Linux安装Kafka，并使用Flink连接读取Kafka

文章目录

前言

一、获取Kafka安装包

二、安装步骤

1.解压文件

2.重命名

3.设置环境变量

4.使环境变量生效

三、启动Kafka

1.先启动ZooKeeper服务

2.启动kafka服务

3.创建一个名为"topTest"的topic

4.打开Producer（生产者）服务

5.打开Customer（消费者）服务

四，Java连接kafka

1.maven依赖

2.实体类

3.连接工具类

4.运行

五，Flink连接读取Kafka

1.主方法类

2.运行

---

 

---

前言

Kafka是一种高吞吐量的分布式发布订阅消息系统，它可以处理消费者在网站中的所有动作流数据。

---

一、获取Kafka安装包

wget http://mirror.bit.edu.cn/apache/kafka/2.3.1/kafka_2.11-2.3.1.tgz

二、安装步骤

1.解压文件

tar -zxvf kafka_2.11-2.3.1.tgz

2.重命名

mv kafka_2.11-2.3.1 kafka

3.设置环境变量

vim /etc/profile
export KAFKA_HOME=/opt/kafka
export PATH=$PATH:$KAFKA_HOME/bin

4.使环境变量生效

source /etc/profile

三、启动Kafka

1.先启动ZooKeeper服务

bin/zookeeper-server-start.sh config/zookeeper.properties

2.启动kafka服务

bin/kafka-server-start.sh config/server.properties

3.创建一个名为"topTest"的topic

bin/kafka-topics.sh --create --zookeeper localhost:2181 --replication-factor 1 --partitions 1 --topic topTest

4.打开Producer（生产者）服务

bin/kafka-console-producer.sh --broker-list localhost:9092 --topic topTest

5.打开Customer（消费者）服务

bin/kafka-console-consumer.sh --bootstrap-server localhost:9092 --topic topTest--from-beginning

  

  

四，Java连接kafka

1.maven依赖

    <properties>
        <java.version>1.8</java.version>
        <flink.version>1.6.1</flink.version>
        <scala.binary.version>2.11</scala.binary.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter</artifactId>
        </dependency>

        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-test</artifactId>
            <scope>test</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <!--flink kafka connector-->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka-0.11_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>

2.实体类

package com.flink.model;

import java.util.Map;

public class Metric {
    public String name;
    public long timestamp;
    public Map<String, Object> fields;
    public Map<String, String> tags;

    public Metric() {
    }

    public Metric(String name, long timestamp, Map<String, Object> fields, Map<String, String> tags) {
        this.name = name;
        this.timestamp = timestamp;
        this.fields = fields;
        this.tags = tags;
    }

    @Override
    public String toString() {
        return "Metric{" +
                "name='" + name + '\'' +
                ", timestamp='" + timestamp + '\'' +
                ", fields=" + fields +
                ", tags=" + tags +
                '}';
    }

    public String getName() {
        return name;
    }

    public void setName(String name) {
        this.name = name;
    }

    public long getTimestamp() {
        return timestamp;
    }

    public void setTimestamp(long timestamp) {
        this.timestamp = timestamp;
    }

    public Map<String, Object> getFields() {
        return fields;
    }

    public void setFields(Map<String, Object> fields) {
        this.fields = fields;
    }

    public Map<String, String> getTags() {
        return tags;
    }

    public void setTags(Map<String, String> tags) {
        this.tags = tags;
    }
}

3.连接工具类

package com.flink.kafka;

import com.alibaba.fastjson.JSON;
import com.flink.model.Metric;
import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.ProducerRecord;

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

public class KafkaUtils {
    public static final String broker_list = "node1:9092";
    public static final String topic = "topTest";  // kafka topic，Flink 程序中需要和这个统一

    public static void writeToKafka() throws InterruptedException {
        Properties props = new Properties();
        props.put("bootstrap.servers", broker_list);
        props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer"); //key 序列化
        props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer"); //value 序列化
        KafkaProducer producer = new KafkaProducer<String, String>(props);

        Metric metric = new Metric();
        metric.setTimestamp(System.currentTimeMillis());
        metric.setName("mem");
        Map<String, String> tags = new HashMap<>();
        Map<String, Object> fields = new HashMap<>();

        tags.put("cluster", "阵雨");
        tags.put("host_ip", "localhost");

        fields.put("used_percent", 90d);
        fields.put("max", 27244873d);
        fields.put("used", 17244873d);
        fields.put("init", 27244873d);

        metric.setTags(tags);
        metric.setFields(fields);

        ProducerRecord record = new ProducerRecord<String, String>(topic, null, null, JSON.toJSONString(metric));
        producer.send(record);
        System.out.println("发送数据: " + JSON.toJSONString(metric));

        producer.flush();
    }

    public static void main(String[] args) throws InterruptedException {
        while (true) {
            Thread.sleep(300);
            writeToKafka();
        }
    }
}

4.运行

五，Flink连接读取Kafka

1.主方法类

package com.flink.kafka;

import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer011;

import java.util.Properties;

public class Main {
    public static void main(String[] args) throws Exception {
        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        Properties props = new Properties();
        props.put("bootstrap.servers", "node1:9092");
        props.put("zookeeper.connect", "node1:2181");
        props.put("group.id", "metric-group");
        props.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");  //key 反序列化
        props.put("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        props.put("auto.offset.reset", "latest"); //value 反序列化

        DataStreamSource<String> dataStreamSource = env.addSource(new FlinkKafkaConsumer011<>(
                "topTest",  //kafka topic
                new SimpleStringSchema(),  // String 序列化
                props)).setParallelism(1);

        dataStreamSource.print(); //把从 kafka 读取到的数据打印在控制台

        env.execute("Flink add data source");
    }
}

2.运行

---

总结

本文总结了linux安装kafka的步骤，以及Flink通过Java连接读取Kafka的方式。