Kafka速览

1.集群规划
    使用3台机器部署，分别是node01、node02、node03
2.下载Kafka安装包
    下载地址http://kafka.apache.org/downloads，选择Kafka版本kafka_2.11-0.10.2.1.tgz
3.安装kafka
    将安装包上传到其中一台机器node01上，并解压到/bigdata目录下：tar -zxvf kafka_2.11-0.10.2.1.tgz
    创建软连接：ln -s /bigdata/kafka_2.11-0.10.2.1 /usr/local/kafka
4.添加到环境变量：vim /etc/profile
    添加内容：export KAFKA_HOME=/usr/local/kafka
            export PATH=$PATH:${KAFKA_HOME}/bin
    刷新环境变量：source /etc/profile
5.修改配置文件
    cd /usr/local/kafka/config
    vim server.properties
6.在/usr/local/kafka中创建kafka-logs文件夹
    mkdir /usr/local/kafka/kafka-logs
7.使用scp将配置好的kafka安装包拷贝到node02和node03两个节点
    scp -r /bigdata/kafka_2.11-0.10.2.1 root@node02:/bigdata/
    scp -r /bigdata/kafka_2.11-0.10.2.1 root@node03:/bigdata/
8.分别修改node02和node03的配置文件server.properties 具体文件在下面
    8.1 node02的server.properties修改项
    broker.id=1
    host.name=node02
    8.2 node03的server.properties修改项
    broker.id=2
    host.name=node03
9.分别在node01、node02、node03启动kafka
    cd /usr/local/kafka
    启动的时候使用-daemon选项，则kafka将以守护进程的方式启动
    bin/kafka-server-start.sh -daemon config/server.properties
10.日志目录
    默认在kafka安装路径生成的logs文件夹中

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

#每个borker的id是唯一的，多个broker要设置不同的id
broker.id=0

#访问端口号
port=9092

#访问地址
host.name=node01

#允许删除topic
delete.topic.enable=true


# 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 #############################

#存储数据路径，默认是在/tmp目录下，需要修改
log.dirs=/usr/local/kafka/kafka-logs

#创建topic默认分区数
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.

#数据保存时间，默认7天，单位小时
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地址，多个地址用逗号隔开
zookeeper.connect=node01:2181,node02:2181,node03:2181

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

创建主题
bin/kafka-topics.sh --create --zookeeper node01:2181 --topic topic1 --replication-factor 2 --partitions 2

查看主题信息
bin/kafka-topics.sh --describe --zookeeper node01:2181 --topic topic1

查看kafka中已经创建的主题列表
bin/kafka-topics.sh --list --zookeeper node01:2181

使用kafka自带的生产者客户端脚本
bin/kafka-console-producer.sh --broker-list node01:9092,node02:9092,node03:9092 --topic topic1

使用kafka自带的消费者客户端脚本
bin/kafka-console-consumer.sh --zookeeper node01:2181 --from-beginning --topic topic1

删除topic：
bin/kafka-topics.sh --delete --zookeeper node01:2181 --topic topic1

增加分区
bin/kafka-topics.sh --alter --zookeeper node01:2181 --topic topic1 --partitions 3

public class Producer extends Thread
{
  private final kafka.javaapi.producer.Producer<Integer, String> producer;
  private final String topic;
  private final Properties props = new Properties();

  public Producer(String topic)
  {
    props.put("serializer.class", "kafka.serializer.StringEncoder"); // 定义message的类型为字符串
   props.put("metadata.broker.list", KafkaProperties.broker_list);
    // Use random partitioner. Don't need the key type. Just set it to Integer.
    // The message is of type String.
    producer = new kafka.javaapi.producer.Producer<Integer, String>(new ProducerConfig(props));
    this.topic = topic;
  }
  
  public void run() {
    int messageNo = 1;
    while(true)
    {
      String messageStr = new String("Message_" + messageNo);
      producer.send(new KeyedMessage<Integer, String>(topic, messageStr));
      System.out.println("已生成数据： " + messageStr);
      messageNo++;
    }
  }

  public static void main(String[] args) {
    Producer producerThread = new Producer(KafkaProperties.TestTopic);
    producerThread.start();
  }
}

public class Consumer extends Thread
{
  private final ConsumerConnector consumer;
  private final String topic;
  
  public Consumer(String topic)
  {
    consumer = kafka.consumer.Consumer.createJavaConsumerConnector(
            createConsumerConfig());
    this.topic = topic;
  }

  private static ConsumerConfig createConsumerConfig()
  {
    Properties props = new Properties();
    props.put("zookeeper.connect", KafkaProperties.zkConnect);
    props.put("group.id", KafkaProperties.groupId);
    props.put("zookeeper.session.timeout.ms", "400");
    props.put("zookeeper.sync.time.ms", "200");
    props.put("auto.commit.interval.ms", "1000"); // 多久更新一次offset

    return new ConsumerConfig(props);

  }
 
  public void run() {
    Map<String, Integer> topicCountMap = new HashMap<String, Integer>();
    topicCountMap.put(topic, new Integer(1));
    Map<String, List<KafkaStream<byte[], byte[]>>> consumerMap = consumer.createMessageStreams(topicCountMap);
   KafkaStream<byte[], byte[]> stream =  consumerMap.get(topic).get(0);
    ConsumerIterator<byte[], byte[]> it = stream.iterator();
    while(it.hasNext())
      System.out.println(new String(it.next().message()));
  }

  public static void main(String[] args) {
    Consumer consumerThread = new Consumer(KafkaProperties.topic);
    consumerThread.start();
  }
}