spark源码分析二(NettyRpcEnv)

NettyRpcEnv

源码版本2.4.7
需要关注的是env里面几个关键的属性和方法如图:

1 dispatcher 分发

消息分发程序，负责将RPC消息路由到适当的端点
dispatcher的成员内部类: EndpointData实体

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

Inbox:收件箱，用于存储[[RpcEndpoint]]的消息并以线程安全的方式向其发布消息
process处理消息,且OnStart消息也是在此产生

  // OnStart should be the first message to process
  inbox.synchronized {
    messages.add(OnStart)
  }
   /**
   * Process stored messages.
   */
  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 e: Throwable =>
                context.sendFailure(e)
                // Throw the exception -- this exception will be caught by the safelyCall function.
                // The endpoint's onError function will be called.
                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 {
        // "enableConcurrent" will be set to false after `onStop` is called, so we should check it
        // every time.
        if (!enableConcurrent && numActiveThreads != 1) {
          // If we are not the only one worker, exit
          numActiveThreads -= 1
          return
        }
        message = messages.poll()
        if (message == null) {
          numActiveThreads -= 1
          return
        }
      }
    }
  }

  def post(message: InboxMessage): Unit = inbox.synchronized {
    if (stopped) {
      // We already put "OnStop" into "messages", so we should drop further messages
      onDrop(message)
    } else {
      messages.add(message)
      false
    }
  }

端点,RPC引用

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

接收消息队列, setUpEndPoint时,会向reveivers发送OnStart消息,异步启动RPC

  // Track the receivers whose inboxes may contain messages.
  private val receivers = new LinkedBlockingQueue[EndpointData]

注册RpcEndpoint

 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)  // for the OnStart message
    }
    endpointRef
  }

处理消息的线程池

  /** Thread pool used for dispatching messages. */
  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
  }

死循环监听消息线程实现类

 /** Message loop used for dispatching messages. */
  private class MessageLoop extends Runnable {
    override def run(): Unit = {
      try {
        while (true) {
          try {
            val data = receivers.take()
            if (data == PoisonPill) {
              // Put PoisonPill back so that other MessageLoops can see it.
              receivers.offer(PoisonPill)
              return
            }
            data.inbox.process(Dispatcher.this)
          } catch {
            case NonFatal(e) => logError(e.getMessage, e)
          }
        }
      } catch {
        case _: InterruptedException => // exit
        case t: Throwable =>
          try {
            // Re-submit a MessageLoop so that Dispatcher will still work if
            // UncaughtExceptionHandler decides to not kill JVM.
            threadpool.execute(new MessageLoop)
          } finally {
            throw t
          }
      }
    }
  }

消息处理通过postMessage

 /**
   * Posts a message to a specific endpoint.
   *
   * @param endpointName name of the endpoint.
   * @param message the message to post
   * @param callbackIfStopped callback function if the endpoint is stopped.
   */
  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
      }
    }
    // We don't need to call `onStop` in the `synchronized` block
    error.foreach(callbackIfStopped)
  }

2 startServer

启动TransportServer,并调用dispacher的registerRpcEndpoint方法触发
receivers.offer(data) // for the OnStart message
启动此RpcEnv所对应的角色类

  def startServer(bindAddress: String, port: Int): Unit = {
    val bootstraps: java.util.List[TransportServerBootstrap] =
      if (securityManager.isAuthenticationEnabled()) {
        java.util.Arrays.asList(new AuthServerBootstrap(transportConf, securityManager))
      } else {
        java.util.Collections.emptyList()
      }
    server = transportContext.createServer(bindAddress, port, bootstraps)
    dispatcher.registerRpcEndpoint(
      RpcEndpointVerifier.NAME, new RpcEndpointVerifier(this, dispatcher))
  }

RpcEnv是Master、Worker的通信基础
调用流程: