心跳机制
在Consumer启动后，它就会通过定时任务不断地向RocketMQ集群中的所有Broker实例发送心跳包
心跳包内容包含了
-
-
- 消息消费分组名称
- 订阅关系集合
- 消息通信模式
- 客户端id的值
-
Broker端在收到Consumer的心跳消息后，会将它维护在ConsumerManager的本地缓存变量—consumerTable，同时并将封装后的客户端网络通道信息保存在本地缓存变量—channelInfoTable中，为之后做Consumer端的负载均衡提供可以依据的元数据信息。
消息拉取-PullMessageService
PUSH模式
rocketMQ的push模式并没没有实现真正的推送模式，而是通过一个pullMessageServce开启一个线程专门来不断从broker循环地拉取数据，这样一有消息就会及时拉取到本地，封装给用户使用时就有是broker端push到消费者的感觉。
PullMessageService
消息拉取是由PullMessageService服务线程负责的，在PullMessageService中维护了一个PullRequest队列，在该线程启动后，会从PullRequest队列中取出PullRequest对象，然后调用pullMessage()方法进行消息拉取。
PullMessageService也是继承了ServiceThread类的，当该线程启动后会执行其run()方法，如下。
private final LinkedBlockingQueue<PullRequest> pullRequestQueue = new LinkedBlockingQueue<PullRequest>();
@Override
public void run() {
log.info(this.getServiceName() + " service started");
while (!this.isStopped()) {
try {
PullRequest pullRequest = this.pullRequestQueue.take();
this.pullMessage(pullRequest);
} catch (InterruptedException ignored) {
} catch (Exception e) {
log.error("Pull Message Service Run Method exception", e);
}
}
log.info(this.getServiceName() + " service end");
}
可以看到pullRequestQueue是一个阻塞队列，因此该队列为空时，该线程会等待队列中有值也就是pullRequest对象时才会调用pullMessage方法。
PullRequest
消息拉取时是通过PullRequest中封装的订阅信息来从broker中拉取消息的，PullRequest是在RebalnceImpl中，负载均衡完成后，根据分配的消息队列进行封装，然后put到PullMessageService中pullRequestQueue中的
public class PullRequest {
private String consumerGroup;//消费者组
private MessageQueue messageQueue;//消息队列
private ProcessQueue processQueue;//消息处理队列
private long nextOffset;//消费的起始偏移量
private boolean lockedFirst = false;
...
}
pullMessage()##PullMessageService
private void pullMessage(final PullRequest pullRequest) {
final MQConsumerInner consumer = this.mQClientFactory.selectConsumer(pullRequest.getConsumerGroup());
if (consumer != null) {
DefaultMQPushConsumerImpl impl = (DefaultMQPushConsumerImpl) consumer;
impl.pullMessage(pullRequest);
} else {
log.warn("No matched consumer for the PullRequest {}, drop it", pullRequest);
}
}
pullMessage()##DefaultMQPushConsumerImpl
public void pullMessage(final PullRequest pullRequest) {
final ProcessQueue processQueue = pullRequest.getProcessQueue();
//判断当前processQueue是否被移除
if (processQueue.isDropped()) {
log.info("the pull request[{}] is dropped.", pullRequest.toString());
return;
}
//更新processQueue的lastPullTimestamp，即最后拉取时间戳
pullRequest.getProcessQueue().setLastPullTimestamp(System.currentTimeMillis());
try {
this.makeSureStateOK();
} catch (MQClientException e) {
log.warn("pullMessage exception, consumer state not ok", e);
this.executePullRequestLater(pullRequest, pullTimeDelayMillsWhenException);
return;
}
//如果当前消费者被挂起，则将processQueue延迟一秒后再次放入PullMessageService的pullRequestQueue队列
if (this.isPause()) {
log.warn("consumer was paused, execute pull request later. instanceName={}, group={}", this.defaultMQPushConsumer.getInstanceName(), this.defaultMQPushConsumer.getConsumerGroup());
this.executePullRequestLater(pullRequest, PULL_TIME_DELAY_MILLS_WHEN_SUSPEND);
return;
}
//对消费端进行限流控制，从消息数量和消息大小两个维度来限制
//获取当前processQueue中堆积的消息总数和消息总内存大小
long cachedMessageCount = processQueue.getMsgCount().get();
long cachedMessageSizeInMiB = processQueue.getMsgSize().get() / (1024 * 1024);
//如果堆积消息总量达到限流阈值，则放弃该队列的本次消息拉取任务，并在50毫秒延迟后重新加入PullMessageService的pullRequestQueue队列
if (cachedMessageCount > this.defaultMQPushConsumer.getPullThresholdForQueue()) {
this.executePullRequestLater(pullRequest, PULL_TIME_DELAY_MILLS_WHEN_FLOW_CONTROL);
if ((queueFlowControlTimes++ % 1000) == 0) {
log.warn(
"the cached message count exceeds the threshold {}, so do flow control, minOffset={}, maxOffset={}, count={}, size={} MiB, pullRequest={}, flowControlTimes={}",
this.defaultMQPushConsumer.getPullThresholdForQueue(), processQueue.getMsgTreeMap().firstKey(), processQueue.getMsgTreeMap().lastKey(), cachedMessageCount, cachedMessageSizeInMiB, pullRequest, queueFlowControlTimes);
}
return;
}
if (cachedMessageSizeInMiB > this.defaultMQPushConsumer.getPullThresholdSizeForQueue()) {
this.executePullRequestLater(pullRequest, PULL_TIME_DELAY_MILLS_WHEN_FLOW_CONTROL);
if ((queueFlowControlTimes++ % 1000) == 0) {
log.warn(
"the cached message size exceeds the threshold {} MiB, so do flow control, minOffset={}, maxOffset={}, count={}, size={} MiB, pullRequest={}, flowControlTimes={}",
this.defaultMQPushConsumer.getPullThresholdSizeForQueue(), processQueue.getMsgTreeMap().firstKey(), processQueue.getMsgTreeMap().lastKey(), cachedMessageCount, cachedMessageSizeInMiB, pullRequest, queueFlowControlTimes);
}
return;
}
//判断是否顺序消费
if (!this.consumeOrderly) {
//processQueue中消息的最大偏移量与最小偏移量直接的差值不能大于2000
//这个主要是避免存在某条消息堵塞，消息进度无法向前推进
if (processQueue.getMaxSpan() > this.defaultMQPushConsumer.getConsumeConcurrentlyMaxSpan()) {
this.executePullRequestLater(pullRequest, PULL_TIME_DELAY_MILLS_WHEN_FLOW_CONTROL);
if ((queueMaxSpanFlowControlTimes++ % 1000) == 0) {
log.warn(
"the queue's messages, span too long, so do flow control, minOffset={}, maxOffset={}, maxSpan={}, pullRequest={}, flowControlTimes={}",
processQueue.getMsgTreeMap().firstKey(), processQueue.getMsgTreeMap().lastKey(), processQueue.getMaxSpan(),
pullRequest, queueMaxSpanFlowControlTimes);
}
return;
}
} else {
if (processQueue.isLocked()) {
if (!pullRequest.isLockedFirst()) {
final long offset = this.rebalanceImpl.computePullFromWhere(pullRequest.getMessageQueue());
boolean brokerBusy = offset < pullRequest.getNextOffset();
log.info("the first time to pull message, so fix offset from broker. pullRequest: {} NewOffset: {} brokerBusy: {}",
pullRequest, offset, brokerBusy);
if (brokerBusy) {
log.info("[NOTIFYME]the first time to pull message, but pull request offset larger than broker consume offset. pullRequest: {} NewOffset: {}",
pullRequest, offset);
}
pullRequest.setLockedFirst(true);
pullRequest.setNextOffset(offset);
}
} else {
this.executePullRequestLater(pullRequest, pullTimeDelayMillsWhenException);
log.info("pull message later because not locked in broker, {}", pullRequest);
return;
}
}
//获取该主题的订阅信息，如果为空，则停止本次任务，等待三秒后重新放入PullMessageService的pullRequestQueue队列
final SubscriptionData subscriptionData = this.rebalanceImpl.getSubscriptionInner().get(pullRequest.getMessageQueue().getTopic());
if (null == subscriptionData) {
this.executePullRequestLater(pullRequest, pullTimeDelayMillsWhenException);
log.warn("find the consumer's subscription failed, {}", pullRequest);
return;
}
final long beginTimestamp = System.currentTimeMillis();
//负责拉取到消息后的回调处理，我觉得可以单独用一个方法来返回该对象的，写在这里导致pullMessage方法太长了，影响阅读
PullCallback pullCallback = new PullCallback() {
@Override
public void onSuccess(PullResult pullResult) {
...省略，太长了，后面讲...
}
@Override
public void onException(Throwable e) {
if (!pullRequest.getMessageQueue().getTopic().startsWith(MixAll.RETRY_GROUP_TOPIC_PREFIX)) {
log.warn("execute the pull request exception", e);}
DefaultMQPushConsumerImpl.this.executePullRequestLater(pullRequest, pullTimeDelayMillsWhenException);
}
};
boolean commitOffsetEnable = false;
long commitOffsetValue = 0L;
if (MessageModel.CLUSTERING == this.defaultMQPushConsumer.getMessageModel()) {
commitOffsetValue = this.offsetStore.readOffset(pullRequest.getMessageQueue(), ReadOffsetType.READ_FROM_MEMORY);
if (commitOffsetValue > 0) {
commitOffsetEnable = true;
}
}
String subExpression = null;
boolean classFilter = false;
SubscriptionData sd = this.rebalanceImpl.getSubscriptionInner().get(pullRequest.getMessageQueue().getTopic());
if (sd != null) {
if (this.defaultMQPushConsumer.isPostSubscriptionWhenPull() && !sd.isClassFilterMode()) {
subExpression = sd.getSubString();
}
classFilter = sd.isClassFilterMode();
}
int sysFlag = PullSysFlag.buildSysFlag(
commitOffsetEnable, // commitOffset
true, // suspend
subExpression != null, // subscription
classFilter // class filter
);
try {
//执行消息拉取操作，拉取成功后调用pullCallback回调方法
//pullAPIWrapper对客户端API进行了封装，隐藏了消息拉取的具体步骤
this.pullAPIWrapper.pullKernelImpl(
pullRequest.getMessageQueue(), //拉取消息的队列
subExpression, //消息过滤表达式
subscriptionData.getExpressionType(), //消息过滤表达式类型，支持按TAG过滤以及SQL表达式过滤
subscriptionData.getSubVersion(), //版本
pullRequest.getNextOffset(),//消息拉取的偏移量
this.defaultMQPushConsumer.getPullBatchSize(),//批量拉取的最大条数，默认32
sysFlag,//拉取系统标记
commitOffsetValue,//当前MessageQueue消费进度
BROKER_SUSPEND_MAX_TIME_MILLIS,//消息拉取过程中允许Broker挂起的时间，默认15s
CONSUMER_TIMEOUT_MILLIS_WHEN_SUSPEND,//消息拉取超时时间
CommunicationMode.ASYNC,//消息拉取模式，异步
pullCallback//消息拉取成功后的回调方法
);
} catch (Exception e) {
log.error("pullKernelImpl exception", e);
this.executePullRequestLater(pullRequest, pullTimeDelayMillsWhenException);
}
}
流量控制
根据上面源码可以发现，RocketMQ从下面三个维度来对消费者客户端进行流量控制，在push模式下。如果是pull模式则无需控制，
因为pull模式本就是消费者按照消息消费速率自动控制消息拉取的。
- 消费者本地缓存消息数超过pullThresholdForQueue时，默认1000。
- 消费者本地缓存消息大小超过pullThresholdSizeForQueue时，默认100MB。
- 消费者本地缓存消息跨度超过consumeConcurrentlyMaxSpan时，默认2000。
消费者流控的结果是降低拉取频率。
pullKernelImpl()##PullAPIWrapper
public PullResult pullKernelImpl(
final MessageQueue mq,
final String subExpression,
final String expressionType,
final long subVersion,
final long offset,
final int maxNums,
final int sysFlag,
final long commitOffset,
final long brokerSuspendMaxTimeMillis,
final long timeoutMillis,
final CommunicationMode communicationMode,
final PullCallback pullCallback
) throws MQClientException, RemotingException, MQBrokerException, InterruptedException {
FindBrokerResult findBrokerResult =
this.mQClientFactory.findBrokerAddressInSubscribe(mq.getBrokerName(),
this.recalculatePullFromWhichNode(mq), false);
if (null == findBrokerResult) {
this.mQClientFactory.updateTopicRouteInfoFromNameServer(mq.getTopic());
findBrokerResult =
this.mQClientFactory.findBrokerAddressInSubscribe(mq.getBrokerName(),
this.recalculatePullFromWhichNode(mq), false);
}
if (findBrokerResult != null) {
{
// check version
if (!ExpressionType.isTagType(expressionType)
&& findBrokerResult.getBrokerVersion() < MQVersion.Version.V4_1_0_SNAPSHOT.ordinal()) {
throw new MQClientException("The broker[" + mq.getBrokerName() + ", "
+ findBrokerResult.getBrokerVersion() + "] does not upgrade to support for filter message by " + expressionType, null);
}
}
int sysFlagInner = sysFlag;
if (findBrokerResult.isSlave()) {
sysFlagInner = PullSysFlag.clearCommitOffsetFlag(sysFlagInner);
}
PullMessageRequestHeader requestHeader = new PullMessageRequestHeader();
requestHeader.setConsumerGroup(this.consumerGroup);
requestHeader.setTopic(mq.getTopic());
requestHeader.setQueueId(mq.getQueueId());
requestHeader.setQueueOffset(offset);
requestHeader.setMaxMsgNums(maxNums);
requestHeader.setSysFlag(sysFlagInner);
requestHeader.setCommitOffset(commitOffset);
requestHeader.setSuspendTimeoutMillis(brokerSuspendMaxTimeMillis);
requestHeader.setSubscription(subExpression);
requestHeader.setSubVersion(subVersion);
requestHeader.setExpressionType(expressionType);
String brokerAddr = findBrokerResult.getBrokerAddr();
if (PullSysFlag.hasClassFilterFlag(sysFlagInner)) {
brokerAddr = computPullFromWhichFilterServer(mq.getTopic(), brokerAddr);
}
//通过NettyRemotingClient执行消
PullResult pullResult = this.mQClientFactory.getMQClientAPIImpl().pullMessage(
brokerAddr,
requestHeader,
timeoutMillis,
communicationMode,
pullCallback);
return pullResult;
}
throw new MQClientException("The broker[" + mq.getBrokerName() + "] not exist", null);
}
pullMessage()##MQClientAPIImpl
public PullResult pullMessage(
final String addr,
final PullMessageRequestHeader requestHeader,
final long timeoutMillis,
final CommunicationMode communicationMode,
final PullCallback pullCallback
) throws RemotingException, MQBrokerException, InterruptedException {
RemotingCommand request = RemotingCommand.createRequestCommand(RequestCode.PULL_MESSAGE, requestHeader);
switch (communicationMode) {
case ONEWAY:
assert false;
return null;
case ASYNC:
this.pullMessageAsync(addr, request, timeoutMillis, pullCallback);
return null;
case SYNC:
return this.pullMessageSync(addr, request, timeoutMillis);
default:
assert false;
break;
}
return null;
}
private void pullMessageAsync(
final String addr,
final RemotingCommand request,
final long timeoutMillis,
final PullCallback pullCallback
) throws RemotingException, InterruptedException {
//调用remote模块执行异步请求，remote模块底层实现为netty
this.remotingClient.invokeAsync(addr, request, timeoutMillis, new InvokeCallback() {
//操作完成回调
@Override
public void operationComplete(ResponseFuture responseFuture) {
RemotingCommand response = responseFuture.getResponseCommand();
if (response != null) {
try {
//将broker端返回数据封装成PullResult对象
PullResult pullResult = MQClientAPIImpl.this.processPullResponse(response);
assert pullResult != null;
//执行回调，之前在DefaultMQPushConsumerImpl中实现了一个回调接口的匿名内部类
pullCallback.onSuccess(pullResult);
} catch (Exception e) {
pullCallback.onException(e);
}
} else {
if (!responseFuture.isSendRequestOK()) {
pullCallback.onException(new MQClientException("send request failed to " + addr + ". Request: " + request, responseFuture.getCause()));
} else if (responseFuture.isTimeout()) {
pullCallback.onException(new MQClientException("wait response from " + addr + " timeout :" + responseFuture.getTimeoutMillis() + "ms" + ". Request: " + request,
responseFuture.getCause()));
} else {
pullCallback.onException(new MQClientException("unknown reason. addr: " + addr + ", timeoutMillis: " + timeoutMillis + ". Request: " + request, responseFuture.getCause()));
}
}
}
});
}
回调处理-PullCallback
现在我们看一下之前的回调接口的onSuccess()方法
PullCallback pullCallback = new PullCallback() {
@Override
public void onSuccess(PullResult pullResult) {
if (pullResult != null) {
pullResult = DefaultMQPushConsumerImpl.this.pullAPIWrapper.processPullResult(pullRequest.getMessageQueue(), pullResult,
subscriptionData);
switch (pullResult.getPullStatus()) {
case FOUND:
long prevRequestOffset = pullRequest.getNextOffset();
pullRequest.setNextOffset(pullResult.getNextBeginOffset());
long pullRT = System.currentTimeMillis() - beginTimestamp;
DefaultMQPushConsumerImpl.this.getConsumerStatsManager().incPullRT(pullRequest.getConsumerGroup(),
pullRequest.getMessageQueue().getTopic(), pullRT);
long firstMsgOffset = Long.MAX_VALUE;
if (pullResult.getMsgFoundList() == null || pullResult.getMsgFoundList().isEmpty()) {
DefaultMQPushConsumerImpl.this.executePullRequestImmediately(pullRequest);
} else {
firstMsgOffset = pullResult.getMsgFoundList().get(0).getQueueOffset();
DefaultMQPushConsumerImpl.this.getConsumerStatsManager().incPullTPS(pullRequest.getConsumerGroup(),
pullRequest.getMessageQueue().getTopic(), pullResult.getMsgFoundList().size());
boolean dispatchToConsume = processQueue.putMessage(pullResult.getMsgFoundList());
DefaultMQPushConsumerImpl.this.consumeMessageService.submitConsumeRequest(
pullResult.getMsgFoundList(),
processQueue,
pullRequest.getMessageQueue(),
dispatchToConsume);
if (DefaultMQPushConsumerImpl.this.defaultMQPushConsumer.getPullInterval() > 0) {
DefaultMQPushConsumerImpl.this.executePullRequestLater(pullRequest,
DefaultMQPushConsumerImpl.this.defaultMQPushConsumer.getPullInterval());
} else {
DefaultMQPushConsumerImpl.this.executePullRequestImmediately(pullRequest);
}
}
if (pullResult.getNextBeginOffset() < prevRequestOffset
|| firstMsgOffset < prevRequestOffset) {
log.warn(
"[BUG] pull message result maybe data wrong, nextBeginOffset: {} firstMsgOffset: {} prevRequestOffset: {}",
pullResult.getNextBeginOffset(),
firstMsgOffset,
prevRequestOffset);
}
break;
case NO_NEW_MSG:
pullRequest.setNextOffset(pullResult.getNextBeginOffset());
DefaultMQPushConsumerImpl.this.correctTagsOffset(pullRequest);
DefaultMQPushConsumerImpl.this.executePullRequestImmediately(pullRequest);
break;
case NO_MATCHED_MSG:
pullRequest.setNextOffset(pullResult.getNextBeginOffset());
DefaultMQPushConsumerImpl.this.correctTagsOffset(pullRequest);
DefaultMQPushConsumerImpl.this.executePullRequestImmediately(pullRequest);
break;
case OFFSET_ILLEGAL:
log.warn("the pull request offset illegal, {} {}",
pullRequest.toString(), pullResult.toString());
pullRequest.setNextOffset(pullResult.getNextBeginOffset());
pullRequest.getProcessQueue().setDropped(true);
DefaultMQPushConsumerImpl.this.executeTaskLater(new Runnable() {
@Override
public void run() {
try {
DefaultMQPushConsumerImpl.this.offsetStore.updateOffset(pullRequest.getMessageQueue(),
pullRequest.getNextOffset(), false);
DefaultMQPushConsumerImpl.this.offsetStore.persist(pullRequest.getMessageQueue());
DefaultMQPushConsumerImpl.this.rebalanceImpl.removeProcessQueue(pullRequest.getMessageQueue());
log.warn("fix the pull request offset, {}", pullRequest);
} catch (Throwable e) {
log.error("executeTaskLater Exception", e);
}
}
}, 10000);
break;
default:
break;
}
}
}
@Override
public void onException(Throwable e) {
if (!pullRequest.getMessageQueue().getTopic().startsWith(MixAll.RETRY_GROUP_TOPIC_PREFIX)) {
log.warn("execute the pull request exception", e);
}
DefaultMQPushConsumerImpl.this.executePullRequestLater(pullRequest, pullTimeDelayMillsWhenException);
}
};
消息消费 - ConsumeMessageService
根据前面可知，当拉取到消息后，会将消息提交到消息消费任务ConsumeMessageService
public interface ConsumeMessageService {
void start();
void shutdown();
void updateCorePoolSize(int corePoolSize);
void incCorePoolSize();
void decCorePoolSize();
int getCorePoolSize();
//直接消费消息
ConsumeMessageDirectlyResult consumeMessageDirectly(final MessageExt msg, final String brokerName);
//提交消息任务到线程池进行消费
void submitConsumeRequest(
final List<MessageExt> msgs,
final ProcessQueue processQueue,
final MessageQueue messageQueue,
final boolean dispathToConsume);
}
RocketMQ消费者有两种消息消费模式，并发消费和顺序消费
并发消费-ConsumeMessageConcurrentlyService
并发消费时，会根据最大批消费数量，将拉取到的消费拆分到多个消费任务，提交到线程池中并发消费。
submitConsumeRequest()##ConsumeMessageConcurrentlyService
public void submitConsumeRequest(
final List<MessageExt> msgs,
final ProcessQueue processQueue,
final MessageQueue messageQueue,
final boolean dispatchToConsume) {
//消费批次数量，一个消息消费任务ConsumeRequest中包含的消息数量，默认为1
final int consumeBatchSize = this.defaultMQPushConsumer.getConsumeMessageBatchMaxSize();
if (msgs.size() <= consumeBatchSize) {
ConsumeRequest consumeRequest = new ConsumeRequest(msgs, processQueue, messageQueue);
try {
//将消息消费任务提交到线程池
this.consumeExecutor.submit(consumeRequest);
} catch (RejectedExecutionException e) {
//当线程池拒绝该任务，即线程池满了之后，延迟5秒后重新投递
this.submitConsumeRequestLater(consumeRequest);
}
} else {
//当消息数量大于consumeBatchSize时，则对消息进行拆分，每个任务分配consumeBatchSize条消息
for (int total = 0; total < msgs.size(); ) {
List<MessageExt> msgThis = new ArrayList<MessageExt>(consumeBatchSize);
for (int i = 0; i < consumeBatchSize; i++, total++) {
if (total < msgs.size()) {
msgThis.add(msgs.get(total));
} else {
break;
}
}
ConsumeRequest consumeRequest = new ConsumeRequest(msgThis, processQueue, messageQueue);
try {
this.consumeExecutor.submit(consumeRequest);
} catch (RejectedExecutionException e) {
for (; total < msgs.size(); total++) {
msgThis.add(msgs.get(total));
}
this.submitConsumeRequestLater(consumeRequest);
}
}
}
}
ConsumeMessageConcurrentlyService$ConsumeRequest
提交到消息消费服务的消息，最终都会封装成一个个ConsumeRequest任务提交到线程池，ConsumeRequest实现了Runnable接口，可以开启一个独立的线程，消息消费的过程就在其run()方法中。
public void run() {
//检查该处理队列是否已被移除，如果被移除则停止消费该队列里的消息。
//在执行重均衡时，如果该消息队列被分配给消费者组其它消费者，则需要将当前消费者中的该队列的dropped置为true
//这样可以避免消费者消费到不属于自己队列的消息，避免消息重复消费
if (this.processQueue.isDropped()) {
log.info("the message queue not be able to consume, because it's dropped. group={} {}", ConsumeMessageConcurrentlyService.this.consumerGroup, this.messageQueue);
return;
}
//获取消息消费监听器，我们构建消费者实例时通过registerMessageListener()方法注册自定义的消息消费监听
//即执行我们实际业务的处理程序
MessageListenerConcurrently listener = ConsumeMessageConcurrentlyService.this.messageListener;
ConsumeConcurrentlyContext context = new ConsumeConcurrentlyContext(messageQueue);
ConsumeConcurrentlyStatus status = null;
defaultMQPushConsumerImpl.resetRetryAndNamespace(msgs, defaultMQPushConsumer.getConsumerGroup());
//执行消息消费前置钩子函数
//通过 consumer.getDefaultMQPushConsumerImpl().registerConsumeMessageHook() 方法进行注册钩子函数
ConsumeMessageContext consumeMessageContext = null;
if (ConsumeMessageConcurrentlyService.this.defaultMQPushConsumerImpl.hasHook()) {
consumeMessageContext = new ConsumeMessageContext();
consumeMessageContext.setNamespace(defaultMQPushConsumer.getNamespace());
consumeMessageContext.setConsumerGroup(defaultMQPushConsumer.getConsumerGroup());
consumeMessageContext.setProps(new HashMap<String, String>());
consumeMessageContext.setMq(messageQueue);
consumeMessageContext.setMsgList(msgs);
consumeMessageContext.setSuccess(false);
ConsumeMessageConcurrentlyService.this.defaultMQPushConsumerImpl.executeHookBefore(consumeMessageContext);
}
long beginTimestamp = System.currentTimeMillis();
boolean hasException = false;
ConsumeReturnType returnType = ConsumeReturnType.SUCCESS;
try {
if (msgs != null && !msgs.isEmpty()) {
for (MessageExt msg : msgs) {
MessageAccessor.setConsumeStartTimeStamp(msg, String.valueOf(System.currentTimeMillis()));
}
}
//调用具体的消息消费程序，并获取返回的执行结果
status = listener.consumeMessage(Collections.unmodifiableList(msgs), context);
} catch (Throwable e) {
log.warn("consumeMessage exception: {} Group: {} Msgs: {} MQ: {}",
RemotingHelper.exceptionSimpleDesc(e),
ConsumeMessageConcurrentlyService.this.consumerGroup,
msgs,
messageQueue);
hasException = true;
}
long consumeRT = System.currentTimeMillis() - beginTimestamp;
//对消费结果进行处理
if (null == status) {
if (hasException) {
returnType = ConsumeReturnType.EXCEPTION;
} else {
returnType = ConsumeReturnType.RETURNNULL;
}
} else if (consumeRT >= defaultMQPushConsumer.getConsumeTimeout() * 60 * 1000) {
returnType = ConsumeReturnType.TIME_OUT;
} else if (ConsumeConcurrentlyStatus.RECONSUME_LATER == status) {
returnType = ConsumeReturnType.FAILED;
} else if (ConsumeConcurrentlyStatus.CONSUME_SUCCESS == status) {
returnType = ConsumeReturnType.SUCCESS;
}
if (ConsumeMessageConcurrentlyService.this.defaultMQPushConsumerImpl.hasHook()) {
consumeMessageContext.getProps().put(MixAll.CONSUME_CONTEXT_TYPE, returnType.name());
}
if (null == status) {
log.warn("consumeMessage return null, Group: {} Msgs: {} MQ: {}",
ConsumeMessageConcurrentlyService.this.consumerGroup,
msgs,
messageQueue);
status = ConsumeConcurrentlyStatus.RECONSUME_LATER;
}
//执行消息消费后置钩子函数
if (ConsumeMessageConcurrentlyService.this.defaultMQPushConsumerImpl.hasHook()) {
consumeMessageContext.setStatus(status.toString());
consumeMessageContext.setSuccess(ConsumeConcurrentlyStatus.CONSUME_SUCCESS == status);
ConsumeMessageConcurrentlyService.this.defaultMQPushConsumerImpl.executeHookAfter(consumeMessageContext);
}
ConsumeMessageConcurrentlyService.this.getConsumerStatsManager()
.incConsumeRT(ConsumeMessageConcurrentlyService.this.consumerGroup, messageQueue.getTopic(), consumeRT);
//如果在消息消费过程中，该队列被分配给了其它消费者，则不对消费结果进行处理。
//因此可能会造成消息重复消费，因此需要用户自己在业务端自行实现重复消费限制
if (!processQueue.isDropped()) {
//对消费结果进行处理
ConsumeMessageConcurrentlyService.this.processConsumeResult(status, context, this);
} else {
log.warn("processQueue is dropped without process consume result. messageQueue={}, msgs={}", messageQueue, msgs);
}
}
根据源码可以得出，消息消费分为以下几个步骤：
- 校验当前消息队列是否已被移除，避免重复消费
- 执行消息消费前置钩子函数
- 调用MessageListener来执行用户注册的实际消息消费过程
- 对消息消费返回结果进行处理以及消息消费是否超时判断
- 执行消息消费后置钩子函数
- 执行消息消费结果处理程序，包括消息重试，offset提交等
消费结果处理及提交
processConsumeResult()
public void processConsumeResult(
final ConsumeConcurrentlyStatus status,
final ConsumeConcurrentlyContext context,
final ConsumeRequest consumeRequest
) {
int ackIndex = context.getAckIndex();
if (consumeRequest.getMsgs().isEmpty())
return;
switch (status) {
case CONSUME_SUCCESS:
if (ackIndex >= consumeRequest.getMsgs().size()) {
ackIndex = consumeRequest.getMsgs().size() - 1;
}
int ok = ackIndex + 1;
int failed = consumeRequest.getMsgs().size() - ok;
this.getConsumerStatsManager().incConsumeOKTPS(consumerGroup, consumeRequest.getMessageQueue().getTopic(), ok);
this.getConsumerStatsManager().incConsumeFailedTPS(consumerGroup, consumeRequest.getMessageQueue().getTopic(), failed);
break;
case RECONSUME_LATER:
ackIndex = -1;
this.getConsumerStatsManager().incConsumeFailedTPS(consumerGroup, consumeRequest.getMessageQueue().getTopic(),
consumeRequest.getMsgs().size());
break;
default:
break;
}
switch (this.defaultMQPushConsumer.getMessageModel()) {
case BROADCASTING:
//广播模式下，消息消费失败后不会重新消费，而是打印warn级别日志提醒
for (int i = ackIndex + 1; i < consumeRequest.getMsgs().size(); i++) {
MessageExt msg = consumeRequest.getMsgs().get(i);
log.warn("BROADCASTING, the message consume failed, drop it, {}", msg.toString());
}
break;
case CLUSTERING:
List<MessageExt> msgBackFailed = new ArrayList<MessageExt>(consumeRequest.getMsgs().size());
//集群模式下，如果该批消息消费失败，则把该批消息投递到重试队列
for (int i = ackIndex + 1; i < consumeRequest.getMsgs().size(); i++) {
MessageExt msg = consumeRequest.getMsgs().get(i);
//将消息发送到重试队列
boolean result = this.sendMessageBack(msg, context);
if (!result) {
msg.setReconsumeTimes(msg.getReconsumeTimes() + 1);
msgBackFailed.add(msg);
}
}
//如果有消息投递到重试队列失败，则将该消息从当前consumeRequest中移除，并重新提交到消息消费服务，延迟5S后重新消费。
if (!msgBackFailed.isEmpty()) {
consumeRequest.getMsgs().removeAll(msgBackFailed);
this.submitConsumeRequestLater(msgBackFailed, consumeRequest.getProcessQueue(), consumeRequest.getMessageQueue());
}
break;
default:
break;
}
//从processQueue中移除这批消息，并返回移除这些消息后processQueue中最小的消息偏移量，然后用该offset更新消息消费进度
long offset = consumeRequest.getProcessQueue().removeMessage(consumeRequest.getMsgs());
//更新消费偏移量
if (offset >= 0 && !consumeRequest.getProcessQueue().isDropped()) {
this.defaultMQPushConsumerImpl.getOffsetStore().updateOffset(consumeRequest.getMessageQueue(), offset, true);
}
}
重试队列
RocketMQ会为每个消费组都设置一个Topic名称为“%RETRY%+consumerGroup”的重试队列（这里需要注意的是，这个Topic的重试队列是针对消费组，而不是针对每个Topic设置的），用于暂时保存因为各种异常而导致Consumer端无法消费的消息。
考虑到异常恢复起来需要一些时间，会为重试队列设置多个重试级别，每个重试级别都有与之对应的重新投递延时，重试次数越多投递延时就越大。延迟级别有以下18个级别，依次递增。重试级别为1则表示延时5S，为2则表示10S。每消费失败一次，重试级别+1
private String messageDelayLevel = "1s 5s 10s 30s 1m 2m 3m 4m 5m 6m 7m 8m 9m 10m 20m 30m 1h 2h";
当重试级别大于0时，即需要延迟处理时，RocketMQ对于重试消息的处理是先保存至Topic名称为“SCHEDULE_TOPIC_XXXX”的延迟队列中，队列ID为对应的延迟级别 -1。后台定时任务按照对应的时间进行Delay后重新保存至“%RETRY%+consumerGroup”的重试队列中。关于重试和定时队列的相关内容会单独开一篇文章进行详细分析。这里暂不多说。
提交offset
偏移量提交是通过OffsetStore的updateOffset()方法实现的。OffsetStore默认有两个实现类，LocalFileOffsetStore和RemoteBrokerOffsetStore分别对应广播消费模式和集群消费模式，广播消费模式时offset是存储在消费者本地的，而集群模式时通过broker端对消费进度进行统一管理。
两种模式下都是先将offset存储到本地的Map结构中，然后会定时调用持久化方法将offset持久化，只不过LocalFileOffsetStore是直接保存到本地文件中，而RemoteBrokerOffsetStore是将offset保存到Borker端。默认每10秒持久化一次
private ConcurrentMap<MessageQueue, AtomicLong> offsetTable =
new ConcurrentHashMap<MessageQueue, AtomicLong>();
@Override
public void updateOffset(MessageQueue mq, long offset, boolean increaseOnly) {
if (mq != null) {
AtomicLong offsetOld = this.offsetTable.get(mq);
if (null == offsetOld) {
offsetOld = this.offsetTable.putIfAbsent(mq, new AtomicLong(offset));
}
if (null != offsetOld) {
if (increaseOnly) {
MixAll.compareAndIncreaseOnly(offsetOld, offset);
} else {
offsetOld.set(offset);
}
}
}
}
关于offset的值
前面消费结果处理方法分析中已经介绍了，当一批消息消费结束后，需要从processQueue中删除该批消息，并返回processQueue中删除该批消息后最小的消息offset值。假如processQueue中有offset分别为10，20，21，23，...的消息，其中taskA中的消息offset是20，当taskA结束后，会删除offset为20的消息，但是返回的offset不会是21，而是10。只有等offset为10的消息被消费完成后，才会用下一个最小的offset去更新比如21。
那么当offset为10的消息消费过程中由于死锁或者其它原因导致长时间阻塞，那么消息进度会无法向前推进。所以在拉取消息的时候如果processQueue中消息跨度大于限制值时，则延迟该队列的消息拉取。
- 消费者本地缓存消息跨度超过consumeConcurrentlyMaxSpan时，默认2000
顺序消费-ConsumeMessageOrderlyService
顺序消费和并发消费一样，也是通过submitConsumeRequest()方法将消息封装为ConsumeRequest任务并提交到线程池消费。
不过消息不会拆分，而是封装到一个ConsumeRequest任务中顺序消费。
ConsumeMessageOrderlyService$ConsumeRequest
public void run() {
if (this.processQueue.isDropped()) {
log.warn("run, the message queue not be able to consume, because it's dropped. {}", this.messageQueue);
return;
}
//消费时会对该消息队列加锁，因此一个消息队列同一时刻只会被一个线程访问，保证了同一个队列内部消费的顺序。
final Object objLock = messageQueueLock.fetchLockObject(this.messageQueue);
synchronized (objLock) {
if (MessageModel.BROADCASTING.equals(ConsumeMessageOrderlyService.this.defaultMQPushConsumerImpl.messageModel())
|| (this.processQueue.isLocked() && !this.processQueue.isLockExpired())) {
final long beginTime = System.currentTimeMillis();
for (boolean continueConsume = true; continueConsume; ) {
//判断该消息队列是否已经被移除
if (this.processQueue.isDropped()) {
log.warn("the message queue not be able to consume, because it's dropped. {}", this.messageQueue);
break;
}
//是否获得当前消息队列的锁，如果没有则尝试获取锁之后重新消费，如果获取锁失败则延迟3S之后重新提交
if (MessageModel.CLUSTERING.equals(ConsumeMessageOrderlyService.this.defaultMQPushConsumerImpl.messageModel())
&& !this.processQueue.isLocked()) {
log.warn("the message queue not locked, so consume later, {}", this.messageQueue);
ConsumeMessageOrderlyService.this.tryLockLaterAndReconsume(this.messageQueue, this.processQueue, 10);
break;
}
//锁如果已经过期也重新执行获得锁的操作
if (MessageModel.CLUSTERING.equals(ConsumeMessageOrderlyService.this.defaultMQPushConsumerImpl.messageModel())
&& this.processQueue.isLockExpired()) {
log.warn("the message queue lock expired, so consume later, {}", this.messageQueue);
ConsumeMessageOrderlyService.this.tryLockLaterAndReconsume(this.messageQueue, this.processQueue, 10);
break;
}
long interval = System.currentTimeMillis() - beginTime;
//顺序消费时，循环地从处理队列中获取consumeBatchSize个消息进行消费，直至没有消息，
// 每次循环都会判断本次消费任务是否已消费超时，如果超时则重新提交消费该批消息
//顺序消费时，每个ConsumeRequest任务是根据消费时间来限制的，当一个任务消费时间达到阈值(60S)
//则停止本次任务，让出线程池资源。
if (interval > MAX_TIME_CONSUME_CONTINUOUSLY) {
ConsumeMessageOrderlyService.this.submitConsumeRequestLater(processQueue, messageQueue, 10);
break;
}
final int consumeBatchSize =
ConsumeMessageOrderlyService.this.defaultMQPushConsumer.getConsumeMessageBatchMaxSize();
//每次从处理队列中按消费批处理数量来一次取出对应数量的消息，如果获取消息为空，则表明消息已经消费完了。则结束本次任务
List<MessageExt> msgs = this.processQueue.takeMessags(consumeBatchSize);
defaultMQPushConsumerImpl.resetRetryAndNamespace(msgs, defaultMQPushConsumer.getConsumerGroup());
if (!msgs.isEmpty()) {
final ConsumeOrderlyContext context = new ConsumeOrderlyContext(this.messageQueue);
ConsumeOrderlyStatus status = null;
ConsumeMessageContext consumeMessageContext = null;
if (ConsumeMessageOrderlyService.this.defaultMQPushConsumerImpl.hasHook()) {
consumeMessageContext = new ConsumeMessageContext();
consumeMessageContext
.setConsumerGroup(ConsumeMessageOrderlyService.this.defaultMQPushConsumer.getConsumerGroup());
consumeMessageContext.setNamespace(defaultMQPushConsumer.getNamespace());
consumeMessageContext.setMq(messageQueue);
consumeMessageContext.setMsgList(msgs);
consumeMessageContext.setSuccess(false);
// init the consume context type
consumeMessageContext.setProps(new HashMap<String, String>());
ConsumeMessageOrderlyService.this.defaultMQPushConsumerImpl.executeHookBefore(consumeMessageContext);
}
long beginTimestamp = System.currentTimeMillis();
ConsumeReturnType returnType = ConsumeReturnType.SUCCESS;
boolean hasException = false;
try {
//申请消费锁，每个处理队列持有一个Lock对象，保证消息消费时，一个处理队列不会被并发消费
this.processQueue.getLockConsume().lock();
if (this.processQueue.isDropped()) {
log.warn("consumeMessage, the message queue not be able to consume, because it's dropped. {}",
this.messageQueue);
break;
}
//调用真正的消息消费逻辑
status = messageListener.consumeMessage(Collections.unmodifiableList(msgs), context);
} catch (Throwable e) {
log.warn("consumeMessage exception: {} Group: {} Msgs: {} MQ: {}",
RemotingHelper.exceptionSimpleDesc(e),
ConsumeMessageOrderlyService.this.consumerGroup,
msgs,
messageQueue);
hasException = true;
} finally {
this.processQueue.getLockConsume().unlock();
}
if (null == status
|| ConsumeOrderlyStatus.ROLLBACK == status
|| ConsumeOrderlyStatus.SUSPEND_CURRENT_QUEUE_A_MOMENT == status) {
log.warn("consumeMessage Orderly return not OK, Group: {} Msgs: {} MQ: {}",
ConsumeMessageOrderlyService.this.consumerGroup,
msgs,
messageQueue);
}
long consumeRT = System.currentTimeMillis() - beginTimestamp;
if (null == status) {
if (hasException) {
returnType = ConsumeReturnType.EXCEPTION;
} else {
returnType = ConsumeReturnType.RETURNNULL;
}
} else if (consumeRT >= defaultMQPushConsumer.getConsumeTimeout() * 60 * 1000) {
returnType = ConsumeReturnType.TIME_OUT;
} else if (ConsumeOrderlyStatus.SUSPEND_CURRENT_QUEUE_A_MOMENT == status) {
returnType = ConsumeReturnType.FAILED;
} else if (ConsumeOrderlyStatus.SUCCESS == status) {
returnType = ConsumeReturnType.SUCCESS;
}
if (ConsumeMessageOrderlyService.this.defaultMQPushConsumerImpl.hasHook()) {
consumeMessageContext.getProps().put(MixAll.CONSUME_CONTEXT_TYPE, returnType.name());
}
if (null == status) {
status = ConsumeOrderlyStatus.SUSPEND_CURRENT_QUEUE_A_MOMENT;
}
if (ConsumeMessageOrderlyService.this.defaultMQPushConsumerImpl.hasHook()) {
consumeMessageContext.setStatus(status.toString());
consumeMessageContext
.setSuccess(ConsumeOrderlyStatus.SUCCESS == status || ConsumeOrderlyStatus.COMMIT == status);
ConsumeMessageOrderlyService.this.defaultMQPushConsumerImpl.executeHookAfter(consumeMessageContext);
}
ConsumeMessageOrderlyService.this.getConsumerStatsManager()
.incConsumeRT(ConsumeMessageOrderlyService.this.consumerGroup, messageQueue.getTopic(), consumeRT);
continueConsume = ConsumeMessageOrderlyService.this.processConsumeResult(msgs, status, context, this);
} else {
continueConsume = false;
}
}
} else {
if (this.processQueue.isDropped()) {
log.warn("the message queue not be able to consume, because it's dropped. {}", this.messageQueue);
return;
}
ConsumeMessageOrderlyService.this.tryLockLaterAndReconsume(this.messageQueue, this.processQueue, 100);
}
}
}
本节重点
- 顺序消费时，会按照处理队列来对消费任务进行加锁，避免并发消费导致顺序不一致。
- 消费开始前，会判断当前消费者是否获的该消息队列的锁，以及锁是否过期。并执行获取锁的操作之后重新投递任务。
- 顺序消费时，每次拉取到的消息会放入一个ConsumeRequest任务中提交到线程池，消费时，每次从处理队列获取一定数量的消息进行消费。而不是按照本次拉取的消息维度来进行消费。
因为根据前面分析可知，即便是顺序消费，也是每次拉取消息后都会开启一个ConsumeRequest任务线程进行消费。
如果是根据拉取的消息维度来进行消费，那么如果拉取消息时，如果上次拉取到的消息还没有消费完，而本次任务又开始了就会导致消费顺序乱序。
假如上次拉取到的是20-40offset的消息，本次是41-50offset的消息。那么上次消费到31的时候，本次认为又开始了，那么本次就会从41开始消费，这样导致顺序就乱了。
- 每次消费任务按照时间进行限制，阈值为60S，即当一批消息提交后，即使没有消费完成，只要超过该值，则结束本次消费任务，重新投递消费请求。
long interval = System.currentTimeMillis() - beginTime;
//顺序消费时，循环地从处理队列中获取consumeBatchSize个消息进行消费，直至没有消息，
// 每次循环都会判断本次消费任务是否已消费超时，如果超时则重新提交消费该批消息
//顺序消费时，每个ConsumeRequest任务是根据消费时间来限制的，当一个任务消费时间达到阈值(60S)
//则停止本次任务，让出线程池资源。
if (interval > MAX_TIME_CONSUME_CONTINUOUSLY) {
ConsumeMessageOrderlyService.this.submitConsumeRequestLater(processQueue, messageQueue, 10);
break;
}
进度提交
自动提交时，每消费成功一次消息则会提交一次offset
if (context.isAutoCommit()) {
switch (status) {
//这两种执行结果在自动提交时是不允许的
case COMMIT:
case ROLLBACK:
log.warn("the message queue consume result is illegal, we think you want to ack these message {}",
consumeRequest.getMessageQueue());
case SUCCESS:
//获取要提交的offset值，offset为本次消费的消息里的最大offset值+1，即下一个要消费的消息的offset
commitOffset = consumeRequest.getProcessQueue().commit();
this.getConsumerStatsManager().incConsumeOKTPS(consumerGroup, consumeRequest.getMessageQueue().getTopic(), msgs.size());
break;
手动提交时，需要返回COMMIT状态才会提交
} else {
switch (status) {
case SUCCESS:
this.getConsumerStatsManager().incConsumeOKTPS(consumerGroup, consumeRequest.getMessageQueue().getTopic(), msgs.size());
break;
case COMMIT:
commitOffset = consumeRequest.getProcessQueue().commit();
更新offset
if (commitOffset >= 0 && !consumeRequest.getProcessQueue().isDropped()) {
this.defaultMQPushConsumerImpl.getOffsetStore().updateOffset(consumeRequest.getMessageQueue(), commitOffset, false);
}
消费重试
当消息消费返回状态为SUSPEND_CURRENT_QUEUE_A_MOMENT时，如果当前消息的重试次数没有达到阈值，则将该批消息重新放好处理队列中，然后清除consumingMsgOrderlyTreeMap。1S延迟后重新加入到消费队列中，并终止本次消费。
如果已经达到或超过最大阈值，则投递到死信队列，并提交进度，继续消费后续消息。
case SUSPEND_CURRENT_QUEUE_A_MOMENT:
this.getConsumerStatsManager().incConsumeFailedTPS(consumerGroup, consumeRequest.getMessageQueue().getTopic(), msgs.size());
if (checkReconsumeTimes(msgs)) {
//重新将当前消息加入到处理队列的消息列表中
consumeRequest.getProcessQueue().makeMessageToCosumeAgain(msgs);
//重新提交消费请求
this.submitConsumeRequestLater(
consumeRequest.getProcessQueue(),
consumeRequest.getMessageQueue(),
context.getSuspendCurrentQueueTimeMillis());
//停止本次消费任务
continueConsume = false;
} else {
//自动提交时，如果消息的重试次数已经达到最大限制，也提交消息消费进度。
commitOffset = consumeRequest.getProcessQueue().commit();
}
private boolean checkReconsumeTimes(List<MessageExt> msgs) {
boolean suspend = false;
if (msgs != null && !msgs.isEmpty()) {
for (MessageExt msg : msgs) {
if (msg.getReconsumeTimes() >= getMaxReconsumeTimes()) {
MessageAccessor.setReconsumeTime(msg, String.valueOf(msg.getReconsumeTimes()));
//发送消息到死信队列，如果失败则继续重试消费，并将重试次数+1
if (!sendMessageBack(msg)) {
suspend = true;
msg.setReconsumeTimes(msg.getReconsumeTimes() + 1);
}
} else {
suspend = true;
msg.setReconsumeTimes(msg.getReconsumeTimes() + 1);
}
}
}
return suspend;
}