kafka 高级API和低级API

高级 API

produce

package com.sinoiov.kafka.test;

import kafka.javaapi.producer.Producer;
import kafka.producer.KeyedMessage;
import kafka.producer.ProducerConfig;
import kafka.serializer.StringEncoder;

import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.Properties;

/**
 * Created by caoyu on 16/4/21.
 * By 中交兴路 大数据中心-基础平台部
 */
public class Kafka_produce extends Thread{
    private String topic;
    private SimpleDateFormat sdf = new SimpleDateFormat("MM-dd hh:mm:ss");

    public Kafka_produce(String topic){
        super();
        this.topic = topic;
    }

    @Override
    public void run() {
        Producer<String, String> producer = createProducer();
        long i = 0;
        while(true){
            i++;
            long now = System.currentTimeMillis();
            KeyedMessage<String, String> message = new KeyedMessage<String, String>(topic,sdf.format(new Date(now))+"_"+i+"");
            producer.send(message);
            try {
                Thread.sleep(1000);
            } catch (InterruptedException e) {
                e.printStackTrace();
            }
        }
    }

    private Producer<String,String> createProducer(){
        Properties properties = new Properties();
        properties.put("metadata.broker.list","192.168.110.81:9092,192.168.110.82:9092,192.168.110.83:9092");
        properties.put("serializer.class", StringEncoder.class.getName());
        properties.put("zookeeper.connect", "nnn1:2181,nnn2:2181,nslave1:2181");
        return new Producer<String, String>(new ProducerConfig(properties));
    }
}
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50

代码很简单，参考一下基本上都能看懂。

consumer

同样来一段示例代码

package com.sinoiov.kafka.test;

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

import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.Properties;

/**
 * Created by caoyu on 16/4/21.
 * By 中交兴路 大数据中心-基础平台部
 */
public class Kafka_consumer extends Thread {
    private String topic;
    private ConsumerConnector consumer;

    public Kafka_consumer(String topic){
        super();
        this.topic = topic;
        consumer = createConsumer();
    }

    public void shutDown(){
        if(consumer != null)
            consumer.shutdown();
    }

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

    private ConsumerConnector createConsumer(){
        Properties properties = new Properties();
        properties.put("zookeeper.connect","nnn1:2181,nnn2:2181,nslave1:2181");
        properties.put("group.id", "testsecond");
        return Consumer.createJavaConsumerConnector(new ConsumerConfig(properties));
    }
}
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53

同样，代码也不复杂，基本都能参考看懂。

高级 API 的特点

优点

• 高级 API 写起来简单

• 不需要去自行去 管理offset，系统通过 zookeeper 自行管理

• 不需要管理分区，副本等情况，系统自动管理

• 消费者断线会自动根据上一次记录在 zookeeper 中的 offset去接着获取数据（默认设置1分钟更新一下 zookeeper 中存的的 offset）

• 可以使用 group 来区分对同一个 topic 的不同程序访问分离开来（不同的 group 记录不同的 offset，这样不同程序读取同一个 topic 才不会因为 offset 互相影响）

缺点

• 不能自行控制 offset（对于某些特殊需求来说）

• 不能细化控制如分区、副本、zk 等

低级 API 的特点

优点

• 能够开发者自己控制 offset，想从哪里读取就从哪里读取。

• 自行控制连接分区，对分区自定义进行负载均衡

• 对 zookeeper 的依赖性降低（如：offset 不一定非要靠 zk 存储，自行存储 offset 即可，比如存在文件或者内存中）

缺点

• 太过复杂，需要自行控制 offset，连接哪个分区，找到分区 leader 等，请参考下面的低级 API 的示例代码

低级 API 示例代码

此代码引用了http://www.tuicool.com/articles/j6ZZnaI 内的代码，特此声明

示例代码其实和官网上的示例代码基本上差不多，只是引用的代码对一些不太明白的地方有了实际写法，学习价值高。推荐配合官网文档学习最佳。

package com.sinoiov.kafka.test;

import java.nio.ByteBuffer;
import java.util.ArrayList;
import java.util.Collections;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

import kafka.api.FetchRequest;
import kafka.api.FetchRequestBuilder;
import kafka.api.PartitionOffsetRequestInfo;
import kafka.cluster.BrokerEndPoint;
import kafka.common.ErrorMapping;
import kafka.common.TopicAndPartition;
import kafka.javaapi.FetchResponse;
import kafka.javaapi.OffsetResponse;
import kafka.javaapi.PartitionMetadata;
import kafka.javaapi.TopicMetadata;
import kafka.javaapi.TopicMetadataRequest;
import kafka.javaapi.consumer.SimpleConsumer;
import kafka.message.MessageAndOffset;

/**
 * Created by caoyu on 16/4/26.
 * By 中交兴路 大数据中心-基础平台部
 */
public class SimpleExample {
    private List<String> m_replicaBrokers = new ArrayList<String>();

    public SimpleExample() {
        m_replicaBrokers = new ArrayList<String>();
    }

    public static void main(String args[]) {
        SimpleExample example = new SimpleExample();
        // 最大读取消息数量
        long maxReads = Long.parseLong("3");
        // 要订阅的topic
        String topic = "test1";
        // 要查找的分区
        int partition = Integer.parseInt("0");
        // broker节点的ip
        List<String> seeds = new ArrayList<String>();
        seeds.add("192.168.110.81");
        seeds.add("192.168.110.82");
        seeds.add("192.168.110.83");
        // 端口
        int port = Integer.parseInt("9092");
        try {
            example.run(maxReads, topic, partition, seeds, port);
        } catch (Exception e) {
            System.out.println("Oops:" + e);
            e.printStackTrace();
        }
    }

    public void run(long a_maxReads, String a_topic, int a_partition, List<String> a_seedBrokers, int a_port) throws Exception {
        // 获取指定Topic partition的元数据
        PartitionMetadata metadata = findLeader(a_seedBrokers, a_port, a_topic, a_partition);
        if (metadata == null) {
            System.out.println("Can't find metadata for Topic and Partition. Exiting");
            return;
        }
        if (metadata.leader() == null) {
            System.out.println("Can't find Leader for Topic and Partition. Exiting");
            return;
        }
        String leadBroker = metadata.leader().host();
        String clientName = "Client_" + a_topic + "_" + a_partition;

        SimpleConsumer consumer = new SimpleConsumer(leadBroker, a_port, 100000, 64 * 1024, clientName);
        long readOffset = getLastOffset(consumer, a_topic, a_partition, kafka.api.OffsetRequest.EarliestTime(), clientName);
        int numErrors = 0;
        while (a_maxReads > 0) {
            if (consumer == null) {
                consumer = new SimpleConsumer(leadBroker, a_port, 100000, 64 * 1024, clientName);
            }
            FetchRequest req = new FetchRequestBuilder().clientId(clientName).addFetch(a_topic, a_partition, readOffset, 100000).build();
            FetchResponse fetchResponse = consumer.fetch(req);

            if (fetchResponse.hasError()) {
                numErrors++;
                // Something went wrong!
                short code = fetchResponse.errorCode(a_topic, a_partition);
                System.out.println("Error fetching data from the Broker:" + leadBroker + " Reason: " + code);
                if (numErrors > 5)
                    break;
                if (code == ErrorMapping.OffsetOutOfRangeCode()) {
                    // We asked for an invalid offset. For simple case ask for
                    // the last element to reset
                    readOffset = getLastOffset(consumer, a_topic, a_partition, kafka.api.OffsetRequest.LatestTime(), clientName);
                    continue;
                }
                consumer.close();
                consumer = null;
                leadBroker = findNewLeader(leadBroker, a_topic, a_partition, a_port);
                continue;
            }
            numErrors = 0;

            long numRead = 0;
            for (MessageAndOffset messageAndOffset : fetchResponse.messageSet(a_topic, a_partition)) {
                long currentOffset = messageAndOffset.offset();
                if (currentOffset < readOffset) {
                    System.out.println("Found an old offset: " + currentOffset + " Expecting: " + readOffset);
                    continue;
                }

                readOffset = messageAndOffset.nextOffset();
                ByteBuffer payload = messageAndOffset.message().payload();

                byte[] bytes = new byte[payload.limit()];
                payload.get(bytes);
                System.out.println(String.valueOf(messageAndOffset.offset()) + ": " + new String(bytes, "UTF-8"));
                numRead++;
                a_maxReads--;
            }

            if (numRead == 0) {
                try {
                    Thread.sleep(1000);
                } catch (InterruptedException ie) {
                }
            }
        }
        if (consumer != null)
            consumer.close();
    }

    public static long getLastOffset(SimpleConsumer consumer, String topic, int partition, long whichTime, String clientName) {
        TopicAndPartition topicAndPartition = new TopicAndPartition(topic, partition);
        Map<TopicAndPartition, PartitionOffsetRequestInfo> requestInfo = new HashMap<TopicAndPartition, PartitionOffsetRequestInfo>();
        requestInfo.put(topicAndPartition, new PartitionOffsetRequestInfo(whichTime, 1));
        kafka.javaapi.OffsetRequest request = new kafka.javaapi.OffsetRequest(requestInfo, kafka.api.OffsetRequest.CurrentVersion(), clientName);
        OffsetResponse response = consumer.getOffsetsBefore(request);

        if (response.hasError()) {
            System.out.println("Error fetching data Offset Data the Broker. Reason: " + response.errorCode(topic, partition));
            return 0;
        }
        long[] offsets = response.offsets(topic, partition);
        return offsets[0];
    }

    /**
     * @param a_oldLeader
     * @param a_topic
     * @param a_partition
     * @param a_port
     * @return String
     * @throws Exception
     *             找一个leader broker
     */
    private String findNewLeader(String a_oldLeader, String a_topic, int a_partition, int a_port) throws Exception {
        for (int i = 0; i < 3; i++) {
            boolean goToSleep = false;
            PartitionMetadata metadata = findLeader(m_replicaBrokers, a_port, a_topic, a_partition);
            if (metadata == null) {
                goToSleep = true;
            } else if (metadata.leader() == null) {
                goToSleep = true;
            } else if (a_oldLeader.equalsIgnoreCase(metadata.leader().host()) && i == 0) {
                // first time through if the leader hasn't changed give
                // ZooKeeper a second to recover
                // second time, assume the broker did recover before failover,
                // or it was a non-Broker issue
                //
                goToSleep = true;
            } else {
                return metadata.leader().host();
            }
            if (goToSleep) {
                try {
                    Thread.sleep(1000);
                } catch (InterruptedException ie) {
                }
            }
        }
        System.out.println("Unable to find new leader after Broker failure. Exiting");
        throw new Exception("Unable to find new leader after Broker failure. Exiting");
    }

    private PartitionMetadata findLeader(List<String> a_seedBrokers, int a_port, String a_topic, int a_partition) {
        PartitionMetadata returnMetaData = null;
        loop: for (String seed : a_seedBrokers) {
            SimpleConsumer consumer = null;
            try {
                consumer = new SimpleConsumer(seed, a_port, 100000, 64 * 1024, "leaderLookup");
                List<String> topics = Collections.singletonList(a_topic);
                TopicMetadataRequest req = new TopicMetadataRequest(topics);
                kafka.javaapi.TopicMetadataResponse resp = consumer.send(req);

                List<TopicMetadata> metaData = resp.topicsMetadata();
                for (TopicMetadata item : metaData) {
                    for (PartitionMetadata part : item.partitionsMetadata()) {
                        if (part.partitionId() == a_partition) {
                            returnMetaData = part;
                            break loop;
                        }
                    }
                }
            } catch (Exception e) {
                System.out.println("Error communicating with Broker [" + seed + "] to find Leader for [" + a_topic + ", " + a_partition + "] Reason: " + e);
            } finally {
                if (consumer != null)
                    consumer.close();
            }
        }
        if (returnMetaData != null) {
            m_replicaBrokers.clear();
            for (BrokerEndPoint replica : returnMetaData.replicas()) {
                m_replicaBrokers.add(replica.host());
            }
        }
        return returnMetaData;
    }
}