hadoop如何执行自己编写的MapReduce程序
比如我们现在写好了一个mapred程序如下：
package com.besttone.mapred;
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 SingleWordCount {
public static class SingleWordCountMapper 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());
String keyword = context.getConfiguration().get("word");
while (itr.hasMoreTokens()) {
String nextkey = itr.nextToken();
if (nextkey.trim().equals(keyword)) {
word.set(nextkey);
context.write(word, one);
}
}
}
}
public static class SingleWordCountReducer extends
Reducer<Text, IntWritable, Text, IntWritable> {
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable<IntWritable> values,
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);
}
}
/**
* @param args
* @throws IOException
*/
public static void main(String[] args) throws Exception {
// TODO Auto-generated method stub
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args)
.getRemainingArgs();
if (otherArgs.length != 3) {
System.err.println("Usage: singlewordcount <in> <out> <word>");
System.exit(2);
}
conf.set("word", otherArgs[2]);
Job job = new Job(conf, "single word count");
job.setJarByClass(SingleWordCount.class);
job.setMapperClass(SingleWordCountMapper.class);
job.setCombinerClass(SingleWordCountReducer.class);
job.setReducerClass(SingleWordCountReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.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);
}
}
这个mapred程序是用来统计指定单词的数量。
然后我们可以把这个类打包成JAR，比如命名叫：myexample.jar。拷贝到远程HADOOP_HOME目录下，比如我们统计input目录下的"hello"这个单词的个数，执行bin/hadoop jar myexample.jar com.besttone.mapred.SingleWordCount hdfs://master:9000/user/hadoop/input/* hdfs://master:9000/user/hadoop/output hello 。
另外一只执行方式是写一个Driver程序：
/**
* 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 com.besttone.mapred;
import org.apache.hadoop.util.ProgramDriver;
/**
* A description of an example program based on its class and a
* human-readable description.
*/
public class MapRedDriver {
public static void main(String argv[]){
int exitCode = -1;
ProgramDriver pgd = new ProgramDriver();
try {
pgd.addClass("singlewordcount", SingleWordCount.class,
"A map/reduce program that counts the words in the input files.");
pgd.driver(argv);
// Success
exitCode = 0;
}
catch(Throwable e){
e.printStackTrace();
}
System.exit(exitCode);
}
}
然后和上面那个类一起重新打包成JAR，双击jar文件打开，修改META-INF下的MANIFEST.MF文件如下：
Manifest-Version: 1.0
Ant-Version: Apache Ant 1.7.1
Created-By: 20.6-b01 (Sun Microsystems Inc.)
Main-Class: com/besttone/mapred/MapRedDriver
将Main-Class设置为Driver的全路径名,然后将jar包拷贝到hadoop_home目录下。这时候就可以不用写mapred的全路径名了，而是使用Driver里定义的别名：
bin/hadoop jar myexample.jar singlewordcount hdfs://master:9000/user/hadoop/input/* hdfs://master:9000/user/hadoop/output hello 。
执行过程中可能会遇到hadoop mapred执行目录文件权限问题
错误信息如下：
job Submission failed with exception 'java.io.IOException(The ownership/permissions on the staging directory /tmp/hadoop-hadoop-user1/mapred/staging/hadoop-user1/.staging is not as expected. It is owned by hadoop-user1 and permissions are rwxrwxrwx. The directory must be owned by the submitter hadoop-user1 or by hadoop-user1 and permissions must be rwx------)
修改权限：
bin/hadoop fs -chmod -R 700 /home/hadoop/tmp