eclipse - 运行从 Eclipse 导出的 jar 时出现 InvalidInputException

Question

我在centos7中安装了Hadoop 2.6，运行良好。但是当我运行从 Eclipse 导出的 jar 时，出现以下错误:

[root@myspark ~]# hadoop jar fengcount.jar intput output1 
17/05/26 21:24:51 INFO client.RMProxy: Connecting to ResourceManager
    at myspark/192.168.44.100:8032 17/05/26 21:24:53 INFO mapreduce.JobSubmitter: Cleaning up the staging area /tmp/hadoop-yarn/staging/root/.staging/job_1495765615548_0004 Exception in thread "main" org.apache.hadoop.mapreduce.lib.input.InvalidInputException: Input path does not exist: hdfs://myspark:54310/user/root/intput
    at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:321)
    at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.listStatus(FileInputFormat.java:264)
    at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.getSplits(FileInputFormat.java:385)
    at org.apache.hadoop.mapreduce.JobSubmitter.writeNewSplits(JobSubmitter.java:302)
    at org.apache.hadoop.mapreduce.JobSubmitter.writeSplits(JobSubmitter.java:319)
    at org.apache.hadoop.mapreduce.JobSubmitter.submitJobInternal(JobSubmitter.java:197)
    at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1297)
    at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1294)
    at java.security.AccessController.doPrivileged(Native Method)
    at javax.security.auth.Subject.doAs(Subject.java:422)
    at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1692)
    at org.apache.hadoop.mapreduce.Job.submit(Job.java:1294)
    at org.apache.hadoop.mapreduce.Job.waitForCompletion(Job.java:1315)
    at hdfs.hadoop_hdfs.fengcount.main(fengcount.java:39)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at org.apache.hadoop.util.RunJar.run(RunJar.java:221)
    at org.apache.hadoop.util.RunJar.main(RunJar.java:136)

文件input/test1.txt实际存在:

[root@myspark ~]# hdfs dfs -ls -R
drwxr-xr-x   - root supergroup          0 2017-05-26 21:02 input
-rw-r--r--   1 root supergroup         16 2017-05-24 01:57 input/test1.txt

我的代码:

package hdfs.hadoop_hdfs;

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;



public class fengcount {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        // TODO Auto-generated method stub
        Configuration conf=new Configuration();
        String[] otherargs=new GenericOptionsParser(conf,args).getRemainingArgs();
        if (otherargs.length!=2) {
            System.err.println("Usage:fengcount<int><out>");
            System.exit(2);
        } 
        @SuppressWarnings("deprecation")
        Job job=new Job(conf, "fengcount");
        job.setJarByClass(fengcount.class);
        job.setMapperClass(TokerizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, new Path(otherargs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherargs[1]));
        System.exit(job.waitForCompletion(true)?0:1);

    }

    // mapper class
    public static class TokerizerMapper extends Mapper<Object, Text, Text, IntWritable> {
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        @Override
        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            // TODO Auto-generated method stub
            System.out.println("key=" + key.toString());
            System.out.println("value=" + value.toString());

            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
            }
        }
    }
    //reduce process  
    public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();

        @Override
        public void reduce(Text key, Iterable<IntWritable> values,
                Reducer<Text, IntWritable, Text, IntWritable>.Context context)
                throws IOException, InterruptedException {
            // TODO Auto-generated method stub
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
        }
    }
    //mapreduce process
}

Answer 1

从错误日志中，我可以看到 hdfs://myspark:54310/user/root/input，我怀疑它不正确。我猜路径以 input 结尾。

祝你好运!