spring boot与kafka

　　1.项目搭建

　　2.关键代码与配置

　　3.性能调优

注意,本项目基于spring boot 1,如果是spring boot 2有可能会报错.相应的包需要更新

1.项目搭建

　　kafka版本:kafka_2.11-1.0.0

　　jar包版本:1.1.7.REALEASE

  <dependency>
            <groupId>org.springframework.kafka</groupId>
            <artifactId>spring-kafka</artifactId>
            <version>1.1..RELEASE</version>
        </dependency>

　　只需要在spring boot工程中加入改jar即可

2.关键代码与配置

　　实现生产者消费者需要实现几个关键bean

　　类 KafkaProducerConfig:

import org.apache.kafka.clients.producer.ProducerConfig;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
import org.springframework.kafka.annotation.EnableKafka;
import org.springframework.kafka.core.DefaultKafkaProducerFactory;
import org.springframework.kafka.core.KafkaTemplate;
import org.springframework.kafka.core.ProducerFactory;

import java.util.HashMap;
import java.util.Map;

@Configuration
@EnableKafka
public class KafkaProducerConfig {

    @Bean("kafkaTemplate")
    public KafkaTemplate<String, String> kafkaTemplate() {
        KafkaTemplate<String, String> kafkaTemplate = new KafkaTemplate<String, String>(producerFactory());
        return kafkaTemplate;
    }

    @Value("${spring.kafka.bootstrap-servers}")
    private String kafkaServers;

    @Value("${spring.kafka.producer.retries}")
    private String retry;

    @Value("${spring.kafka.producer.batch-size}")
    private String batch;

    @Value("${spring.kafka.producer.buffer-memory}")
    private String mem;

    @Value("${spring.kafka.producer.key-serializer}")
    private String keySerializer;

    @Value("${spring.kafka.producer.value-serializer}")
    private String valueSerializer;

    public ProducerFactory<String, String> producerFactory() {
        Map<String, Object> properties = new HashMap<String, Object>();
        properties.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG,kafkaServers);
        properties.put(ProducerConfig.RETRIES_CONFIG, retry);
        properties.put(ProducerConfig.BATCH_SIZE_CONFIG, batch);
        properties.put(ProducerConfig.LINGER_MS_CONFIG, 1);
        properties.put(ProducerConfig.BUFFER_MEMORY_CONFIG, mem);
        properties.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, keySerializer);
        properties.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, valueSerializer);
        return new DefaultKafkaProducerFactory<String, String>(properties);
    }
}

　　几个关键配置:

ProducerConfig.BOOTSTRAP_SERVERS_CONFIG  //kafka地址
ProducerConfig.BATCH_SIZE_CONFIG //批量发送配置,单位字节 当多个数据同时发往一个分区时,将被批量控制,减少对服务端的请求
ProducerConfig.BUFFER_MEMORY_CONFIG //生产者缓存,单位字节 生产者对发送数据的缓存总数

　　现在就构造出了kafkaTemplate对象,可以用他发送消息

kafkaTemplate.send(topic, 0, gson.toJson(Object));

send可以只传三个参数:topic,分区,数据

消费者代码和配置:
类 KafkaConsumerBatchConfig

package com.newland.dc.kafka.kafka;

import org.apache.kafka.clients.consumer.ConsumerConfig;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
import org.springframework.kafka.annotation.EnableKafka;
import org.springframework.kafka.config.ConcurrentKafkaListenerContainerFactory;
import org.springframework.kafka.config.KafkaListenerContainerFactory;
import org.springframework.kafka.core.ConsumerFactory;
import org.springframework.kafka.core.DefaultKafkaConsumerFactory;
import org.springframework.kafka.listener.AbstractMessageListenerContainer;
import org.springframework.kafka.listener.ConcurrentMessageListenerContainer;

import java.util.HashMap;
import java.util.Map;

@Configuration
@EnableKafka
public class KafkaConsumerBatchConfig {

    @Value("${spring.kafka.bootstrap-servers}")
    private String servers;

    @Value("${spring.kafka.consumer.enable-auto-commit}")
    private boolean auto;

    @Value("${spring.kafka.consumer.auto-commit-interval}")
    private int interval;

    @Value("${spring.kafka.consumer.group-id}")
    private String group;

    @Value("${spring.kafka.consumer.auto-offset-reset}")
    private String reset;

    @Value("${spring.kafka.consumer.key-deserializer}")
    private String keyDeserializer;

    @Value("${spring.kafka.consumer.value-deserializer}")
    private String valueDeserializer;

    @Value("${spring.kafka.consumer.max-poll-records:100}")
    private String maxPollRecords;

    @Value("${spring.kafka.consumer.max-poll-interval:1000000}")
    private String maxPollInterval;

    public ConsumerFactory<String, String> consumerFactory() {
        Map<String, Object> properties = new HashMap<String, Object>();
        properties.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, servers);//注意这里修改为kafka的具体配置项目，我这里只是为了开发演示方便
        properties.put(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG, auto);
        properties.put(ConsumerConfig.AUTO_COMMIT_INTERVAL_MS_CONFIG, interval);
        properties.put(ConsumerConfig.SESSION_TIMEOUT_MS_CONFIG, "15000");
        properties.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, keyDeserializer);
        properties.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, valueDeserializer);
        properties.put(ConsumerConfig.GROUP_ID_CONFIG, group);
        properties.put(ConsumerConfig.MAX_POLL_RECORDS_CONFIG, maxPollRecords);
        properties.put(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, reset);
        properties.put(ConsumerConfig.MAX_POLL_INTERVAL_MS_CONFIG, maxPollInterval);
        return new DefaultKafkaConsumerFactory<String, String>(properties);
    }

    @Bean
    public KafkaListenerContainerFactory<?> batchFactory() {
    ConcurrentKafkaListenerContainerFactory<String, String> factory =
    new ConcurrentKafkaListenerContainerFactory<>();
    factory.setConsumerFactory(consumerFactory());
    factory.setConcurrency(1);
    factory.setBatchListener(true);//设置为批量消费，每个批次数量在Kafka配置参数中设置ConsumerConfig.MAX_POLL_RECORDS_CONFIG
    factory.getContainerProperties().setAckMode(AbstractMessageListenerContainer.AckMode.MANUAL_IMMEDIATE);//设置提交偏移量的方式
    return factory;
    }

}

　　关键配置:

ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG //由于此处批量我们用手动提交,所以该配置改为false
ConsumerConfig.MAX_POLL_RECORDS_CONFIG //每次批量消费最大数
factory.setBatchListener(true); //注意把批量消费开启

消费者代码:对话题的每个分区监听,注意containerFactory配置

@Component
public class MyListener {

    @Autowired
    private KafkaReceiverBatch kafkaReceiverBatch;
    private  final Log log = LogFactory.getLogger(MyListener.class);

    @KafkaListener(id = "id0",containerFactory = "batchFactory", topicPartitions = { @TopicPartition(topic = "${consumer.log.topic:log.business}", partitions = { "0" }) })
    public void listenPartition0(List<ConsumerRecord<?, ?>> records, Acknowledgment ack) {
        log.info(LogProperty.LOGCONFIG_DEALID,"partition:0, size " + records.size());
        kafkaReceiverBatch.batchConsumer(records,ack);
        a1 = printNum("0",a += records.size(),a1);
    }
    @KafkaListener(id = "id1",containerFactory = "batchFactory", topicPartitions = { @TopicPartition(topic = "${consumer.log.topic:log.business}", partitions = { "1" }) })
    public void listenPartition1(List<ConsumerRecord<?, ?>> records, Acknowledgment ack) {
        log.info(LogProperty.LOGCONFIG_DEALID,"partition:1, size " + records.size());
        kafkaReceiverBatch.batchConsumer(records,ack);
        b1 = printNum("1",b += records.size(),b1);
    }
    @KafkaListener(id = "id2",containerFactory = "batchFactory", topicPartitions = { @TopicPartition(topic = "${consumer.log.topic:log.business}", partitions = { "2" }) })
    public void listenPartition2(List<ConsumerRecord<?, ?>> records, Acknowledgment ack) {
        log.info(LogProperty.LOGCONFIG_DEALID,"partition:2, size " + records.size());
        kafkaReceiverBatch.batchConsumer(records,ack);
        c1 = printNum("2",c += records.size(),c1);
    }

    static Integer a = 0,b = 0,c = 0;
    static Integer a1 = 0,b1 = 0 ,c1 = 0 ;
    private Integer printNum(String threadTag, Integer num, Integer printTimes){
        if( num/100000 > printTimes ){
            System.out.println("partition:" + threadTag + ",consumer num:" + num);
            printTimes ++;
        }
        return printTimes;
    }
}

消费逻辑也贴个例子:

    protected void batchConsumer(List<ConsumerRecord<?, ?>> records, Acknowledgment ack){
        for (ConsumerRecord<?, ?> record : records) {
            try {
                Optional<?> kafkaMessage = Optional.ofNullable(record.value());
                if (kafkaMessage.isPresent()) {
                    Object message = kafkaMessage.get();
                    AllLogBase allLogBase = gson.fromJson(message.toString(), AllLogBase.class);
                }
            } catch (Exception e) {
                e.printStackTrace();
                continue;
            }

        }
        ack.acknowledge();//手动提交偏移量
    }

3.性能调优

　　kafka生产和消费要注意几个关键点:

　　1.kafka生产者异步:

pool.execute(()->{kafkaTemplate.send(topic, 0, gson.toJson(Object));});

　　比如此处可以改为线程池

　　2.批量写入,可以更改生产者的批量发送值和缓存值,加大该值将大幅提升性能

　　3.消费者分区监听,并开启批量消费,提升性能