Hadoop Mapreduce提交任务到集群时报错

Driver类代码：

package part4;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WordCount extends Configured implements Tool {
    public static void main(String[] args) throws Exception {
        String[] myArgs = {"/user/root/wordcountin/a.txt", "/user/root/wordcountout", "Hello", "\\s"};
        ToolRunner.run(new WordCount(), myArgs);
    }

    @Override
    public Configuration getConf() {
        Configuration conf = new Configuration();

        conf.setBoolean("mapreduce.app-submission.cross-platform", true);
        conf.set("fs.defaultFS", "hdfs://master:8020");
        conf.set("mapreduce.framework.name", "yarn");
        conf.set("yarn.resourcemanager.address", "master:8032");
        conf.set("yarn.resourcemanager.scheduler.address", "master:8030");
        conf.set("mapreduce.jobhistory.address", "master:10020");
        conf.set("mapreduce.job.jar", "D:\\Documents\\大数据\\作业\\homework2\\target\\homework2-1.0-SNAPSHOT.jar");

        return conf;
    }

    @Override
    public int run(String[] args) throws Exception {
        // 获取配置
        Configuration conf = getConf();
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

        if (otherArgs.length < 4) {
            System.err.println("Must have 4 arguments: input_path, output_path, word, split");
            System.exit(2);
        }

        conf.set("word", otherArgs[2]);
        conf.set("split", otherArgs[3]);

        // 任务
        Job job = Job.getInstance(conf);
        job.setJarByClass(WordCount.class);
        job.setMapperClass(MyMapper.class);
        job.setReducerClass(MyReducer.class);
        job.setJobName("homework2 part4");
        // 输入路径
        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
        // 输出路径
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        // Mapper输出键的类
        job.setMapOutputKeyClass(NullWritable.class);
        // Reducer输出键的类
        job.setOutputKeyClass(Text.class);
        // Mapper和Reducer输出值的类
        job.setOutputValueClass(IntWritable.class);
        return job.waitForCompletion(true) ? 0 : 1;
    }
}

我的hadoop版本是2.6.5，报错如下：

Exception in thread "main" java.io.IOException: Cannot initialize Cluster. Please check your configuration for mapreduce.framework.name and the correspond server addresses.

一番测试后发现问题出在conf.set("mapreduce.framework.name", "yarn");这行代码上，删掉的话能运行，但这样就用不了yarn了。

最后发现报错的原因是依赖没添加全。下面是我的pom.xml中的依赖配置：

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.6.5</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.6.5</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.6.5</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-common</artifactId>
            <version>2.6.5</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-auth</artifactId>
            <version>2.6.5</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-app</artifactId>
            <version>2.6.5</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
            <version>2.6.5</version>
        </dependency>
    </dependencies>

最终应该是hadoop-mapreduce-client-jobclient这个包起了作用。如果不确定缺了什么依赖，就试试把所有hadoop相关依赖加上吧。