四、Kafka API实战

个人专题目录


1. 环境准备

1)启动zk和kafka集群,在kafka集群中打开一个消费者
$ bin/kafka-console-consumer.sh --zookeeper hadoop102:2181 --topic first
2)导入pom依赖
<dependencies>
    <dependency>
        <groupId>org.apache.kafka</groupId>
        <artifactId>kafka-clients</artifactId>
        <version>0.11.0.0</version>
    </dependency>
    <dependency>
        <groupId>org.apache.kafka</groupId>
        <artifactId>kafka_2.12</artifactId>
        <version>0.11.0.0</version>
    </dependency>
</dependencies>

2. Kafka生产者Java API

创建生产者(过时的API)

package com.test.kafka;
import java.util.Properties;
import kafka.javaapi.producer.Producer;
import kafka.producer.KeyedMessage;
import kafka.producer.ProducerConfig;

public class OldProducer {

    public static void main(String[] args) {
        Properties properties = new Properties();
        properties.put("metadata.broker.list", "hadoop102:9092");
        properties.put("request.required.acks", "1");
        properties.put("serializer.class", "kafka.serializer.StringEncoder");
        
        Producer<Integer, String> producer = new Producer<Integer,String>(new ProducerConfig(properties));
        
        KeyedMessage<Integer, String> message = new KeyedMessage<Integer, String>("first", "hello world");
        producer.send(message );
    }
}

创建生产者(新API)

package com.test.kafka;
import java.util.Properties;
import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.Producer;
import org.apache.kafka.clients.producer.ProducerRecord;

public class NewProducer {

    public static void main(String[] args) {
        
        Properties props = new Properties();
        // Kafka服务端的主机名和端口号
        props.put("bootstrap.servers", "hadoop103:9092");
        // 等待所有副本节点的应答
        props.put("acks", "all");
        // 消息发送最大尝试次数
        props.put("retries", 0);
        // 一批消息处理大小
        props.put("batch.size", 16384);
        // 请求延时
        props.put("linger.ms", 1);
        // 发送缓存区内存大小
        props.put("buffer.memory", 33554432);
        // key序列化
        props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
        // value序列化
        props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");

        Producer<String, String> producer = new KafkaProducer<>(props);
        for (int i = 0; i < 50; i++) {
            producer.send(new ProducerRecord<String, String>("first", Integer.toString(i), "hello world-" + i));
        }

        producer.close();
    }
}

创建生产者带回调函数(新API)

package com.test.kafka;
import java.util.Properties;
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;

public class CallBackProducer {

    public static void main(String[] args) {

        Properties props = new Properties();
        // Kafka服务端的主机名和端口号
        props.put("bootstrap.servers", "hadoop103:9092");
        // 等待所有副本节点的应答
        props.put("acks", "all");
        // 消息发送最大尝试次数
        props.put("retries", 0);
        // 一批消息处理大小
        props.put("batch.size", 16384);
        // 增加服务端请求延时
        props.put("linger.ms", 1);
// 发送缓存区内存大小
        props.put("buffer.memory", 33554432);
        // key序列化
        props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
        // value序列化
        props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");

        KafkaProducer<String, String> kafkaProducer = new KafkaProducer<>(props);

        for (int i = 0; i < 50; i++) {

            kafkaProducer.send(new ProducerRecord<String, String>("first", "hello" + i), new Callback() {

                @Override
                public void onCompletion(RecordMetadata metadata, Exception exception) {

                    if (metadata != null) {

                        System.err.println(metadata.partition() + "---" + metadata.offset());
                    }
                }
            });
        }

        kafkaProducer.close();
    }
}

自定义分区生产者

0)需求:将所有数据存储到topic的第0号分区上
1)定义一个类实现Partitioner接口,重写里面的方法(过时API)
package com.test.kafka;
import java.util.Map;
import kafka.producer.Partitioner;

public class CustomPartitioner implements Partitioner {

    public CustomPartitioner() {
        super();
    }

    @Override
    public int partition(Object key, int numPartitions) {
        // 控制分区
        return 0;
    }
}
2)自定义分区(新API)
package com.test.kafka;
import java.util.Map;
import org.apache.kafka.clients.producer.Partitioner;
import org.apache.kafka.common.Cluster;

public class CustomPartitioner implements Partitioner {

    @Override
    public void configure(Map<String, ?> configs) {
        
    }

    @Override
    public int partition(String topic, Object key, byte[] keyBytes, Object value, byte[] valueBytes, Cluster cluster) {
        // 控制分区
        return 0;
    }

    @Override
    public void close() {
        
    }
}
3)在代码中调用
package com.test.kafka;
import java.util.Properties;
import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.Producer;
import org.apache.kafka.clients.producer.ProducerRecord;

public class PartitionerProducer {

    public static void main(String[] args) {
        
        Properties props = new Properties();
        // Kafka服务端的主机名和端口号
        props.put("bootstrap.servers", "hadoop103:9092");
        // 等待所有副本节点的应答
        props.put("acks", "all");
        // 消息发送最大尝试次数
        props.put("retries", 0);
        // 一批消息处理大小
        props.put("batch.size", 16384);
        // 增加服务端请求延时
        props.put("linger.ms", 1);
        // 发送缓存区内存大小
        props.put("buffer.memory", 33554432);
        // key序列化
        props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
        // value序列化
        props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");
        // 自定义分区
        props.put("partitioner.class", "com.test.kafka.CustomPartitioner");

        Producer<String, String> producer = new KafkaProducer<>(props);
        producer.send(new ProducerRecord<String, String>("first", "1", "test"));

        producer.close();
    }
}
4)测试
(1)在hadoop102上监控/opt/module/kafka/logs/目录下first主题3个分区的log日志动态变化情况
tail -f 00000000000000000000.log
(2)发现数据都存储到指定的分区了。

3. Kafka消费者Java API

高级API

0)在控制台创建发送者
$ bin/kafka-console-producer.sh --broker-list hadoop102:9092 --topic first
>hello world
1)创建消费者(过时API)
package com.test.kafka.consume;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.Properties;
import kafka.consumer.Consumer;
import kafka.consumer.ConsumerConfig;
import kafka.consumer.ConsumerIterator;
import kafka.consumer.KafkaStream;
import kafka.javaapi.consumer.ConsumerConnector;

public class CustomConsumer {

    @SuppressWarnings("deprecation")
    public static void main(String[] args) {
        Properties properties = new Properties();
        
        properties.put("zookeeper.connect", "hadoop102:2181");
        properties.put("group.id", "g1");
        properties.put("zookeeper.session.timeout.ms", "500");
        properties.put("zookeeper.sync.time.ms", "250");
        properties.put("auto.commit.interval.ms", "1000");
        
        // 创建消费者连接器
        ConsumerConnector consumer = Consumer.createJavaConsumerConnector(new ConsumerConfig(properties));
        
        HashMap<String, Integer> topicCount = new HashMap<>();
        topicCount.put("first", 1);
        
        Map<String, List<KafkaStream<byte[], byte[]>>> consumerMap = consumer.createMessageStreams(topicCount);
        
        KafkaStream<byte[], byte[]> stream = consumerMap.get("first").get(0);
        
        ConsumerIterator<byte[], byte[]> it = stream.iterator();
        
        while (it.hasNext()) {
            System.out.println(new String(it.next().message()));
        }
    }
}
2)官方提供案例(自动维护消费情况)(新API)
package com.test.kafka.consume;
import java.util.Arrays;
import java.util.Properties;
import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;

public class CustomNewConsumer {

    public static void main(String[] args) {

        Properties props = new Properties();
        // 定义kakfa 服务的地址,不需要将所有broker指定上 
        props.put("bootstrap.servers", "hadoop102:9092");
        // 制定consumer group 
        props.put("group.id", "test");
        // 是否自动确认offset 
        props.put("enable.auto.commit", "true");
        // 自动确认offset的时间间隔 
        props.put("auto.commit.interval.ms", "1000");
        // key的序列化类
        props.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        // value的序列化类 
        props.put("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        // 定义consumer 
        KafkaConsumer<String, String> consumer = new KafkaConsumer<>(props);
        
        // 消费者订阅的topic, 可同时订阅多个 
        consumer.subscribe(Arrays.asList("first", "second","third"));

        while (true) {
            // 读取数据,读取超时时间为100ms 
            ConsumerRecords<String, String> records = consumer.poll(100);
            
            for (ConsumerRecord<String, String> record : records)
                System.out.printf("offset = %d, key = %s, value = %s%n", record.offset(), record.key(), record.value());
        }
    }
}

低级API

实现使用低级API读取指定topic,指定partition,指定offset的数据。

1)消费者使用低级API 的主要步骤:

步骤 主要工作
1 根据指定的分区从主题元数据中找到主副本
2 获取分区最新的消费进度
3 从主副本拉取分区的消息
4 识别主副本的变化,重试

2)方法描述:

findLeader() 客户端向种子节点发送主题元数据,将副本集加入备用节点
getLastOffset() 消费者客户端发送偏移量请求,获取分区最近的偏移量
run() 消费者低级AP I拉取消息的主要方法
findNewLeader() 当分区的主副本节点发生故障,客户将要找出新的主副本

3)代码:

package com.test;
import java.nio.ByteBuffer;
import java.util.ArrayList;
import java.util.Collections;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

import kafka.api.FetchRequest;
import kafka.api.FetchRequestBuilder;
import kafka.api.PartitionOffsetRequestInfo;
import kafka.cluster.BrokerEndPoint;
import kafka.common.ErrorMapping;
import kafka.common.TopicAndPartition;
import kafka.javaapi.FetchResponse;
import kafka.javaapi.OffsetResponse;
import kafka.javaapi.PartitionMetadata;
import kafka.javaapi.TopicMetadata;
import kafka.javaapi.TopicMetadataRequest;
import kafka.javaapi.consumer.SimpleConsumer;
import kafka.message.MessageAndOffset;

public class SimpleExample {
    private List<String> m_replicaBrokers = new ArrayList<>();

    public SimpleExample() {
        m_replicaBrokers = new ArrayList<>();
    }

    public static void main(String args[]) {
        SimpleExample example = new SimpleExample();
        // 最大读取消息数量
        long maxReads = Long.parseLong("3");
        // 要订阅的topic
        String topic = "test1";
        // 要查找的分区
        int partition = Integer.parseInt("0");
        // broker节点的ip
        List<String> seeds = new ArrayList<>();
        seeds.add("192.168.9.102");
        seeds.add("192.168.9.103");
        seeds.add("192.168.9.104");
        // 端口
        int port = Integer.parseInt("9092");
        try {
            example.run(maxReads, topic, partition, seeds, port);
        } catch (Exception e) {
            System.out.println("Oops:" + e);
            e.printStackTrace();
        }
    }

    public void run(long a_maxReads, String a_topic, int a_partition, List<String> a_seedBrokers, int a_port) throws Exception {
        // 获取指定Topic partition的元数据
        PartitionMetadata metadata = findLeader(a_seedBrokers, a_port, a_topic, a_partition);
        if (metadata == null) {
            System.out.println("Can't find metadata for Topic and Partition. Exiting");
            return;
        }
        if (metadata.leader() == null) {
            System.out.println("Can't find Leader for Topic and Partition. Exiting");
            return;
        }
        String leadBroker = metadata.leader().host();
        String clientName = "Client_" + a_topic + "_" + a_partition;

        SimpleConsumer consumer = new SimpleConsumer(leadBroker, a_port, 100000, 64 * 1024, clientName);
        long readOffset = getLastOffset(consumer, a_topic, a_partition, kafka.api.OffsetRequest.EarliestTime(), clientName);
        int numErrors = 0;
        while (a_maxReads > 0) {
            if (consumer == null) {
                consumer = new SimpleConsumer(leadBroker, a_port, 100000, 64 * 1024, clientName);
            }
            FetchRequest req = new FetchRequestBuilder().clientId(clientName).addFetch(a_topic, a_partition, readOffset, 100000).build();
            FetchResponse fetchResponse = consumer.fetch(req);

            if (fetchResponse.hasError()) {
                numErrors++;
                // Something went wrong!
                short code = fetchResponse.errorCode(a_topic, a_partition);
                System.out.println("Error fetching data from the Broker:" + leadBroker + " Reason: " + code);
                if (numErrors > 5)
                    break;
                if (code == ErrorMapping.OffsetOutOfRangeCode()) {
                    // We asked for an invalid offset. For simple case ask for
                    // the last element to reset
                    readOffset = getLastOffset(consumer, a_topic, a_partition, kafka.api.OffsetRequest.LatestTime(), clientName);
                    continue;
                }
                consumer.close();
                consumer = null;
                leadBroker = findNewLeader(leadBroker, a_topic, a_partition, a_port);
                continue;
            }
            numErrors = 0;

            long numRead = 0;
            for (MessageAndOffset messageAndOffset : fetchResponse.messageSet(a_topic, a_partition)) {
                long currentOffset = messageAndOffset.offset();
                if (currentOffset < readOffset) {
                    System.out.println("Found an old offset: " + currentOffset + " Expecting: " + readOffset);
                    continue;
                }
                readOffset = messageAndOffset.nextOffset();
                ByteBuffer payload = messageAndOffset.message().payload();

                byte[] bytes = new byte[payload.limit()];
                payload.get(bytes);
                System.out.println(String.valueOf(messageAndOffset.offset()) + ": " + new String(bytes, "UTF-8"));
                numRead++;
                a_maxReads--;
            }

            if (numRead == 0) {
                try {
                    Thread.sleep(1000);
                } catch (InterruptedException ie) {
                }
            }
        }
        if (consumer != null)
            consumer.close();
    }

    public static long getLastOffset(SimpleConsumer consumer, String topic, int partition, long whichTime, String clientName) {
        TopicAndPartition topicAndPartition = new TopicAndPartition(topic, partition);
        Map<TopicAndPartition, PartitionOffsetRequestInfo> requestInfo = new HashMap<TopicAndPartition, PartitionOffsetRequestInfo>();
        requestInfo.put(topicAndPartition, new PartitionOffsetRequestInfo(whichTime, 1));
        kafka.javaapi.OffsetRequest request = new kafka.javaapi.OffsetRequest(requestInfo, kafka.api.OffsetRequest.CurrentVersion(), clientName);
        OffsetResponse response = consumer.getOffsetsBefore(request);

        if (response.hasError()) {
            System.out.println("Error fetching data Offset Data the Broker. Reason: " + response.errorCode(topic, partition));
            return 0;
        }
        long[] offsets = response.offsets(topic, partition);
        return offsets[0];
    }


    private String findNewLeader(String a_oldLeader, String a_topic, int a_partition, int a_port) throws Exception {
        for (int i = 0; i < 3; i++) {
            boolean goToSleep = false;
            PartitionMetadata metadata = findLeader(m_replicaBrokers, a_port, a_topic, a_partition);
            if (metadata == null) {
                goToSleep = true;
            } else if (metadata.leader() == null) {
                goToSleep = true;
            } else if (a_oldLeader.equalsIgnoreCase(metadata.leader().host()) && i == 0) {
                // first time through if the leader hasn't changed give
                // ZooKeeper a second to recover
                // second time, assume the broker did recover before failover,
                // or it was a non-Broker issue
                //
                goToSleep = true;
            } else {
                return metadata.leader().host();
            }
            if (goToSleep) {
                    Thread.sleep(1000);
            }
        }
        System.out.println("Unable to find new leader after Broker failure. Exiting");
        throw new Exception("Unable to find new leader after Broker failure. Exiting");
    }

    private PartitionMetadata findLeader(List<String> a_seedBrokers, int a_port, String a_topic, int a_partition) {
        PartitionMetadata returnMetaData = null;
        loop:
        for (String seed : a_seedBrokers) {
            SimpleConsumer consumer = null;
            try {
                consumer = new SimpleConsumer(seed, a_port, 100000, 64 * 1024, "leaderLookup");
                List<String> topics = Collections.singletonList(a_topic);
                TopicMetadataRequest req = new TopicMetadataRequest(topics);
                kafka.javaapi.TopicMetadataResponse resp = consumer.send(req);

                List<TopicMetadata> metaData = resp.topicsMetadata();
                for (TopicMetadata item : metaData) {
                    for (PartitionMetadata part : item.partitionsMetadata()) {
                        if (part.partitionId() == a_partition) {
                            returnMetaData = part;
                            break loop;
                        }
                    }
                }
            } catch (Exception e) {
                System.out.println("Error communicating with Broker [" + seed + "] to find Leader for [" + a_topic + ", " + a_partition + "] Reason: " + e);
            } finally {
                if (consumer != null)
                    consumer.close();
            }
        }
        if (returnMetaData != null) {
            m_replicaBrokers.clear();
            for (BrokerEndPoint replica : returnMetaData.replicas()) {
                m_replicaBrokers.add(replica.host());
            }
        }
        return returnMetaData;
    }
}
最后编辑于
©著作权归作者所有,转载或内容合作请联系作者
  • 序言:七十年代末,一起剥皮案震惊了整个滨河市,随后出现的几起案子,更是在滨河造成了极大的恐慌,老刑警刘岩,带你破解...
    沈念sama阅读 151,688评论 1 330
  • 序言:滨河连续发生了三起死亡事件,死亡现场离奇诡异,居然都是意外死亡,警方通过查阅死者的电脑和手机,发现死者居然都...
    沈念sama阅读 64,559评论 1 273
  • 文/潘晓璐 我一进店门,熙熙楼的掌柜王于贵愁眉苦脸地迎上来,“玉大人,你说我怎么就摊上这事。” “怎么了?”我有些...
    开封第一讲书人阅读 101,749评论 0 226
  • 文/不坏的土叔 我叫张陵,是天一观的道长。 经常有香客问我,道长,这世上最难降的妖魔是什么? 我笑而不...
    开封第一讲书人阅读 42,581评论 0 191
  • 正文 为了忘掉前任,我火速办了婚礼,结果婚礼上,老公的妹妹穿的比我还像新娘。我一直安慰自己,他们只是感情好,可当我...
    茶点故事阅读 50,741评论 3 271
  • 文/花漫 我一把揭开白布。 她就那样静静地躺着,像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上,一...
    开封第一讲书人阅读 39,684评论 1 192
  • 那天,我揣着相机与录音,去河边找鬼。 笑死,一个胖子当着我的面吹牛,可吹牛的内容都是我干的。 我是一名探鬼主播,决...
    沈念sama阅读 31,122评论 2 292
  • 文/苍兰香墨 我猛地睁开眼,长吁一口气:“原来是场噩梦啊……” “哼!你这毒妇竟也来了?” 一声冷哼从身侧响起,我...
    开封第一讲书人阅读 29,847评论 0 182
  • 序言:老挝万荣一对情侣失踪,失踪者是张志新(化名)和其女友刘颖,没想到半个月后,有当地人在树林里发现了一具尸体,经...
    沈念sama阅读 33,441评论 0 228
  • 正文 独居荒郊野岭守林人离奇死亡,尸身上长有42处带血的脓包…… 初始之章·张勋 以下内容为张勋视角 年9月15日...
    茶点故事阅读 29,939评论 2 232
  • 正文 我和宋清朗相恋三年,在试婚纱的时候发现自己被绿了。 大学时的朋友给我发了我未婚夫和他白月光在一起吃饭的照片。...
    茶点故事阅读 31,333评论 1 242
  • 序言:一个原本活蹦乱跳的男人离奇死亡,死状恐怖,灵堂内的尸体忽然破棺而出,到底是诈尸还是另有隐情,我是刑警宁泽,带...
    沈念sama阅读 27,783评论 2 236
  • 正文 年R本政府宣布,位于F岛的核电站,受9级特大地震影响,放射性物质发生泄漏。R本人自食恶果不足惜,却给世界环境...
    茶点故事阅读 32,275评论 3 220
  • 文/蒙蒙 一、第九天 我趴在偏房一处隐蔽的房顶上张望。 院中可真热闹,春花似锦、人声如沸。这庄子的主人今日做“春日...
    开封第一讲书人阅读 25,830评论 0 8
  • 文/苍兰香墨 我抬头看了看天上的太阳。三九已至,却和暖如春,着一层夹袄步出监牢的瞬间,已是汗流浃背。 一阵脚步声响...
    开封第一讲书人阅读 26,444评论 0 180
  • 我被黑心中介骗来泰国打工, 没想到刚下飞机就差点儿被人妖公主榨干…… 1. 我叫王不留,地道东北人。 一个月前我还...
    沈念sama阅读 34,553评论 2 249
  • 正文 我出身青楼,却偏偏与公主长得像,于是被迫代替她去往敌国和亲。 传闻我的和亲对象是个残疾皇子,可洞房花烛夜当晚...
    茶点故事阅读 34,618评论 2 249

推荐阅读更多精彩内容

  • kafka的定义:是一个分布式消息系统,由LinkedIn使用Scala编写,用作LinkedIn的活动流(Act...
    时待吾阅读 5,229评论 1 15
  • 本文转载自http://dataunion.org/?p=9307 背景介绍Kafka简介Kafka是一种分布式的...
    Bottle丶Fish阅读 5,340评论 0 34
  • 本文是对Kafka的一个学习总结,共包括如下内容: 概述 基本结构 重要概念 快速起步 Java API 参考资料...
    我是老薛阅读 1,270评论 0 4
  • 在我决定记录下这躁郁之旅的点点滴滴之前,我曾尝试曲线救国:先为别人写作,让别人认可我,然后我才可以倾倒真实的我,让...
    璐囍法阅读 535评论 2 6
  • #!/usr/bin/env python # -*- coding: utf-8 -*- u"""文档说明(编码...
    AGRH1209阅读 197评论 0 0