= 1
          return
        }
        message = messages.poll()
        if (message == null) {
          numActiveThreads -= 1
          return
        }
      }
    }
  }

private[netty] sealed trait InboxMessage

private[netty] case class OneWayMessage(
    senderAddress: RpcAddress,
    content: Any) extends InboxMessage

private[netty] case class RpcMessage(
    senderAddress: RpcAddress,
    content: Any,
    context: NettyRpcCallContext) extends InboxMessage

private[netty] case object OnStart extends InboxMessage

private[netty] case object OnStop extends InboxMessage

private[netty] case class RemoteProcessConnected(remoteAddress: RpcAddress) extends InboxMessage

private[netty] case class RemoteProcessDisconnected(remoteAddress: RpcAddress) extends InboxMessage

private[netty] case class RemoteProcessConnectionError(cause: Throwable, remoteAddress: RpcAddress) extends InboxMessage

  def registerRpcEndpoint(name: String, endpoint: RpcEndpoint): NettyRpcEndpointRef = {
    val addr = RpcEndpointAddress(nettyEnv.address, name)
    val endpointRef = new NettyRpcEndpointRef(nettyEnv.conf, addr, nettyEnv)
    synchronized {
      if (stopped) {
        throw new IllegalStateException("RpcEnv has been stopped")
      }
      if (endpoints.putIfAbsent(name, new EndpointData(name, endpoint, endpointRef)) != null) {
        throw new IllegalArgumentException(s"There is already an RpcEndpoint called $name")
      }
      val data = endpoints.get(name)
      endpointRefs.put(data.endpoint, data.ref)
      receivers.offer(data) 
    }
    endpointRef
  }

  inbox.synchronized {
    messages.add(OnStart)
  }

  private def postMessage(
      endpointName: String,
      message: InboxMessage,
      callbackIfStopped: (Exception) => Unit): Unit = {
    val error = synchronized {
      val data = endpoints.get(endpointName)
      if (stopped) {
        Some(new RpcEnvStoppedException())
      } else if (data == null) {
        Some(new SparkException(s"Could not find $endpointName."))
      } else {
        data.inbox.post(message)
        receivers.offer(data)
        None
      }
    }
    error.foreach(callbackIfStopped)
  }

def stop(): Unit = {
    synchronized {
      if (stopped) {
        return
      }
      stopped = true
    }

    endpoints.keySet().asScala.foreach(unregisterRpcEndpoint)
    receivers.offer(PoisonPill)
    threadpool.shutdown()
  }