java自己手動控制kafka的offset操作

之前使用kafka的KafkaStream,讓每個消費者和對應的patition建立對應的流來讀取kafka上面的數據,如果comsumer得到數據,那麼kafka就會自動去維護該comsumer的offset,例如在獲取到kafka的消息後正準備入庫(未入庫),但是消費者掛瞭,那麼如果讓kafka自動去維護offset,它就會認為這條數據已經被消費瞭,那麼會造成數據丟失。

但是kafka可以讓你自己去手動提交,如果在上面的場景中,那麼需要我們手動commit,如果comsumer掛瞭 那麼程序就不會執行commit這樣的話 其他同group的消費者又可以消費這條數據,保證數據不丟,先要做如下設置:

//設置不自動提交,自己手動更新offset
properties.put("enable.auto.commit", "false");

使用如下api提交:

consumer.commitSync();

註意:

剛做瞭個測試,如果我從kafka中取出5條數據,分別為1,2,3,4,5,如果消費者在執行一些邏輯在執行1,2,3,4的時候都失敗瞭未提交commit,然後消費5做邏輯成功瞭提交瞭commit,那麼offset也會被移動到5那一條數據那裡,1,2,3,4 相當於也會丟失

如果是做消費者取出數據執行一些操作,全部都失敗的話,然後重啟消費者,這些數據會從失敗的時候重新開始讀取

所以消費者還是應該自己做容錯機制

測試項目結構如下:

其中ConsumerThreadNew類:

package com.lijie.kafka;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
 * 
 *            
 * @Filename ConsumerThreadNew.java
 *
 * @Description 
 *
 * @Version 1.0
 *
 * @Author Lijie
 *
 * @Email [email protected]
 *    
 * @History
 *<li>Author: Lijie</li>
 *<li>Date: 2017年3月21日</li>
 *<li>Version: 1.0</li>
 *<li>Content: create</li>
 *
 */
public class ConsumerThreadNew implements Runnable {
  private static Logger          LOG = LoggerFactory.getLogger(ConsumerThreadNew.class);
  //KafkaConsumer kafka生產者
  private KafkaConsumer<String, String>  consumer;
  //消費者名字
  private String             name;
  //消費的topic組
  private List<String>          topics;
  //構造函數
  public ConsumerThreadNew(KafkaConsumer<String, String> consumer, String topic, String name) {
    super();
    this.consumer = consumer;
    this.name = name;
    this.topics = Arrays.asList(topic);
  }
  @Override
  public void run() {
    consumer.subscribe(topics);
    List<ConsumerRecord<String, String>> buffer = new ArrayList<>();
    // 批量提交數量
    final int minBatchSize = 1; 
    while (true) {
      ConsumerRecords<String, String> records = consumer.poll(100);
      for (ConsumerRecord<String, String> record : records) {
        LOG.info("消費者的名字為:" + name + ",消費的消息為:" + record.value());
        buffer.add(record);
      }
      if (buffer.size() >= minBatchSize) {
        //這裡就是處理成功瞭然後自己手動提交
        consumer.commitSync();
        LOG.info("提交完畢");
        buffer.clear();
      }
    }
  }
}

MyConsume類如下:

package com.lijie.kafka;
import java.util.Properties;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;
import org.apache.kafka.clients.consumer.KafkaConsumer;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
 * 
 *            
 * @Filename MyConsume.java
 *
 * @Description 
 *
 * @Version 1.0
 *
 * @Author Lijie
 *
 * @Email [email protected]
 *    
 * @History
 *<li>Author: Lijie</li>
 *<li>Date: 2017年3月21日</li>
 *<li>Version: 1.0</li>
 *<li>Content: create</li>
 *
 */
public class MyConsume {
  private static Logger  LOG = LoggerFactory.getLogger(MyConsume.class);
  public MyConsume() {
    // TODO Auto-generated constructor stub
  }
  public static void main(String[] args) {
    Properties properties = new Properties();
    properties.put("bootstrap.servers", "10.0.4.141:19093,10.0.4.142:19093,10.0.4.143:19093");
    //設置不自動提交,自己手動更新offset
    properties.put("enable.auto.commit", "false");
    properties.put("auto.offset.reset", "latest");
    properties.put("zookeeper.connect", "10.0.4.141:2181,10.0.4.142:2181,10.0.4.143:2181");
    properties.put("session.timeout.ms", "30000");
    properties.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
    properties.put("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
    properties.put("group.id", "lijieGroup");
    properties.put("zookeeper.connect", "192.168.80.123:2181");
    properties.put("auto.commit.interval.ms", "1000");
    ExecutorService executor = Executors.newFixedThreadPool(5);
    //執行消費
    for (int i = 0; i < 7; i++) {
      executor.execute(new ConsumerThreadNew(new KafkaConsumer<String, String>(properties),
        "lijietest", "消費者" + (i + 1)));
    }
  }
}

MyProducer類如下:

package com.lijie.kafka;
import java.util.Properties;
import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.ProducerRecord;
/**
 * 
 *            
 * @Filename MyProducer.java
 *
 * @Description 
 *
 * @Version 1.0
 *
 * @Author Lijie
 *
 * @Email [email protected]
 *    
 * @History
 *<li>Author: Lijie</li>
 *<li>Date: 2017年3月21日</li>
 *<li>Version: 1.0</li>
 *<li>Content: create</li>
 *
 */
public class MyProducer {
  private static Properties            properties;
  private static KafkaProducer<String, String>  pro;
  static {
    //配置
    properties = new Properties();
    properties.put("bootstrap.servers", "10.0.4.141:19093,10.0.4.142:19093,10.0.4.143:19093");
    //序列化類型
    properties
      .put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");
    properties.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
    //創建生產者
    pro = new KafkaProducer<>(properties);
  }
  public static void main(String[] args) throws Exception {
    produce("lijietest");
  }
  public static void produce(String topic) throws Exception {
    //模擬message
    //     String value = UUID.randomUUID().toString();
    for (int i = 0; i < 10000; i++) {
      //封裝message
      ProducerRecord<String, String> pr = new ProducerRecord<String, String>(topic, i + "");
      //發送消息
      pro.send(pr);
      Thread.sleep(1000);
    }
  }
}

pom文件如下:

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>lijie-kafka-offset</groupId>
  <artifactId>lijie-kafka-offset</artifactId>
  <version>0.0.1-SNAPSHOT</version>
  <dependencies>
    <dependency>
      <groupId>org.apache.kafka</groupId>
      <artifactId>kafka_2.11</artifactId>
      <version>0.10.1.1</version>
    </dependency>
    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-common</artifactId>
      <version>2.2.0</version>
    </dependency>
    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-hdfs</artifactId>
      <version>2.2.0</version>
    </dependency>
    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-client</artifactId>
      <version>2.2.0</version>
    </dependency>
    <dependency>
      <groupId>org.apache.hbase</groupId>
      <artifactId>hbase-client</artifactId>
      <version>1.0.3</version>
    </dependency>
    <dependency>
      <groupId>org.apache.hbase</groupId>
      <artifactId>hbase-server</artifactId>
      <version>1.0.3</version>
    </dependency>
    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-hdfs</artifactId>
      <version>2.2.0</version>
    </dependency>
    <dependency>
      <groupId>jdk.tools</groupId>
      <artifactId>jdk.tools</artifactId>
      <version>1.7</version>
      <scope>system</scope>
      <systemPath>${JAVA_HOME}/lib/tools.jar</systemPath>
    </dependency>
    <dependency>
      <groupId>org.apache.httpcomponents</groupId>
      <artifactId>httpclient</artifactId>
      <version>4.3.6</version>
    </dependency>
  </dependencies>
  <build>
    <plugins>
      <plugin>
        <groupId>org.apache.maven.plugins</groupId>
        <artifactId>maven-compiler-plugin</artifactId>
        <configuration>
          <source>1.7</source>
          <target>1.7</target>
        </configuration>
      </plugin>
    </plugins>
  </build>
</project>

補充:kafka javaAPI 手動維護偏移量

我就廢話不多說瞭,大傢還是直接看代碼吧~

package com.kafka;
import kafka.javaapi.PartitionMetadata;
import kafka.javaapi.consumer.SimpleConsumer;
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.clients.consumer.OffsetAndMetadata;
import org.apache.kafka.common.TopicPartition;
import org.junit.Test;
import java.util.*;
public class ConsumerManageOffet {
//broker的地址,
//與老版的kafka的區別是,新版本的kafka把偏移量保存到瞭broker,而老版本的是把偏移量保存到瞭zookeeper中
//所以在讀取數據時,應當設置broker的地址
  private static String ips = "192.168.136.150:9092,192.168.136.151:9092,192.168.136.152:9092";
  public static void main(String[] args) {
    Properties props = new Properties();
    props.put("bootstrap.servers",ips);
    props.put("group.id","test02");
    props.put("auto.offset.reset","earliest");
    props.put("max.poll.records","10"); 
    props.put("key.deserializer","org.apache.kafka.common.serialization.StringDeserializer");
    props.put("value.deserializer","org.apache.kafka.common.serialization.StringDeserializer");
    KafkaConsumer<String,String> consumer = new KafkaConsumer<>(props);
    consumer.subscribe(Arrays.asList("my-topic"));
    System.out.println("---------------------");
    while(true){
      ConsumerRecords<String,String> records = consumer.poll(10);
      System.out.println("+++++++++++++++++++++++");
      for(ConsumerRecord<String,String> record: records){
        System.out.println("---");
        System.out.printf("offset=%d,key=%s,value=%s%n",record.offset(),
            record.key(),record.value());
      }
    }
  }
  //手動維護偏移量
  @Test
  public void autoManageOffset2(){
    Properties props = new Properties();
    //broker的地址
    props.put("bootstrap.servers",ips);
    //這是消費者組
    props.put("group.id","groupPP");
    //設置消費的偏移量,如果以前消費過則接著消費,如果沒有就從頭開始消費
    props.put("auto.offset.reset","earliest");
    //設置自動提交偏移量為false
    props.put("enable.auto.commit","false");
    //設置Key和value的序列化
    props.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
    props.put("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
    //new一個消費者
    KafkaConsumer<String, String> consumer = new KafkaConsumer<>(props);
    //指定消費的topic
    consumer.subscribe(Arrays.asList("my-topic"));
    while(true){
      ConsumerRecords<String, String> records = consumer.poll(1000);
      //通過records獲取這個集合中的數據屬於那幾個partition
      Set<TopicPartition> partitions = records.partitions();
      for(TopicPartition tp : partitions){
        //通過具體的partition把該partition中的數據拿出來消費
        List<ConsumerRecord<String, String>> partitionRecords = records.records(tp);
        for(ConsumerRecord r : partitionRecords){
          System.out.println(r.offset()  +"   "+r.key()+"   "+r.value());
        }
        //獲取新這個partition中的最後一條記錄的offset並加1 那麼這個位置就是下一次要提交的offset
        long newOffset = partitionRecords.get(partitionRecords.size() - 1).offset() + 1;
        consumer.commitSync(Collections.singletonMap(tp,new OffsetAndMetadata(newOffset)));
      }
    }
  }
}

以上為個人經驗,希望能給大傢一個參考,也希望大傢多多支持WalkonNet。如有錯誤或未考慮完全的地方,望不吝賜教。

推薦閱讀: