- 环境:jdk1.8,eclipse,maven
- maven:
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka_2.11</artifactId>
<version>0.10.2.1</version>
</dependency>
- 代码
package com.utils.kafka;
import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.Producer;
import org.apache.kafka.clients.producer.ProducerRecord;
import java.util.Properties;
import java.util.concurrent.TimeUnit;
import org.apache.kafka.clients.consumer.ConsumerRebalanceListener;
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.TopicPartition;
import java.util.Arrays;
import java.util.Collection;
public class KafkaTest {
public static void main(String[] args) {
shengchanzhe();
// xiaofeizhe();
}
private static void xiaofeizhe() {
Properties props = new Properties();
props.put("bootstrap.servers", "127.0.0.1:9092");
props.put("group.id", "test-consumer-group");
props.put("enable.auto.commit", "true");
props.put("auto.commit.interval.ms", "1000");
props.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
props.put("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
final KafkaConsumer<String, String> consumer = new KafkaConsumer<String, String>(props);
consumer.subscribe(Arrays.asList("topic1"), new ConsumerRebalanceListener() {
@Override
public void onPartitionsRevoked(Collection<TopicPartition> collection) {
}
@Override
public void onPartitionsAssigned(Collection<TopicPartition> collection) {
// 将偏移设置到最开始:每次启动都从头开始消费
// consumer.seekToBeginning(collection);
}
});
while (true) {
ConsumerRecords<String, String> records = consumer.poll(100);
for (ConsumerRecord<String, String> record : records) {
System.out.printf("offset = %d, key = %s, value = %s%n", record.offset(), record.key(), record.value());
}
}
}
private static void shengchanzhe() {
Properties props = new Properties();
props.put("bootstrap.servers", "127.0.0.1:9092");
props.put("acks", "all");
props.put("retries", 0);
props.put("batch.size", 16384);
props.put("linger.ms", 1);
props.put("buffer.memory", 33554432);
props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");
Producer producer = new KafkaProducer<Integer, String>(props);
int i = 0;
while (true) {
// i=666;
if (i > 5) {
break;
}
producer.send(new ProducerRecord<String, String>("topic1", "key" + i, "message: " + i++));
try {
TimeUnit.SECONDS.sleep(1);
} catch (InterruptedException e) {
e.printStackTrace();
}
System.out.println("MyProducer.main _" + i);
}
}
}
- 一个生产者,多个消费者(消费的数据相同),配置多个group id监听同一个topic
public static void main(String[] args) {
new Thread(() -> xiaofeizhe("test-group1")).start();
new Thread(() -> xiaofeizhe("test-group2")).start();
}
运行原理
-
生产者发送消息到主题(topic),消费者订阅主题(消费组名义订阅groupid),主题下是分区,消息存储在分区中
事实上:生产者将消息发送到分区中,消费者从分区读取消息 -
主题的分区数量,默认1,可在配置文件server.properties修改 num.partitions=2
每个主题可以设置自己的分区,不设置则用默认分区数量
-
一个消息只能被同一组(groupId)的一个消费者消费
消费者订阅主题,主题下所有的分区都会被组中的消费者消费到,意味着 主题下的每个分区只从属于组中的一个消费者,不可能出现组中的两个消费者负责同一个分区 -
分区数 >= 组中消费者实例 (否则相当于多线程调用一个消息,会造成消息处理重复)