linux下远程调用hadoop集群服务

1 .非集群的机器也需要hadoop的运行环境，所以版本一直，xml配置为官方初始化的，只需要将集群机器的yarn-site.xml拷贝过来即可

2.  程序里面指定需要调用的namenode

3.另外 SSH免密码RSA也最好和集群机器一样都添加一下

<?xml version="1.0"?>
<!--
  Licensed under the Apache License, Version 2.0 (the "License");
  you may not use this file except in compliance with the License.
  You may obtain a copy of the License at

    http://www.apache.org/licenses/LICENSE-2.0

  Unless required by applicable law or agreed to in writing, software
  distributed under the License is distributed on an "AS IS" BASIS,
  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  See the License for the specific language governing permissions and
  limitations under the License. See accompanying LICENSE file.
-->
<configuration>

		<property>

    <name>yarn.resourcemanager.hostname</name>

    <value>hadoop1</value>

 </property>


 <property>
               <name>yarn.nodemanager.aux-services</name>
               <value>mapreduce_shuffle</value>
        </property>
        <property>                                                                
<name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>
               <value>org.apache.hadoop.mapred.ShuffleHandler</value>
        </property>
        <property>
               <name>yarn.resourcemanager.address</name>
               <value>hadoop1:8032</value>
       </property>
       <property>
               <name>yarn.resourcemanager.scheduler.address</name>
               <value>hadoop1:8030</value>
       </property>
       <property>
            <name>yarn.resourcemanager.resource-tracker.address</name>
             <value>hadoop1:8031</value>
      </property>
      <property>
              <name>yarn.resourcemanager.admin.address</name>
               <value>hadoop1:8033</value>
       </property>
       <property>
               <name>yarn.resourcemanager.webapp.address</name>
               <value>hadoop1:8088</value>
       </property>
</configuration>

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package hadoop;
	
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.yarn.conf.YarnConfiguration;

public class GtWebCount {
	
	static final String INPUT_PATH="hdfs://192.168.3.150:8020/kpi01";
	static final String OUT_PATH="hdfs://192.168.3.150:8020/output7878";

	public static void main(String[] args) throws Exception {
		Configuration conf = new YarnConfiguration();  
        conf.set("fs.defaultFS", "hdfs://192.168.3.150:8020");
        conf.set("mapreduce.framework.name", "yarn");  
        conf.set("yarn.resourcemanager.address", "192.168.3.150:8032");  
        
	    Job job = new Job(conf, "Gt word count");
	    job.setJarByClass(GtWebCount.class);
	    job.setMapperClass(GtTokenizerMapper.class);
	    job.setCombinerClass(GtIntSumReducer.class);
	    job.setReducerClass(GtIntSumReducer.class);
	    job.setOutputKeyClass(Text.class);
	    job.setOutputValueClass(IntWritable.class);
	      FileInputFormat.addInputPath(job, new Path(INPUT_PATH));
	    FileOutputFormat.setOutputPath(job,new Path(OUT_PATH));
	    System.exit(job.waitForCompletion(true) ? 0 : 1);
	  }
	
  public static class GtTokenizerMapper 
       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());
        System.out.println("word.toString()"+word.toString());
        context.write(word, one);
      }
    }
  }
  
  public static class GtIntSumReducer 
       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);
   //   if(sum>5){
      context.write(key, result);
    //  	}
      }
  }

  
}