hadoop入门，跑出第一个WordCount

1.环境准备

下载：http://mirror.bit.edu.cn/apache/hadoop/common/hadoop-2.7.2/hadoop-2.7.2.tar.gz

解压：解压后，修改etc/hadoop/hadoop-env.sh 中JAVA_HOME, 我的java_home(可以通过cat /etc/profile)是/user/java/latest

2.Hadoop Single_Node Cluster

参考官方文档：http://hadoop.apache.org/docs/current/hadoop-project-dist/hadoop-common/SingleCluster.html

3.WordCount示例

a.maven 配置(pom.xml)

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/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>my.hadoopstudy</groupId>
  <artifactId>hadoopstudy</artifactId>
  <packaging>jar</packaging>
  <version>1.0-SNAPSHOT</version>
  <name>hadoopstudy</name>
  <url>http://maven.apache.org</url>
  <dependencies>
       <dependency>  
            <groupId>org.apache.hadoop</groupId>  
            <artifactId>hadoop-common</artifactId>  
            <version>2.5.1</version>  
        </dependency>  
        <dependency>  
            <groupId>org.apache.hadoop</groupId>  
            <artifactId>hadoop-hdfs</artifactId>  
            <version>2.5.1</version>  
        </dependency>  
        <dependency>  
            <groupId>org.apache.hadoop</groupId>  
            <artifactId>hadoop-client</artifactId>  
            <version>2.5.1</version>  
        </dependency>
        <dependency>
            <groupId>jdk.tools</groupId>
            <artifactId>jdk.tools</artifactId>
            <version>1.8.0_65</version>
            <scope>system</scope>
            <systemPath>${JAVA_HOME}/lib/tools.jar</systemPath>
        </dependency>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>3.8.1</version>
      <scope>test</scope>
    </dependency>
  </dependencies>
</project>

b.Mapper代码：

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);
            }
        }
    }

c.Reducer代码：

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);
        }
    }

d.整个java代码如下:

package my.hadoopstudy.mapreduce;

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(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

e.打包：在项目目录下 mvn package，将target中jar包放到hadoop目录下自己建的study目录

f.运行：bin/hadoop jar study/hadoopstudy-1.0-SNAPSHOT.jar my.hadoopstudy.mapreduce.WordCount /user/wangke/wordcount/input /user/wangke/wordcount/output

4.遇到的问题及解决方式：

a.JAVA_HOME一定要记得修改

b.要按照2中官方文档修改相关的xml文件配置

c.第二次按照官方pseudo-distributed,报错如下：hadoop-there-are-0-datanodes-running-and-no-nodes-are-excluded-in-this-operation

解决方式： sbin/stop_all.sh --> 删除current文件(rm -r /tmp/hadoop-admin/dfs/data/current) ,然后重新按照pseudo-distributed就没问题了

d.在pseudo-distributed下跑jar时，connecting to resourcemanager一直连不上，，retry。这是因为没有启动yarn（本来以为这个local跑的时候，根本不需要yarn，但是只有启动yarn，才能打开8032resourceManager端口）

解决方式：修改yarn-site.xml配置：

<configuration>

<!-- Site specific YARN configuration properties -->
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>
    <property>
        <name>yarn.resourcemanager.address</name>
        <value>127.0.0.1:8032</value>
    </property>
    <property>
        <name>yarn.resourcemanager.scheduler.address</name>
        <value>127.0.0.1:8030</value>
    </property>
    <property>
        <name>yarn.resourcemanager.resource-tracker.address</name>
        <value>127.0.0.1:8031</value>
    </property>
</configuration>

sbin/yarn-start.sh 发现执行成功，bin/hdfs dfs -cat /user/wangke/wordcount/output/part-r-00000 查看结果没问题