一、生产者代码
生产者代码中主要通过KafkaProducer类生成生产者对象,传入Properties配置的参数。
注意send方法可以同步也可以异步,异步时需要实现Callback接口
package com.ptah.kafkaproducer;
import org.apache.kafka.clients.producer.Callback;
import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.ProducerRecord;
import org.apache.kafka.clients.producer.RecordMetadata;
import java.util.Properties;
public class KafkaProducer01 {
public static void main(String[] args) {
//配置属性
Properties props = new Properties();
//kafka集群地址
props.put("bootstrap.servers", "node01:9092,node02:9092,node03:9092");
//acks代表消息确认机制 // 1 0 -1 all
/**
* acks = 0: 表示produce请求立即返回,不需要等待leader的任何确认。
* 这种方案有最高的吞吐率,但是不保证消息是否真的发送成功。
*
* acks = 1: 表示leader副本必须应答此produce请求并写入消息到本地日志,之后produce请求被认为成功. 如果leader挂掉有数据丢失的风险
* acks = -1或者all: 表示分区leader必须等待消息被成功写入到所有的ISR副本(同步副本)中才认为produce请求成功。
* 这种方案提供最高的消息持久性保证,但是理论上吞吐率也是最差的。
*/
props.put("acks", "0");
//重试的次数
props.put("retries", 0);
//缓冲区的大小 //默认32M
props.put("buffer.memory", 33554432);
//批处理数据的大小,每次写入多少数据到topic //默认16KB
props.put("batch.size", 16384);
//可以延长多久发送数据 //默认为0 表示不等待 ,立即发送
props.put("linger.ms", 1);
//指定key和value的序列化器
props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");
//创建producer对象
KafkaProducer<String, String> producer = new KafkaProducer<String, String>(props);
for(int i = 0; i < 200; i++){
//向topic发送数据
ProducerRecord<String, String> record = new ProducerRecord<String, String>("test", "key" + i, "value" + i);
//(1)同步发送
//producer.send(record);
//(2)异步发送
producer.send(record, new MyCallback(i, "value" + i));
}
//关闭producer
producer.close();
}
}
class MyCallback implements Callback {
private final int key;
private final String message;
public MyCallback(int key, String message) {
this.key = key;
this.message = message;
}
@Override
public void onCompletion(RecordMetadata metadata, Exception exception) {
if(exception != null){
System.out.println("报错");
} else {
System.out.println("成功");
}
if(metadata != null) {
System.out.println("分区:"+metadata.partition());
System.out.println("offset: "+metadata.offset());
}
}
}
二、消费者代码
通过KafkaConsumer类创建消费者对象,可以设置自动或者手动提交offset
1. 自动提交offset
package com.ptah.kafkaconsumer;
import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;
import java.time.Duration;
import java.util.Arrays;
import java.util.Properties;
public class KafkaConsumerAutoCommit {
public static void main(String[] args) {
Properties props = new Properties();
//kafka集群地址
props.put("bootstrap.servers", "node01:9092,node02:9092,node03:9092");
//消费者组id
props.put("group.id", "consumer-test");
//自动提交偏移量
props.put("enable.auto.commit", "true");
//自动提交偏移量的时间间隔
props.put("auto.commit.interval.ms", "1000");
//默认是latest
//earliest: 当各分区下有已提交的offset时,从提交的offset开始消费;无提交的offset时,从头开始消费
//latest: 当各分区下有已提交的offset时,从提交的offset开始消费;无提交的offset时,消费新产生的该分区下的数据
//none : topic各分区都存在已提交的offset时,从offset后开始消费;只要有一个分区不存在已提交的offset,则抛出异常
props.put("auto.offset.reset","earliest");
props.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
props.put("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
//创建消费者对象
KafkaConsumer<String, String> consumer = new KafkaConsumer<String, String>(props);
//设置topic
consumer.subscribe(Arrays.asList("test"));
//消费数据
while(true){
ConsumerRecords<String, String> records = consumer.poll(Duration.ofSeconds(1));
for (ConsumerRecord<String, String> record : records) {
//获取分区
int partition = record.partition();
//获取key
String key = record.key();
//获取offset
long offset = record.offset();
//获取topic
String topic = record.topic();
System.out.println("topic: " + topic + " 分区:" + partition + " key: " + key + " offset: " + offset);
}
}
}
}
2. 手动提交offset
package com.ptah.kafkaconsumer;
import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;
import java.time.Duration;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Properties;
public class KafkaConsumerManulCommit {
public static void main(String[] args) {
Properties props = new Properties();
//kafka集群地址
props.put("bootstrap.servers", "node01:9092,node02:9092,node03:9092");
//消费者组id
props.put("group.id", "consumer-test");
//自动提交偏移量
props.put("enable.auto.commit", "false");
//默认是latest
//earliest: 当各分区下有已提交的offset时,从提交的offset开始消费;无提交的offset时,从头开始消费
//latest: 当各分区下有已提交的offset时,从提交的offset开始消费;无提交的offset时,消费新产生的该分区下的数据
//none : topic各分区都存在已提交的offset时,从offset后开始消费;只要有一个分区不存在已提交的offset,则抛出异常
props.put("auto.offset.reset","earliest");
props.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
props.put("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
//创建消费者对象
KafkaConsumer<String, String> consumer = new KafkaConsumer<String, String>(props);
//设置topic
consumer.subscribe(Arrays.asList("test"));
final int minBatchSize = 10;
ArrayList<ConsumerRecord<String, String>> buffer = new ArrayList<ConsumerRecord<String, String>>();
while (true) {
ConsumerRecords<String, String> records = consumer.poll(Duration.ofSeconds(3));
for (ConsumerRecord<String, String> record : records) {
buffer.add(record);
}
if(buffer.size() >= minBatchSize){
System.out.println("已处理条数:" + buffer.size());
consumer.commitSync();
buffer.clear();
}
}
}
}
–The End–