1.MapReduce是什么

     Hadoop MapReduce是一个软件框架,基于该框架能够容易地编写应用程序,这些应用程序能够运行在由上千个商用机器组成的大集群上,并以一种可靠的,具有容错能力的方式并行地处理上TB级别的海量数据集。这个定义里面有着这些关键词,

一是软件框架,二是并行处理,三是可靠且容错,四是大规模集群,五是海量数据集。

2 MapReduce做什么

     MapReduce擅长处理大数据,它为什么具有这种能力呢?这可由MapReduce的设计思想发觉。MapReduce的思想就是“分而治之”。

  (1)Mapper负责“分”,即把复杂的任务分解为若干个“简单的任务”来处理。“简单的任务”包含三层含义:

一是数据或计算的规模相对原任务要大大缩小;二是就近计算原则,即任务会分配到存放着所需数据的节点上进行计算;三是这些小任务可以并行计算,彼此间几乎没有依赖关系。

  (2)Reducer负责对map阶段的结果进行汇总。至于需要多少个Reducer,用户可以根据具体问题,通过在mapred-site.xml配置文件里设置参数mapred.reduce.tasks的值,缺省值为1。

一个比较形象的语言解释MapReduce:  

我们要数图书馆中的所有书。你数1号书架,我数2号书架。这就是“Map”。我们人越多,数书就更快。 现在我们到一起,把所有人的统计数加在一起。这就是“Reduce”。

MapReduce流程

  • inputFormat 先通过inputFormat 读进来
  • InputSplit 然后通过split进行分片
  • RecordReaders 简称RR 通过 recordReader读取切片
  • map map处理 输出个临时结果
  • Combiner 本机先做一次reduce 减少io 提升作业执行性能,但是也有缺点,如果做全局平均数 等就不准了
  • shuffing - partitioner shuffing分发
  • shuffing - sort shuffing排序
  • reduce
  • OutputFormat 最终输出

MapReduce的输入输出

  MapReduce框架运转在<key,value>键值对上,也就是说,框架把作业的输入看成是一组<key,value>键值对,同样也产生一组<key,value>键值对作为作业的输出,这两组键值对有可能是不同的。

  一个MapReduce作业的输入和输出类型如下图所示:可以看出在整个流程中,会有三组<key,value>键值对类型的存在。

MapReduce的处理流程

  这里以WordCount单词计数为例,介绍map和reduce两个阶段需要进行哪些处理。单词计数主要完成的功能是:统计一系列文本文件中每个单词出现的次数,如图所示:

编写一个简单的 WordCount mapReduce 脚本

编写map脚本

//继承mapper类
/**
 *  KEYIN, Map任务读数据的key类型,offset,是每行数据起始位置的偏移量 Long
 *  VALUEIN,  Map任务读取数据的 value类型  就是一行行字符串 String
 *  KEYOUT,   map方法自定义实现输出key类型
 *  VALUEOUT  map方法自定义实现输出value类型
 *
 *  hello world welcome
 *  hello welcome
 *  keyout  String  valueout  int
 *  (world,1)
 *  hadoop 会有自定义类型  支持序列化和反序列化
 */
public class WordCountMapper extends Mapper<LongWritable,Text,Text,IntWritable> {
    //自定义map 把自己需要的数据截取出来 然后交给后续步骤来做
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //多个单词用 空格拆开
        String[] words = value.toString().split("-");
        for(String word:words) {
            context.write(new Text(word),new IntWritable(1));
        }
    }
}

编写Reduce

/**
 * Reduce 的输入是map的输出
 *  KEYIN, VALUEIN, KEYOUT, VALUEOUT 输入是 word,1  输出是 word,3  都是 string,int
 */
public class WordCountReduce extends Reducer<Text,IntWritable,Text,IntWritable> {
    /**
     *
     * @param key  对应的单词
     * @param values  可以迭代的value 相同的key都会分发到一个reduce上面去 类似于  (hello,<1,1,1,1>)
     * @param context
     * @throws IOException
     * @throws InterruptedException
     */
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int count = 0;
        Iterator<IntWritable> iterator = values.iterator();
        while(iterator.hasNext()) {
            IntWritable value = iterator.next();
            //累加
            count += value.get();
        }
        context.write(key,new IntWritable(count));
    }
}

创建Job 运行

    //windows需要设置 hadoop.home.dir
    System.setProperty("hadoop.home.dir", "D:\\javaroot\\soft\\hadoop-2.6.0-cdh5.15.1");

    //设置hadoop帐号
    System.setProperty("HADOOP_USER_NAME","hadoop");
    Configuration configuration = new Configuration();
    configuration.set("fs.defaultFS","hdfs://192.168.1.100:8020");

   //提交个作业
    Job job = Job.getInstance(configuration);
    //设置job对应的主类
    job.setJarByClass(App.class);
     //添加 Combiner
    job.setCombinerClass(WordCountReduce.class);
    //设置自定义的mapper类型
    job.setMapperClass(WordCountMapper.class);
    job.setReducerClass(WordCountReduce.class);

    //设置输出类型
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);

    //设置reduce输出
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    //设置输入和输出的路径
    FileInputFormat.setInputPaths(job, new Path("/demo/wordcount/input"));
    FileOutputFormat.setOutputPath(job,new Path("/demo/wordcount/output"));

    //提交job
    boolean res  = job.waitForCompletion(true);
   System.exit(res ? 0 :1);

实例:解析流量日志 算出每个手机号 上行和下行的流量和总流量

数据log

1363157985066 	13726230503	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com		24	27	2481	24681	200
1363157995052 	13826544101	5C-0E-8B-C7-F1-E0:CMCC	120.197.40.4			4	0	264	0	200
1363157991076 	13926435656	20-10-7A-28-CC-0A:CMCC	120.196.100.99			2	4	132	1512	200
1363154400022 	13926251106	5C-0E-8B-8B-B1-50:CMCC	120.197.40.4			4	0	240	0	200
1363157993044 	18211575961	94-71-AC-CD-E6-18:CMCC-EASY	120.196.100.99	iface.qiyi.com	视频网站	15	12	1527	2106	200
1363157995074 	84138413	5C-0E-8B-8C-E8-20:7DaysInn	120.197.40.4	122.72.52.12		20	16	4116	1432	200
1363157993055 	13560439658	C4-17-FE-BA-DE-D9:CMCC	120.196.100.99			18	15	1116	954	200
1363157995033 	15920133257	5C-0E-8B-C7-BA-20:CMCC	120.197.40.4	sug.so.360.cn	信息安全	20	20	3156	2936	200
1363157983019 	13719199419	68-A1-B7-03-07-B1:CMCC-EASY	120.196.100.82			4	0	240	0	200
1363157984041 	13660577991	5C-0E-8B-92-5C-20:CMCC-EASY	120.197.40.4	s19.cnzz.com	站点统计	24	9	6960	690	200
1363157973098 	15013685858	5C-0E-8B-C7-F7-90:CMCC	120.197.40.4	rank.ie.sogou.com	搜索引擎	28	27	3659	3538	200
1363157986029 	15989002119	E8-99-C4-4E-93-E0:CMCC-EASY	120.196.100.99	www.umeng.com	站点统计	3	3	1938	180	200
1363157992093 	13560439658	C4-17-FE-BA-DE-D9:CMCC	120.196.100.99			15	9	918	4938	200
1363157986041 	13480253104	5C-0E-8B-C7-FC-80:CMCC-EASY	120.197.40.4			3	3	180	180	200
1363157984040 	13602846565	5C-0E-8B-8B-B6-00:CMCC	120.197.40.4	2052.flash2-http.qq.com	综合门户	15	12	1938	2910	200
1363157995093 	13922314466	00-FD-07-A2-EC-BA:CMCC	120.196.100.82	img.qfc.cn		12	12	3008	3720	200
1363157982040 	13502468823	5C-0A-5B-6A-0B-D4:CMCC-EASY	120.196.100.99	y0.ifengimg.com	综合门户	57	102	7335	110349	200
1363157986072 	18320173382	84-25-DB-4F-10-1A:CMCC-EASY	120.196.100.99	input.shouji.sogou.com	搜索引擎	21	18	9531	2412	200
1363157990043 	13925057413	00-1F-64-E1-E6-9A:CMCC	120.196.100.55	t3.baidu.com	搜索引擎	69	63	11058	48243	200
1363157988072 	13760778710	00-FD-07-A4-7B-08:CMCC	120.196.100.82			2	2	120	120	200
1363157985066 	13726238888	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com		24	27	2481	24681	200
1363157993055 	13560436666	C4-17-FE-BA-DE-D9:CMCC	120.196.100.99			18	15	1116	954	200
1363157985066 	13726238888	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com		24	27	10000	20000	200

代码实现
//map类
public class AccessMapper extends Mapper<LongWritable,Text,Text,Access> {
    //把日志按切分 找到需要的三个字段
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] lines = value.toString().split("\t");
        String phone = lines[1];
        long up = Long.parseLong(lines[lines.length - 3]);
        long down = Long.parseLong(lines[lines.length - 2]);
        context.write(new Text(phone),new Access(phone,up,down,(up+down)));
    }
}

//reduce 类
public class AccessReduce extends Reducer<Text,Access,NullWritable,Access> {
    /**
     * @param key  手机号
     * @param values   Access
     * @param context
     * @throws IOException
     * @throws InterruptedException
     */
    @Override
    protected void reduce(Text key, Iterable<Access> values, Context context) throws IOException, InterruptedException {
        long ups = 0;
        long downs = 0;
        for (Access access:values) {
            ups += access.getUp();
            downs += access.getDown();
        }
        context.write(NullWritable.get(),new Access(key.toString(),ups,downs,(ups+downs)));
    }
}

//job 执行
  public static void main(String[] args) throws Exception {
    //windows需要设置 hadoop.home.dir
    System.setProperty("hadoop.home.dir", "D:\\javaroot\\soft\\hadoop-2.6.0-cdh5.15.1");
    //设置hadoop帐号
   // System.setProperty("HADOOP_USER_NAME","hadoop");
    Configuration configuration = new Configuration();
    //configuration.set("fs.defaultFS","hdfs://192.168.1.100:8020");
    Job job = Job.getInstance(configuration);
    job.setJarByClass(App.class);
    job.setMapperClass(AccessMapper.class);
    job.setReducerClass(AccessReduce.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(Access.class);
    job.setOutputKeyClass(NullWritable.class);
    job.setOutputValueClass(Access.class);
    //设置输入和输出的路径
    FileInputFormat.setInputPaths(job, new Path("input"));
    FileOutputFormat.setOutputPath(job,new Path("output"));
    //提交job
    boolean res  = job.waitForCompletion(true);
    System.exit(res ? 0 :1);

}

最后执行结果

phone='13480253104', up=180, down=180, sum=360
phone='13502468823', up=7335, down=110349, sum=117684
phone='13560436666', up=1116, down=954, sum=2070
phone='13560439658', up=2034, down=5892, sum=7926
phone='13602846565', up=1938, down=2910, sum=4848
phone='13660577991', up=6960, down=690, sum=7650
phone='13719199419', up=240, down=0, sum=240
phone='13726230503', up=2481, down=24681, sum=27162
phone='13726238888', up=12481, down=44681, sum=57162
phone='13760778710', up=120, down=120, sum=240
phone='13826544101', up=264, down=0, sum=264
phone='13922314466', up=3008, down=3720, sum=6728
phone='13925057413', up=11058, down=48243, sum=59301
phone='13926251106', up=240, down=0, sum=240
phone='13926435656', up=132, down=1512, sum=1644
phone='15013685858', up=3659, down=3538, sum=7197
phone='15920133257', up=3156, down=2936, sum=6092
phone='15989002119', up=1938, down=180, sum=2118
phone='18211575961', up=1527, down=2106, sum=3633
phone='18320173382', up=9531, down=2412, sum=11943
phone='84138413', up=4116, down=1432, sum=5548


标题:一文读懂MapReduce 附流量解析实例
作者:gwyy
地址:https://liangtian.me/MapReduce
微信公众号:胡说代码

添加新评论