http://download.csdn.net/download/liangmaoxuan/10228805

1. kafka_2.10-0.10.2.0.tar

1.解压kafka_2.10-0.10.2.0安装包

tar -xvf kafka_2.10-0.10.2.0.tar  

2.配置kafka

cd /software/kafka_2.10-0.10.2.0/conf

(1) server.properties

# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# see kafka.server.KafkaConfig for additional details and defaults

############################# Server Basics #############################

# The id of the broker. This must be set to a unique integer for each broker.
broker.id=0

# Switch to enable topic deletion or not, default value is false
#delete.topic.enable=true

############################# Socket Server Settings #############################

# The address the socket server listens on. It will get the value returned from 
# java.net.InetAddress.getCanonicalHostName() if not configured.
#   FORMAT:
#     listeners = listener_name://host_name:port
#   EXAMPLE:
#     listeners = PLAINTEXT://your.host.name:9092
listeners=PLAINTEXT://192.168.1.104:9092

# Hostname and port the broker will advertise to producers and consumers. If not set, 
# it uses the value for "listeners" if configured.  Otherwise, it will use the value
# returned from java.net.InetAddress.getCanonicalHostName().

advertised.listeners=PLAINTEXT://192.168.1.104:9092
hostname=192.168.1.104


# Maps listener names to security protocols, the default is for them to be the same. See the config documentation for more details
#listener.security.protocol.map=PLAINTEXT:PLAINTEXT,SSL:SSL,SASL_PLAINTEXT:SASL_PLAINTEXT,SASL_SSL:SASL_SSL

# The number of threads handling network requests
num.network.threads=3

# The number of threads doing disk I/O
num.io.threads=8

# The send buffer (SO_SNDBUF) used by the socket server
socket.send.buffer.bytes=102400

# The receive buffer (SO_RCVBUF) used by the socket server
socket.receive.buffer.bytes=102400

# The maximum size of a request that the socket server will accept (protection against OOM)
socket.request.max.bytes=104857600


############################# Log Basics #############################

# A comma seperated list of directories under which to store log files
log.dirs=/tmp/kafka-logs

# The default number of log partitions per topic. More partitions allow greater
# parallelism for consumption, but this will also result in more files across
# the brokers.
num.partitions=1

# The number of threads per data directory to be used for log recovery at startup and flushing at shutdown.
# This value is recommended to be increased for installations with data dirs located in RAID array.
num.recovery.threads.per.data.dir=1

############################# Log Flush Policy #############################

# Messages are immediately written to the filesystem but by default we only fsync() to sync
# the OS cache lazily. The following configurations control the flush of data to disk.
# There are a few important trade-offs here:
#    1. Durability: Unflushed data may be lost if you are not using replication.
#    2. Latency: Very large flush intervals may lead to latency spikes when the flush does occur as there will be a lot of data to flush.
#    3. Throughput: The flush is generally the most expensive operation, and a small flush interval may lead to exceessive seeks.
# The settings below allow one to configure the flush policy to flush data after a period of time or
# every N messages (or both). This can be done globally and overridden on a per-topic basis.

# The number of messages to accept before forcing a flush of data to disk
#log.flush.interval.messages=10000

# The maximum amount of time a message can sit in a log before we force a flush
#log.flush.interval.ms=1000

############################# Log Retention Policy #############################

# The following configurations control the disposal of log segments. The policy can
# be set to delete segments after a period of time, or after a given size has accumulated.
# A segment will be deleted whenever *either* of these criteria are met. Deletion always happens
# from the end of the log.

# The minimum age of a log file to be eligible for deletion due to age
log.retention.hours=168

# A size-based retention policy for logs. Segments are pruned from the log as long as the remaining
# segments don't drop below log.retention.bytes. Functions independently of log.retention.hours.
#log.retention.bytes=1073741824

# The maximum size of a log segment file. When this size is reached a new log segment will be created.
log.segment.bytes=1073741824

# The interval at which log segments are checked to see if they can be deleted according
# to the retention policies
log.retention.check.interval.ms=300000

############################# Zookeeper #############################

# Zookeeper connection string (see zookeeper docs for details).
# This is a comma separated host:port pairs, each corresponding to a zk
# server. e.g. "127.0.0.1:3000,127.0.0.1:3001,127.0.0.1:3002".
# You can also append an optional chroot string to the urls to specify the
# root directory for all kafka znodes.
zookeeper.connect=192.168.1.104:2181

# Timeout in ms for connecting to zookeeper
zookeeper.connection.timeout.ms=6000

3.启动kafka

启动zookeeper：nohup bin/zookeeper-server-start.sh config/zookeeper.properties 1>zookeeper.log 2>zookeeper.err &
启动kafka：nohup bin/kafka-server-start.sh config/server.properties &

4.单机测试：

（1）生产者

bin/kafka-console-producer.sh --broker-list 192.168.1.104:9092 --topic test
输进消息： lmx

（2）消费者

bin/kafka-console-consumer.sh --zookeeper 192.168.1.104:2181 --topic test --from-beginning
收到消息： lmx

4.JAVA代码测试：

（1）配置类：ConfigureAPI.class

package kafkaDemo;

public class ConfigureAPI
{

    public final static String GROUP_ID = "test";

    public final static String TOPIC = "test-lmx";

    public final static int BUFFER_SIZE = 64 * 1024;

    public final static int TIMEOUT = 20000;

    public final static int INTERVAL = 10000;

    public final static String BROKER_LIST = "192.168.1.104:9092,192.168.1.105:9092";

    // 去数据间隔
    public final static int GET_MEG_INTERVAL = 1000;

}

( 2 ) 生产者类：JProducer.class

package kafkaDemo;


import java.util.Properties;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;

import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.Producer;
import org.apache.kafka.clients.producer.ProducerRecord;


public class JProducer implements Runnable
{
    private Producer<String, String> producer;

    public JProducer()
    {
        Properties props = new Properties();

        props.put("bootstrap.servers", ConfigureAPI.BROKER_LIST);
        props.put("acks", "all");
        props.put("retries", 0);
        props.put("batch.size", 16384);
        props.put("linger.ms", 1);
        props.put("buffer.memory", 33554432);
        props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
        props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");
        props.put("request.required.acks", "-1");

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

    }

    @Override
    public void run()
    {
        // TODO Auto-generated method stub
        try
        {
            String data = "hello lmx!";
            producer.send(new ProducerRecord<String, String>(ConfigureAPI.TOPIC, data));
            System.out.println(data);
        }
        catch (Exception e)
        {
            // TODO: handle exception
            e.getStackTrace();
        }
        finally
        {
            producer.close();
        }

    }

    public static void main(String[] args)
    {
        ExecutorService threadPool = Executors.newCachedThreadPool();
        threadPool.execute(new JProducer());
        threadPool.shutdown();
    }

}

执行效果:

package kafkaDemo;


import java.util.Arrays;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.Properties;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;

import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;

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;


public class JConsumer implements Runnable
{

    private KafkaConsumer<String, String> consumer;

    private JConsumer()
    {
        Properties props = new Properties();

        props.put("bootstrap.servers", ConfigureAPI.BROKER_LIST);
        props.put("group.id", ConfigureAPI.GROUP_ID);
        props.put("enable.auto.commit", true);
        props.put("auto.commit.interval.ms", 1000);
        props.put("session.timeout.ms", 30000);
        props.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        props.put("value.deserializer","org.apache.kafka.common.serialization.StringDeserializer");

        consumer = new KafkaConsumer<String, String>(props);
        consumer.subscribe(Arrays.asList(ConfigureAPI.TOPIC)); // 多个topic逗号隔开

    }

    @Override
    public void run()
    {
        // TODO Auto-generated method stub
        while (true)
        {
            System.out.println("poll Server message");
            ConsumerRecords<String, String> records = consumer.poll(ConfigureAPI.GET_MEG_INTERVAL);
            for (ConsumerRecord<String, String> record : records)
            {
                handleMeg(record.value());

            }
        }

    }

    private void handleMeg(String record)
    {

        System.out.println(record);

    }

    public static void main(String[] args)
    {
        ExecutorService threadPool = Executors.newCachedThreadPool();
        threadPool.execute(new JConsumer());
        threadPool.shutdown();
    }
}

执行效果：

JAVA代码demo下载地址：http://download.csdn.net/download/liangmaoxuan/10258460

附属某些错误解决办法：

(1) 错误：Unable to connect to zookeeper server '192.168.1.104:2181' with timeout of 4000 ms   

解决办法:  

1.防火墙要关闭

使用service iptables stop 关闭防火墙  
使用service iptables status确认  
使用chkconfig iptables off禁用防火墙  

2.只打开2181端口

iptables -I INPUT -p tcp --dport 2181 -j ACCEPT

(2) 错误：kafka Failed to send messages after 3 tries  

解决办法:

修改server.properties

listeners=PLAINTEXT://192.168.1.104:9092
advertised.listeners=PLAINTEXT://192.168.1.104:9092
hostname=192.168.1.104

总结不好多多担待，文章只单纯个人总结，如不好勿喷，技术有限，有错漏麻烦指正提出。本人QQ:373965070