Nameserver 启动流程
流程图
NameServer启动流程.png
此处不做过多赘述，NameServer主要是维护了消息服务端和客户端的信息
但是这边提一个RocketMQ中比较优雅的写法（利用JVM的钩子函数）
public static NamesrvController start(final NamesrvController controller) throws Exception {
// 利用JVM的钩子函数，在停机时进行一下流的关闭，线程池的停机
Runtime.getRuntime().addShutdownHook(new ShutdownHookThread(log, new Callable<Void>() {
@Override
public Void call() throws Exception {
controller.shutdown();
return null;
}
}));
controller.start();
}
public void start() throws Exception {
this.remotingServer.start();
if (this.fileWatchService != null) {
this.fileWatchService.start();
}
}
public void shutdown() {
this.remotingServer.shutdown();
this.remotingExecutor.shutdown();
this.scheduledExecutorService.shutdown();
if (this.fileWatchService != null) {
this.fileWatchService.shutdown();
}
}
Broker 启动
主要内容
Broker启动流程.png
这边我们主要知道Broker启动流程都做了哪些事情，具体这些事情是怎么做的，将在后续的模块中进行介绍
客户端启动 Producer/Consumer
流程图
ClientInstance启动流程.png
关键代码
Producer
public void start(final boolean startFactory) throws MQClientException {
switch (this.serviceState) {
case CREATE_JUST:
this.serviceState = ServiceState.START_FAILED;
// 校验producerGroup是否符合要求
this.checkConfig();
if (!this.defaultMQProducer.getProducerGroup().equals(MixAll.CLIENT_INNER_PRODUCER_GROUP)) {
// 更改生产者id为进程id
this.defaultMQProducer.changeInstanceNameToPID();
}
// 创建实例
this.mQClientFactory = MQClientManager.getInstance().getOrCreateMQClientInstance(this.defaultMQProducer, rpcHook);
// 向MQClientInstance注册实例（将当前实体加入MQClientInstance管理）方便后续调用网络请求、心跳检测等
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);
}
this.topicPublishInfoTable.put(this.defaultMQProducer.getCreateTopicKey(), new TopicPublishInfo());
// 如果MQClientInstance已经启动，本次启动不会真正执行
if (startFactory) {
// 没有启动，启动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;
}
this.mQClientFactory.sendHeartbeatToAllBrokerWithLock();
this.timer.scheduleAtFixedRate(new TimerTask() {
@Override
public void run() {
try {
RequestFutureTable.scanExpiredRequest();
} catch (Throwable e) {
log.error("scan RequestFutureTable exception", e);
}
}
}, 1000 * 3, 1000);
}
Consumer
public synchronized void start() throws MQClientException {
switch (this.serviceState) {
case CREATE_JUST:
log.info("the consumer [{}] start beginning. messageModel={}, isUnitMode={}", this.defaultMQPushConsumer.getConsumerGroup(),
this.defaultMQPushConsumer.getMessageModel(), this.defaultMQPushConsumer.isUnitMode());
this.serviceState = ServiceState.START_FAILED;
this.checkConfig();
// 构建订阅信息并加入到RebalanceImpl的订阅消息中
this.copySubscription();
if (this.defaultMQPushConsumer.getMessageModel() == MessageModel.CLUSTERING) {
this.defaultMQPushConsumer.changeInstanceNameToPID();
}
// 初始化MQClientInstance
this.mQClientFactory = MQClientManager.getInstance().getOrCreateMQClientInstance(this.defaultMQPushConsumer, this.rpcHook);
// 初始化RebalanceImpl
this.rebalanceImpl.setConsumerGroup(this.defaultMQPushConsumer.getConsumerGroup());
this.rebalanceImpl.setMessageModel(this.defaultMQPushConsumer.getMessageModel());
this.rebalanceImpl.setAllocateMessageQueueStrategy(this.defaultMQPushConsumer.getAllocateMessageQueueStrategy());
this.rebalanceImpl.setmQClientFactory(this.mQClientFactory);
this.pullAPIWrapper = new PullAPIWrapper(
mQClientFactory,
this.defaultMQPushConsumer.getConsumerGroup(), isUnitMode());
this.pullAPIWrapper.registerFilterMessageHook(filterMessageHookList);
// 初始化消息进度
if (this.defaultMQPushConsumer.getOffsetStore() != null) {
this.offsetStore = this.defaultMQPushConsumer.getOffsetStore();
} else {
switch (this.defaultMQPushConsumer.getMessageModel()) {
case BROADCASTING:
// 广播模式，进度存在消费端
this.offsetStore = new LocalFileOffsetStore(this.mQClientFactory, this.defaultMQPushConsumer.getConsumerGroup());
break;
case CLUSTERING:
// 集群模式，进度存在Broker
this.offsetStore = new RemoteBrokerOffsetStore(this.mQClientFactory, this.defaultMQPushConsumer.getConsumerGroup());
break;
default:
break;
}
this.defaultMQPushConsumer.setOffsetStore(this.offsetStore);
}
this.offsetStore.load();
if (this.getMessageListenerInner() instanceof MessageListenerOrderly) {
// 顺序消费
this.consumeOrderly = true;
this.consumeMessageService =
new ConsumeMessageOrderlyService(this, (MessageListenerOrderly) this.getMessageListenerInner());
} else if (this.getMessageListenerInner() instanceof MessageListenerConcurrently) {
this.consumeOrderly = false;
this.consumeMessageService =
new ConsumeMessageConcurrentlyService(this, (MessageListenerConcurrently) this.getMessageListenerInner());
}
this.consumeMessageService.start();
// 向MQClientInstance注册消费者
boolean registerOK = mQClientFactory.registerConsumer(this.defaultMQPushConsumer.getConsumerGroup(), this);
if (!registerOK) {
this.serviceState = ServiceState.CREATE_JUST;
this.consumeMessageService.shutdown();
throw new MQClientException("The consumer group[" + this.defaultMQPushConsumer.getConsumerGroup()
+ "] has been created before, specify another name please." + FAQUrl.suggestTodo(FAQUrl.GROUP_NAME_DUPLICATE_URL),
null);
}
// 启动MQClientInstance（统一JVM中的所有的消费者生产者共用同一个MQClientInstance，且MQClientInstance只会启动一次）
mQClientFactory.start();
log.info("the consumer [{}] start OK.", this.defaultMQPushConsumer.getConsumerGroup());
this.serviceState = ServiceState.RUNNING;
break;
case RUNNING:
case START_FAILED:
case SHUTDOWN_ALREADY:
throw new MQClientException("The PushConsumer service state not OK, maybe started once, "
+ this.serviceState
+ FAQUrl.suggestTodo(FAQUrl.CLIENT_SERVICE_NOT_OK),
null);
default:
break;
}
this.updateTopicSubscribeInfoWhenSubscriptionChanged();
this.mQClientFactory.checkClientInBroker();
this.mQClientFactory.sendHeartbeatToAllBrokerWithLock();
this.mQClientFactory.rebalanceImmediately();
}
公共部分
// 获取实例
public MQClientInstance getOrCreateMQClientInstance(final ClientConfig clientConfig, RPCHook rpcHook) {
// ip + instance + unitname (关于同一个机器的问题，instance是上一步修改的进程id，但是同一个jvm的消费者和生产者，client是同一个)
String clientId = clientConfig.buildMQClientId();
MQClientInstance instance = this.factoryTable.get(clientId);
// 同一个clientId只会有一个实例
if (null == instance) {
instance =
// 封装了RocketMQ网络处理的API =》 客户端与NameServer，Broker交互的网络通道
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;
}
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
this.startScheduledTask();
// Start pull service
// 拉取消息
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;
}
}
}
备注
其中，关于消费者的ReblanceImpl流程，加载消费进度之类的，在后续消费者模块会详细介绍。此处就不做过多的介绍
消息发送流程
Produer 发送消息
流程图
Producer消息发送流程.png
关键代码
发送消息主干流程
private SendResult sendDefaultImpl(
Message msg,
final CommunicationMode communicationMode,
final SendCallback sendCallback,
final long timeout
) throws MQClientException, RemotingException, MQBrokerException, InterruptedException {
this.makeSureStateOK();
// 校验消息topic，内容，长度等
Validators.checkMessage(msg, this.defaultMQProducer);
final long invokeID = random.nextLong();
long beginTimestampFirst = System.currentTimeMillis();
long beginTimestampPrev = beginTimestampFirst;
long endTimestamp = beginTimestampFirst;
// 获取主题路由信息
TopicPublishInfo topicPublishInfo = this.tryToFindTopicPublishInfo(msg.getTopic());
if (topicPublishInfo != null && topicPublishInfo.ok()) {
boolean callTimeout = false;
MessageQueue mq = null;
Exception exception = null;
SendResult sendResult = null;
// 重试次数（异步才重试）
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();
// 获取的队列
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;
}
// 发送消息
sendResult = this.sendKernelImpl(msg, mq, communicationMode, sendCallback, topicPublishInfo, timeout - costTime);
endTimestamp = System.currentTimeMillis();
// 假如要规避的话，根据具体的消息发送耗时来决定规避
this.updateFaultItem(mq.getBrokerName(), endTimestamp - beginTimestampPrev, false);
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;
}
} catch (RemotingException e) {
endTimestamp = System.currentTimeMillis();
// 假如要规避的话，isolation = true，直接30s失败规避
this.updateFaultItem(mq.getBrokerName(), endTimestamp - beginTimestampPrev, true);
log.warn(String.format("sendKernelImpl exception, resend at once, InvokeID: %s, RT: %sms, Broker: %s", invokeID, endTimestamp - beginTimestampPrev, mq), e);
log.warn(msg.toString());
exception = e;
continue;
} catch (MQClientException e) {
endTimestamp = System.currentTimeMillis();
this.updateFaultItem(mq.getBrokerName(), endTimestamp - beginTimestampPrev, true);
log.warn(String.format("sendKernelImpl exception, resend at once, InvokeID: %s, RT: %sms, Broker: %s", invokeID, endTimestamp - beginTimestampPrev, mq), e);
log.warn(msg.toString());
exception = e;
continue;
} catch (MQBrokerException e) {
endTimestamp = System.currentTimeMillis();
this.updateFaultItem(mq.getBrokerName(), endTimestamp - beginTimestampPrev, true);
log.warn(String.format("sendKernelImpl exception, resend at once, InvokeID: %s, RT: %sms, Broker: %s", invokeID, endTimestamp - beginTimestampPrev, mq), e);
log.warn(msg.toString());
exception = e;
switch (e.getResponseCode()) {
case ResponseCode.TOPIC_NOT_EXIST:
case ResponseCode.SERVICE_NOT_AVAILABLE:
case ResponseCode.SYSTEM_ERROR:
case ResponseCode.NO_PERMISSION:
case ResponseCode.NO_BUYER_ID:
case ResponseCode.NOT_IN_CURRENT_UNIT:
continue;
default:
if (sendResult != null) {
return sendResult;
}
throw e;
}
} catch (InterruptedException e) {
endTimestamp = System.currentTimeMillis();
this.updateFaultItem(mq.getBrokerName(), endTimestamp - beginTimestampPrev, false);
log.warn(String.format("sendKernelImpl exception, throw exception, InvokeID: %s, RT: %sms, Broker: %s", invokeID, endTimestamp - beginTimestampPrev, mq), e);
log.warn(msg.toString());
log.warn("sendKernelImpl exception", e);
log.warn(msg.toString());
throw e;
}
} else {
break;
}
}
if (sendResult != null) {
return sendResult;
}
String info = String.format("Send [%d] times, still failed, cost [%d]ms, Topic: %s, BrokersSent: %s",
times,
System.currentTimeMillis() - beginTimestampFirst,
msg.getTopic(),
Arrays.toString(brokersSent));
info += FAQUrl.suggestTodo(FAQUrl.SEND_MSG_FAILED);
MQClientException mqClientException = new MQClientException(info, exception);
if (callTimeout) {
throw new RemotingTooMuchRequestException("sendDefaultImpl call timeout");
}
if (exception instanceof MQBrokerException) {
mqClientException.setResponseCode(((MQBrokerException) exception).getResponseCode());
} else if (exception instanceof RemotingConnectException) {
mqClientException.setResponseCode(ClientErrorCode.CONNECT_BROKER_EXCEPTION);
} else if (exception instanceof RemotingTimeoutException) {
mqClientException.setResponseCode(ClientErrorCode.ACCESS_BROKER_TIMEOUT);
} else if (exception instanceof MQClientException) {
mqClientException.setResponseCode(ClientErrorCode.BROKER_NOT_EXIST_EXCEPTION);
}
throw mqClientException;
}
validateNameServerSetting();
throw new MQClientException("No route info of this topic: " + msg.getTopic() + FAQUrl.suggestTodo(FAQUrl.NO_TOPIC_ROUTE_INFO),
null).setResponseCode(ClientErrorCode.NOT_FOUND_TOPIC_EXCEPTION);
}
失败规避
// 开不开启失败规避的区别：
// 开启的话：只要失败一次，就悲观的认为失败的Broker不可用，在接下来一段时间内就不会再发送消息
// 不开启的话：只是在本次消息发送过程中规避该Broker，下次消息发送还是会继续尝试
// 之所以需要失败规避，是因为Broker变动NameServer不会主动推送，而是客户端每隔30s定时去拉取
public MessageQueue selectOneMessageQueue(final TopicPublishInfo tpInfo, final String lastBrokerName) {
// 为true代表开启故障延迟机制
if (this.sendLatencyFaultEnable) {
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);
// 当前broker是否可用
if (latencyFaultTolerance.isAvailable(mq.getBrokerName())) {
if (null == lastBrokerName || mq.getBrokerName().equals(lastBrokerName))
return mq;
}
}
// 没有可用的broker, 从之前的失败规避列表中选出一个broker
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();
}
return tpInfo.selectOneMessageQueue(lastBrokerName);
}
public void updateFaultItem(final String brokerName, final long currentLatency, boolean isolation) {
// currentLatency 发送消息消耗时间
if (this.sendLatencyFaultEnable) {
long duration = computeNotAvailableDuration(isolation ? 30000 : currentLatency);
this.latencyFaultTolerance.updateFaultItem(brokerName, currentLatency, duration);
}
}
private final ConcurrentHashMap<String, FaultItem> faultItemTable = new ConcurrentHashMap<String, FaultItem>(16);
@Override
public boolean isAvailable(final String name) {
final FaultItem faultItem = this.faultItemTable.get(name);
if (faultItem != null) {
return faultItem.isAvailable();
}
return true;
}
消息发送具体逻辑
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();
// 获取broker地址
String brokerAddr = this.mQClientFactory.findBrokerAddressInPublish(mq.getBrokerName());
if (null == brokerAddr) {
// 从NameServer主动更新topic路由信息
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)) {
// 批量发送消息，在生成过程中已设置id
// 此处针对单挑发送消息的情况，分配全局唯一id
MessageClientIDSetter.setUniqID(msg);
}
boolean topicWithNamespace = false;
if (null != this.mQClientFactory.getClientConfig().getNamespace()) {
msg.setInstanceId(this.mQClientFactory.getClientConfig().getNamespace());
topicWithNamespace = true;
}
int sysFlag = 0;
boolean msgBodyCompressed = false;
// 消息大小默认超过4kb，zip压缩消息
if (this.tryToCompressMessage(msg)) {
sysFlag |= MessageSysFlag.COMPRESSED_FLAG;
msgBodyCompressed = true;
}
// 如果是事务消息，对sysFlag打上事务消息的标记
final String tranMsg = msg.getProperty(MessageConst.PROPERTY_TRANSACTION_PREPARED);
if (tranMsg != null && Boolean.parseBoolean(tranMsg)) {
sysFlag |= MessageSysFlag.TRANSACTION_PREPARED_TYPE;
}
if (hasCheckForbiddenHook()) {
CheckForbiddenContext checkForbiddenContext = new CheckForbiddenContext();
checkForbiddenContext.setNameSrvAddr(this.defaultMQProducer.getNamesrvAddr());
checkForbiddenContext.setGroup(this.defaultMQProducer.getProducerGroup());
checkForbiddenContext.setCommunicationMode(communicationMode);
checkForbiddenContext.setBrokerAddr(brokerAddr);
checkForbiddenContext.setMessage(msg);
checkForbiddenContext.setMq(mq);
checkForbiddenContext.setUnitMode(this.isUnitMode());
this.executeCheckForbiddenHook(checkForbiddenContext);
}
// 如果注册了消息钩子函数
if (this.hasSendMessageHook()) {
// 对消息进行增强（发送前后）
context = new SendMessageContext();
context.setProducer(this);
context.setProducerGroup(this.defaultMQProducer.getProducerGroup());
context.setCommunicationMode(communicationMode);
context.setBornHost(this.defaultMQProducer.getClientIP());
context.setBrokerAddr(brokerAddr);
context.setMessage(msg);
context.setMq(mq);
context.setNamespace(this.defaultMQProducer.getNamespace());
String isTrans = msg.getProperty(MessageConst.PROPERTY_TRANSACTION_PREPARED);
if (isTrans != null && isTrans.equals("true")) {
context.setMsgType(MessageType.Trans_Msg_Half);
}
if (msg.getProperty("__STARTDELIVERTIME") != null || msg.getProperty(MessageConst.PROPERTY_DELAY_TIME_LEVEL) != null) {
context.setMsgType(MessageType.Delay_Msg);
}
this.executeSendMessageHookBefore(context);
}
// 构建消息发送请求包
SendMessageRequestHeader requestHeader = new SendMessageRequestHeader();
requestHeader.setProducerGroup(this.defaultMQProducer.getProducerGroup());
requestHeader.setTopic(msg.getTopic());
requestHeader.setDefaultTopic(this.defaultMQProducer.getCreateTopicKey());
requestHeader.setDefaultTopicQueueNums(this.defaultMQProducer.getDefaultTopicQueueNums());
requestHeader.setQueueId(mq.getQueueId());
requestHeader.setSysFlag(sysFlag);
requestHeader.setBornTimestamp(System.currentTimeMillis());
requestHeader.setFlag(msg.getFlag());
requestHeader.setProperties(MessageDecoder.messageProperties2String(msg.getProperties()));
requestHeader.setReconsumeTimes(0);
requestHeader.setUnitMode(this.isUnitMode());
requestHeader.setBatch(msg instanceof MessageBatch);
if (requestHeader.getTopic().startsWith(MixAll.RETRY_GROUP_TOPIC_PREFIX)) {
String reconsumeTimes = MessageAccessor.getReconsumeTime(msg);
if (reconsumeTimes != null) {
requestHeader.setReconsumeTimes(Integer.valueOf(reconsumeTimes));
MessageAccessor.clearProperty(msg, MessageConst.PROPERTY_RECONSUME_TIME);
}
String maxReconsumeTimes = MessageAccessor.getMaxReconsumeTimes(msg);
if (maxReconsumeTimes != null) {
requestHeader.setMaxReconsumeTimes(Integer.valueOf(maxReconsumeTimes));
MessageAccessor.clearProperty(msg, MessageConst.PROPERTY_MAX_RECONSUME_TIMES);
}
}
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");
}
sendResult = this.mQClientFactory.getMQClientAPIImpl().sendMessage(
brokerAddr,
mq.getBrokerName(),
msg,
requestHeader,
timeout - costTimeSync,
communicationMode,
context,
this);
break;
default:
assert false;
break;
}
if (this.hasSendMessageHook()) {
context.setSendResult(sendResult);
this.executeSendMessageHookAfter(context);
}
return sendResult;
} catch (RemotingException e) {
if (this.hasSendMessageHook()) {
context.setException(e);
this.executeSendMessageHookAfter(context);
}
throw e;
} catch (MQBrokerException e) {
if (this.hasSendMessageHook()) {
context.setException(e);
this.executeSendMessageHookAfter(context);
}
throw e;
} catch (InterruptedException e) {
if (this.hasSendMessageHook()) {
context.setException(e);
this.executeSendMessageHookAfter(context);
}
throw e;
} finally {
msg.setBody(prevBody);
msg.setTopic(NamespaceUtil.withoutNamespace(msg.getTopic(), this.defaultMQProducer.getNamespace()));
}
}
throw new MQClientException("The broker[" + mq.getBrokerName() + "] not exist", null);
}
Broker 接收消息
流程图
Broker消息发送流程.png
关键代码
主干流程
private RemotingCommand sendMessage(final ChannelHandlerContext ctx,
final RemotingCommand request,
final SendMessageContext sendMessageContext,
final SendMessageRequestHeader requestHeader) throws RemotingCommandException {
final RemotingCommand response = RemotingCommand.createResponseCommand(SendMessageResponseHeader.class);
final SendMessageResponseHeader responseHeader = (SendMessageResponseHeader)response.readCustomHeader();
response.setOpaque(request.getOpaque());
response.addExtField(MessageConst.PROPERTY_MSG_REGION, this.brokerController.getBrokerConfig().getRegionId());
response.addExtField(MessageConst.PROPERTY_TRACE_SWITCH, String.valueOf(this.brokerController.getBrokerConfig().isTraceOn()));
log.debug("receive SendMessage request command, {}", request);
final long startTimstamp = this.brokerController.getBrokerConfig().getStartAcceptSendRequestTimeStamp();
if (this.brokerController.getMessageStore().now() < startTimstamp) {
response.setCode(ResponseCode.SYSTEM_ERROR);
response.setRemark(String.format("broker unable to service, until %s", UtilAll.timeMillisToHumanString2(startTimstamp)));
return response;
}
response.setCode(-1);
// 消息校验
super.msgCheck(ctx, requestHeader, response);
if (response.getCode() != -1) {
return response;
}
final byte[] body = request.getBody();
int queueIdInt = requestHeader.getQueueId();
TopicConfig topicConfig = this.brokerController.getTopicConfigManager().selectTopicConfig(requestHeader.getTopic());
if (queueIdInt < 0) {
queueIdInt = Math.abs(this.random.nextInt() % 99999999) % topicConfig.getWriteQueueNums();
}
MessageExtBrokerInner msgInner = new MessageExtBrokerInner();
msgInner.setTopic(requestHeader.getTopic());
msgInner.setQueueId(queueIdInt);
// 校验重试次数是否超过最大次数，超过则丢入死信队列
// %DLQ%+消费组名
if (!handleRetryAndDLQ(requestHeader, response, request, msgInner, topicConfig)) {
return response;
}
msgInner.setBody(body);
msgInner.setFlag(requestHeader.getFlag());
MessageAccessor.setProperties(msgInner, MessageDecoder.string2messageProperties(requestHeader.getProperties()));
msgInner.setBornTimestamp(requestHeader.getBornTimestamp());
msgInner.setBornHost(ctx.channel().remoteAddress());
msgInner.setStoreHost(this.getStoreHost());
msgInner.setReconsumeTimes(requestHeader.getReconsumeTimes() == null ? 0 : requestHeader.getReconsumeTimes());
String clusterName = this.brokerController.getBrokerConfig().getBrokerClusterName();
MessageAccessor.putProperty(msgInner, MessageConst.PROPERTY_CLUSTER, clusterName);
msgInner.setPropertiesString(MessageDecoder.messageProperties2String(msgInner.getProperties()));
PutMessageResult putMessageResult = null;
Map<String, String> oriProps = MessageDecoder.string2messageProperties(requestHeader.getProperties());
String traFlag = oriProps.get(MessageConst.PROPERTY_TRANSACTION_PREPARED);
if (traFlag != null && Boolean.parseBoolean(traFlag)) {
if (this.brokerController.getBrokerConfig().isRejectTransactionMessage()) {
response.setCode(ResponseCode.NO_PERMISSION);
response.setRemark(
"the broker[" + this.brokerController.getBrokerConfig().getBrokerIP1()
+ "] sending transaction message is forbidden");
return response;
}
putMessageResult = this.brokerController.getTransactionalMessageService().prepareMessage(msgInner);
} else {
// 存储消息
putMessageResult = this.brokerController.getMessageStore().putMessage(msgInner);
}
return handlePutMessageResult(putMessageResult, response, request, msgInner, responseHeader, sendMessageContext, ctx, queueIdInt);
}
校验消息
protected RemotingCommand msgCheck(final ChannelHandlerContext ctx,
final SendMessageRequestHeader requestHeader, final RemotingCommand response) {
// 校验broker是否有写的权限
if (!PermName.isWriteable(this.brokerController.getBrokerConfig().getBrokerPermission())
&& this.brokerController.getTopicConfigManager().isOrderTopic(requestHeader.getTopic())) {
response.setCode(ResponseCode.NO_PERMISSION);
response.setRemark("the broker[" + this.brokerController.getBrokerConfig().getBrokerIP1()
+ "] sending message is forbidden");
return response;
}
// 检查topic是否可以进行消息发送，主要针对默认主题，默认主题不能发送消息，仅供路由查找
if (!this.brokerController.getTopicConfigManager().isTopicCanSendMessage(requestHeader.getTopic())) {
String errorMsg = "the topic[" + requestHeader.getTopic() + "] is conflict with system reserved words.";
log.warn(errorMsg);
response.setCode(ResponseCode.SYSTEM_ERROR);
response.setRemark(errorMsg);
return response;
}
// 获取topic信息
TopicConfig topicConfig =
this.brokerController.getTopicConfigManager().selectTopicConfig(requestHeader.getTopic());
if (null == topicConfig) {
int topicSysFlag = 0;
if (requestHeader.isUnitMode()) {
if (requestHeader.getTopic().startsWith(MixAll.RETRY_GROUP_TOPIC_PREFIX)) {
topicSysFlag = TopicSysFlag.buildSysFlag(false, true);
} else {
topicSysFlag = TopicSysFlag.buildSysFlag(true, false);
}
}
log.warn("the topic {} not exist, producer: {}", requestHeader.getTopic(), ctx.channel().remoteAddress());
topicConfig = this.brokerController.getTopicConfigManager().createTopicInSendMessageMethod(
requestHeader.getTopic(),
requestHeader.getDefaultTopic(),
RemotingHelper.parseChannelRemoteAddr(ctx.channel()),
requestHeader.getDefaultTopicQueueNums(), topicSysFlag);
if (null == topicConfig) {
if (requestHeader.getTopic().startsWith(MixAll.RETRY_GROUP_TOPIC_PREFIX)) {
topicConfig =
this.brokerController.getTopicConfigManager().createTopicInSendMessageBackMethod(
requestHeader.getTopic(), 1, PermName.PERM_WRITE | PermName.PERM_READ,
topicSysFlag);
}
}
if (null == topicConfig) {
response.setCode(ResponseCode.TOPIC_NOT_EXIST);
response.setRemark("topic[" + requestHeader.getTopic() + "] not exist, apply first please!"
+ FAQUrl.suggestTodo(FAQUrl.APPLY_TOPIC_URL));
return response;
}
}
// 检查队列id是否有效
int queueIdInt = requestHeader.getQueueId();
int idValid = Math.max(topicConfig.getWriteQueueNums(), topicConfig.getReadQueueNums());
if (queueIdInt >= idValid) {
String errorInfo = String.format("request queueId[%d] is illegal, %s Producer: %s",
queueIdInt,
topicConfig.toString(),
RemotingHelper.parseChannelRemoteAddr(ctx.channel()));
log.warn(errorInfo);
response.setCode(ResponseCode.SYSTEM_ERROR);
response.setRemark(errorInfo);
return response;
}
return response;
}
Broker接收到消息之后，就涉及到了消息的存储与刷盘
消息存储流程
消息存储
流程图
Broker存储消息流程.png
关键代码
public PutMessageResult putMessage(MessageExtBrokerInner msg) {
if (this.shutdown) {
log.warn("message store has shutdown, so putMessage is forbidden");
return new PutMessageResult(PutMessageStatus.SERVICE_NOT_AVAILABLE, null);
}
if (BrokerRole.SLAVE == this.messageStoreConfig.getBrokerRole()) {
long value = this.printTimes.getAndIncrement();
if ((value % 50000) == 0) {
log.warn("message store is slave mode, so putMessage is forbidden ");
}
return new PutMessageResult(PutMessageStatus.SERVICE_NOT_AVAILABLE, null);
}
// 磁盘空间不足
if (!this.runningFlags.isWriteable()) {
long value = this.printTimes.getAndIncrement();
if ((value % 50000) == 0) {
log.warn("message store is not writeable, so putMessage is forbidden " + this.runningFlags.getFlagBits());
}
return new PutMessageResult(PutMessageStatus.SERVICE_NOT_AVAILABLE, null);
} else {
this.printTimes.set(0);
}
// 消息topic长度不能超过127个字符
if (msg.getTopic().length() > Byte.MAX_VALUE) {
log.warn("putMessage message topic length too long " + msg.getTopic().length());
return new PutMessageResult(PutMessageStatus.MESSAGE_ILLEGAL, null);
}
// 消息属性长度不能超过32767
if (msg.getPropertiesString() != null && msg.getPropertiesString().length() > Short.MAX_VALUE) {
log.warn("putMessage message properties length too long " + msg.getPropertiesString().length());
return new PutMessageResult(PutMessageStatus.PROPERTIES_SIZE_EXCEEDED, null);
}
if (this.isOSPageCacheBusy()) {
return new PutMessageResult(PutMessageStatus.OS_PAGECACHE_BUSY, null);
}
long beginTime = this.getSystemClock().now();
PutMessageResult result = this.commitLog.putMessage(msg);
long elapsedTime = this.getSystemClock().now() - beginTime;
if (elapsedTime > 500) {
log.warn("putMessage not in lock elapsed time(ms)={}, bodyLength={}", elapsedTime, msg.getBody().length);
}
this.storeStatsService.setPutMessageEntireTimeMax(elapsedTime);
if (null == result || !result.isOk()) {
this.storeStatsService.getPutMessageFailedTimes().incrementAndGet();
}
return result;
}
public PutMessageResult putMessage(final MessageExtBrokerInner msg) {
// Set the storage time
msg.setStoreTimestamp(System.currentTimeMillis());
// Set the message body BODY CRC (consider the most appropriate setting
// on the client)
msg.setBodyCRC(UtilAll.crc32(msg.getBody()));
// Back to Results
AppendMessageResult result = null;
StoreStatsService storeStatsService = this.defaultMessageStore.getStoreStatsService();
String topic = msg.getTopic();
int queueId = msg.getQueueId();
// 事务消息逻辑
final int tranType = MessageSysFlag.getTransactionValue(msg.getSysFlag());
// 非事务消息 或 事务已经提交
if (tranType == MessageSysFlag.TRANSACTION_NOT_TYPE
|| tranType == MessageSysFlag.TRANSACTION_COMMIT_TYPE) {
// Delay Delivery
if (msg.getDelayTimeLevel() > 0) {
// 设置延时等级
if (msg.getDelayTimeLevel() > this.defaultMessageStore.getScheduleMessageService().getMaxDelayLevel()) {
msg.setDelayTimeLevel(this.defaultMessageStore.getScheduleMessageService().getMaxDelayLevel());
}
// 替换topic为 SCHEDULE_TOPIC_XXXX , 延时消息的topic
topic = ScheduleMessageService.SCHEDULE_TOPIC;
// 计算要丢到哪个队列中 根据延时等级计算队列id
queueId = ScheduleMessageService.delayLevel2QueueId(msg.getDelayTimeLevel());
// Backup real topic, queueId
MessageAccessor.putProperty(msg, MessageConst.PROPERTY_REAL_TOPIC, msg.getTopic());
MessageAccessor.putProperty(msg, MessageConst.PROPERTY_REAL_QUEUE_ID, String.valueOf(msg.getQueueId()));
msg.setPropertiesString(MessageDecoder.messageProperties2String(msg.getProperties()));
msg.setTopic(topic);
msg.setQueueId(queueId);
}
}
InetSocketAddress bornSocketAddress = (InetSocketAddress) msg.getBornHost();
if (bornSocketAddress.getAddress() instanceof Inet6Address) {
msg.setBornHostV6Flag();
}
InetSocketAddress storeSocketAddress = (InetSocketAddress) msg.getStoreHost();
if (storeSocketAddress.getAddress() instanceof Inet6Address) {
msg.setStoreHostAddressV6Flag();
}
long eclipsedTimeInLock = 0;
// 获取mappedFile
MappedFile unlockMappedFile = null;
MappedFile mappedFile = this.mappedFileQueue.getLastMappedFile();
// 申请锁
putMessageLock.lock(); //spin or ReentrantLock ,depending on store config
try {
long beginLockTimestamp = this.defaultMessageStore.getSystemClock().now();
this.beginTimeInLock = beginLockTimestamp;
// Here settings are stored timestamp, in order to ensure an orderly
// global
msg.setStoreTimestamp(beginLockTimestamp);
// 代表第一次写入，以偏移量0创建CommitLog文件
if (null == mappedFile || mappedFile.isFull()) {
mappedFile = this.mappedFileQueue.getLastMappedFile(0); // Mark: NewFile may be cause noise
}
if (null == mappedFile) {
log.error("create mapped file1 error, topic: " + msg.getTopic() + " clientAddr: " + msg.getBornHostString());
beginTimeInLock = 0;
return new PutMessageResult(PutMessageStatus.CREATE_MAPEDFILE_FAILED, null);
}
// 写入消息
result = mappedFile.appendMessage(msg, this.appendMessageCallback);
switch (result.getStatus()) {
case PUT_OK:
break;
case END_OF_FILE:
unlockMappedFile = mappedFile;
// Create a new file, re-write the message
mappedFile = this.mappedFileQueue.getLastMappedFile(0);
if (null == mappedFile) {
// XXX: warn and notify me
log.error("create mapped file2 error, topic: " + msg.getTopic() + " clientAddr: " + msg.getBornHostString());
beginTimeInLock = 0;
return new PutMessageResult(PutMessageStatus.CREATE_MAPEDFILE_FAILED, result);
}
result = mappedFile.appendMessage(msg, this.appendMessageCallback);
break;
case MESSAGE_SIZE_EXCEEDED:
case PROPERTIES_SIZE_EXCEEDED:
beginTimeInLock = 0;
return new PutMessageResult(PutMessageStatus.MESSAGE_ILLEGAL, result);
case UNKNOWN_ERROR:
beginTimeInLock = 0;
return new PutMessageResult(PutMessageStatus.UNKNOWN_ERROR, result);
default:
beginTimeInLock = 0;
return new PutMessageResult(PutMessageStatus.UNKNOWN_ERROR, result);
}
eclipsedTimeInLock = this.defaultMessageStore.getSystemClock().now() - beginLockTimestamp;
beginTimeInLock = 0;
} finally {
// 释放锁
putMessageLock.unlock();
}
if (eclipsedTimeInLock > 500) {
log.warn("[NOTIFYME]putMessage in lock cost time(ms)={}, bodyLength={} AppendMessageResult={}", eclipsedTimeInLock, msg.getBody().length, result);
}
if (null != unlockMappedFile && this.defaultMessageStore.getMessageStoreConfig().isWarmMapedFileEnable()) {
this.defaultMessageStore.unlockMappedFile(unlockMappedFile);
}
PutMessageResult putMessageResult = new PutMessageResult(PutMessageStatus.PUT_OK, result);
// Statistics
storeStatsService.getSinglePutMessageTopicTimesTotal(msg.getTopic()).incrementAndGet();
storeStatsService.getSinglePutMessageTopicSizeTotal(topic).addAndGet(result.getWroteBytes());
// 刷盘
handleDiskFlush(result, putMessageResult, msg);
// HA主从同步复制
handleHA(result, putMessageResult, msg);
return putMessageResult;
}
public AppendMessageResult appendMessagesInner(final MessageExt messageExt, final AppendMessageCallback cb) {
assert messageExt != null;
assert cb != null;
int currentPos = this.wrotePosition.get();
if (currentPos < this.fileSize) {
// 创建一个与原ByteBuffer共享的内存区(根据是否开启堆外内存来决定使用 writeBuffer 还是 mappedByteBuffer)
ByteBuffer byteBuffer = writeBuffer != null ? writeBuffer.slice() : this.mappedByteBuffer.slice();
byteBuffer.position(currentPos);
AppendMessageResult result;
if (messageExt instanceof MessageExtBrokerInner) {
result = cb.doAppend(this.getFileFromOffset(), byteBuffer, this.fileSize - currentPos, (MessageExtBrokerInner) messageExt);
} else if (messageExt instanceof MessageExtBatch) {
result = cb.doAppend(this.getFileFromOffset(), byteBuffer, this.fileSize - currentPos, (MessageExtBatch) messageExt);
} else {
return new AppendMessageResult(AppendMessageStatus.UNKNOWN_ERROR);
}
this.wrotePosition.addAndGet(result.getWroteBytes());
this.storeTimestamp = result.getStoreTimestamp();
return result;
}
// 代表文件写满
log.error("MappedFile.appendMessage return null, wrotePosition: {} fileSize: {}", currentPos, this.fileSize);
return new AppendMessageResult(AppendMessageStatus.UNKNOWN_ERROR);
}
消息刷盘
流程图
RocketMQ CommitLog 刷盘.png
关键代码
public void handleDiskFlush(AppendMessageResult result, PutMessageResult putMessageResult, MessageExt messageExt) {
// Synchronization flush
if (FlushDiskType.SYNC_FLUSH == this.defaultMessageStore.getMessageStoreConfig().getFlushDiskType()) {
final GroupCommitService service = (GroupCommitService) this.flushCommitLogService;
if (messageExt.isWaitStoreMsgOK()) {
// 构建 GroupCommitRequest 同步任务并提交到 GroupCommitService
GroupCommitRequest request = new GroupCommitRequest(result.getWroteOffset() + result.getWroteBytes());
service.putRequest(request);
boolean flushOK = request.waitForFlush(this.defaultMessageStore.getMessageStoreConfig().getSyncFlushTimeout());
if (!flushOK) {
log.error("do groupcommit, wait for flush failed, topic: " + messageExt.getTopic() + " tags: " + messageExt.getTags()
+ " client address: " + messageExt.getBornHostString());
putMessageResult.setPutMessageStatus(PutMessageStatus.FLUSH_DISK_TIMEOUT);
}
} else {
service.wakeup();
}
}
// Asynchronous flush
else {
if (!this.defaultMessageStore.getMessageStoreConfig().isTransientStorePoolEnable()) {
flushCommitLogService.wakeup();
} else {
commitLogService.wakeup();
}
}
}
public void run() {
CommitLog.log.info(this.getServiceName() + " service started");
while (!this.isStopped()) {
try {
this.waitForRunning(10);
this.doCommit();
} catch (Exception e) {
CommitLog.log.warn(this.getServiceName() + " service has exception. ", e);
}
}
// Under normal circumstances shutdown, wait for the arrival of the
// request, and then flush
try {
Thread.sleep(10);
} catch (InterruptedException e) {
CommitLog.log.warn("GroupCommitService Exception, ", e);
}
synchronized (this) {
// 交换请求
this.swapRequests();
}
this.doCommit();
CommitLog.log.info(this.getServiceName() + " service end");
}
private void doCommit() {
synchronized (this.requestsRead) {
if (!this.requestsRead.isEmpty()) {
for (GroupCommitRequest req : this.requestsRead) {
// There may be a message in the next file, so a maximum of
// two times the flush
boolean flushOK = false;
for (int i = 0; i < 2 && !flushOK; i++) {
flushOK = CommitLog.this.mappedFileQueue.getFlushedWhere() >= req.getNextOffset();
if (!flushOK) {
// 文件刷盘
CommitLog.this.mappedFileQueue.flush(0);
}
}
req.wakeupCustomer(flushOK);
}
long storeTimestamp = CommitLog.this.mappedFileQueue.getStoreTimestamp();
if (storeTimestamp > 0) {
CommitLog.this.defaultMessageStore.getStoreCheckpoint().setPhysicMsgTimestamp(storeTimestamp);
}
this.requestsRead.clear();
} else {
// Because of individual messages is set to not sync flush, it
// will come to this process
CommitLog.this.mappedFileQueue.flush(0);
}
}
}
// 为了避免同步刷盘消费任务与其他消息生产者提交任务产生锁竞争，
// GroupCommitService提供读容器与写容器，
// 这两个容器每执行完一次任务后交互，继续消费任务
private void swapRequests() {
List<GroupCommitRequest> tmp = this.requestsWrite;
this.requestsWrite = this.requestsRead;
this.requestsRead = tmp;
}
消息存储堆外内存相关
RocketMQ使用堆外内存（Direct Memory）可以提高消息传输的效率和性能，主要表现在以下几个方面：
减少了GC的开销：在使用堆内存时，生产者和消费者将消息转换成字节数组并存储在堆中，这些数据最终会被JVM垃圾回收器清理掉。如果消息量很大，就会产生大量的垃圾回收，导致系统效率下降。而使用堆外内存可以避免这个问题，因为这些内存不受JVM垃圾回收的管理，因此可以减少GC的开销。
提高了消息传输的效率：在使用堆外内存时，生产者和消费者可以直接将消息写入到内存中，而不需要将数据从堆中拷贝到直接内存中，这样可以减少内存拷贝的次数和数据在内存中的复制次数，从而提高了消息传输的效率。
提高了内存使用效率：由于JVM会为堆内存预留一定的内存空间，因此在堆内存使用时，很难将整个JVM进程的内存使用控制在合理的范围内。而使用堆外内存可以将内存管理的责任交给操作系统，避免了JVM管理内存带来的一些问题。需要注意的是，使用堆外内存也会带来一些额外的内存管理和维护的负担，例如需要管理内存映射和释放等问题。此外，在某些情况下，如果使用不当，可能会导致内存泄漏等问题，因此需要谨慎使用。
