kafka批量消费手动提交ACK

 一次性拉取多条数据，消费后再手动提交ACK，因为要保存到数据库去， 这过程如果失败的话， 需要重新消费这些数据

所以 配置的时候，KAFKA不能自动提交 ，

批量消费数据

1. 设置ENABLE_AUTO_COMMIT_CONFIG=false，禁止自动提交
2. 设置AckMode=MANUAL_IMMEDIATE
3. 监听方法加入Acknowledgment ack 参数

 

package com.zenlayer.ad.kafuka;

import org.apache.kafka.clients.consumer.ConsumerConfig;
import org.apache.kafka.clients.producer.ProducerConfig;
import org.apache.kafka.common.serialization.StringDeserializer;
import org.apache.kafka.common.serialization.StringSerializer;
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.DefaultKafkaConsumerFactory;
import org.springframework.kafka.core.DefaultKafkaProducerFactory;
import org.springframework.kafka.core.KafkaTemplate;
import org.springframework.kafka.core.ProducerFactory;
import org.springframework.kafka.listener.AbstractMessageListenerContainer;

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

@Configuration
@EnableKafka
public class KafkaConfiguration {
    /**
     * @author zhff
     * @version 2019/9/1 下午04:07
     */
    @Value("${spring.kafka.bootstrap-servers}")
    private String bootstrapServers;

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

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

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

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

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

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

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

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

    /**
     * 生产者配置信息
     */
    @Bean
    public Map<String, Object> producerConfigs() {
        Map<String, Object> props = new HashMap<String, Object>();
        props.put(ProducerConfig.ACKS_CONFIG, "0");//默认为1,all和-1都是消费在服务副本里 也已经接收成功，防止数据丢失
        props.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, bootstrapServers);
        props.put(ProducerConfig.RETRIES_CONFIG, retries);
        props.put(ProducerConfig.BATCH_SIZE_CONFIG, batchSize);
        props.put(ProducerConfig.LINGER_MS_CONFIG, 1);
        props.put(ProducerConfig.BUFFER_MEMORY_CONFIG, bufferMemory);
        props.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
        props.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
        return props;
    }

    /**
     * 生产者工厂
     */
    @Bean
    public ProducerFactory<String, String> producerFactory() {
        return new DefaultKafkaProducerFactory<>(producerConfigs());
    }

    /**
     * 生产者模板
     */
    @Bean
    public KafkaTemplate<String, String> kafkaTemplate() {
        return new KafkaTemplate<>(producerFactory());
    }

    /**
     * 消费者配置信息
     */
    @Bean
    public Map<String, Object> consumerConfigs() {
        Map<String, Object> props = new HashMap<String, Object>();
        props.put(ConsumerConfig.GROUP_ID_CONFIG, groupId);
        props.put(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, autoOffsetReset);
        props.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, bootstrapServers);
        props.put(ConsumerConfig.MAX_POLL_RECORDS_CONFIG, maxPollRecords);
        props.put(ConsumerConfig.MAX_POLL_RECORDS_CONFIG, maxPollRecords);
        props.put(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG, autoCommit);// 手动提交 配置 false
        props.put(ConsumerConfig.SESSION_TIMEOUT_MS_CONFIG, 120000);
        props.put(ConsumerConfig.REQUEST_TIMEOUT_MS_CONFIG, 180000);
        props.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
        props.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);

        return props;
    }

    /**
     * 消费者批量工程
     */
    @Bean
    public KafkaListenerContainerFactory<?> batchFactory() {
        ConcurrentKafkaListenerContainerFactory<Integer, String> factory = new ConcurrentKafkaListenerContainerFactory<>();
        factory.setConsumerFactory(new DefaultKafkaConsumerFactory<>(consumerConfigs()));
        // 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.setBatchListener(true);
        factory.setConcurrency(4);
        factory.getContainerProperties().setAckMode(AbstractMessageListenerContainer.AckMode.MANUAL_IMMEDIATE);
        factory.getContainerProperties().setPollTimeout(30000);
        return factory;
    }
}

配置文件    也可以把手动提交配置 写成这样 

ack-mode: MANUAL_IMMEDIATE

spring:
  kafka:
    bootstrap-servers: 192.168.1.125:9092 192.168.1.126:9092 192.168.1.127:9092
    producer:
      # 重试次数
      retries: 3
      # 批量发送的消息数量
      batch-size: 16384
      # 32MB的批处理缓冲区
      buffer-memory: 33554432
      key-serializer: org.apache.kafka.common.serialization.StringSerializer
      value-serializer: org.apache.kafka.common.serialization.StringSerializer
    consumer:
      # 默认消费者组
      group-id: 0
      # 最早未被消费的offset
      auto-offset-reset: earliest
      # 批量一次最大拉取数据量
      max-poll-records: 3000
      # 自动提交时间间隔， 这种直接拉到数据就提交 容易丢数据
      auto-commit-interval: 2000
      # 禁止自动提交
      enable-auto-commit: false
      # 批量拉取间隔，要大于批量拉取数据的处理时间，时间间隔太小会有重复消费
      max.poll.interval.ms: 5000
topicName:
  topic2: topic_collect1
  topic5: topic_collect111

消费的方法如下， 方法比较简单

    @KafkaListener(id = "0", topics = "topic_collect", containerFactory = "batchFactory")
    public void listen100(List<ConsumerRecord<String, String>> records, Acknowledgment ack) {
        System.out.println(records.size() + "条数被消费");
        try {
            batchConsumer(records);
            ack.acknowledge();
        } catch (Exception ex) {
            logger.error("消费数据出错 ", ex.getStackTrace());
        }
    }