kafka同一个gruopid下多个consumer订阅同一个topic，只有一个consumer能消费到数据

发布于 2022-01-05 11:19:33 字数 8430 浏览 486 评论 6

kafka 版本 kafka_2.10-0.8.2.2

启动两个consumer同时订阅topic “test” ；groupid都为test1；producter向test发送10条数据，结果全部数据都被一个consumer接收到了，另外一个consumer没有接受到任何数据；

同一个groupid下的多个consumer订阅同一个topic是怎样做负载均衡的呢？感觉这里没有做负载均衡处理；

consumer代码如下：

package com.xlf.storm.common.utils;

import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.Properties;
import java.util.Queue;
import java.util.concurrent.ConcurrentLinkedQueue;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;

import kafka.consumer.ConsumerConfig;
import kafka.javaapi.consumer.ConsumerConnector;
import kafka.consumer.ConsumerIterator;
import kafka.consumer.KafkaStream;

/**
 * kafka消息消费线程；
 */
public class KafkaMessageConsumer extends Thread {
	private static final Log LOG = LogFactory.getLog(KafkaMessageConsumer.class);

	private String topic = null;
	private String groupId = null;
	private ConsumerConnector consumer = null;
	private Queue<String> queue = new ConcurrentLinkedQueue<String>();

	/**
	 * Constructor；
	 * 
	 * @param topic 监听的kafka主题；
	 * @param groupId consumer的 group id；
	 */
	public KafkaMessageConsumer(String topic, String groupId) {
		this.topic = topic;
		this.groupId = groupId;
		ConsumerConfig config = createConsumerConfig();
		if (config != null) {
			consumer = kafka.consumer.Consumer.createJavaConsumerConnector(config);
		} else {
			LOG.error("topic : " + topic + " consumer create faid !");
		}
	}

	private ConsumerConfig createConsumerConfig() {
		String zookeeper_connect = PropertiesUtils.getConfigProperty("zookeeper_connect");
		if (zookeeper_connect != null) {
			Properties props = new Properties();
			props.put("zookeeper.connect", zookeeper_connect);
			props.put("group.id", groupId);
			props.put("zookeeper.session.timeout.ms", "5000");
			props.put("zookeeper.connection.timeout.ms", "10000");
//			props.put("zookeeper.sync.time.ms", "2000");
			props.put("rebalance.backoff.ms", "2000");
			props.put("rebalance.max.retries", "10");
			props.put("auto.commit.interval.ms", "1000");
			return new ConsumerConfig(props);
		} else {
			LOG.error("read properties file error!,can't get the zookeeper connect ");
			return null;
		}
	}

	@Override
	public void run() {
		try {
			if (consumer != null) {
				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()) {
					/** 主动pull消息，然后保存在队列里面 */
					String message = new String(it.next().message());
					if (message != null && message.length() > 0) {
						System.err.println("kafka topic: " + topic + " group:" + groupId + "  read message : " + message);
						queue.add(message);
					}
				}
			}
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

	/**
	 * 获取存储消息的队列对象；
	 * 
	 * @return 存储消息的队列对象；
	 */
	public Queue<String> getQueue() {
		return queue;
	}

	public static void main(String[] args) {
		KafkaMessageConsumer consumerThread = new KafkaMessageConsumer("test",
				"test1");
		consumerThread.start();
	}
}

server.properties配置如下：

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

# The id of the broker. This must be set to a unique integer for each broker.
broker.id=1

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

# The port the socket server listens on
port=9092

# Hostname the broker will bind to. If not set, the server will bind to all interfaces
#host.name=localhost

# Hostname the broker will advertise to producers and consumers. If not set, it uses the
# value for "host.name" if configured. Otherwise, it will use the value returned from
# java.net.InetAddress.getCanonicalHostName().
#advertised.host.name=<hostname routable by clients>

# The port to publish to ZooKeeper for clients to use. If this is not set,
# it will publish the same port that the broker binds to.
#advertised.port=<port accessible by clients>

# 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=/opt/kafka_2.10-0.8.2.2/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=4

# 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=1

# 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

# By default the log cleaner is disabled and the log retention policy will default to just delete segments after their retention expires.
# If log.cleaner.enable=true is set the cleaner will be enabled and individual logs can then be marked for log compaction.
log.cleaner.enable=false

############################# 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=storm-node1:2181,storm-node2:2181,storm-node3:2181

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

分享到QQ

分享到微博