kafka批量消費手動提交ACK

 一次性拉取多條數據，消費後再手動提交ACK，因爲要保存到數據庫去， 這過程如果失敗的話， 需要重新消費這些數據

所以 配置的時候，KAFKA不能自動提交 ，

批量消費數據

1. 設置ENABLE_AUTO_COMMIT_CONFIG=false，禁止自動提交
2. 設置AckMode=MANUAL_IMMEDIATE
3. 監聽方法加入Acknowledgment ack 參數

 

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;

    /**
     * 生產者配置信息
     */
    @Bean
    public Map<String, Object> producerConfigs() {
        Map<String, Object> props = new HashMap<String, Object>();
        props.put(ProducerConfig.ACKS_CONFIG, "0");//默認爲1,all和-1都是消費在服務副本里 也已經接收成功，防止數據丟失
        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;
    }

    /**
     * 生產者工廠
     */
    @Bean
    public ProducerFactory<String, String> producerFactory() {
        return new DefaultKafkaProducerFactory<>(producerConfigs());
    }

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

    /**
     * 消費者配置信息
     */
    @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);// 手動提交 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;
    }

    /**
     * 消費者批量工程
     */
    @Bean
    public KafkaListenerContainerFactory<?> batchFactory() {
        ConcurrentKafkaListenerContainerFactory<Integer, String> factory = new ConcurrentKafkaListenerContainerFactory<>();
        factory.setConsumerFactory(new DefaultKafkaConsumerFactory<>(consumerConfigs()));
        // 設置爲批量消費，每個批次數量在Kafka配置參數中設置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    也可以把手動提交配置 寫成這樣 

ack-mode: MANUAL_IMMEDIATE

spring:
  kafka:
    bootstrap-servers: 192.168.1.125:9092 192.168.1.126:9092 192.168.1.127:9092
    producer:
      # 重試次數
      retries: 3
      # 批量發送的消息數量
      batch-size: 16384
      # 32MB的批處理緩衝區
      buffer-memory: 33554432
      key-serializer: org.apache.kafka.common.serialization.StringSerializer
      value-serializer: org.apache.kafka.common.serialization.StringSerializer
    consumer:
      # 默認消費者組
      group-id: 0
      # 最早未被消費的offset
      auto-offset-reset: earliest
      # 批量一次最大拉取數據量
      max-poll-records: 3000
      # 自動提交時間間隔， 這種直接拉到數據就提交 容易丟數據
      auto-commit-interval: 2000
      # 禁止自動提交
      enable-auto-commit: false
      # 批量拉取間隔，要大於批量拉取數據的處理時間，時間間隔太小會有重複消費
      max.poll.interval.ms: 5000
topicName:
  topic2: topic_collect1
  topic5: topic_collect111

消費的方法如下， 方法比較簡單

    @KafkaListener(id = "0", topics = "topic_collect", containerFactory = "batchFactory")
    public void listen100(List<ConsumerRecord<String, String>> records, Acknowledgment ack) {
        System.out.println(records.size() + "條數被消費");
        try {
            batchConsumer(records);
            ack.acknowledge();
        } catch (Exception ex) {
            logger.error("消費數據出錯 ", ex.getStackTrace());
        }
    }