RocketMq重复消费问题排查

前情

出现了重复消费的问题，同一个消息被重复消费了多次，导致了用户端收到了多条重复的消息，最终排查发现，是因为消费者在处理消息的方法onMessage中有异常没有捕获到，导致异常上抛，被consumeMessage捕获并判定为消费失败，从而放到了重试队列当中进行重试，下面我们就来看看RocketMq中会引起消息重试的两种情况，内部异常和消费超时。

源码

在Consumer中处理消息时，会在消费完消息后判断消费的总时长，如果比超时时间要长则返回TIME_OUT,注意这里的超时是在consumeMessage内部逻辑处理完毕之后在进行判断的，如果内部逻辑处理成功，但耗时较长，那么也会被判断为超时。

在DefaultMQPushConsumer.java中定义了消费的超时时间为15分钟。

consumeMessage方法中会有两种返回状态，正常的状态消费成功CONSUME_SUCCESS和出现异常时的重试状态RECONSUME_LATER。

如果消费时长超过超时时间那么即便consumeMessage方法处理成功，返回状态也是TIME_OUT。

代码

class ConsumeRequest implements Runnable {
        private final List msgs;
        private final ProcessQueue processQueue;
        private final MessageQueue messageQueue;
 
        public ConsumeRequest(List msgs, ProcessQueue processQueue, MessageQueue messageQueue) {
            this.msgs = msgs;
            this.processQueue = processQueue;
            this.messageQueue = messageQueue;
        }
 
        public List getMsgs() {
            return msgs;
        }
 
        public ProcessQueue getProcessQueue() {
            return processQueue;
        }
 
        @Override
        public void run() {
            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;
            }
 
            MessageListenerConcurrently listener = ConsumeMessageConcurrentlyService.this.messageListener;
            ConsumeConcurrentlyContext context = new ConsumeConcurrentlyContext(messageQueue);
            ConsumeConcurrentlyStatus status = null;
 
            ConsumeMessageContext consumeMessageContext = null;
            if (ConsumeMessageConcurrentlyService.this.defaultMQPushConsumerImpl.hasHook()) {
                consumeMessageContext = new ConsumeMessageContext();
                consumeMessageContext.setConsumerGroup(defaultMQPushConsumer.getConsumerGroup());
                consumeMessageContext.setProps(new HashMap());
                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 {
                ConsumeMessageConcurrentlyService.this.resetRetryTopic(msgs);
                if (msgs != null && !msgs.isEmpty()) {
                    for (MessageExt msg : msgs) {
                        MessageAccessor.setConsumeStartTimeStamp(msg, String.valueOf(System.currentTimeMillis()));
                    }
                }
                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;
            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;
            }
 
            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);
 
            if (!processQueue.isDropped()) {
                ConsumeMessageConcurrentlyService.this.processConsumeResult(status, context, this);
            } else {
                log.warn("processQueue is dropped without process consume result. messageQueue={}, msgs={}", messageQueue, msgs);
            }
        }
 
        public MessageQueue getMessageQueue() {
            return messageQueue;
        }
 
    }