模拟spark中streaming的JavaKafkaWordCount案列

一、首先找到spark-1.6.1-bin-hadoop2.6.tgz 的JavaKafkaWordCount

    位置具体在

spark-1.6.1-bin-hadoop2.6\examples\src\main\java\org\apache\spark\examples\streaming\JavaKafkaWordCount

打开可以看到

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * 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.
 */

package org.apache.spark.examples.streaming;

import java.util.Map;
import java.util.HashMap;
import java.util.regex.Pattern;


import scala.Tuple2;

import com.google.common.collect.Lists;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.examples.streaming.StreamingExamples;
import org.apache.spark.streaming.Duration;
import org.apache.spark.streaming.api.java.JavaDStream;
import org.apache.spark.streaming.api.java.JavaPairDStream;
import org.apache.spark.streaming.api.java.JavaPairReceiverInputDStream;
import org.apache.spark.streaming.api.java.JavaStreamingContext;
import org.apache.spark.streaming.kafka.KafkaUtils;

/**
 * Consumes messages from one or more topics in Kafka and does wordcount.
 *
 * Usage: JavaKafkaWordCount <zkQuorum> <group> <topics> <numThreads>
 *   <zkQuorum> is a list of one or more zookeeper servers that make quorum
 *   <group> is the name of kafka consumer group
 *   <topics> is a list of one or more kafka topics to consume from
 *   <numThreads> is the number of threads the kafka consumer should use
 *
 * To run this example:
 *   `$ bin/run-example org.apache.spark.examples.streaming.JavaKafkaWordCount zoo01,zoo02, \
 *    zoo03 my-consumer-group topic1,topic2 1`
 */

public final class JavaKafkaWordCount {
  private static final Pattern SPACE = Pattern.compile(" ");

  private JavaKafkaWordCount() {
  }

  public static void main(String[] args) {
    if (args.length < 4) {
      System.err.println("Usage: JavaKafkaWordCount <zkQuorum> <group> <topics> <numThreads>");
      System.exit(1);
    }

    StreamingExamples.setStreamingLogLevels();
    SparkConf sparkConf = new SparkConf().setAppName("JavaKafkaWordCount");
    // Create the context with 2 seconds batch size
    JavaStreamingContext jssc = new JavaStreamingContext(sparkConf, new Duration(2000));

    int numThreads = Integer.parseInt(args[3]);
    Map<String, Integer> topicMap = new HashMap<String, Integer>();
    String[] topics = args[2].split(",");
    for (String topic: topics) {
      topicMap.put(topic, numThreads);
    }

    JavaPairReceiverInputDStream<String, String> messages =
            KafkaUtils.createStream(jssc, args[0], args[1], topicMap);

    JavaDStream<String> lines = messages.map(new Function<Tuple2<String, String>, String>() {
      @Override
      public String call(Tuple2<String, String> tuple2) {
        return tuple2._2();
      }
    });

    JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
      @Override
      public Iterable<String> call(String x) {
        return Lists.newArrayList(SPACE.split(x));
      }
    });

    JavaPairDStream<String, Integer> wordCounts = words.mapToPair(
      new PairFunction<String, String, Integer>() {
        @Override
        public Tuple2<String, Integer> call(String s) {
          return new Tuple2<String, Integer>(s, 1);
        }
      }).reduceByKey(new Function2<Integer, Integer, Integer>() {
        @Override
        public Integer call(Integer i1, Integer i2) {
          return i1 + i2;
        }
      });

    wordCounts.print();
    jssc.start();
    jssc.awaitTermination();
  }
}

首选部署spark平台启动 根据类上面的注释：启动的方式：

 bin/run-example org.apache.spark.examples.streaming.JavaKafkaWordCount zoo01,zoo02,zoo03 my-consumer-group topic1,topic2 1

第一个参数为zk;

第二个参数为消费组名称，这个自己可以任意命名

第三个是kafka 要消费的主题

第四个 是 线程数，一般根据cpu的内核定义

自己模拟如下:  首先你到spark部署的位置 cd  /opt/spark-1.6.1-bin-custom-spark  然后执行下面命令

./bin/run-example org.apache.spark.examples.streaming.JavaKafkaWordCount 192.168.186.29:2181 test_java_kafka_word_count test-topic 4

等启动起来，开始编写kafka生产者

package com.ultrapower.scala.kafka.producer;

import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.Producer;
import org.apache.kafka.clients.producer.ProducerRecord;

import java.util.Properties;

/**
 *
 * @author xiefg
 */
public class KafkaProducerExample {

    public void run()
    {
        Properties props = getConfig();
        Producer<String, String> producer = new KafkaProducer<String, String>(props);
        String topic="test-topic",key,value;
        for (int i = 0; i < 1000; i++) {
            key = "key_"+i;
            value="value_"+i;
            System.out.println("TOPIC: test-topic;发送KEY："+key+";Value:"+value);
            producer.send(new ProducerRecord<String, String>(topic, key,value));
            try {
                Thread.sleep(1000);
            }
            catch (InterruptedException e) {
                e.printStackTrace();
            }
        }

        producer.close();
    }

    // config
    public Properties getConfig()
    {
        Properties props = new Properties();
        //kafka节点
        props.put("bootstrap.servers", "192.168.186.29:9092");
        props.put("acks", "all");
        props.put("retries", 0);
        props.put("batch.size", 16384);
        props.put("linger.ms", 1);
        props.put("buffer.memory", 33554432);
        props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
        props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");
        return props;
    }

    public static void main(String[] args)
    {
        KafkaProducerExample example = new KafkaProducerExample();
        example.run();
    }
}

在idea运行起来如图：

接下来看一下spark启动的后端生成的日志

可以看到生产者在发送消息主题，消费者在实时的处理。同时我们可以用工具监控一下消费的情况

可以看到分区数，偏移指针的变化和日志的大小等等。

本案列应该是最简单的一个从生产到消费的过程思路，如果牵涉到具体的业务需要具体的做相应的处理