Flume之——Flume读取日志数据写入Kafka

转载请注明出处：http://blog.csdn.net/l1028386804/article/details/79366155

一、Flume配置

flume要求1.6以上版本

flume-conf.properties文件配置内容，sinks的输出作为kafka的product

a1.sources = r1
a1.sinks = k1
a1.channels = c1

# Describe/configure the source
a1.sources.r1.type = exec
a1.sources.r1.command = tail -F /home/flume/nginx.log

# Describe the sink
#a1.sinks.k1.type = logger
a1.sinks.k1.type = org.apache.flume.sink.kafka.KafkaSink
a1.sinks.k1.topic = mytopic
a1.sinks.k1.brokerList = 192.168.209.121:9092
a1.sinks.k1.requiredAcks = 1
a1.sinks.k1.batchSize = 20

# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

flume启动

bin/flume-ng agent --conf conf --conf-file conf/flume-conf.properties --name a1 -Dflume.root.logger=INFO,console

二、Kafka消费者

package com.lyz.flume.kafka;

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

import kafka.consumer.ConsumerConfig;
import kafka.consumer.ConsumerIterator;
import kafka.consumer.KafkaStream;
import kafka.javaapi.consumer.ConsumerConnector;
import kafka.serializer.StringDecoder;
import kafka.utils.VerifiableProperties;

/**
 * 消费Flume的数据
 * @author liuyazhuang
 */
public class KafkaConsumer {

    private final ConsumerConnector consumer;

    public KafkaConsumer() {
        Properties props = new Properties();
        //zookeeper 配置
        props.put("zookeeper.connect", "192.168.209.121:2181");

        //group 代表一个消费组
        props.put("group.id", "consumer-group");

        //zk连接超时
        props.put("zookeeper.session.timeout.ms", "4000");
        props.put("zookeeper.sync.time.ms", "200");
        props.put("auto.commit.interval.ms", "1000");
        props.put("auto.offset.reset", "smallest");
        //序列化类
        props.put("serializer.class", "kafka.serializer.StringEncoder");

        ConsumerConfig config = new ConsumerConfig(props);

        consumer = kafka.consumer.Consumer.createJavaConsumerConnector(config);
    }

    public void execute() {
        Map topicCountMap = new HashMap();
        topicCountMap.put("mytopic", new Integer(1));

        StringDecoder keyDecoder = new StringDecoder(new VerifiableProperties());
        StringDecoder valueDecoder = new StringDecoder(new VerifiableProperties());

        Map>> consumerMap = 
                consumer.createMessageStreams(topicCountMap,keyDecoder,valueDecoder);
        KafkaStream stream = consumerMap.get("mytopic").get(0);
        ConsumerIterator it = stream.iterator();
        while (it.hasNext())
            System.out.println(it.next().message());
    }

    public static void main(String[] args) {
        new KafkaConsumer().execute();
    }
}

三、启动命令

启动Zookeeper server： 
bin/zookeeper-server-start.sh config/zookeeper.properties &

启动Kafka server:
bin/kafka-server-start.sh config/server.properties & 

运行producer： 
bin/kafka-console-producer.sh --broker-list 192.168.209.121:9092 --topic mytopic

运行consumer： 
bin/kafka-console-consumer.sh --zookeeper 192.168.209.121:2181 --topic mytopic --from-beginning