kafka环境搭建与实战(2)kafka API实战

kafka环境搭建与实战(1)安装kafka           http://zilongzilong.iteye.com/blog/2267913
kafka环境搭建与实战(2)kafka API实战       http://zilongzilong.iteye.com/blog/2267924

1.maven项目中添加依赖

 

		<!-- kafka -->
		<dependency>
			<groupId>org.apache.kafka</groupId>
			<artifactId>kafka-clients</artifactId>
			<version>0.9.0.0</version>
		</dependency>

 

2.spring集成kafka

与spring集成spring-kafka.xml

 

<?xml version="1.0" encoding="UTF-8"?>
<beans xmlns="http://www.springframework.org/schema/beans"
	xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:beans="http://www.springframework.org/schema/beans"
	xsi:schemaLocation="
    http://www.springframework.org/schema/beans 
    http://www.springframework.org/schema/beans/spring-beans.xsd">

	<bean id="testProducer" class="org.apache.kafka.clients.producer.KafkaProducer" scope="prototype">
		<constructor-arg type="java.util.Properties">
			<props>
				<prop key="bootstrap.servers">kafka0:9092,kafka1:9092,kafka2</prop>
				<prop key="acks">all</prop>
				<prop key="retries">0</prop>
				<prop key="batch.size">16384</prop>
				<prop key="linger.ms">1</prop>
				<prop key="buffer.memory">33554432</prop>
				<prop key="key.serializer">org.apache.kafka.common.serialization.StringSerializer</prop>
				<prop key="value.serializer">org.apache.kafka.common.serialization.StringSerializer</prop>
				<prop key="partitioner.class">com.***.kafka.Partitioner.RandomPartitioner</prop>
			</props>
		</constructor-arg>
	</bean>

	<bean id="group1Consumer" class="org.apache.kafka.clients.consumer.KafkaConsumer" scope="prototype">
		<constructor-arg type="java.util.Properties">
			<props>
				<prop key="bootstrap.servers">kafka0:9092,kafka1:9092,kafka2:9092</prop>
				<prop key="group.id">group1</prop>
				<prop key="enable.auto.commit">true</prop>
				<prop key="auto.commit.interval.ms">1000</prop>
				<prop key="session.timeout.ms">30000</prop>
				<prop key="key.deserializer">org.apache.kafka.common.serialization.StringDeserializer</prop>
				<prop key="value.deserializer">org.apache.kafka.common.serialization.StringDeserializer</prop>
			</props>
		</constructor-arg>
	</bean>

	<bean id="group2Consumer" class="org.apache.kafka.clients.consumer.KafkaConsumer" scope="prototype">
		<constructor-arg type="java.util.Properties">
			<props>
				<prop key="bootstrap.servers">kafka0:9092,kafka1:9092,kafka2:9092</prop>
				<prop key="group.id">group2</prop>
				<prop key="enable.auto.commit">true</prop>
				<prop key="auto.commit.interval.ms">1000</prop>
				<prop key="session.timeout.ms">30000</prop>
				<prop key="key.deserializer">org.apache.kafka.common.serialization.StringDeserializer</prop>
				<prop key="value.deserializer">org.apache.kafka.common.serialization.StringDeserializer</prop>
			</props>
		</constructor-arg>
	</bean>
</beans>

 

3.producer使用

自己的partion策略类

public class RandomPartitioner implements Partitioner {
	@Override
	public void configure(Map<String, ?> configs) {

	}

	@Override
	public int partition(String topic, Object key, byte[] keyBytes, Object value, byte[] valueBytes, Cluster cluster) {
		Random random = new Random();
		List<PartitionInfo> partitions = cluster.partitionsForTopic(topic);
		int numPartitions = partitions.size();
		if (numPartitions > 0) {
			return Math.abs(random.nextInt()) % numPartitions;
		} else {
			return 0;
		}
	}

	@Override
	public void close() {

	}
}

 

public class ProducerUtil {
	private static Producer<String, String> producer = SpringContextHolder.getBean("testProducer");
	public static void produce(String message) {
		producer.send(new ProducerRecord<String, String>("test",message));
	}
}

 

4.consumer使用

public class KafkaServletContextListener implements ServletContextListener {
	@Override
	public void contextInitialized(ServletContextEvent sce) {
		ExecutorService executor = Executors.newFixedThreadPool(2);
		executor.execute(new Runnable() {
			@Override
			public void run() {
				KafkaConsumer<String, String> consumer = SpringContextHolder.getBean("group1Consumer");
				consumer.subscribe(Arrays.asList("test"));
				while (true) {
					ConsumerRecords<String, String> records = consumer.poll(100);
					for (ConsumerRecord<String, String> record : records) {
						record.key();
						record.offset();
						record.partition();
						record.topic();
						record.value();
						//TODO
					}
				}
			}
		});
		executor.execute(new Runnable() {
			@Override
			public void run() {
				KafkaConsumer<String, String> consumer = SpringContextHolder.getBean("group2Consumer");
				consumer.subscribe(Arrays.asList("test"));
				while (true) {
					ConsumerRecords<String, String> records = consumer.poll(100);
					for (ConsumerRecord<String, String> record : records) {
						record.key();
						record.offset();
						record.partition();
						record.topic();
						record.value();
						//TODO
					}
				}
			}
		});
	}

	@Override
	public void contextDestroyed(ServletContextEvent sce) {
		
	}
}

 

   在web.xml中添加listener

   

	<listener>
		<listener-class>com.***.web.listener.KafkaServletContextListener</listener-class>
	</listener>

 

5.kafka中遇到的错误

    5.1 消费者在消费消息的时候，一直报如下错误：

ILLEGAL_GENERATION occurred while committing offsets for group

    在网上找到一篇文章http://comments.gmane.org/gmane.comp.apache.kafka.user/10708，但是按照这个调整了auto.commit.interval.ms和session.timeout.ms，但是还是无济于事。

    最后的根本解决办法是，优化消费者的处理逻辑，因为我在消费这种用到了jredis，jredis中对于exist、get时间复杂度为o（1），而smembers方法时间复杂度为o（N），我做的是一是优化代码，二是尽量优先用jredis中对于exist、get方法，然后部署上去，问题经观察，没有出现了。

    总之，解决办法是优化消费者代码，减少耗时，让消费者能及时反馈消费状态给zookeeper