hadoop2.6集群无法初始化.使用本地jar成功运行，但未使用maven依赖项

Question

我正在尝试使用apachehadoop2.6.0调试wordcount示例。我在eclipse中创建了该项目。我的第一次尝试是配置构建路径，并将所有hadoop jar文件（从hadoop文件夹中提取）包含在构建路径中。我可以成功地运行单词计数并得到结果。然后，我的第二个尝试是使这个项目成为一个"maven"项目，并使用pom.xml指定所需的hadoop jar（并在buildpath中删除本地jar）。问题来了。这次异常抛出如下：

Exception in thread "main" java.io.IOException: Cannot initialize Cluster. Please check your configuration for mapreduce.framework.name and the correspond server addresses.
    at org.apache.hadoop.mapreduce.Cluster.initialize(Cluster.java:120)
    at org.apache.hadoop.mapreduce.Cluster.<init>(Cluster.java:82)
    at org.apache.hadoop.mapreduce.Cluster.<init>(Cluster.java:75)
    at org.apache.hadoop.mapreduce.Job$9.run(Job.java:1266)
    at org.apache.hadoop.mapreduce.Job$9.run(Job.java:1262)
    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:1628)
    at org.apache.hadoop.mapreduce.Job.connect(Job.java:1261)
    at org.apache.hadoop.mapreduce.Job.submit(Job.java:1290)
    at org.apache.hadoop.mapreduce.Job.waitForCompletion(Job.java:1314)
    at WordCount.main(WordCount.java:59)

我的wordcount代码是非常简单和经典的wordcount。

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;
public class WordCount {
  public static class TokenizerMapper
       extends Mapper<Object, Text, Text, IntWritable>{
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();
    public void map(Object key, Text value, Context context
                    ) throws IOException, InterruptedException {
      StringTokenizer itr = new StringTokenizer(value.toString());
      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());
        context.write(word, one);
      }
    }
  }
  public static class IntSumReducer
       extends Reducer<Text,IntWritable,Text,IntWritable> {
    private IntWritable result = new IntWritable();
    public void reduce(Text key, Iterable<IntWritable> values,
                       Context context
              ) throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable val : values) {
          sum += val.get();
        }
        result.set(sum);
        context.write(key, result);
      }
    }
    public static void main(String[] args) throws Exception {
      Configuration conf = new Configuration();
      Job job = Job.getInstance(conf, "word count");
      job.setJarByClass(WordCount.class);
      job.setMapperClass(TokenizerMapper.class);
      job.setCombinerClass(IntSumReducer.class);
      job.setReducerClass(IntSumReducer.class);
      job.setOutputKeyClass(Text.class);
      job.setOutputValueClass(IntWritable.class);
      FileInputFormat.addInputPath(job, new Path("/home/jsun/share/wc/input"));              
      FileOutputFormat.setOutputPath(job, new Path("/home/jsun/share/wc/output"));
      System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
  }

maven的pom.xml：

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/1/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>wordcount2</groupId>
  <artifactId>wordcount2</artifactId>
  <version>0.0.1-SNAPSHOT</version>
  <repositories>                                                                                     
    <repository>
      <id>apache</id>
      <url>http://central.maven.org/maven2/</url>
    </repository>
  </repositories>
  <build>
    <sourceDirectory>src</sourceDirectory>
    <resources>
      <resource>
        <directory>src</directory>
        <excludes>
          <exclude>**/*.java</exclude>
        </excludes>
      </resource>
    </resources>
    <plugins>
      <plugin>
        <artifactId>maven-compiler-plugin</artifactId>
        <version>3.1</version>
        <configuration>
          <source>1.8</source>
          <target>1.8</target>
        </configuration>
      </plugin>
    </plugins>
  </build>
  <dependencies>
    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-common</artifactId>
      <version>2.6.0</version>
    </dependency>
    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-mapreduce-client-core</artifactId>
      <version>2.6.0</version>
      <type>jar</type>
    </dependency>
  </dependencies>
</project>

使用本地hadoop jar和使用maven依赖关系有什么区别？这是集群、字数或使用maven的问题吗？

提前谢谢。

Answer 1

请检查此链接我遇到了同样的问题，我的机器上没有安装hadoop。没有安装就无法运行该程序。我认为它会寻找一些环境变量来运行hadoop命令。

希望这能帮助