@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
// 拦截器相关操作
ProducerRecord<K, V> interceptedRecord = this.interceptors.onSend(record);
return doSend(interceptedRecord, callback);
}
点击 onSend()方法，进行拦截器相关处理。ProducerInterceptors.java
public ProducerRecord<K, V> onSend(ProducerRecord<K, V> record) {
ProducerRecord<K, V> interceptRecord = record;
// 拦截器处理发送的数据
for (ProducerInterceptor<K, V> interceptor : this.interceptors) {
try {
// 拦截处理
interceptRecord = interceptor.onSend(interceptRecord);
} catch (Exception e) {
// do not propagate interceptor exception, log and continue calling other interceptors
// be careful not to throw exception from here
if (record != null)
log.warn("Error executing interceptor onSend callback for topic: {}, partition: {}", record.topic(), record.partition(), e);
else
log.warn("Error executing interceptor onSend callback", e);
}
}
return interceptRecord;
}
从拦截器处理中返回，点击 doSend()方法。KafkaProducer.java
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 {
// 从 Kafka 拉取元数据。maxBlockTimeMs 表示最多能等待多长时间。
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;
// 剩余时间 = 最多能等待时间 - 用了多少时间；
long remainingWaitMs = Math.max(0, maxBlockTimeMs - clusterAndWaitTime.waitedOnMetadataMs);
// 更新集群元数据
Cluster cluster = clusterAndWaitTime.cluster;
// 序列化相关操作
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);
}
// 分区操作
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);
// 校验发送消息的大小是否超过最大值，默认是 1m（序列化后、压缩后的）
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);
// accumulator缓存，追加数据 ，result是是否添加成功后的结果
RecordAccumulator.RecordAppendResult result = accumulator.append(tp, timestamp, serializedKey,
serializedValue, headers, interceptCallback, remainingWaitMs, true, nowMs);
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.maybeAddPartition(tp);
}
// 批次大小已满了，获取一个新批次创建
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);
// 唤醒发送线程
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) {
... ...
}
}
分区选择
KafkaProducer.java，详解默认分区规则。
private int partition(ProducerRecord<K, V> record, byte[] serializedKey, byte[] serializedValue, Cluster cluster) {
Integer partition = record.partition();
// 如果指定分区，按照指定分区配置
// 如果没有指定分区：没有指定key照粘性分区处理；如果有key，按照key的hashcode值对分区数求模
if (partition != null) {
return partition;
}
int customPartition = partitioner.partition(
record.topic(), record.key(), serializedKey, record.value(), serializedValue, cluster);
if (customPartition < 0) {
throw new IllegalArgumentException(String.format(
"The partitioner generated an invalid partition number: %d. Partition number should always be non-negative.", customPartition));
}
return customPartition;
}
public int partition(String topic, Object key, byte[] keyBytes, Object value, byte[] valueBytes, Cluster cluster,
int numPartitions) {
// 没有指定key
if (keyBytes == null) {
// 按照粘性分区处理
return stickyPartitionCache.partition(topic, cluster);
}
// 如果有key，按照key的hashcode值对分区数求模
// hash the keyBytes to choose a partition
return Utils.toPositive(Utils.murmur2(keyBytes)) % numPartitions;
}
发送消息大小检验
KafkaProducer.java详解缓冲区大小
private void ensureValidRecordSize(int size) {
// 单条信息的最大值maxRequestSize是1M
if (size > maxRequestSize)
throw new RecordTooLargeException("The message is " + size +
" bytes when serialized which is larger than " + maxRequestSize + ", which is the value of the " +
ProducerConfig.MAX_REQUEST_SIZE_CONFIG + " configuration.");
// totalMemorySize 默认是32M
if (size > totalMemorySize)
throw new RecordTooLargeException("The message is " + size +
" bytes when serialized which is larger than the total memory buffer you have configured with the " +
ProducerConfig.BUFFER_MEMORY_CONFIG +
" configuration.");
}
内存池
KafkaProducer.java详解内存池。
public RecordAppendResult append(TopicPartition tp,
long timestamp,
byte[] key,
byte[] value,
Header[] headers,
Callback callback,
long maxTimeToBlock,
boolean abortOnNewBatch,
long nowMs) throws InterruptedException {
// We keep track of the number of appending thread to make sure we do not miss batches in
// abortIncompleteBatches().
appendsInProgress.incrementAndGet();
ByteBuffer buffer = null;
if (headers == null) headers = Record.EMPTY_HEADERS;
try {
// check if we have an in-progress batch
// 获取/创建一个队列（按照每个主题的分区，创建队列）
Deque<ProducerBatch> dq = getOrCreateDeque(tp);
synchronized (dq) {
if (closed)
throw new KafkaException("Producer closed while send in progress");
// 尝试向队列里面添加数据（正常添加不成功）
RecordAppendResult appendResult = tryAppend(timestamp, key, value, headers, callback, dq, nowMs);
if (appendResult != null)
return appendResult;
}
// we don't have an in-progress record batch try to allocate a new batch
if (abortOnNewBatch) {
// Return a result that will cause another call to append.
return new RecordAppendResult(null, false, false, true);
}
byte maxUsableMagic = apiVersions.maxUsableProduceMagic();
// 取批次大小（默认 16k）和消息大小的最大值（上限默认 1m）。这样设计的主要原因是有可能一条消息的大小大于批次大小。
int size = Math.max(this.batchSize, AbstractRecords.estimateSizeInBytesUpperBound(maxUsableMagic, compression, key, value, headers));
log.trace("Allocating a new {} byte message buffer for topic {} partition {} with remaining timeout {}ms", size, tp.topic(), tp.partition(), maxTimeToBlock);
// 根据批次大小（默认 16k）和消息大小中最大值，分配内存
buffer = free.allocate(size, maxTimeToBlock);
// Update the current time in case the buffer allocation blocked above.
nowMs = time.milliseconds();
synchronized (dq) {
// Need to check if producer is closed again after grabbing the dequeue lock.
if (closed)
throw new KafkaException("Producer closed while send in progress");
// 尝试向队列里面添加数据（有内存，但是没有批次对象）
RecordAppendResult appendResult = tryAppend(timestamp, key, value, headers, callback, dq, nowMs);
if (appendResult != null) {
// Somebody else found us a batch, return the one we waited for! Hopefully this doesn't happen often...
return appendResult;
}
// 封装内存
MemoryRecordsBuilder recordsBuilder = recordsBuilder(buffer, maxUsableMagic);
// 根据内存大小封装批次（有内存、有批次对象）
ProducerBatch batch = new ProducerBatch(tp, recordsBuilder, nowMs);
// 尝试向队列里面添加数据
FutureRecordMetadata future = Objects.requireNonNull(batch.tryAppend(timestamp, key, value, headers,
callback, nowMs));
// 把新创建的批次放到队列末尾
dq.addLast(batch);
incomplete.add(batch);
// Don't deallocate this buffer in the finally block as it's being used in the record batch
buffer = null;
return new RecordAppendResult(future, dq.size() > 1 || batch.isFull(), true, false);
}
} finally {
if (buffer != null)
free.deallocate(buffer);
appendsInProgress.decrementAndGet();
}
}
sender线程发送数据
KafkaProducer.java详解发送线程。doSend()方法
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);
// 唤醒发送线程
this.sender.wakeup();
}
进入 sender 发送线程的 run()方法。
@Override
public void run() {
log.debug("Starting Kafka producer I/O thread.");
// main loop, runs until close is called
while (running) {
try {
runOnce();
} catch (Exception e) {
log.error("Uncaught error in kafka producer I/O thread: ", e);
}
}
....
}
void runOnce() {
...
}
消费者源码
消费者组初始化流程
初始化
消费者初始化
程序入口
1）从用户自己编写的 main 方法开始阅读
public class CustomConsumer {
public static void main(String[] args) {
// 0 配置
Properties properties = new Properties();
// 连接 bootstrap.servers
properties.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG,"192.168.183.101:9092");
// 反序列化
properties.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG,
StringDeserializer.class.getName());
properties.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG,
StringDeserializer.class.getName());
// 配置消费者组 id
properties.put(ConsumerConfig.GROUP_ID_CONFIG,"test");
// 手动提交
properties.put(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG,false);
// 1 创建一个消费者 "", "hello"
KafkaConsumer<String, String> kafkaConsumer = new
KafkaConsumer<>(properties);
// 2 订阅主题 first
ArrayList<String> topics = new ArrayList<>();
topics.add("first");
kafkaConsumer.subscribe(topics);
// 3 消费数据
while (true){
ConsumerRecords<String, String> consumerRecords =
kafkaConsumer.poll(Duration.ofSeconds(1));
for (ConsumerRecord<String, String> consumerRecord : consumerRecords) {
System.out.println(consumerRecord);
}
// 手动提交 offset
// kafkaConsumer.commitSync();
kafkaConsumer.commitAsync();
}
}
}
消费者初始化
点击 main()方法中的 KafkaConsumer()。
KafkaConsumer(ConsumerConfig config, Deserializer<K> keyDeserializer, Deserializer<V> valueDeserializer) {
try {
// 消费者组平衡
GroupRebalanceConfig groupRebalanceConfig = new GroupRebalanceConfig(config,
GroupRebalanceConfig.ProtocolType.CONSUMER);
// 获取消费者id
this.groupId = Optional.ofNullable(groupRebalanceConfig.groupId);
// 客户端id
this.clientId = config.getString(CommonClientConfigs.CLIENT_ID_CONFIG);
LogContext logContext;
// If group.instance.id is set, we will append it to the log context.
if (groupRebalanceConfig.groupInstanceId.isPresent()) {
logContext = new LogContext("[Consumer instanceId=" + groupRebalanceConfig.groupInstanceId.get() +
", clientId=" + clientId + ", groupId=" + groupId.orElse("null") + "] ");
} else {
logContext = new LogContext("[Consumer clientId=" + clientId + ", groupId=" + groupId.orElse("null") + "] ");
}
this.log = logContext.logger(getClass());
boolean enableAutoCommit = config.maybeOverrideEnableAutoCommit();
groupId.ifPresent(groupIdStr -> {
if (groupIdStr.isEmpty()) {
log.warn("Support for using the empty group id by consumers is deprecated and will be removed in the next major release.");
}
});
log.debug("Initializing the Kafka consumer");
// 客户端请求服务端的请求等待时间，默认是30s
this.requestTimeoutMs = config.getInt(ConsumerConfig.REQUEST_TIMEOUT_MS_CONFIG);
this.defaultApiTimeoutMs = config.getInt(ConsumerConfig.DEFAULT_API_TIMEOUT_MS_CONFIG);
this.time = Time.SYSTEM;
this.metrics = buildMetrics(config, time, clientId);
// 重试时间，默认是100ms
this.retryBackoffMs = config.getLong(ConsumerConfig.RETRY_BACKOFF_MS_CONFIG);
// 拦截器相关处理
List<ConsumerInterceptor<K, V>> interceptorList = (List) config.getConfiguredInstances(
ConsumerConfig.INTERCEPTOR_CLASSES_CONFIG,
ConsumerInterceptor.class,
Collections.singletonMap(ConsumerConfig.CLIENT_ID_CONFIG, clientId));
this.interceptors = new ConsumerInterceptors<>(interceptorList);
// 反序列化相关操作
if (keyDeserializer == null) {
this.keyDeserializer = config.getConfiguredInstance(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, Deserializer.class);
this.keyDeserializer.configure(config.originals(Collections.singletonMap(ConsumerConfig.CLIENT_ID_CONFIG, clientId)), true);
} else {
config.ignore(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG);
this.keyDeserializer = keyDeserializer;
}
if (valueDeserializer == null) {
this.valueDeserializer = config.getConfiguredInstance(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, Deserializer.class);
this.valueDeserializer.configure(config.originals(Collections.singletonMap(ConsumerConfig.CLIENT_ID_CONFIG, clientId)), false);
} else {
config.ignore(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG);
this.valueDeserializer = valueDeserializer;
}
// offset从什么位置开始消费，默认 lastest
OffsetResetStrategy offsetResetStrategy = OffsetResetStrategy.valueOf(config.getString(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG).toUpperCase(Locale.ROOT));
this.subscriptions = new SubscriptionState(logContext, offsetResetStrategy);
ClusterResourceListeners clusterResourceListeners = configureClusterResourceListeners(keyDeserializer,
valueDeserializer, metrics.reporters(), interceptorList);
// 元数据
this.metadata = new ConsumerMetadata(retryBackoffMs, // 重试时间
config.getLong(ConsumerConfig.METADATA_MAX_AGE_CONFIG),
!config.getBoolean(ConsumerConfig.EXCLUDE_INTERNAL_TOPICS_CONFIG),// 是否允许访问系统主题，默认是true，表示不允许
config.getBoolean(ConsumerConfig.ALLOW_AUTO_CREATE_TOPICS_CONFIG),// 是否允许自动创建主题，默认是true，表示允许
subscriptions, logContext, clusterResourceListeners);
// 连接kafka集群
List<InetSocketAddress> addresses = ClientUtils.parseAndValidateAddresses(
config.getList(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG), config.getString(ConsumerConfig.CLIENT_DNS_LOOKUP_CONFIG));
this.metadata.bootstrap(addresses);
String metricGrpPrefix = "consumer";
FetcherMetricsRegistry metricsRegistry = new FetcherMetricsRegistry(Collections.singleton(CLIENT_ID_METRIC_TAG), metricGrpPrefix);
ChannelBuilder channelBuilder = ClientUtils.createChannelBuilder(config, time, logContext);
this.isolationLevel = IsolationLevel.valueOf(
config.getString(ConsumerConfig.ISOLATION_LEVEL_CONFIG).toUpperCase(Locale.ROOT));
Sensor throttleTimeSensor = Fetcher.throttleTimeSensor(metrics, metricsRegistry);
int heartbeatIntervalMs = config.getInt(ConsumerConfig.HEARTBEAT_INTERVAL_MS_CONFIG);
ApiVersions apiVersions = new ApiVersions();
// 创建客户端对象
NetworkClient netClient = new NetworkClient(
new Selector(config.getLong(ConsumerConfig.CONNECTIONS_MAX_IDLE_MS_CONFIG), metrics, time, metricGrpPrefix, channelBuilder, logContext),
this.metadata,
clientId,
100, // a fixed large enough value will suffice for max in-flight requests
config.getLong(ConsumerConfig.RECONNECT_BACKOFF_MS_CONFIG),//连接重试时间，默认是50ms
config.getLong(ConsumerConfig.RECONNECT_BACKOFF_MAX_MS_CONFIG),// 最大连接重试时间，默认是1s
config.getInt(ConsumerConfig.SEND_BUFFER_CONFIG), // 发送缓存，默认是128kb
config.getInt(ConsumerConfig.RECEIVE_BUFFER_CONFIG),// 接收缓存，默认是64kb
config.getInt(ConsumerConfig.REQUEST_TIMEOUT_MS_CONFIG), // 客户端请求服务端的请求等待时间，默认是30s
config.getLong(ConsumerConfig.SOCKET_CONNECTION_SETUP_TIMEOUT_MS_CONFIG),
config.getLong(ConsumerConfig.SOCKET_CONNECTION_SETUP_TIMEOUT_MAX_MS_CONFIG),
time,
true,
apiVersions,
throttleTimeSensor,
logContext);
this.client = new ConsumerNetworkClient(
logContext,
netClient,
metadata,
time,
retryBackoffMs,
config.getInt(ConsumerConfig.REQUEST_TIMEOUT_MS_CONFIG),
heartbeatIntervalMs); //Will avoid blocking an extended period of time to prevent heartbeat thread starvation
this.assignors = ConsumerPartitionAssignor.getAssignorInstances(
config.getList(ConsumerConfig.PARTITION_ASSIGNMENT_STRATEGY_CONFIG),
config.originals(Collections.singletonMap(ConsumerConfig.CLIENT_ID_CONFIG, clientId))
);
// no coordinator will be constructed for the default (null) group id
// 创建消费者协调器
// 自动提交 Offset 时间间隔，默认 5s
this.coordinator = !groupId.isPresent() ? null :
new ConsumerCoordinator(groupRebalanceConfig,
logContext,
this.client,
assignors,
this.metadata,
this.subscriptions,
metrics,
metricGrpPrefix,
this.time,
enableAutoCommit,
config.getInt(ConsumerConfig.AUTO_COMMIT_INTERVAL_MS_CONFIG),
this.interceptors,
config.getBoolean(ConsumerConfig.THROW_ON_FETCH_STABLE_OFFSET_UNSUPPORTED));
// 一次抓取最小值，默认 1 个字节
// 一次抓取最大值，默认 50m
// 一次抓取最大等待时间，默认 500ms
// 每个分区抓取的最大字节数，默认 1m
// 一次 poll 拉取数据返回消息的最大条数，默认是 500 条。
// key 和 value 的反序列化
this.fetcher = new Fetcher<>(
logContext,
this.client,
config.getInt(ConsumerConfig.FETCH_MIN_BYTES_CONFIG),
config.getInt(ConsumerConfig.FETCH_MAX_BYTES_CONFIG),
config.getInt(ConsumerConfig.FETCH_MAX_WAIT_MS_CONFIG),
config.getInt(ConsumerConfig.MAX_PARTITION_FETCH_BYTES_CONFIG),
config.getInt(ConsumerConfig.MAX_POLL_RECORDS_CONFIG),
config.getBoolean(ConsumerConfig.CHECK_CRCS_CONFIG),
config.getString(ConsumerConfig.CLIENT_RACK_CONFIG),
this.keyDeserializer,
this.valueDeserializer,
this.metadata,
this.subscriptions,
metrics,
metricsRegistry,
this.time,
this.retryBackoffMs,
this.requestTimeoutMs,
isolationLevel,
apiVersions);
this.kafkaConsumerMetrics = new KafkaConsumerMetrics(metrics, metricGrpPrefix);
config.logUnused();
AppInfoParser.registerAppInfo(JMX_PREFIX, clientId, metrics, time.milliseconds());
log.debug("Kafka consumer initialized");
} catch (Throwable t) {
// call close methods if internal objects are already constructed; this is to prevent resource leak. see KAFKA-2121
// we do not need to call `close` at all when `log` is null, which means no internal objects were initialized.
if (this.log != null) {
close(0, true);
}
// now propagate the exception
throw new KafkaException("Failed to construct kafka consumer", t);
}
}
消费者订阅主题
订阅流程
点击自己编写的 CustomConsumer.java 中的 subscribe ()方法。
// 2 订阅主题 first
ArrayList<String> topics = new ArrayList<>();
topics.add("first");
kafkaConsumer.subscribe(topics);
KafkaConsumer.java
@Override
public void subscribe(Collection<String> topics, ConsumerRebalanceListener listener) {
acquireAndEnsureOpen();
try {
maybeThrowInvalidGroupIdException();
// 如果订阅的主题为null，直接抛异常
if (topics == null)
throw new IllegalArgumentException("Topic collection to subscribe to cannot be null");
// 如果订阅的主题，里面没有数据
if (topics.isEmpty()) {
// treat subscribing to empty topic list as the same as unsubscribing
this.unsubscribe();
} else {
// 正常的处理操作
for (String topic : topics) {
if (Utils.isBlank(topic))
throw new IllegalArgumentException("Topic collection to subscribe to cannot contain null or empty topic");
}
throwIfNoAssignorsConfigured();
// 清空订阅异常主题的缓存数据
fetcher.clearBufferedDataForUnassignedTopics(topics);
log.info("Subscribed to topic(s): {}", Utils.join(topics, ", "));
// 订阅主题（判断是否需要更改订阅主题，如果需要更改主题，则更新元数据信息）
if (this.subscriptions.subscribe(new HashSet<>(topics), listener))
// 如果订阅的和以前不一致，需要更新元数据信息
metadata.requestUpdateForNewTopics();
}
} finally {
release();
}
}
public synchronized boolean subscribe(Set<String> topics, ConsumerRebalanceListener listener) {
// 注册负载均衡监听（例如消费者组中，其他消费者退出触发再平衡）
registerRebalanceListener(listener);
// 按照设置的主题开始订阅，自动分配分区
setSubscriptionType(SubscriptionType.AUTO_TOPICS);
// 修改订阅主题信息
return changeSubscription(topics);
}
private boolean changeSubscription(Set<String> topicsToSubscribe) {
// 如果订阅的主题和以前订阅的一致，就不需要修改订阅信息。如果不一致，就需要修改。
if (subscription.equals(topicsToSubscribe))
return false;
subscription = topicsToSubscribe;
return true;
}
// 如果订阅的和以前不一致，需要更新元数据信息
public synchronized int requestUpdateForNewTopics() {
// Override the timestamp of last refresh to let immediate update.
this.lastRefreshMs = 0;
this.needPartialUpdate = true;
this.requestVersion++;
return this.updateVersion;
}
消费者拉取和处理数据
数据处理流程
消费总体流程
点击自己编写的 CustomConsumer.java 中的 poll ()方法。
// 3 消费数据
while (true){
ConsumerRecords<String, String> consumerRecords =
kafkaConsumer.poll(Duration.ofSeconds(1));
for (ConsumerRecord<String, String> consumerRecord :
consumerRecords) {
System.out.println(consumerRecord);
}
}
KafkaConsumer.java
private ConsumerRecords<K, V> poll(final Timer timer, final boolean includeMetadataInTimeout) {
acquireAndEnsureOpen();
try {
this.kafkaConsumerMetrics.recordPollStart(timer.currentTimeMs());
if (this.subscriptions.hasNoSubscriptionOrUserAssignment()) {
throw new IllegalStateException("Consumer is not subscribed to any topics or assigned any partitions");
}
do {
client.maybeTriggerWakeup();
if (includeMetadataInTimeout) {
// 消费者或者消费者组初始化
// try to update assignment metadata BUT do not need to block on the timer for join group
updateAssignmentMetadataIfNeeded(timer, false);
} else {
while (!updateAssignmentMetadataIfNeeded(time.timer(Long.MAX_VALUE), true)) {
log.warn("Still waiting for metadata");
}
}
// 2. 抓取数据
final Fetch<K, V> fetch = pollForFetches(timer);
if (!fetch.isEmpty()) {
// before returning the fetched records, we can send off the next round of fetches
// and avoid block waiting for their responses to enable pipelining while the user
// is handling the fetched records.
//
// NOTE: since the consumed position has already been updated, we must not allow
// wakeups or any other errors to be triggered prior to returning the fetched records.
if (fetcher.sendFetches() > 0 || client.hasPendingRequests()) {
client.transmitSends();
}
if (fetch.records().isEmpty()) {
log.trace("Returning empty records from `poll()` "
+ "since the consumer's position has advanced for at least one topic partition");
}
// 拦截器处理数据
return this.interceptors.onConsume(new ConsumerRecords<>(fetch.records()));
}
} while (timer.notExpired());
return ConsumerRecords.empty();
} finally {
release();
this.kafkaConsumerMetrics.recordPollEnd(timer.currentTimeMs());
}
}
