一个MapReduce 程序示例 细节决定成败（一）

最近在看MapReduce，想起一直都是Copy 然后修改的方法来写。突然想试试自己动手写一个级其简单的mr程序。
细节决定成败啊，不试不知道，一试才能发现平时注意不到的细节。
下面是我用了很快时间写好的一个程序，注意，这份是有问题的！

package wordcount;

import java.io.IOException;

import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apache.log4j.Logger;

public class MyWordCountJob extends Configured implements Tool {
        Logger log = Logger.getLogger(MyWordCountJob.class);

        public class MyWordCountMapper extends
                        Mapper<LongWritable, Text, LongWritable, Text> {
                Logger log = Logger.getLogger(MyWordCountJob.class);

                LongWritable mapKey = new LongWritable();
                Text mapValue = new Text();
                @Override
                protected void map(LongWritable key, Text value, Context context)
                                throws IOException, InterruptedException {
                        mapKey.set(key.get());
                        mapValue.set(value.toString());
                        log.info("Mapper: mapKey--" + mapKey.get() + "mapValue --"+ mapValue.toString());
                        context.write(mapKey, mapValue);
                }

        }

        public class MyWordCountReducer extends Reducer<LongWritable, Text, LongWritable, Text> {

                @Override
                protected void reduce(LongWritable key, Iterable<Text> values,Context context)
                                throws IOException, InterruptedException {
                        for(Text value :values)
                                context.write(key, value);
                }
        }

        @Override
        public int run(String[] args) throws Exception {
                log.info("begin to run");
                Job job = Job.getInstance(getConf(), "MyWordCountJob");
                job.setJarByClass(MyWordCountJob.class);

                Path inPath = new Path("demos/pigdemo.txt");
                Path outPath = new Path("demos/pigdemoOut.txt");

                outPath.getFileSystem(getConf()).delete(outPath,true);
                TextInputFormat.setInputPaths(job, inPath);
                TextOutputFormat.setOutputPath(job, outPath);


                job.setMapperClass(MyWordCountJob.MyWordCountMapper.class);
                job.setReducerClass(MyWordCountJob.MyWordCountReducer.class);
                job.setInputFormatClass(TextInputFormat.class);
                job.setOutputFormatClass(TextOutputFormat.class);

                job.setMapOutputKeyClass(LongWritable.class);
                job.setMapOutputValueClass(Text.class);
                job.setOutputKeyClass(LongWritable.class);
                job.setOutputValueClass(Text.class);
                return job.waitForCompletion(true)?0:1;
        }
        public static void main(String [] args){
                int result = 0;
                try {
                        result = ToolRunner.run(new Configuration(), new MyWordCountJob(), args);
                } catch (Exception e) {
                        e.printStackTrace();
                }
                System.exit(result);
        }

}

写完成编译，打包然后运行。

16/05/10 22:43:46 INFO mapreduce.Job: Running job: job_1462517728035_0033
16/05/10 22:43:54 INFO mapreduce.Job: Job job_1462517728035_0033 running in uber mode : false
16/05/10 22:43:54 INFO mapreduce.Job: map 0% reduce 0%
16/05/10 22:43:58 INFO mapreduce.Job: Task Id : attempt_1462517728035_0033_m_000000_0, Status : FAILED
Error: java.lang.RuntimeException: java.lang.NoSuchMethodException: wordcount.MyWordCountJob$MyWordCountMapper.<init>()
        at org.apache.hadoop.util.ReflectionUtils.newInstance(ReflectionUtils.java:131)
        at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:721)
        at org.apache.hadoop.mapred.MapTask.run(MapTask.java:339)
        at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:162)
        at java.security.AccessController.doPrivileged(Native Method)
        at javax.security.auth.Subject.doAs(Subject.java:396)
        at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1491)
        at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:157)
Caused by: java.lang.NoSuchMethodException: wordcount.MyWordCountJob$MyWordCountMapper.<init>()
        at java.lang.Class.getConstructor0(Class.java:2706)
        at java.lang.Class.getDeclaredConstructor(Class.java:1985)
        at org.apache.hadoop.util.ReflectionUtils.newInstance(ReflectionUtils.java:125)
        ... 7 more

16/05/10 22:44:02 INFO mapreduce.Job: Task Id : attempt_1462517728035_0033_m_000000_1, Status : FAILED
Error: java.lang.RuntimeException: java.lang.NoSuchMethodException: wordcount.MyWordCountJob$MyWordCountMapper.<init>()
        at org.apache.hadoop.util.ReflectionUtils.newInstance(ReflectionUtils.java:131)
        at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:721)
        at org.apache.hadoop.mapred.MapTask.run(MapTask.java:339)
        at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:162)
        at java.security.AccessController.doPrivileged(Native Method)
        at javax.security.auth.Subject.doAs(Subject.java:396)
        at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1491)
        at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:157)
Caused by: java.lang.NoSuchMethodException: wordcount.MyWordCountJob$MyWordCountMapper.<init>()
        at java.lang.Class.getConstructor0(Class.java:2706)
        at java.lang.Class.getDeclaredConstructor(Class.java:1985)
        at org.apache.hadoop.util.ReflectionUtils.newInstance(ReflectionUtils.java:125)
        ... 7 more

16/05/10 22:44:07 INFO mapreduce.Job: Task Id : attempt_1462517728035_0033_m_000000_2, Status : FAILED
Error: java.lang.RuntimeException: java.lang.NoSuchMethodException: wordcount.MyWordCountJob$MyWordCountMapper.<init>()
        at org.apache.hadoop.util.ReflectionUtils.newInstance(ReflectionUtils.java:131)
        at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:721)
        at org.apache.hadoop.mapred.MapTask.run(MapTask.java:339)
        at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:162)
        at java.security.AccessController.doPrivileged(Native Method)
        at javax.security.auth.Subject.doAs(Subject.java:396)
        at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1491)
        at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:157)
Caused by: java.lang.NoSuchMethodException: wordcount.MyWordCountJob$MyWordCountMapper.<init>()
        at java.lang.Class.getConstructor0(Class.java:2706)
        at java.lang.Class.getDeclaredConstructor(Class.java:1985)
        at org.apache.hadoop.util.ReflectionUtils.newInstance(ReflectionUtils.java:125)
        ... 7 more

16/05/10 22:44:14 INFO mapreduce.Job: map 100% reduce 100%
16/05/10 22:44:14 INFO mapreduce.Job: Job job_1462517728035_0033 failed with state FAILED due to: Task failed task_1462517728035_0033_m_000000
Job failed as tasks failed. failedMaps:1 failedReduces:0

16/05/10 22:44:15 INFO mapreduce.Job: Counters: 6
        Job Counters 
                Failed map tasks=4
                Launched map tasks=4
                Other local map tasks=3
                Data-local map tasks=1
                Total time spent by all maps in occupied slots (ms)=99584
                Total time spent by all reduces in occupied slots (ms)=0

上面的问题百思不得甚解，完全不知道什么地方错了。
然后跟之前copy的代码进行比对。终于找出了问题所在！
注意Mapper 与 Reducer 类写成内部类，一定要加static ！！！！
留个小任务，查看一下生成的结果文件可以发现什么？
使用TextInputFormat时，进入map 函数中的LongWritable类型的key 代表什么？
经实验确认这个key 其实是本行的首字符在整个文件中的偏移量。

下一篇中介绍了如何查看执行日志，通过不断改进一个mapreduce 任务学习hadoop