(defserverfn mk-worker [conf shared-mq-context storm-id assignment-id port worker-id]
  (log-message "Launching worker for " storm-id " on " assignment-id ":" port " with id " worker-id
               " and conf " conf)
  (if-not (local-mode? conf)
    (redirect-stdio-to-slf4j!))
  ;; because in local mode, its not a separate
  ;; process. supervisor will register it in this case
  (when (= :distributed (cluster-mode conf))
    (touch (worker-pid-path conf worker-id (process-pid))))
  (let [worker (worker-data conf shared-mq-context storm-id assignment-id port worker-id) ;;1.1 生成work-data
        ;;1.2 生成worker的hb

        heartbeat-fn #(do-heartbeat worker)
        ;; do this here so that the worker process dies if this fails
        ;; it's important that worker heartbeat to supervisor ASAP when launching so that the supervisor knows it's running (and can move on)
        _ (heartbeat-fn)
        
        ;; heartbeat immediately to nimbus so that it knows that the worker has been started
        _ (do-executor-heartbeats worker)        
        
        executors (atom nil)
        ;; launch heartbeat threads immediately so that slow-loading tasks don't cause the worker to timeout
        ;; to the supervisor
        _ (schedule-recurring (:heartbeat-timer worker) 0 (conf WORKER-HEARTBEAT-FREQUENCY-SECS) heartbeat-fn)
        _ (schedule-recurring (:executor-heartbeat-timer worker) 0 (conf TASK-HEARTBEAT-FREQUENCY-SECS) #(do-executor-heartbeats worker :executors @executors))

        ;;1.3 更新发送connections
        refresh-connections (mk-refresh-connections worker)
        _ (refresh-connections nil)
        _ (refresh-storm-active worker nil)
                

        ;;1.4 创建executors  
        _ (reset! executors (dofor [e (:executors worker)] (executor/mk-executor worker e)))
        

        ;;1.5 launch接收线程,将数据从server的侦听端口, 不停的放到task对应的接收队列

         receive-thread-shutdown (launch-receive-thread worker) ;;返回值是thread的close function
        

        ;;1.6 定义event handler来处理transfer queue里面的数据, 并创建transfer-thread
        transfer-tuples (mk-transfer-tuples-handler worker)     
        transfer-thread (disruptor/consume-loop* (:transfer-queue worker) transfer-tuples)  

        ;;1.7 定义worker shutdown函数, 以及worker的操作接口实现                      
        shutdown* (fn []
                    (log-message "Shutting down worker " storm-id " " assignment-id " " port)
                    (doseq [[_ socket] @(:cached-node+port->socket worker)]
                      ;; this will do best effort flushing since the linger period
                      ;; was set on creation
                      (.close socket))
                    (log-message "Shutting down receive thread")
                    (receive-thread-shutdown)
                    (log-message "Shut down receive thread")
                    (log-message "Terminating messaging context")
                    (log-message "Shutting down executors")
                    (doseq [executor @executors] (.shutdown executor))
                    (log-message "Shut down executors")
                                        
                    ;;this is fine because the only time this is shared is when it's a local context,
                    ;;in which case it's a noop
                    (.term ^IContext (:mq-context worker))
                    (log-message "Shutting down transfer thread")
                    (disruptor/halt-with-interrupt! (:transfer-queue worker))

                    (.interrupt transfer-thread)
                    (.join transfer-thread)
                    (log-message "Shut down transfer thread")
                    (cancel-timer (:heartbeat-timer worker))
                    (cancel-timer (:refresh-connections-timer worker))
                    (cancel-timer (:refresh-active-timer worker))
                    (cancel-timer (:executor-heartbeat-timer worker))
                    (cancel-timer (:user-timer worker))
                    
                    (close-resources worker)
                    
                    ;; TODO: here need to invoke the "shutdown" method of WorkerHook
                    
                    (.remove-worker-heartbeat! (:storm-cluster-state worker) storm-id assignment-id port)
                    (log-message "Disconnecting from storm cluster state context")
                    (.disconnect (:storm-cluster-state worker))
                    (.close (:cluster-state worker))
                    (log-message "Shut down worker " storm-id " " assignment-id " " port))
        ret (reify
             Shutdownable
             (shutdown
              [this]
              (shutdown*))
             DaemonCommon
             (waiting? [this]
               (and
                 (timer-waiting? (:heartbeat-timer worker))
                 (timer-waiting? (:refresh-connections-timer worker))
                 (timer-waiting? (:refresh-active-timer worker))
                 (timer-waiting? (:executor-heartbeat-timer worker))
                 (timer-waiting? (:user-timer worker))
                 ))
             )]
    
    (schedule-recurring (:refresh-connections-timer worker) 0 (conf TASK-REFRESH-POLL-SECS) refresh-connections)
    (schedule-recurring (:refresh-active-timer worker) 0 (conf TASK-REFRESH-POLL-SECS) (partial refresh-storm-active worker))

    (log-message "Worker has topology config " (:storm-conf worker))
    (log-message "Worker " worker-id " for storm " storm-id " on " assignment-id ":" port " has finished loading")
    ret
    ))

(defn worker-data [conf mq-context storm-id assignment-id port worker-id]
  (let [cluster-state (cluster/mk-distributed-cluster-state conf)
        storm-cluster-state (cluster/mk-storm-cluster-state cluster-state)
        storm-conf (read-supervisor-storm-conf conf storm-id)

        ;;从assignments里面找出分配给这个worker的executors, 另外加上个SYSTEM_EXECUTOR
        executors (set (read-worker-executors storm-conf storm-cluster-state storm-id assignment-id port))
        ;;基于disruptor创建worker用于接收和发送messgae的buffer queue

        ;;创建基于disruptor的transfer-queue

        transfer-queue (disruptor/disruptor-queue (storm-conf TOPOLOGY-TRANSFER-BUFFER-SIZE)
                                                  :wait-strategy (storm-conf TOPOLOGY-DISRUPTOR-WAIT-STRATEGY))
        ;;对于每个executors创建receive-queue(基于disruptor-queue),并生成{e,queue}的map返回

         executor-receive-queue-map (mk-receive-queue-map storm-conf executors)
        ;;executor可能有多个tasks,相同executor的tasks公用一个queue, 将{e,queue}转化为{t,queue}
        receive-queue-map (->> executor-receive-queue-map
                               (mapcat (fn [[e queue]] (for [t (executor-id->tasks e)] [t queue])))
                               (into {}))
        ;;读取supervisor机器上存储的stormcode.ser (topology对象的序列化文件)
        topology (read-supervisor-topology conf storm-id)]  

     ;;recursive-map,会将底下value都执行一遍, 用返回值和key生成新的map

     (recursive-map
      :conf conf
      :mq-context (if mq-context
                      mq-context
                      (TransportFactory/makeContext storm-conf)) ;;已经prepare的具有IContext接口的对象
       :storm-id storm-id
      :assignment-id assignment-id
      :port port
      :worker-id worker-id
      :cluster-state cluster-state
      :storm-cluster-state storm-cluster-state
      :storm-active-atom (atom false)
      :executors executors
      :task-ids (->> receive-queue-map keys (map int) sort)
      :storm-conf storm-conf
      :topology topology
      :system-topology (system-topology! storm-conf topology)
      :heartbeat-timer (mk-halting-timer)
      :refresh-connections-timer (mk-halting-timer)
      :refresh-active-timer (mk-halting-timer)
      :executor-heartbeat-timer (mk-halting-timer)
      :user-timer (mk-halting-timer)
      :task->component (HashMap. (storm-task-info topology storm-conf)) ; for optimized access when used in tasks later on
      :component->stream->fields (component->stream->fields (:system-topology <>)) ;;从ComponentCommon中读出steams的fields信息
       :component->sorted-tasks (->> (:task->component <>) reverse-map (map-val sort))
      :endpoint-socket-lock (mk-rw-lock)
      :cached-node+port->socket (atom {})
      :cached-task->node+port (atom {})
      :transfer-queue transfer-queue
      :executor-receive-queue-map executor-receive-queue-map
      :short-executor-receive-queue-map (map-key first executor-receive-queue-map) ;;单纯为了简化executor的表示, 由[first-task,last-task]变为first-task
      :task->short-executor (->> executors         ;;列出task和简化后的short-executor的对应关系
                                 (mapcat (fn [e] (for [t (executor-id->tasks e)] [t (first e)])))
                                 (into {})
                                 (HashMap.))
      :suicide-fn (mk-suicide-fn conf)
      :uptime (uptime-computer)
      :default-shared-resources (mk-default-resources <>)
      :user-shared-resources (mk-user-resources <>)
      :transfer-local-fn (mk-transfer-local-fn <>) ;;接收messages并发到task对应的接收队列
       :transfer-fn (mk-transfer-fn <>) ;;将处理过的message放到发送队列transfer-queue
      )))

(defn mk-refresh-connections [worker]
  (let [outbound-tasks (worker-outbound-tasks worker) ;;a.找出该woker需要向哪些component tasks发送数据,to-tasks
        conf (:conf worker)
       storm-cluster-state (:storm-cluster-state worker)
       storm-id (:storm-id worker)]
    (fn this
      ([]
        (this (fn [& ignored] (schedule (:refresh-connections-timer worker) 0 this)))) ;;schedule往timer里面加event
      ([callback]
        (let [assignment (.assignment-info storm-cluster-state storm-id callback)
              my-assignment (-> assignment   ;;b.得到to-tasks的node+port
                                :executor->node+port
                                to-task->node+port
                                (select-keys outbound-tasks)
                                (#(map-val endpoint->string %)))
              ;; we dont need a connection for the local tasks anymore
              needed-assignment (->> my-assignment  ;;c.排除local tasks
                                      (filter-key (complement (-> worker :task-ids set))))
              needed-connections (-> needed-assignment vals set)
              needed-tasks (-> needed-assignment keys)
              
              current-connections (set (keys @(:cached-node+port->socket worker)))
              new-connections (set/difference needed-connections current-connections) ;;d.需要add的和remove的connections
              remove-connections (set/difference current-connections needed-connections)]
              (swap! (:cached-node+port->socket worker) ;;e.创建新的connections
                     #(HashMap. (merge (into {} %1) %2))
                     (into {}
                       (dofor [endpoint-str new-connections
                               :let [[node port] (string->endpoint endpoint-str)]]
                         [endpoint-str
                          (.connect
                           ^IContext (:mq-context worker)
                           storm-id
                           ((:node->host assignment) node)
                           port)
                          ]
                         )))
              (write-locked (:endpoint-socket-lock worker)
                (reset! (:cached-task->node+port worker)
                        (HashMap. my-assignment)))
              (doseq [endpoint remove-connections]
                (.close (get @(:cached-node+port->socket worker) endpoint)))
              (apply swap!
                     (:cached-node+port->socket worker)
                     #(HashMap. (apply dissoc (into {} %1) %&))
                     remove-connections)
              
              (let [missing-tasks (->> needed-tasks
                                       (filter (complement my-assignment)))]
                (when-not (empty? missing-tasks)
                  (log-warn "Missing assignment for following tasks: " (pr-str missing-tasks))
                  )))))))

refresh-connections的步骤

a. 找出该worker下需要往其他task发送数据的task, outbound-tasks

    worker-outbound-tasks, 找出当前work中的task属于的component, 并找出该component的目标component

    最终找出目标compoennt所对应的所有task, 作为返回   

b. 找出outbound-tasks对应的tasks->node+port, my-assignment

c. 如果outbound-tasks在同一个worker进程中, 不需要建connection, 所以排除掉, 剩下needed-assignment 

   :value –> needed-connections , :key –> needed-tasks

d. 和当前已经创建并cache的connection集合对比一下, 找出new-connections和remove-connections

e. 调用Icontext.connect, (.connect ^IContext (:mq-context worker) storm-id ((:node->host assignment) node) port), 创建新的connection, 并merge到:cached-node+port->socket中

f. 使用my-assignment更新:cached-task->node+port (结合:cached-node+port->socket, 就可以得到task->socket) 

g. close所有remove-connections, 并从:cached-node+port->socket中删除

(defn launch-receive-thread [worker]
  (log-message "Launching receive-thread for " (:assignment-id worker) ":" (:port worker))
  (msg-loader/launch-receive-thread!
    (:mq-context worker)
    (:storm-id worker)
    (:port worker)
    (:transfer-local-fn worker)
    (-> worker :storm-conf (get TOPOLOGY-RECEIVER-BUFFER-SIZE))
    :kill-fn (fn [t] (halt-process! 11))))

(defn mk-transfer-local-fn [worker]
  (let [short-executor-receive-queue-map (:short-executor-receive-queue-map worker)
        task->short-executor (:task->short-executor worker)
        task-getter (comp #(get task->short-executor %) fast-first)]
    (fn [tuple-batch]
      (let [grouped (fast-group-by task-getter tuple-batch)] ;;将tuple-batch按executor进行分组
        (fast-map-iter [[short-executor pairs] grouped] ;;对应grouped里面每个entry执行下面的逻辑
          (let [q (short-executor-receive-queue-map short-executor)]
            (if q
              (disruptor/publish q pairs) ;;将tuple pairs发送到executor所对应的接收queue里面
              (log-warn "Received invalid messages for unknown tasks. Dropping... ")
              )))))))

(defnk launch-receive-thread!
  [context storm-id port transfer-local-fn max-buffer-size
   :daemon true
   :kill-fn (fn [t] (System/exit 1))
   :priority Thread/NORM_PRIORITY]
  (let [max-buffer-size (int max-buffer-size)
        vthread (async-loop
                 (fn []
                   (let [socket (.bind ^IContext context storm-id port)]
                     (fn []
                       (let [batched (ArrayList.)
                             init (.recv ^IConnection socket 0)]  ;;block方式
                         (loop [packet init]
                           (let [task (if packet (.task ^TaskMessage packet))
                                 message (if packet (.message ^TaskMessage packet))]
                             (if (= task -1) ;;收到结束命令
                               (do (log-message "Receiving-thread:[" storm-id ", " port "] received shutdown notice")
                                 (.close socket)
                                 nil )
                               (do
                                 (when packet (.add batched [task message]))
                                 (if (and packet (< (.size batched) max-buffer-size))
                                   (recur (.recv ^IConnection socket 1)) ;;non-block方式, 无数据则loop结束
                                   (do (transfer-local-fn batched) ;;将batched数据放到各个task对应的接收队列
                                     0 ))))))))))
                 :factory? true
                 :daemon daemon
                 :kill-fn kill-fn
                 :priority priority)]
    (fn []  ;;该thread的close function
      (let [kill-socket (.connect ^IContext context storm-id "localhost" port)] ;;本地创建client socket用于发送kill cmd
        (log-message "Shutting down receiving-thread: [" storm-id ", " port "]")
        (.send ^IConnection kill-socket   ;;发送kill cmd, -1
                  -1
                  (byte-array []))
        (log-message "Waiting for receiving-thread:[" storm-id ", " port "] to die")
        (.join vthread)  ;;等待thread结束
        (.close ^IConnection kill-socket)
        (log-message "Shutdown receiving-thread: [" storm-id ", " port "]")
        ))))

(defn mk-transfer-tuples-handler [worker]
  (let [^DisruptorQueue transfer-queue (:transfer-queue worker)
        drainer (ArrayList.)
        node+port->socket (:cached-node+port->socket worker)
        task->node+port (:cached-task->node+port worker)
        endpoint-socket-lock (:endpoint-socket-lock worker)
        ]
    (disruptor/clojure-handler
      (fn [packets _ batch-end?]
        (.addAll drainer packets)
        (when batch-end?
          (read-locked endpoint-socket-lock
            (let [node+port->socket @node+port->socket
                  task->node+port @task->node+port]
              ;; consider doing some automatic batching here (would need to not be serialized at this point to remove per-tuple overhead)
              ;; try using multipart messages ... first sort the tuples by the target node (without changing the local ordering)
            
              (fast-list-iter [[task ser-tuple] drainer]
                ;; TODO: consider write a batch of tuples here to every target worker  
                ;; group by node+port, do multipart send              
                (let [node-port (get task->node+port task)]
                  (when node-port
                    (.send ^IConnection (get node+port->socket node-port) task ser-tuple))
                    ))))
          (.clear drainer))))))