Kafka实战——简单易懂的生产者消费者demo

CarsonBigData

已于 2022-09-15 13:23:16 修改

阅读量1.3k

点赞数 1

分类专栏：服务端大数据文章标签： kafka 消息队列

于 2020-06-04 17:15:06 首次发布

本文链接：https://blog.csdn.net/Carson073/article/details/106489831

版权

服务端同时被 2 个专栏收录

85 篇文章 2 订阅

订阅专栏

大数据

40 篇文章 24 订阅

订阅专栏

单线程版本适合本地调试，多线程版本适合做压测

1、引入maven依赖

<dependency>
   <groupId>org.apache.kafka</groupId>
   <artifactId>kafka-clients</artifactId>
   <version>1.1.0</version>
</dependency>

2、生产者代码

单线程版

public class MsgProducer {
    public static void main(String[] args) throws InterruptedException, ExecutionException {
        Properties props = new Properties();
        props.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, "192.168.0.60:9092,192.168.0.60:9093,192.168.0.60:9094");
        /*
         发出消息持久化机制参数
        （1）acks=0： 表示producer不需要等待任何broker确认收到消息的回复，就可以继续发送下一条消息。性能最高，但是最容易丢消息。
        （2）acks=1： 至少要等待leader已经成功将数据写入本地log，但是不需要等待所有follower是否成功写入。就可以继续发送下一条消息。这种情况下，如果follower没有成功备份数据，而此时leader
        又挂掉，则消息会丢失。
        （3）acks=-1或all： 这意味着leader需要等待所有备份(min.insync.replicas配置的备份个数)都成功写入日志，这种策略会保证只要有一个备份存活就不会丢失数据。
                            这是最强的数据保证。一般除非是金融级别，或跟钱打交道的场景才会使用这种配置。
        */
        props.put(ProducerConfig.ACKS_CONFIG, "1");
        //发送失败会重试，默认重试间隔100ms，重试能保证消息发送的可靠性，但是也可能造成消息重复发送，比如网络抖动，所以需要在接收者那边做好消息接收的幂等性处理
        props.put(ProducerConfig.RETRIES_CONFIG, 3);
        //重试间隔设置
        props.put(ProducerConfig.RETRY_BACKOFF_MS_CONFIG, 300);
        //设置发送消息的本地缓冲区，如果设置了该缓冲区，消息会先发送到本地缓冲区，可以提高消息发送性能，默认值是33554432，即32MB
        props.put(ProducerConfig.BUFFER_MEMORY_CONFIG, 33554432);
        //kafka本地线程会从缓冲区取数据，批量发送到broker，
        //设置批量发送消息的大小，默认值是16384，即16kb，就是说一个batch满了16kb就发送出去
        props.put(ProducerConfig.BATCH_SIZE_CONFIG, 16384);
        //默认值是0，意思就是消息必须立即被发送，但这样会影响性能
        //一般设置100毫秒左右，就是说这个消息发送完后会进入本地的一个batch，如果100毫秒内，这个batch满了16kb就会随batch一起被发送出去
        //如果100毫秒内，batch没满，那么也必须把消息发送出去，不能让消息的发送延迟时间太长
        props.put(ProducerConfig.LINGER_MS_CONFIG, 100);
        //把发送的key从字符串序列化为字节数组
        props.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class.getName());
        //把发送消息value从字符串序列化为字节数组
        props.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class.getName());

        Producer<String, String> producer = new KafkaProducer<>(props);

        int msgNum = 5;
        CountDownLatch countDownLatch = new CountDownLatch(msgNum);
        for (int i = 1; i <= msgNum; i++) {
            Order order = new Order(i, 100 + i, 1, 1000.00);
            //指定发送分区
            ProducerRecord<String, String> producerRecord = new ProducerRecord<String, String>("order-topic"
                    , 0, order.getOrderId().toString(), JSON.toJSONString(order));
            //未指定发送分区，具体发送的分区计算公式：hash(key)%partitionNum
            /*ProducerRecord<String, String> producerRecord = new ProducerRecord<String, String>("my-replicated-topic"
                    , order.getOrderId().toString(), JSON.toJSONString(order));*/

            //等待消息发送成功的同步阻塞方法
         /*RecordMetadata metadata = producer.send(producerRecord).get();
         System.out.println("同步方式发送消息结果：" + "topic-" + metadata.topic() + "|partition-"
                 + metadata.partition() + "|offset-" + metadata.offset());*/

            //异步方式发送消息
            producer.send(producerRecord, new Callback() {
                @Override
                public void onCompletion(RecordMetadata metadata, Exception exception) {
                    if (exception != null) {
                        System.err.println("发送消息失败：" + exception.getStackTrace());

                    }
                    if (metadata != null) {
                        System.out.println("异步方式发送消息结果：" + "topic-" + metadata.topic() + "|partition-"
                                + metadata.partition() + "|offset-" + metadata.offset());
                    }
                    countDownLatch.countDown();
                }
            });

            //送积分 TODO

        }

        countDownLatch.await(5, TimeUnit.SECONDS);
        producer.close();
    }
}

多线程版

package com.test.kafka;

import org.apache.kafka.clients.producer.*;
import org.apache.kafka.common.serialization.StringSerializer;

import java.util.Properties;
import java.util.concurrent.CountDownLatch;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;

public class MsgProducer {

    //发送消息的个数
    private static final int MSG_SIZE = 500000;
    //负责发送消息的线程池
    private static ExecutorService executorService = Executors.newFixedThreadPool(Runtime.getRuntime().availableProcessors());
    private static CountDownLatch countDownLatch = new CountDownLatch(MSG_SIZE);


    /*发送消息的任务*/
    private static class ProduceWorker implements Runnable {

        private ProducerRecord<String, String> record;
        private KafkaProducer<String, String> producer;

        public ProduceWorker(ProducerRecord<String, String> record, KafkaProducer<String, String> producer) {
            this.record = record;
            this.producer = producer;
        }

        public void run() {
            final String id = Thread.currentThread().getId() + "-" + System.identityHashCode(producer);
            try {
                producer.send(record, new Callback() {
                    public void onCompletion(RecordMetadata metadata, Exception exception) {
                        if (null != exception) {
                            exception.printStackTrace();
                        }
                        if (null != metadata) {
                            System.out.println(id + "|"
                                    + String.format("偏移量：%s,分区：%s",
                                    metadata.offset(), metadata.partition()));
                        }
                    }
                });
                System.out.println(id + ":数据[" + record.key() + "-" + record.value() + "]已发送。");
                countDownLatch.countDown();
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
    }

    public static void main(String[] args) {
        // 消费主题
        String topicName = "test_datax_kafka_read";
        Properties properties = new Properties();
        properties.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, "10.254.21.6:59292,10.254.21.1:59292,10.254.21.2:59292");
        properties.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
        properties.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
        KafkaProducer<String, String> producer = new KafkaProducer(properties);

        try {
            //循环发送，通过线程池的方式
            for (int i = 0; i < MSG_SIZE; i++) {

                ProducerRecord<String, String> record = new ProducerRecord(
                        topicName,
                        null,
                        "{\"data\":[{\"byteSize\":5,\"rawData\":28108,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":60,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":99,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":70,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":31,\"type\":\"LONG\"},{\"byteSize\":1,\"rawData\":0,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":82,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":94,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":70,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":22,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":10,\"type\":\"LONG\"},{\"byteSize\":1,\"rawData\":1,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":89,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":14,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":38,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":20,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":50,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":30,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":13,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":36,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":53,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":42,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":11,\"type\":\"LONG\"},{\"byteSize\":1,\"rawData\":4,\"type\":\"LONG\"},{\"byteSize\":1,\"rawData\":6,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":49,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":35,\"type\":\"LONG\"},{\"byteSize\":1,\"rawData\":4,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":48,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":46,\"type\":\"LONG\"},{\"byteSize\":1,\"rawData\":1,\"type\":\"LONG\"},{\"byteSize\":2,\"rawData\":73,\"type\":\"LONG\"},{\"byteSize\":1,\"rawData\":6,\"type\":\"LONG\"},{\"byteSize\":8,\"rawData\":1659515670000,\"subType\":\"DATETIME\",\"type\":\"DATE\"}],\"size\":34}\n"
                );
                executorService.submit(new ProduceWorker(record, producer));
            }
            countDownLatch.await();
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            producer.close();
            executorService.shutdown();
        }
    }
}

3、消费者代码

单线程版

public class MsgConsumer {
    public static void main(String[] args) {
        Properties props = new Properties();
        props.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, "192.168.0.60:9092,192.168.0.60:9093,192.168.0.60:9094");
        // 消费分组名
        props.put(ConsumerConfig.GROUP_ID_CONFIG, "testGroup");
        // 是否自动提交offset
      /*props.put(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG, "true");
      // 自动提交offset的间隔时间
      props.put(ConsumerConfig.AUTO_COMMIT_INTERVAL_MS_CONFIG , "1000");*/
        props.put(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG, "false");
      /*
      心跳时间，服务端broker通过心跳确认consumer是否故障，如果发现故障，就会通过心跳下发
      rebalance的指令给其他的consumer通知他们进行rebalance操作，这个时间可以稍微短一点
      */
        props.put(ConsumerConfig.HEARTBEAT_INTERVAL_MS_CONFIG, 1000);
        //服务端broker多久感知不到一个consumer心跳就认为他故障了，默认是10秒
        props.put(ConsumerConfig.SESSION_TIMEOUT_MS_CONFIG, 10 * 1000);
        /*
        如果两次poll操作间隔超过了这个时间，broker就会认为这个consumer处理能力太弱，
        会将其踢出消费组，将分区分配给别的consumer消费
        */
        props.put(ConsumerConfig.MAX_POLL_INTERVAL_MS_CONFIG, 30 * 1000);
        props.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class.getName());
        props.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class.getName());
        KafkaConsumer<String, String> consumer = new KafkaConsumer<>(props);
        // 消费主题
        String topicName = "order-topic";
        //consumer.subscribe(Arrays.asList(topicName));
        // 消费指定分区
        //consumer.assign(Arrays.asList(new TopicPartition(topicName, 0)));

        //消息回溯消费
        consumer.assign(Arrays.asList(new TopicPartition(topicName, 0)));
        consumer.seekToBeginning(Arrays.asList(new TopicPartition(topicName, 0)));
        //指定offset消费
        //consumer.seek(new TopicPartition(topicName, 0), 10);

        while (true) {
            /*
             * poll() API 是拉取消息的长轮询，主要是判断consumer是否还活着，只要我们持续调用poll()，
             * 消费者就会存活在自己所在的group中，并且持续的消费指定partition的消息。
             * 底层是这么做的：消费者向server持续发送心跳，如果一个时间段（session.
             * timeout.ms）consumer挂掉或是不能发送心跳，这个消费者会被认为是挂掉了，
             * 这个Partition也会被重新分配给其他consumer
             */
            ConsumerRecords<String, String> records = consumer.poll(Integer.MAX_VALUE);
            for (ConsumerRecord<String, String> record : records) {
                System.out.printf("收到消息：offset = %d, key = %s, value = %s%n", record.offset(), record.key(),
                        record.value());
            }

            if (records.count() > 0) {
                // 提交offset
                consumer.commitSync();
            }
        }
    }
}

多线程版

package com.test.kafka;

import org.apache.kafka.clients.consumer.ConsumerConfig;
import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;
import org.apache.kafka.common.serialization.StringDeserializer;

import java.time.Duration;
import java.util.Arrays;
import java.util.Properties;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;

public class MsgConsumer {


    private static ExecutorService receiveMsgExecutorService = Executors.newFixedThreadPool(Runtime.getRuntime().availableProcessors());

    public static void main(String[] args) {
        // 消费主题
        String topicName = "test_datax_kafka_read";

        int consumerThreadNum = 12;
        for (int i = 0; i < consumerThreadNum; i++) {
            receiveMsgExecutorService.submit(new KafkaConsumerThread(initConfig(), topicName));
        }
    }

    public static Properties initConfig() {
        Properties properties = new Properties();
        properties.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, "10.254.21.6:59292,10.254.21.1:59292,10.254.21.2:59292");
        // 消费分组名
        properties.put(ConsumerConfig.GROUP_ID_CONFIG, "local-test-2");
        // 是否自动提交offset
        properties.put(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG, "true");
        // 自动提交offset的间隔时间
        properties.put(ConsumerConfig.AUTO_COMMIT_INTERVAL_MS_CONFIG, "1000");
        // 心跳时间，服务端broker通过心跳确认consumer是否故障，如果发现故障，
        // 就会通过心跳下发rebalance的指令给其他的consumer通知他们进行rebalance操作，这个时间可以稍微短一点
        properties.put(ConsumerConfig.HEARTBEAT_INTERVAL_MS_CONFIG, 1000);
        // 服务端broker多久感知不到一个consumer心跳就认为他故障了，默认是10秒
        properties.put(ConsumerConfig.SESSION_TIMEOUT_MS_CONFIG, 10 * 1000);
        // 如果两次poll操作间隔超过了这个时间，broker就会认为这个consumer处理能力太弱，
        // 会将其踢出消费组，将分区分配给别的consumer消费
        properties.put(ConsumerConfig.MAX_POLL_INTERVAL_MS_CONFIG, 30 * 1000);

        properties.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class.getName());
        properties.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class.getName());
        return properties;
    }


    static class KafkaConsumerThread implements Runnable {
        private KafkaConsumer<String, String> kafkaConsumer;

        public KafkaConsumerThread(Properties properties, String topic) {
            this.kafkaConsumer = new KafkaConsumer<String, String>(properties);
            this.kafkaConsumer.subscribe(Arrays.asList(topic));
        }

        @Override
        public void run() {
            try {
                int consumerCount = 0;
                int lastConsumerCount = 0;
                long lastTime = System.currentTimeMillis();
                while (true) {
                    ConsumerRecords<String, String> records = kafkaConsumer.poll(Duration.ofMillis(1000));
                    for (ConsumerRecord<String, String> record : records) {
                        //处理消息模块
                        System.out.printf("收到消息：partition = %d, offset = %d, key = %s, value = %s%n", record.partition(), record.offset(), record.key(), record.value());
                        consumerCount++;
                    }
                    System.out.println("consumerCount:" + consumerCount);

                    long thisTime = System.currentTimeMillis();
                    long speedTime = thisTime - lastTime;
                    if (speedTime >= 1000L) {
                        lastTime = thisTime;
                        long speedCount = (consumerCount - lastConsumerCount)/(speedTime /1000L);
                        lastConsumerCount = consumerCount;
                        if (speedCount > 10) {
                            System.out.println("消费速度：" + speedCount + "条/s");
                        }
                    }
                }
            } catch (Exception e) {
                e.printStackTrace();
            } finally {
                kafkaConsumer.close();
            }
        }
    }

}