Question

我一直在集群和karmasphere接口上使用分布式缓存尝试复制连接。我在下面粘贴了代码。我的程序无法在缓存中找到该文件

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.util.Hashtable;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.filecache.DistributedCache;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.InputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.KeyValueTextInputFormat;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

// A demostration of Hadoop's DistributedCache tool
// 

public class MapperSideJoinWithDistributedCache extends Configured implements Tool {
        private  final  static  String inputa =  "C:/Users/LopezGG/workspace/Second_join/input1_1" ; 
public static class MapClass extends MapReduceBase implements Mapper<Text, Text, Text, Text> {

  private Hashtable<String, String> joinData = new Hashtable<String, String>();

  @Override
  public void configure(JobConf conf) {
    try {
      Path [] cacheFiles = DistributedCache.getLocalCacheFiles(conf);
          System.out.println("ds"+DistributedCache.getLocalCacheFiles(conf));
      if (cacheFiles != null && cacheFiles.length > 0) {
        String line;
        String[] tokens;
        BufferedReader joinReader = new BufferedReader(new FileReader(cacheFiles[0].toString()));

        try {
          while ((line = joinReader.readLine()) != null) {
          tokens = line.split(",", 2);
          joinData.put(tokens[0], tokens[1]);
        }
        } finally {
          joinReader.close();
        }
      }
      else
          System.out.println("joinreader not set" );
    } catch(IOException e) {
      System.err.println("Exception reading DistributedCache: " + e);
    }
  }

  public void map(Text key, Text value, OutputCollector<Text, Text> output,  Reporter reporter) throws IOException {
    String joinValue = joinData.get(key.toString());
    if (joinValue != null) {
    output.collect(key,new Text(value.toString() + "," + joinValue));
    }
  }
}


public int run(String[] args) throws Exception {
  Configuration conf = getConf();
  JobConf job = new JobConf(conf, MapperSideJoinWithDistributedCache.class);

  DistributedCache.addCacheFile(new Path(args[0]).toUri(), job); 
  //System.out.println( DistributedCache.addCacheFile(new Path(args[0]).toUri(), conf));
    Path in = new Path(args[1]);
  Path out = new Path(args[2]);
  FileInputFormat.setInputPaths(job, in);
  FileOutputFormat.setOutputPath(job, out);
  job.setJobName("DataJoin with DistributedCache");
  job.setMapperClass(MapClass.class);
  job.setNumReduceTasks(0);
  job.setInputFormat( KeyValueTextInputFormat.class);
  job.setOutputFormat(TextOutputFormat.class);
  job.set("key.value.separator.in.input.line", ",");
  JobClient.runJob(job);
  return 0;
}

  public static void main(String[] args) throws Exception {
                long time1= System.currentTimeMillis();
                System.out.println(time1);
      int res = ToolRunner.run(new Configuration(),
      new MapperSideJoinWithDistributedCache(),args);
          long time2= System.currentTimeMillis(); 
          System.out.println(time2);
          System.out.println("millsecs elapsed:"+(time2-time1));
      System.exit(res);

  }
}

我得到的错误是

O mapred.MapTask: numReduceTasks: 0
Exception reading DistributedCache: java.io.FileNotFoundException: \tmp\hadoop-LopezGG\mapred\local\archive\-2564469513526622450_-1173562614_1653082827\file\C\Users\LopezGG\workspace\Second_join\input1_1 (The system cannot find the file specified)
ds[Lorg.apache.hadoop.fs.Path;@366a88bb
12/04/24 23:15:01 INFO mapred.Task: Task:attempt_local_0001_m_000000_0 is done. And is in the process of commiting
12/04/24 23:15:01 INFO mapred.LocalJobRunner:

但任务执行完毕。 Coudl有人请帮助我＆gt;我查看了其他帖子并进行了所有修改，但仍无法正常工作

Answer 1

我必须承认我从不使用DistributedCache类（而是通过GenericOptionsParser使用-files选项），但我不确定DistributedCache会在运行作业之前自动将本地文件复制到HDFS中。

虽然我在Hadoop文档中找不到任何关于这一事实的证据，但在Pro Hadoop书中提到了这样的事情：

http://books.google.com/books?id=8DV-EzeKigQC&pg=PA133&dq=%22The+URI+must+be+on+the+JobTracker+shared+file+system%22&hl=en&sa=X&ei=jNGXT_LKOKLA6AG1-7j6Bg&ved=0CEsQ6AEwAA#v=onepage&q=%22The%20URI%20must%20be%20on%20the%20JobTracker%20shared%20file%20system%22&f=false

在您的情况下，首先将文件复制到HDFS，当您调用DistributedCache.addCacheFile时，在HDFS中传递文件的URI，看看它是否适合您

在Hadoop 0.20中使用分布式缓存进行复制连接

1 个答案: