#创建项目目录

mkdir zookeeper

cd zookeeper

mkdir tmp

mkdir zookeeper-1

mkdir zookeeper-2

mkdir zookeeper-3

cd tmp

mkdir zk1

mkdir zk2

mkdir zk3

cd zk1

mkdir data

mkdir log

cd zk2

mkdir data

mkdir log

cd zk3

mkdir data

mkdir log

#将压缩包分别解压一份到 zookeeper-1, zookeeper-2, zookeeper-3目录下

tar -zxvf zookeeper-3.4.10.tgz

initLimit=10

syncLimit=5

dataDir=/home/hadoop/tmp/zk1/data

dataLogDir=/home/hadoop/tmp/zk1/log

clientPort=2181

server.1=192.168.68.128:2287:3387

server.2=192.168.68.128:2288:3388

server.3=192.168.68.128:2289:3389

initLimit=10

syncLimit=5

dataDir=/home/hadoop/tmp/zk2/data

dataLogDir=/home/hadoop/tmp/zk2/log

clientPort=2182

server.1=192.168.68.128:2287:3387

server.2=192.168.68.128:2288:3388

server.3=192.168.68.128:2289:3389

initLimit=10

syncLimit=5

dataDir=/home/hadoop/tmp/zk3/data

dataLogDir=/home/hadoop/tmp/zk3/log

clientPort=2183

server.1=192.168.68.128:2287:3387

server.2=192.168.68.128:2288:3388

server.3=192.168.68.128:2289:3389

#创建项目目录

mkdir kafka

cd kafka

mkdir tmp

cd tmp

#创建kafka消息目录，主要存放kafka消息

mkdir  kafka-logs-1

mkdir  kafka-logs-2

mkdir  kafka-logs-3

#将压缩包放到usr/kafka内，解压

tar -zxvf kafka_2.10-0.10.1.0.tgz

# 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 = security_protocol://host_name:port

#   EXAMPLE:

#     listeners = PLAINTEXT://your.host.name:9092

#listeners=PLAINTEXT://: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://your.host.name:9092

# 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

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.

#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=localhost:2181

# Timeout in ms for connecting to zookeeper

zookeeper.connection.timeout.ms=6000

listeners=PLAINTEXT://192.168.68.128:9092

log.dirs=/usr/kafka/tmp/kafka-logs-1

zookeeper.connect=192.168.68.128:2181,192.168.68.128:2182,192.168.68.128:2183

listeners=PLAINTEXT://192.168.68.128:9092

log.dirs=/usr/kafka/tmp/kafka-logs-2

zookeeper.connect=192.168.68.128:2181,192.168.68.128:2182,192.168.68.128:2183

listeners=PLAINTEXT://192.168.68.128:9092

log.dirs=/usr/kafka/tmp/kafka-logs-3

zookeeper.connect=192.168.68.128:2181,192.168.68.128:2182,192.168.68.128:2183

import java.util.Properties;

import java.util.concurrent.TimeUnit;

import kafka.javaapi.producer.Producer;

import kafka.producer.KeyedMessage;

import kafka.producer.ProducerConfig;

import kafka.serializer.StringEncoder;

/**

* @author liangyadong

* @date 2017年5月26日 下午3:04:07

* @version 1.0

*/

public class KafkaProducer {

private String topic;

public KafkaProducer(String topic){

super();

this.topic = topic;

}

public void run(){

Producer producer = createProducer();

int i = 0;

while(true){

producer.send(new KeyedMessage<Integer, String>(topic, "message:" + i++));

try{

TimeUnit.SECONDS.sleep(1);

} catch(InterruptedException e) {

e.printStackTrace();

}

}

}

private Producer createProducer(){

Properties properties = new Properties();

properties.put("zookeeper.connect", "192.168.68.128:2181,192.168.68.128:2182,192.168.68.128:2183");// 声明zookeeper

properties.put("serializer.class", StringEncoder.class.getName());

properties.put("metadata.broker.list", "192.168.68.128:9092,192.168.68.128:9093,192.168.68.128:9094");// 声明kafka

return new Producer<Integer,String>(new ProducerConfig(properties));

}

public static void main(String[] args) {

new KafkaProducer("test111").run();// 创建主题,发送消息

}

}

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;

/**

* @author liangyadong

* @date 2017年5月26日 下午4:01:37

* @version 1.0

*/

public class KafkaConsumer extends Thread{

private String topic;

public KafkaConsumer(String topic){

super();

this.topic = topic;

}

public void run() {

ConsumerConnector consumer = createConsumer();

Map<String, Integer> topicCountMap = new HashMap<String, Integer>();

topicCountMap.put(topic, 1); // 一次从主题中获取一个数据

Map<String, List<KafkaStream<byte[], byte[]>>>  messageStreams = consumer.createMessageStreams(topicCountMap);

KafkaStream<byte[], byte[]> stream = messageStreams.get(topic).get(0);// 获取每次接收到的这个数据

ConsumerIterator<byte[], byte[]> iterator =  stream.iterator();

while(iterator.hasNext()){

String message = new String(iterator.next().message());

System.out.println("接收到: " + message);

}

}

private ConsumerConnector createConsumer(){

Properties properties = new Properties();

properties.put("zookeeper.connect", "192.168.68.128:2181,192.168.68.128:2182,192.168.68.128:2183");// 声明zookeeper

properties.put("group.id", "group5");// 必须要使用别的组名称， 如果生产者和消费者都在同一组，则不能访问同一组内的topic数据

return Consumer.createJavaConsumerConnector(new ConsumerConfig(properties));

}

public static void main(String[] args) {

new KafkaConsumer("test111").run();// 使用kafka集群中创建好的主题 test

}

}

接收到: message:2

接收到: message:3

接收到: message:4

接收到: message:5

接收到: message:6

...