private Future<RecordMetadata> doSend(ProducerRecord<K, V> record, Callback callback) {
TopicPartition tp = null;
try {
// first make sure the metadata for the topic is available
// 1.确认数据要发送到的 topic 的 metadata 是可用的
ClusterAndWaitTime clusterAndWaitTime = waitOnMetadata(record.topic(), record.partition(), maxBlockTimeMs);
long remainingWaitMs = Math.max(0, maxBlockTimeMs - clusterAndWaitTime.waitedOnMetadataMs);
Cluster cluster = clusterAndWaitTime.cluster;
// 2.序列化 record 的 key 和 value
byte[] serializedKey;
try {
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 {
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);
}
// 3. 获取该 record 的 partition 的值(可以指定,也可以根据算法计算)
int partition = partition(record, serializedKey, serializedValue, cluster);
tp = new TopicPartition(record.topic(), partition);
setReadOnly(record.headers());
Header[] headers = record.headers().toArray();
int serializedSize = AbstractRecords.estimateSizeInBytesUpperBound(apiVersions.maxUsableProduceMagic(),
compressionType, serializedKey, serializedValue, headers);
ensureValidRecordSize(serializedSize);
long timestamp = record.timestamp() == null ? time.milliseconds() : record.timestamp();
log.trace("Sending 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.maybeAddPartitionToTransaction(tp);
// 4. 向 accumulator 中追加数据
RecordAccumulator.RecordAppendResult result = accumulator.append(tp, timestamp, serializedKey,
serializedValue, headers, interceptCallback, remainingWaitMs);
// 5. 如果 batch 已经满了,唤醒 sender 线程发送数据
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 (ApiException e) {
log.debug("Exception occurred during message send:", e);
if (callback != null)
callback.onCompletion(null, e);
this.errors.record();
this.interceptors.onSendError(record, tp, e);
return new FutureFailure(e);
} catch (InterruptedException e) {
this.errors.record();
this.interceptors.onSendError(record, tp, e);
throw new InterruptException(e);
} catch (BufferExhaustedException e) {
this.errors.record();
this.metrics.sensor("buffer-exhausted-records").record();
this.interceptors.onSendError(record, tp, e);
throw e;
} catch (KafkaException e) {
this.errors.record();
this.interceptors.onSendError(record, tp, e);
throw e;
} 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;
}
}
在 dosend() 方法的实现上,一条 Record 数据的发送,可以分为以下五步:
- 确认数据要发送到的 topic 的 metadata 是可用的(如果该 partition 的 leader 存在则是可用的,如果开启权限时,client 有相应的权限),如果没有 topic 的 metadata 信息,就需要获取相应的metadata;
- 序列化 record 的 key 和 value;
- 获取该 record 要发送到的 partition(可以指定,也可以根据算法计算);
- 向 accumulator 中追加 record 数据,数据会先进行缓存;
- 如果追加完数据后,对应的 RecordBatch 已经达到了 batch.size 的大小(或者batch 的剩余空间不足以添加下一条 Record),则唤醒 sender 线程发送数据。