rocketmq源码解析-生产者启动和发送流程

前言

本文基于rocketmq4.8.0源码，讲解生产者的启动和发送消息的流程

生产者源码分析

生产者启动流程

这是一个简单的同步发送的代码，我们进入producer.start方法康康。

public class SendWayProducer {
    public static void main(String[] args) throws MQClientException, RemotingException, InterruptedException, MQBrokerException, UnsupportedEncodingException {
        DefaultMQProducer producer = new DefaultMQProducer("send_way_group");
        producer.setNamesrvAddr(NAMESRV_ADDR);
        producer.setSendMsgTimeout(150000);
        producer.start(); // 进入
        System.out.println("生产者启动成功");

        long startTime = System.currentTimeMillis();
        for (int i = 0; i < 100; i++) {
            Message message = new Message("send_way",
                    ("Hello RocketMQ" + i).getBytes(RemotingHelper.DEFAULT_CHARSET) /* Message body */
            );
            // 同步发送
            SendResult sendResult = producer.send(message);
            System.out.println(sendResult);
        }
        System.out.println("发送结束，耗时：" + (System.currentTimeMillis() - startTime));


        producer.shutdown();
    }
}

public void start() throws MQClientException {
    this.setProducerGroup(withNamespace(this.producerGroup));
    this.defaultMQProducerImpl.start(); // step into
    if (null != traceDispatcher) {
        try {
            traceDispatcher.start(this.getNamesrvAddr(), this.getAccessChannel());
        } catch (MQClientException e) {
            log.warn("trace dispatcher start failed ", e);
        }
    }
}

生产者实例，实际上是MQClientInstance，步骤如下

1. 先获取MQClientInstance
2. 在调用MQClientInstance#start

public void start() throws MQClientException {
    this.start(true);
}

public void start(final boolean startFactory) throws MQClientException {
    switch (this.serviceState) {
        //todo 第一次创建一定到这里
        case CREATE_JUST:
            this.serviceState = ServiceState.START_FAILED;

            this.checkConfig();

            if (!this.defaultMQProducer.getProducerGroup().equals(MixAll.CLIENT_INNER_PRODUCER_GROUP)) {
                this.defaultMQProducer.changeInstanceNameToPID();
            }
            //todo 从MQClientManager中拿
            this.mQClientFactory = MQClientManager.getInstance().getOrCreateMQClientInstance(this.defaultMQProducer, rpcHook);
            //
            boolean registerOK = mQClientFactory.registerProducer(this.defaultMQProducer.getProducerGroup(), this);
            if (!registerOK) {
                this.serviceState = ServiceState.CREATE_JUST;
                throw new MQClientException("The producer group[" + this.defaultMQProducer.getProducerGroup()
                    + "] has been created before, specify another name please." + FAQUrl.suggestTodo(FAQUrl.GROUP_NAME_DUPLICATE_URL),
                    null);
            }
            //todo 路由信息注册进去
            this.topicPublishInfoTable.put(this.defaultMQProducer.getCreateTopicKey(), new TopicPublishInfo());

            if (startFactory) {
                //todo 最终还是调用MQClientInstance
                mQClientFactory.start();
            }

            log.info("the producer [{}] start OK. sendMessageWithVIPChannel={}", this.defaultMQProducer.getProducerGroup(),
                this.defaultMQProducer.isSendMessageWithVIPChannel());
            this.serviceState = ServiceState.RUNNING;
            break;
        case RUNNING:
        case START_FAILED:
        case SHUTDOWN_ALREADY:
            throw new MQClientException("The producer service state not OK, maybe started once, "
                + this.serviceState
                + FAQUrl.suggestTodo(FAQUrl.CLIENT_SERVICE_NOT_OK),
                null);
        default:
            break;
    }

    // ...
}

获取MQClientInstance

获取MQClientInstance，如果clientId相同，则复用这个MQClientInstance

public MQClientInstance getOrCreateMQClientInstance(final ClientConfig clientConfig, RPCHook rpcHook) {
    //todo 这里可能会复用一个MQClientInstance
    String clientId = clientConfig.buildMQClientId(); // step into
    MQClientInstance instance = this.factoryTable.get(clientId);
    if (null == instance) {
        instance =
            new MQClientInstance(clientConfig.cloneClientConfig(),
                this.factoryIndexGenerator.getAndIncrement(), clientId, rpcHook);
        MQClientInstance prev = this.factoryTable.putIfAbsent(clientId, instance);
        if (prev != null) {
            instance = prev;
            log.warn("Returned Previous MQClientInstance for clientId:[{}]", clientId);
        } else {
            log.info("Created new MQClientInstance for clientId:[{}]", clientId);
        }
    }

    return instance;
}

获取clientId

//todo IP@instanceName@unitName如果相同。那么就会复用
public String buildMQClientId() {
    StringBuilder sb = new StringBuilder();
    sb.append(this.getClientIP());

    sb.append("@");
    sb.append(this.getInstanceName());
    if (!UtilAll.isBlank(this.unitName)) {    // todo unitName不设置缺省为null
        sb.append("@");
        sb.append(this.unitName);
    }

    return sb.toString();
}

MQClientInstance#start

public void start() throws MQClientException {

    synchronized (this) {
        switch (this.serviceState) {
            case CREATE_JUST:
                this.serviceState = ServiceState.START_FAILED;
                // If not specified,looking address from name server
                if (null == this.clientConfig.getNamesrvAddr()) {
                    this.mQClientAPIImpl.fetchNameServerAddr();
                }
                // Start request-response channel
                this.mQClientAPIImpl.start();
                // Start various schedule tasks
                //todo 开启定时任务，处理心跳、还有
                this.startScheduledTask();
                // Start pull service
                this.pullMessageService.start();
                // Start rebalance service
                this.rebalanceService.start();
                // Start push service
                this.defaultMQProducer.getDefaultMQProducerImpl().start(false);
                log.info("the client factory [{}] start OK", this.clientId);
                this.serviceState = ServiceState.RUNNING;
                break;
            case START_FAILED:
                throw new MQClientException("The Factory object[" + this.getClientId() + "] has been created before, and failed.", null);
            default:
                break;
        }
    }
}

最终走到nettyClient的start方法

// MQClientAPIImpl#start
public void start() {
    this.remotingClient.start();
}

开启定时任务

生产者开启定时任务，主要做以下操作：

1. 每两分钟获取NameServer地址？生产者不是一定要配置NameServer吗？否则怎么去发消息？这里有疑问🤔️。难道是去获取最新的NameServer集群？
2. 每30s更新路由信息
3. 每30s一次心跳
4. 每5s持久化消费进度

 //todo 都是定时任务处理，也就是生产者或者消费者不是实时感知Broker的状态，而是会有一定的偏差
// todo  所以如果服务器出现宕机，生产者或者消费要自行处理故障
private void startScheduledTask() {
    //2分钟一次获取路由地址
    if (null == this.clientConfig.getNamesrvAddr()) {
        this.scheduledExecutorService.scheduleAtFixedRate(new Runnable() {

            @Override
            public void run() {
                try {
                    MQClientInstance.this.mQClientAPIImpl.fetchNameServerAddr();
                } catch (Exception e) {
                    log.error("ScheduledTask fetchNameServerAddr exception", e);
                }
            }
        }, 1000 * 10, 1000 * 60 * 2, TimeUnit.MILLISECONDS);
    }
    //30s一次修改路由信息
    this.scheduledExecutorService.scheduleAtFixedRate(new Runnable() {

        @Override
        public void run() {
            try {
                MQClientInstance.this.updateTopicRouteInfoFromNameServer();
            } catch (Exception e) {
                log.error("ScheduledTask updateTopicRouteInfoFromNameServer exception", e);
            }
        }
    }, 10, this.clientConfig.getPollNameServerInterval(), TimeUnit.MILLISECONDS);
    //30s一次心跳
    this.scheduledExecutorService.scheduleAtFixedRate(new Runnable() {

        @Override
        public void run() {
            try {
                MQClientInstance.this.cleanOfflineBroker();
                MQClientInstance.this.sendHeartbeatToAllBrokerWithLock();
            } catch (Exception e) {
                log.error("ScheduledTask sendHeartbeatToAllBroker exception", e);
            }
        }
    }, 1000, this.clientConfig.getHeartbeatBrokerInterval(), TimeUnit.MILLISECONDS);
    //todo 每5s种定时任务---这里持久化消费进度
    this.scheduledExecutorService.scheduleAtFixedRate(new Runnable() {

        @Override
        public void run() {
            try {
                MQClientInstance.this.persistAllConsumerOffset();
            } catch (Exception e) {
                log.error("ScheduledTask persistAllConsumerOffset exception", e);
            }
        }
    }, 1000 * 10, this.clientConfig.getPersistConsumerOffsetInterval(), TimeUnit.MILLISECONDS);

    this.scheduledExecutorService.scheduleAtFixedRate(new Runnable() {

        @Override
        public void run() {
            try {
                MQClientInstance.this.adjustThreadPool();
            } catch (Exception e) {
                log.error("ScheduledTask adjustThreadPool exception", e);
            }
        }
    }, 1, 1, TimeUnit.MINUTES);
}

定时更新路由信息

拿到生产者或消费者的topic列表，更新每个topic的路由信息。

主要操作是，根据topic去NameServer获取路由信息，和旧的比对，如果不同，就更新。

// MQClientInstance#updateTopicRouteInfoFromNameServer()
public void updateTopicRouteInfoFromNameServer() {
    Set<String> topicList = new HashSet<String>();

    // Consumer
    {
        Iterator<Entry<String, MQConsumerInner>> it = this.consumerTable.entrySet().iterator();
        while (it.hasNext()) {
            Entry<String, MQConsumerInner> entry = it.next();
            MQConsumerInner impl = entry.getValue();
            if (impl != null) {
                Set<SubscriptionData> subList = impl.subscriptions();
                if (subList != null) {
                    for (SubscriptionData subData : subList) {
                        topicList.add(subData.getTopic());
                    }
                }
            }
        }
    }

    // Producer
    {
        Iterator<Entry<String, MQProducerInner>> it = this.producerTable.entrySet().iterator();
        while (it.hasNext()) {
            Entry<String, MQProducerInner> entry = it.next();
            MQProducerInner impl = entry.getValue();
            if (impl != null) {
                Set<String> lst = impl.getPublishTopicList();
                topicList.addAll(lst);
            }
        }
    }

    for (String topic : topicList) {
        this.updateTopicRouteInfoFromNameServer(topic);
    }
}

public boolean updateTopicRouteInfoFromNameServer(final String topic) {
    return updateTopicRouteInfoFromNameServer(topic, false, null);
}

public boolean updateTopicRouteInfoFromNameServer(final String topic, boolean isDefault,
        DefaultMQProducer defaultMQProducer) {
        try {
            if (this.lockNamesrv.tryLock(LOCK_TIMEOUT_MILLIS, TimeUnit.MILLISECONDS)) {
                try {
                    TopicRouteData topicRouteData;
                    if (isDefault && defaultMQProducer != null) {
                        topicRouteData = this.mQClientAPIImpl.getDefaultTopicRouteInfoFromNameServer(defaultMQProducer.getCreateTopicKey(),
                            1000 * 3);
                        if (topicRouteData != null) {
                            for (QueueData data : topicRouteData.getQueueDatas()) {
                                int queueNums = Math.min(defaultMQProducer.getDefaultTopicQueueNums(), data.getReadQueueNums());
                                data.setReadQueueNums(queueNums);
                                data.setWriteQueueNums(queueNums);
                            }
                        }
                    } else {
                        topicRouteData = this.mQClientAPIImpl.getTopicRouteInfoFromNameServer(topic, 1000 * 3);
                    }
                    if (topicRouteData != null) {
                        TopicRouteData old = this.topicRouteTable.get(topic);
                        boolean changed = topicRouteDataIsChange(old, topicRouteData);
                        if (!changed) {
                            changed = this.isNeedUpdateTopicRouteInfo(topic);
                        } else {
                            log.info("the topic[{}] route info changed, old[{}] ,new[{}]", topic, old, topicRouteData);
                        }

                      // 如果路由信息有变动，则更新
                        if (changed) {
                            TopicRouteData cloneTopicRouteData = topicRouteData.cloneTopicRouteData();

                            for (BrokerData bd : topicRouteData.getBrokerDatas()) {
                                this.brokerAddrTable.put(bd.getBrokerName(), bd.getBrokerAddrs());
                            }
                            // 更新生产者、消费者的路由，略
                            this.topicRouteTable.put(topic, cloneTopicRouteData);
				// 略
        return false;
    }

NameServer返回路由信息

生产者更新路由信息，需要向NameServer请求路由信息。

// DefaultRequestProcessor#getRouteInfoByTopic
public RemotingCommand getRouteInfoByTopic(ChannelHandlerContext ctx,
    RemotingCommand request) throws RemotingCommandException {
    final RemotingCommand response = RemotingCommand.createResponseCommand(null);
    final GetRouteInfoRequestHeader requestHeader =
        (GetRouteInfoRequestHeader) request.decodeCommandCustomHeader(GetRouteInfoRequestHeader.class);
    //todo 这里用于获取NameServer的路由信息  pickupTopicRouteData()
    TopicRouteData topicRouteData = this.namesrvController.getRouteInfoManager().pickupTopicRouteData(requestHeader.getTopic());

    if (topicRouteData != null) {
        if (this.namesrvController.getNamesrvConfig().isOrderMessageEnable()) {
            String orderTopicConf =
                this.namesrvController.getKvConfigManager().getKVConfig(NamesrvUtil.NAMESPACE_ORDER_TOPIC_CONFIG,
                    requestHeader.getTopic());
            topicRouteData.setOrderTopicConf(orderTopicConf);
        }

        byte[] content = topicRouteData.encode();
        response.setBody(content);
        response.setCode(ResponseCode.SUCCESS);
        response.setRemark(null);
        return response;
    }

    response.setCode(ResponseCode.TOPIC_NOT_EXIST);
    response.setRemark("No topic route info in name server for the topic: " + requestHeader.getTopic()
        + FAQUrl.suggestTodo(FAQUrl.APPLY_TOPIC_URL));
    return response;
}

获取路由表，使用了读锁(读多写少)。根据topic获取队列列表以及broker信息

//从NameServer返回路由表（使用到了读锁）
public TopicRouteData pickupTopicRouteData(final String topic) {
    TopicRouteData topicRouteData = new TopicRouteData();
    boolean foundQueueData = false;
    boolean foundBrokerData = false;
    Set<String> brokerNameSet = new HashSet<String>();
    List<BrokerData> brokerDataList = new LinkedList<BrokerData>();
    topicRouteData.setBrokerDatas(brokerDataList);

    HashMap<String, List<String>> filterServerMap = new HashMap<String, List<String>>();
    topicRouteData.setFilterServerTable(filterServerMap);

    try {
        try {
            //读锁
            this.lock.readLock().lockInterruptibly();
            List<QueueData> queueDataList = this.topicQueueTable.get(topic);
            if (queueDataList != null) {
                topicRouteData.setQueueDatas(queueDataList);
                foundQueueData = true;

                Iterator<QueueData> it = queueDataList.iterator();
                while (it.hasNext()) {
                    QueueData qd = it.next();
                    brokerNameSet.add(qd.getBrokerName());
                }

                for (String brokerName : brokerNameSet) {
                    BrokerData brokerData = this.brokerAddrTable.get(brokerName);
                    if (null != brokerData) {
                        BrokerData brokerDataClone = new BrokerData(brokerData.getCluster(), brokerData.getBrokerName(), (HashMap<Long, String>) brokerData
                            .getBrokerAddrs().clone());
                        brokerDataList.add(brokerDataClone);
                        foundBrokerData = true;
                        for (final String brokerAddr : brokerDataClone.getBrokerAddrs().values()) {
                            List<String> filterServerList = this.filterServerTable.get(brokerAddr);
                            filterServerMap.put(brokerAddr, filterServerList);
                        }
                    }
                }
            }
        } finally {
            //释放读锁
            this.lock.readLock().unlock();
        }
    } catch (Exception e) {
        log.error("pickupTopicRouteData Exception", e);
    }

    log.debug("pickupTopicRouteData {} {}", topic, topicRouteData);

    if (foundBrokerData && foundQueueData) {
        return topicRouteData;
    }

    return null;
}

生产者发送消息

生产者并非在start方法调用之后开启连接，而是在发送消息时进行连接。

发送消息流程：

1. 验证消息

2. 查找路由

3. 选择队列

4. 消息发送

public SendResult send(
    Message msg) throws MQClientException, RemotingException, MQBrokerException, InterruptedException {
    Validators.checkMessage(msg, this);
    msg.setTopic(withNamespace(msg.getTopic()));
    return this.defaultMQProducerImpl.send(msg);
}
// DefaultMQProducerImpl#send
public SendResult send(
    Message msg) throws MQClientException, RemotingException, MQBrokerException, InterruptedException {
    return send(msg, this.defaultMQProducer.getSendMsgTimeout());
}

public SendResult send(Message msg,
        long timeout) throws MQClientException, RemotingException, MQBrokerException, InterruptedException {
        return this.sendDefaultImpl(msg, CommunicationMode.SYNC, null, timeout);
    }

private SendResult sendDefaultImpl(
        Message msg,
        final CommunicationMode communicationMode,
        final SendCallback sendCallback,
        final long timeout
    ) throws MQClientException, RemotingException, MQBrokerException, InterruptedException {
        this.makeSureStateOK();
  			// 验证消息
        Validators.checkMessage(msg, this.defaultMQProducer);
        final long invokeID = random.nextLong();
        long beginTimestampFirst = System.currentTimeMillis();
        long beginTimestampPrev = beginTimestampFirst;
        long endTimestamp = beginTimestampFirst;
   		  // 查找路由
        TopicPublishInfo topicPublishInfo = this.tryToFindTopicPublishInfo(msg.getTopic());
        if (topicPublishInfo != null && topicPublishInfo.ok()) {
            boolean callTimeout = false;
            MessageQueue mq = null;
            Exception exception = null;
            SendResult sendResult = null;
            int timesTotal = communicationMode == CommunicationMode.SYNC ? 1 + this.defaultMQProducer.getRetryTimesWhenSendFailed() : 1;
            int times = 0;
            String[] brokersSent = new String[timesTotal];
            for (; times < timesTotal; times++) {
                String lastBrokerName = null == mq ? null : mq.getBrokerName();
                // 选择队列
                MessageQueue mqSelected = this.selectOneMessageQueue(topicPublishInfo, lastBrokerName);
                if (mqSelected != null) {
                    mq = mqSelected;
                    brokersSent[times] = mq.getBrokerName();
                    try {
                        beginTimestampPrev = System.currentTimeMillis();
                        if (times > 0) {
                            //Reset topic with namespace during resend.
                            msg.setTopic(this.defaultMQProducer.withNamespace(msg.getTopic()));
                        }
                        long costTime = beginTimestampPrev - beginTimestampFirst;
                        if (timeout < costTime) {
                            callTimeout = true;
                            break;
                        }
                        // 消息发送
                        sendResult = this.sendKernelImpl(msg, mq, communicationMode, sendCallback, topicPublishInfo, timeout - costTime);
                        endTimestamp = System.currentTimeMillis();
                        // 更新故障延迟信息，记录消息的发送时间，以及计算broker不可用时间
                        this.updateFaultItem(mq.getBrokerName(), endTimestamp - beginTimestampPrev, false);
                        // 异步/同步/单向发送的返回值。
                        switch (communicationMode) {
                            case ASYNC:
                                return null;
                            case ONEWAY:
                                return null;
                            case SYNC:
                                if (sendResult.getSendStatus() != SendStatus.SEND_OK) {
                                    if (this.defaultMQProducer.isRetryAnotherBrokerWhenNotStoreOK()) {
                                        continue;
                                    }
                                }

                                return sendResult;
                            default:
                                break;
                        }
                    }// ...
            }
//...
    }

验证消息

校验消息的合法性，比如是否超过最大消息大小

public static void checkMessage(Message msg, DefaultMQProducer defaultMQProducer)
    throws MQClientException {
    if (null == msg) {
        throw new MQClientException(ResponseCode.MESSAGE_ILLEGAL, "the message is null");
    }
    // topic
    Validators.checkTopic(msg.getTopic());
    Validators.isNotAllowedSendTopic(msg.getTopic());

    // body
    if (null == msg.getBody()) {
        throw new MQClientException(ResponseCode.MESSAGE_ILLEGAL, "the message body is null");
    }

    if (0 == msg.getBody().length) {
        throw new MQClientException(ResponseCode.MESSAGE_ILLEGAL, "the message body length is zero");
    }

    if (msg.getBody().length > defaultMQProducer.getMaxMessageSize()) {
        throw new MQClientException(ResponseCode.MESSAGE_ILLEGAL,
            "the message body size over max value, MAX: " + defaultMQProducer.getMaxMessageSize());
    }
}

路由查找

先从本地缓存中找是否有该topic的路由信息，如果没有，则去获取路由信息（前面启动流程中有讲到定时更新路由信息的操作）

private TopicPublishInfo tryToFindTopicPublishInfo(final String topic) {
    // 先从本地缓存中找
    TopicPublishInfo topicPublishInfo = this.topicPublishInfoTable.get(topic);
    if (null == topicPublishInfo || !topicPublishInfo.ok()) {
        this.topicPublishInfoTable.putIfAbsent(topic, new TopicPublishInfo());
      	// 本地缓存没有，则从nameserver更新路由信息
      this.mQClientFactory.updateTopicRouteInfoFromNameServer(topic);
        topicPublishInfo = this.topicPublishInfoTable.get(topic);
    }

    if (topicPublishInfo.isHaveTopicRouterInfo() || topicPublishInfo.ok()) {
        return topicPublishInfo;
    } else {
        this.mQClientFactory.updateTopicRouteInfoFromNameServer(topic, true, this.defaultMQProducer);
        topicPublishInfo = this.topicPublishInfoTable.get(topic);
        return topicPublishInfo;
    }
}

选择队列

如果不开启故障延迟（默认），则走简单的轮训算法，如果上一次失败了，则剔除失败的broker再走轮训算法。

rocketmq在发送消息时，会统计发送消息的时间延迟(MQFaultStrategy#updateFaultItem)，可以间接的知道哪些broker发送速度快，如果开启了故障延迟，那么rocketmq会尽可能选择发送速度快的broker。

public MessageQueue selectOneMessageQueue(final TopicPublishInfo tpInfo, final String lastBrokerName) {
    if (this.sendLatencyFaultEnable) {
      	// 如果开启了故障延迟
        try {
            int index = tpInfo.getSendWhichQueue().getAndIncrement();
            for (int i = 0; i < tpInfo.getMessageQueueList().size(); i++) {
                int pos = Math.abs(index++) % tpInfo.getMessageQueueList().size();
                if (pos < 0)
                    pos = 0;
                MessageQueue mq = tpInfo.getMessageQueueList().get(pos);
              	// 判断broker是否可用，即当前时间是否>broker的预计可用时间
                if (latencyFaultTolerance.isAvailable(mq.getBrokerName()))
                    return mq;
            }

            final String notBestBroker = latencyFaultTolerance.pickOneAtLeast();
            int writeQueueNums = tpInfo.getQueueIdByBroker(notBestBroker);
            if (writeQueueNums > 0) {
                final MessageQueue mq = tpInfo.selectOneMessageQueue();
                if (notBestBroker != null) {
                    mq.setBrokerName(notBestBroker);
                    mq.setQueueId(tpInfo.getSendWhichQueue().getAndIncrement() % writeQueueNums);
                }
                return mq;
            } else {
                latencyFaultTolerance.remove(notBestBroker);
            }
        } catch (Exception e) {
            log.error("Error occurred when selecting message queue", e);
        }

        return tpInfo.selectOneMessageQueue();
    }
	  
  	// 走轮训算法
    return tpInfo.selectOneMessageQueue(lastBrokerName);
}

//默认不启用Broker故障延迟机制
public MessageQueue selectOneMessageQueue(final String lastBrokerName) {
    //第一次选择队列
    if (lastBrokerName == null) {
        return selectOneMessageQueue();
    } else {
      	// 失败重试
        //sendWhichQueue
        for (int i = 0; i < this.messageQueueList.size(); i++) {
            int index = this.sendWhichQueue.getAndIncrement();
            //遍历消息队列集合
            int pos = Math.abs(index) % this.messageQueueList.size();
            if (pos < 0)
                pos = 0;
            //规避上次Broker队列
            MessageQueue mq = this.messageQueueList.get(pos);
            if (!mq.getBrokerName().equals(lastBrokerName)) {
                return mq;
            }
        }
        //如果以上情况都不满足,返回sendWhichQueue取模后的队列
        return selectOneMessageQueue();
    }
}
//第一次选择队列
public MessageQueue selectOneMessageQueue() {
    //sendWhichQueue自增
    int index = this.sendWhichQueue.getAndIncrement();
    //对队列大小取模
    int pos = Math.abs(index) % this.messageQueueList.size();
    if (pos < 0)
        pos = 0;
    //返回对应的队列
    return this.messageQueueList.get(pos);
}

故障延迟机制

记录发送延迟

// MQFaultStrategy#updateFaultItem
public void updateFaultItem(final String brokerName, final long currentLatency, boolean isolation) {
    if (this.sendLatencyFaultEnable) {
      	// 默认延迟30000
        long duration = computeNotAvailableDuration(isolation ? 30000 : currentLatency);
      	// 更新延迟信息
        this.latencyFaultTolerance.updateFaultItem(brokerName, currentLatency, duration);
    }
}

根据消息发送时长，计算broker不可用时长，一般认为发送延迟越大，broker不可用时间越长，这个时间是阿里的一个经验值。

// 比如发送延迟在70ms或400ms，那么认为broker不可用时长为0ms
// 发送延迟在2000ms或2500ms，认为broker不可用时长为120000ms
// 发送延迟
private long[] latencyMax = {50L, 100L, 550L, 1000L, 2000L, 3000L, 15000L};
// broker不可用时长
private long[] notAvailableDuration = {0L, 0L, 30000L, 60000L, 120000L, 180000L, 600000L};

private long computeNotAvailableDuration(final long currentLatency) {
    for (int i = latencyMax.length - 1; i >= 0; i--) {
        if (currentLatency >= latencyMax[i])
            return this.notAvailableDuration[i];
    }

    return 0;
}

维护broker的故障延迟信息

public void updateFaultItem(final String name, final long currentLatency, final long notAvailableDuration) {
    FaultItem old = this.faultItemTable.get(name);
    if (null == old) {
        final FaultItem faultItem = new FaultItem(name);
        faultItem.setCurrentLatency(currentLatency);
      	// 这个值表示broker什么时候可用，如果当前时间>这个值，表示该broker可用
        faultItem.setStartTimestamp(System.currentTimeMillis() + notAvailableDuration);

        old = this.faultItemTable.putIfAbsent(name, faultItem);
        if (old != null) {
            old.setCurrentLatency(currentLatency);
            old.setStartTimestamp(System.currentTimeMillis() + notAvailableDuration);
        }
    } else {
        old.setCurrentLatency(currentLatency);
        old.setStartTimestamp(System.currentTimeMillis() + notAvailableDuration);
    }
}

判断broker当前是否可用，即当前时间>broker预计可用时间

LatencyFaultToleranceImpl#isAvailable

public boolean isAvailable(final String name) {
    final FaultItem faultItem = this.faultItemTable.get(name);
    if (faultItem != null) {
        return faultItem.isAvailable();
    }
    return true;
}

public boolean isAvailable() {
  return (System.currentTimeMillis() - startTimestamp) >= 0;
}

消息发送

private SendResult sendKernelImpl(final Message msg,
    final MessageQueue mq,
    final CommunicationMode communicationMode,
    final SendCallback sendCallback,
    final TopicPublishInfo topicPublishInfo,
    final long timeout) throws MQClientException, RemotingException, MQBrokerException, InterruptedException {
    long beginStartTime = System.currentTimeMillis();
    String brokerAddr = this.mQClientFactory.findBrokerAddressInPublish(mq.getBrokerName());
    if (null == brokerAddr) {
        tryToFindTopicPublishInfo(mq.getTopic());
        brokerAddr = this.mQClientFactory.findBrokerAddressInPublish(mq.getBrokerName());
    }

    SendMessageContext context = null;
    if (brokerAddr != null) {
        brokerAddr = MixAll.brokerVIPChannel(this.defaultMQProducer.isSendMessageWithVIPChannel(), brokerAddr);

        byte[] prevBody = msg.getBody();
        try {
            //for MessageBatch,ID has been set in the generating process
            if (!(msg instanceof MessageBatch)) {
                MessageClientIDSetter.setUniqID(msg);
            }
// ...

            SendResult sendResult = null;
            switch (communicationMode) {
                case ASYNC:
                    Message tmpMessage = msg;
                    boolean messageCloned = false;
                    if (msgBodyCompressed) {
                        //If msg body was compressed, msgbody should be reset using prevBody.
                        //Clone new message using commpressed message body and recover origin massage.
                        //Fix bug:https://github.com/apache/rocketmq-externals/issues/66
                        tmpMessage = MessageAccessor.cloneMessage(msg);
                        messageCloned = true;
                        msg.setBody(prevBody);
                    }

                    if (topicWithNamespace) {
                        if (!messageCloned) {
                            tmpMessage = MessageAccessor.cloneMessage(msg);
                            messageCloned = true;
                        }
                        msg.setTopic(NamespaceUtil.withoutNamespace(msg.getTopic(), this.defaultMQProducer.getNamespace()));
                    }

                    long costTimeAsync = System.currentTimeMillis() - beginStartTime;
                    if (timeout < costTimeAsync) {
                        throw new RemotingTooMuchRequestException("sendKernelImpl call timeout");
                    }
                    sendResult = this.mQClientFactory.getMQClientAPIImpl().sendMessage(
                        brokerAddr,
                        mq.getBrokerName(),
                        tmpMessage,
                        requestHeader,
                        timeout - costTimeAsync,
                        communicationMode,
                        sendCallback,
                        topicPublishInfo,
                        this.mQClientFactory,
                        this.defaultMQProducer.getRetryTimesWhenSendAsyncFailed(),
                        context,
                        this);
                    break;
                case ONEWAY:
                case SYNC:
                    long costTimeSync = System.currentTimeMillis() - beginStartTime;
                    if (timeout < costTimeSync) {
                        throw new RemotingTooMuchRequestException("sendKernelImpl call timeout");
                    }
                    // step into 
                    sendResult = this.mQClientFactory.getMQClientAPIImpl().sendMessage(
                        brokerAddr,
                        mq.getBrokerName(),
                        msg,
                        requestHeader,
                        timeout - costTimeSync,
                        communicationMode,
                        context,
                        this);
                    break;
                default:
                    assert false;
                    break;
            }
			// ...
    }

    throw new MQClientException("The broker[" + mq.getBrokerName() + "] not exist", null);
}

MQClientAPIImpl#sendMessage

public SendResult sendMessage(
    final String addr,
    final String brokerName,
    final Message msg,
    final SendMessageRequestHeader requestHeader,
    final long timeoutMillis,
    final CommunicationMode communicationMode,
    final SendCallback sendCallback,
    final TopicPublishInfo topicPublishInfo,
    final MQClientInstance instance,
    final int retryTimesWhenSendFailed,
    final SendMessageContext context,
    final DefaultMQProducerImpl producer
) throws RemotingException, MQBrokerException, InterruptedException {
    long beginStartTime = System.currentTimeMillis();
    RemotingCommand request = null;
    String msgType = msg.getProperty(MessageConst.PROPERTY_MESSAGE_TYPE);
    boolean isReply = msgType != null && msgType.equals(MixAll.REPLY_MESSAGE_FLAG);
    // ...
    switch (communicationMode) {
        case ONEWAY:
            this.remotingClient.invokeOneway(addr, request, timeoutMillis);
            return null;
        case ASYNC:
            final AtomicInteger times = new AtomicInteger();
            long costTimeAsync = System.currentTimeMillis() - beginStartTime;
            if (timeoutMillis < costTimeAsync) {
                throw new RemotingTooMuchRequestException("sendMessage call timeout");
            }
            this.sendMessageAsync(addr, brokerName, msg, timeoutMillis - costTimeAsync, request, sendCallback, topicPublishInfo, instance,
                retryTimesWhenSendFailed, times, context, producer);
            return null;
        case SYNC:
            long costTimeSync = System.currentTimeMillis() - beginStartTime;
            if (timeoutMillis < costTimeSync) {
                throw new RemotingTooMuchRequestException("sendMessage call timeout");
            }
            // step into
            return this.sendMessageSync(addr, brokerName, msg, timeoutMillis - costTimeSync, request);
        default:
            assert false;
            break;
    }

    return null;
}

private SendResult sendMessageSync(
    final String addr,
    final String brokerName,
    final Message msg,
    final long timeoutMillis,
    final RemotingCommand request
) throws RemotingException, MQBrokerException, InterruptedException {
   // invokeSync建立连接
    RemotingCommand response = this.remotingClient.invokeSync(addr, request, timeoutMillis);
    assert response != null;
    return this.processSendResponse(brokerName, msg, response,addr);
}

invokeSync这里就创建了连接Channel

public RemotingCommand invokeSync(String addr, final RemotingCommand request, long timeoutMillis)
    throws InterruptedException, RemotingConnectException, RemotingSendRequestException, RemotingTimeoutException {
    long beginStartTime = System.currentTimeMillis();
    //todo  这里创建连接
    final Channel channel = this.getAndCreateChannel(addr);
    if (channel != null && channel.isActive()) {
        try {
            doBeforeRpcHooks(addr, request);
            long costTime = System.currentTimeMillis() - beginStartTime;
            if (timeoutMillis < costTime) {
                throw new RemotingTimeoutException("invokeSync call timeout");
            }
            RemotingCommand response = this.invokeSyncImpl(channel, request, timeoutMillis - costTime);
            doAfterRpcHooks(RemotingHelper.parseChannelRemoteAddr(channel), request, response);
            return response;
        } catch (RemotingSendRequestException e) {
            log.warn("invokeSync: send request exception, so close the channel[{}]", addr);
            this.closeChannel(addr, channel);
            throw e;
        } catch (RemotingTimeoutException e) {
            if (nettyClientConfig.isClientCloseSocketIfTimeout()) {
                this.closeChannel(addr, channel);
                log.warn("invokeSync: close socket because of timeout, {}ms, {}", timeoutMillis, addr);
            }
            log.warn("invokeSync: wait response timeout exception, the channel[{}]", addr);
            throw e;
        }
    } else {
        this.closeChannel(addr, channel);
        throw new RemotingConnectException(addr);
    }
}

总结

生产者启动并不涉及连接的建立，而且在发送消息时才建立连接。客户端（生产者、消费者）实例实际上是MQClientInstance，调用MQClientInstance的相关方法完成客户端开启操作。客户端在本地维护topic路由表，需要开启定时线程去更新路由信息。

生产者发送消息的流程是，校验消息、查找路由、选择队列、发送消息。其中选择队列的代码需重点关注，rocketmq引入了故障延迟机制，默认关闭。关闭时，则简单的轮训队列，确保消息均匀分布到每个队列上。如果每条消息需要重试，则规避上次发送失败的队列，排除后再进行轮训。当开启故障延迟后，会规避rocketmq认为不可用的broker（通过消息发送时长来确定）