客户端由两种:生产者和消费者

1. 生产者

先看一下生产者的构造方法:

private KafkaProducer(ProducerConfig config, Serializer<K> keySerializer, Serializer<V> valueSerializer) {
try {
log.trace("Starting the Kafka producer");
Map<String, Object> userProvidedConfigs = config.originals();
this.producerConfig = config;
this.time = new SystemTime(); MetricConfig metricConfig = new MetricConfig().samples(config.getInt(ProducerConfig.METRICS_NUM_SAMPLES_CONFIG))
.timeWindow(config.getLong(ProducerConfig.METRICS_SAMPLE_WINDOW_MS_CONFIG),
TimeUnit.MILLISECONDS);
clientId = config.getString(ProducerConfig.CLIENT_ID_CONFIG);
if (clientId.length() <= 0)
clientId = "producer-" + PRODUCER_CLIENT_ID_SEQUENCE.getAndIncrement();
List<MetricsReporter> reporters = config.getConfiguredInstances(ProducerConfig.METRIC_REPORTER_CLASSES_CONFIG,
MetricsReporter.class);
reporters.add(new JmxReporter(JMX_PREFIX));
this.metrics = new Metrics(metricConfig, reporters, time);
this.partitioner = config.getConfiguredInstance(ProducerConfig.PARTITIONER_CLASS_CONFIG, Partitioner.class);
long retryBackoffMs = config.getLong(ProducerConfig.RETRY_BACKOFF_MS_CONFIG);
this.metadata = new Metadata(retryBackoffMs, config.getLong(ProducerConfig.METADATA_MAX_AGE_CONFIG));
this.maxRequestSize = config.getInt(ProducerConfig.MAX_REQUEST_SIZE_CONFIG);
this.totalMemorySize = config.getLong(ProducerConfig.BUFFER_MEMORY_CONFIG);
this.compressionType = CompressionType.forName(config.getString(ProducerConfig.COMPRESSION_TYPE_CONFIG));
/* check for user defined settings.
* If the BLOCK_ON_BUFFER_FULL is set to true,we do not honor METADATA_FETCH_TIMEOUT_CONFIG.
* This should be removed with release 0.9 when the deprecated configs are removed.
*/
if (userProvidedConfigs.containsKey(ProducerConfig.BLOCK_ON_BUFFER_FULL_CONFIG)) {
log.warn(ProducerConfig.BLOCK_ON_BUFFER_FULL_CONFIG + " config is deprecated and will be removed soon. " +
"Please use " + ProducerConfig.MAX_BLOCK_MS_CONFIG);
boolean blockOnBufferFull = config.getBoolean(ProducerConfig.BLOCK_ON_BUFFER_FULL_CONFIG);
if (blockOnBufferFull) {
this.maxBlockTimeMs = Long.MAX_VALUE;
} else if (userProvidedConfigs.containsKey(ProducerConfig.METADATA_FETCH_TIMEOUT_CONFIG)) {
log.warn(ProducerConfig.METADATA_FETCH_TIMEOUT_CONFIG + " config is deprecated and will be removed soon. " +
"Please use " + ProducerConfig.MAX_BLOCK_MS_CONFIG);
this.maxBlockTimeMs = config.getLong(ProducerConfig.METADATA_FETCH_TIMEOUT_CONFIG);
} else {
this.maxBlockTimeMs = config.getLong(ProducerConfig.MAX_BLOCK_MS_CONFIG);
}
} else if (userProvidedConfigs.containsKey(ProducerConfig.METADATA_FETCH_TIMEOUT_CONFIG)) {
log.warn(ProducerConfig.METADATA_FETCH_TIMEOUT_CONFIG + " config is deprecated and will be removed soon. " +
"Please use " + ProducerConfig.MAX_BLOCK_MS_CONFIG);
this.maxBlockTimeMs = config.getLong(ProducerConfig.METADATA_FETCH_TIMEOUT_CONFIG);
} else {
this.maxBlockTimeMs = config.getLong(ProducerConfig.MAX_BLOCK_MS_CONFIG);
} /* check for user defined settings.
* If the TIME_OUT config is set use that for request timeout.
* This should be removed with release 0.9
*/
if (userProvidedConfigs.containsKey(ProducerConfig.TIMEOUT_CONFIG)) {
log.warn(ProducerConfig.TIMEOUT_CONFIG + " config is deprecated and will be removed soon. Please use " +
ProducerConfig.REQUEST_TIMEOUT_MS_CONFIG);
this.requestTimeoutMs = config.getInt(ProducerConfig.TIMEOUT_CONFIG);
} else {
this.requestTimeoutMs = config.getInt(ProducerConfig.REQUEST_TIMEOUT_MS_CONFIG);
} Map<String, String> metricTags = new LinkedHashMap<String, String>();
metricTags.put("client-id", clientId);
this.accumulator = new RecordAccumulator(config.getInt(ProducerConfig.BATCH_SIZE_CONFIG),
this.totalMemorySize,
this.compressionType,
config.getLong(ProducerConfig.LINGER_MS_CONFIG),
retryBackoffMs,
metrics,
time,
metricTags);
List<InetSocketAddress> addresses = ClientUtils.parseAndValidateAddresses(config.getList(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG));
this.metadata.update(Cluster.bootstrap(addresses), time.milliseconds());
ChannelBuilder channelBuilder = ClientUtils.createChannelBuilder(config.values());
NetworkClient client = new NetworkClient(
new Selector(config.getLong(ProducerConfig.CONNECTIONS_MAX_IDLE_MS_CONFIG), this.metrics, time, "producer", metricTags, channelBuilder),
this.metadata,
clientId,
config.getInt(ProducerConfig.MAX_IN_FLIGHT_REQUESTS_PER_CONNECTION),
config.getLong(ProducerConfig.RECONNECT_BACKOFF_MS_CONFIG),
config.getInt(ProducerConfig.SEND_BUFFER_CONFIG),
config.getInt(ProducerConfig.RECEIVE_BUFFER_CONFIG),
this.requestTimeoutMs, time);
this.sender = new Sender(client,
this.metadata,
this.accumulator,
config.getInt(ProducerConfig.MAX_REQUEST_SIZE_CONFIG),
(short) parseAcks(config.getString(ProducerConfig.ACKS_CONFIG)),
config.getInt(ProducerConfig.RETRIES_CONFIG),
this.metrics,
new SystemTime(),
clientId,
this.requestTimeoutMs);
String ioThreadName = "kafka-producer-network-thread" + (clientId.length() > 0 ? " | " + clientId : "");
this.ioThread = new KafkaThread(ioThreadName, this.sender, true);
this.ioThread.start(); this.errors = this.metrics.sensor("errors"); if (keySerializer == null) {
this.keySerializer = config.getConfiguredInstance(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG,
Serializer.class);
this.keySerializer.configure(config.originals(), true);
} else {
config.ignore(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG);
this.keySerializer = keySerializer;
}
if (valueSerializer == null) {
this.valueSerializer = config.getConfiguredInstance(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG,
Serializer.class);
this.valueSerializer.configure(config.originals(), false);
} else {
config.ignore(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG);
this.valueSerializer = valueSerializer;
}
config.logUnused();
AppInfoParser.registerAppInfo(JMX_PREFIX, clientId);
log.debug("Kafka producer started");
} catch (Throwable t) {
// call close methods if internal objects are already constructed
// this is to prevent resource leak. see KAFKA-2121
close(0, TimeUnit.MILLISECONDS, true);
// now propagate the exception
throw new KafkaException("Failed to construct kafka producer", t);
}
}

很多代码是读取配置文件,但红色部分才是主要:

调用Sender线程的run方法

/**
* Run a single iteration of sending
*
* @param now
* The current POSIX time in milliseconds
*/
public void run(long now) {
Cluster cluster = metadata.fetch();
// get the list of partitions with data ready to send
RecordAccumulator.ReadyCheckResult result = this.accumulator.ready(cluster, now); // if there are any partitions whose leaders are not known yet, force metadata update
if (result.unknownLeadersExist)
this.metadata.requestUpdate(); // remove any nodes we aren't ready to send to
Iterator<Node> iter = result.readyNodes.iterator();
long notReadyTimeout = Long.MAX_VALUE;
while (iter.hasNext()) {
Node node = iter.next();
if (!this.client.ready(node, now)) {
iter.remove();
notReadyTimeout = Math.min(notReadyTimeout, this.client.connectionDelay(node, now));
}
} // create produce requests
Map<Integer, List<RecordBatch>> batches = this.accumulator.drain(cluster,
result.readyNodes,
this.maxRequestSize,
now); List<RecordBatch> expiredBatches = this.accumulator.abortExpiredBatches(this.requestTimeout, cluster, now);
// update sensors
for (RecordBatch expiredBatch : expiredBatches)
this.sensors.recordErrors(expiredBatch.topicPartition.topic(), expiredBatch.recordCount); sensors.updateProduceRequestMetrics(batches);
List<ClientRequest> requests = createProduceRequests(batches, now);
// If we have any nodes that are ready to send + have sendable data, poll with 0 timeout so this can immediately
// loop and try sending more data. Otherwise, the timeout is determined by nodes that have partitions with data
// that isn't yet sendable (e.g. lingering, backing off). Note that this specifically does not include nodes
// with sendable data that aren't ready to send since they would cause busy looping.
long pollTimeout = Math.min(result.nextReadyCheckDelayMs, notReadyTimeout);
if (result.readyNodes.size() > 0) {
log.trace("Nodes with data ready to send: {}", result.readyNodes);
log.trace("Created {} produce requests: {}", requests.size(), requests);
pollTimeout = 0;
}
for (ClientRequest request : requests)
client.send(request, now); // if some partitions are already ready to be sent, the select time would be 0;
// otherwise if some partition already has some data accumulated but not ready yet,
// the select time will be the time difference between now and its linger expiry time;
// otherwise the select time will be the time difference between now and the metadata expiry time;
this.client.poll(pollTimeout, now);
}

调用NetworkClient的send方法

    /**
* Queue up the given request for sending. Requests can only be sent out to ready nodes.
*
* @param request The request
* @param now The current timestamp
*/
@Override
public void send(ClientRequest request, long now) {
String nodeId = request.request().destination();
if (!canSendRequest(nodeId))
throw new IllegalStateException("Attempt to send a request to node " + nodeId + " which is not ready.");
doSend(request, now);
} private void doSend(ClientRequest request, long now) {
request.setSendTimeMs(now);
this.inFlightRequests.add(request);
selector.send(request.request());
}

selector调用channel来发送:

    /**
* Queue the given request for sending in the subsequent {@poll(long)} calls
* @param send The request to send
*/
public void send(Send send) {
KafkaChannel channel = channelOrFail(send.destination());
try {
channel.setSend(send);
} catch (CancelledKeyException e) {
this.failedSends.add(send.destination());
close(channel);
}
}

调用channel的send方法:

    public void setSend(Send send) {
if (this.send != null)
throw new IllegalStateException("Attempt to begin a send operation with prior send operation still in progress.");
this.send = send;
this.transportLayer.addInterestOps(SelectionKey.OP_WRITE);
}

这里TransportLayer封装了通信的细节

2. 消费者

kafka源码分析之二客户端分析的更多相关文章

  1. Kafka源码解析(二)---Log分析

    上一篇文章讲了LogSegment和Log的初始化,这篇来讲讲Log的主要操作有哪些. 一般来说Log 的常见操作分为 4 大部分. 高水位管理操作 日志段管理 关键位移值管理 读写操作 其中关键位移 ...

  2. Kafka源码分析(二) - 生产者

    系列文章目录 https://zhuanlan.zhihu.com/p/367683572 目录 系列文章目录 一. 使用方式 step 1: 设置必要参数 step 2: 创建KafkaProduc ...

  3. Kafka源码分析(一) - 概述

    系列文章目录 https://zhuanlan.zhihu.com/p/367683572 目录 系列文章目录 一. 实际问题 二. 什么是Kafka, 如何解决这些问题的 三. 基本原理 1. 基本 ...

  4. kafka源码分析之一server启动分析

    0. 关键概念 关键概念 Concepts Function Topic 用于划分Message的逻辑概念,一个Topic可以分布在多个Broker上. Partition 是Kafka中横向扩展和一 ...

  5. # Volley源码解析(二) 没有缓存的情况下直接走网络请求源码分析#

    Volley源码解析(二) 没有缓存的情况下直接走网络请求源码分析 Volley源码一共40多个类和接口.除去一些工具类的实现,核心代码只有20多个类.所以相对来说分析起来没有那么吃力.但是要想分析透 ...

  6. Kafka源码分析系列-目录(收藏不迷路)

    持续更新中,敬请关注! 目录 <Kafka源码分析>系列文章计划按"数据传递"的顺序写作,即:先分析生产者,其次分析Server端的数据处理,然后分析消费者,最后再补充 ...

  7. Kafka源码分析(三) - Server端 - 消息存储

    系列文章目录 https://zhuanlan.zhihu.com/p/367683572 目录 系列文章目录 一. 业务模型 1.1 概念梳理 1.2 文件分析 1.2.1 数据目录 1.2.2 . ...

  8. Apache Kafka源码分析 – Broker Server

    1. Kafka.scala 在Kafka的main入口中startup KafkaServerStartable, 而KafkaServerStartable这是对KafkaServer的封装 1: ...

  9. Spring源码分析之IOC的三种常见用法及源码实现(二)

    Spring源码分析之IOC的三种常见用法及源码实现(二) 回顾上文 我们研究的是 AnnotationConfigApplicationContext annotationConfigApplica ...

随机推荐

  1. tomcat之Session的管理

    Session是由服务器端的应用服务器容器(如Tomcat.Jetty)存储的.下面分析一下Tomcat是如何管理Session的. 转自:tomcat架构分析 (Session管理) Tomcat中 ...

  2. 原生JS制作贪吃蛇小游戏

    感情都在代码里,来,干了!... <!doctype html> <html> <head> <meta http-equiv="Content-T ...

  3. 自写函数VB6 STUFF函数 和 VB.net 2010 STUFF函数 详解

    '*************************************************************************'**模 块 名:自写函数VB6 STUFF函数 和 ...

  4. Java实现列出目录下所有文件和文件夹

    package com.filetest; import java.io.File; import java.util.Scanner; public class fileview { public ...

  5. 通过html和css做出下拉导航栏的效果

    通过观察了百度的首页,对于更多产品一栏,觉得可以不涉及JS便可写出下拉导航栏的效果 1.先设计出大体的框架 <div class="nav"> <ul> & ...

  6. POS与EPOS区别

    本文分文三个部分来介绍,第一部分是两个概念(POS与EPOS),第三部分是 POS与EPOS的区别. 一.epos ( electronic point of sale ) 俗称电话pos机: .EP ...

  7. ABP理论学习之领域服务

    返回总目录 本篇目录 介绍 IDomainService接口和DomainService类 样例 创建一个接口 服务实现 调用应用服务 一些讨论 何不只使用应用服务 如何强制使用领域服务 介绍 领域服 ...

  8. ABP理论学习之Javascript API(理论完结篇)

    返回总目录 本篇目录 Ajax Notification Message UI block和busy 事件总线 Logging 其他工具功能 说在前面的话 不知不觉,我们送走了2015,同时迎来了20 ...

  9. jqGrid的autoencode参数设置为true在客户端可能引发的编码问题

    不久前使用jqGrid+MVC做过一段时间开发. 一开始,分页参数几乎都是默认值,jqGrid的分页功能很好用. 考虑到each input is evil,我们的系统对安全性又有较高要求,所以,为了 ...

  10. 跟我一起数据挖掘(21)——redis

    什么是Redis Redis是一个开源的使用ANSI C语言编写.支持网络.可基于内存亦可持久化的日志型.Key-Value数据库,并提供多种语言的API.从2010年3月15日起,Redis的开发工 ...