kafka生产者发送消息流程深入分析讲解

// KafkaProducer#partition
private int partition(ProducerRecord<K, V> record, byte[] serializedKey, byte[] serializedValue, Cluster cluster) {
//指定分区partition则直接返回，否则走分区器
        Integer partition = record.partition();
        return partition != null ?
                partition :
                partitioner.partition(
                        record.topic(), record.key(), serializedKey, record.value(),                 serializedValue, cluster);
}

//DefaultPartitioner#partition
public int partition(String topic, Object key, byte[] keyBytes, Object value, byte[] valueBytes, Cluster cluster) {
        if (keyBytes == null) {
            return stickyPartitionCache.partition(topic, cluster);
        } 
        List<PartitionInfo> partitions = cluster.partitionsForTopic(topic);
        int numPartitions = partitions.size();
        // hash the keyBytes to choose a partition
        return Utils.toPositive(Utils.murmur2(keyBytes)) % numPartitions;
    }

ConcurrentMap<TopicPartition, Deque<ProducerBatch>> batches;

//KafkaProducer
@Override
public Future<RecordMetadata> send(ProducerRecord<K, V> record, Callback callback) {
	// intercept the record, which can be potentially modified; this method does not throw exceptions
    //首先执行拦截器链
	ProducerRecord<K, V> interceptedRecord = this.interceptors.onSend(record);
	return doSend(interceptedRecord, callback);
}
private Future<RecordMetadata> doSend(ProducerRecord<K, V> record, Callback callback) {
        TopicPartition tp = null;
	try {
		throwIfProducerClosed();
		// first make sure the metadata for the topic is available
		long nowMs = time.milliseconds();
		ClusterAndWaitTime clusterAndWaitTime;
		try {
			clusterAndWaitTime = waitOnMetadata(record.topic(), record.partition(), nowMs, maxBlockTimeMs);
		} catch (KafkaException e) {
			if (metadata.isClosed())
				throw new KafkaException("Producer closed while send in progress", e);
			throw e;
		}
		nowMs += clusterAndWaitTime.waitedOnMetadataMs;
		long remainingWaitMs = Math.max(0, maxBlockTimeMs - clusterAndWaitTime.waitedOnMetadataMs);
		Cluster cluster = clusterAndWaitTime.cluster;
		byte[] serializedKey;
		try {
			//key序列化
			serializedKey = keySerializer.serialize(record.topic(), record.headers(), record.key());
		} catch (ClassCastException cce) {
			throw new SerializationException("Can't convert key of class " + record.key().getClass().getName() +
					" to class " + producerConfig.getClass(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG).getName() +
					" specified in key.serializer", cce);
		}
		byte[] serializedValue;
		try {
			//value序列化
			serializedValue = valueSerializer.serialize(record.topic(), record.headers(), record.value());
		} catch (ClassCastException cce) {
			throw new SerializationException("Can't convert value of class " + record.value().getClass().getName() +
					" to class " + producerConfig.getClass(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG).getName() +
					" specified in value.serializer", cce);
		}
		//获取分区partition
		int partition = partition(record, serializedKey, serializedValue, cluster);
		tp = new TopicPartition(record.topic(), partition);
		setReadOnly(record.headers());
		Header[] headers = record.headers().toArray();
		//消息压缩
		int serializedSize = AbstractRecords.estimateSizeInBytesUpperBound(apiVersions.maxUsableProduceMagic(),
				compressionType, serializedKey, serializedValue, headers);
		//判断消息是否超过最大允许大小，消息缓存空间是否已满
		ensureValidRecordSize(serializedSize);
		long timestamp = record.timestamp() == null ? nowMs : record.timestamp();
		if (log.isTraceEnabled()) {
			log.trace("Attempting to append record {} with callback {} to topic {} partition {}", record, callback, record.topic(), partition);
		}
		// producer callback will make sure to call both 'callback' and interceptor callback
		Callback interceptCallback = new InterceptorCallback<>(callback, this.interceptors, tp);
 
		if (transactionManager != null && transactionManager.isTransactional()) {
			transactionManager.failIfNotReadyForSend();
		}
		//将消息缓存在消息累加器RecordAccumulator中
		RecordAccumulator.RecordAppendResult result = accumulator.append(tp, timestamp, serializedKey,
				serializedValue, headers, interceptCallback, remainingWaitMs, true, nowMs);
        //开辟新的ProducerBatch
		if (result.abortForNewBatch) {
			int prevPartition = partition;
			partitioner.onNewBatch(record.topic(), cluster, prevPartition);
			partition = partition(record, serializedKey, serializedValue, cluster);
			tp = new TopicPartition(record.topic(), partition);
			if (log.isTraceEnabled()) {
				log.trace("Retrying append due to new batch creation for topic {} partition {}. The old partition was {}", record.topic(), partition, prevPartition);
			}
			// producer callback will make sure to call both 'callback' and interceptor callback
			interceptCallback = new InterceptorCallback<>(callback, this.interceptors, tp);
 
			result = accumulator.append(tp, timestamp, serializedKey,
				serializedValue, headers, interceptCallback, remainingWaitMs, false, nowMs);
		}
		if (transactionManager != null && transactionManager.isTransactional())
			transactionManager.maybeAddPartitionToTransaction(tp);
		//判断消息是否已满，唤醒sender线程进行发送消息
		if (result.batchIsFull || result.newBatchCreated) {
			log.trace("Waking up the sender since topic {} partition {} is either full or getting a new batch", record.topic(), partition);
			this.sender.wakeup();
		}
		return result.future;
		// handling exceptions and record the errors;
		// for API exceptions return them in the future,
		// for other exceptions throw directly
	} catch (Exception e) {
		// we notify interceptor about all exceptions, since onSend is called before anything else in this method
		this.interceptors.onSendError(record, tp, e);
		throw e;
	}
}