hadoop发布一个任务：远程jar包部署（备忘）

た入场券 2022-03-27 03:26 97阅读 0赞

ps：需要装好HDFS的环境

此次实验是统计各ip的访问次数。

准备工作：

1.运行hdfs：

> **\[root@CentOS ~\]\# start-dfs.sh**

2.写好任务

任务结构：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI5NTE5MDQx_size_16_color_FFFFFF_t_70][]

**MapperDemo类，规定了如何分析数据。**

package com.yun;
    
    import org.apache.hadoop.io.IntWritable;
    import org.apache.hadoop.io.LongWritable;
    import org.apache.hadoop.io.Text;
    import org.apache.hadoop.mapreduce.Mapper;
    
    import java.io.IOException;
    
    /**
     *  LongWritable 代表数据中  每行的字节行偏移量
     *  Test 每行的文本内容
     */
    public class MapperDemo extends Mapper<LongWritable, Text,Text, IntWritable> {
    
        /**
         *
         * @param key :文本偏移量
         * @param value ：每行文本
         * @param context
         * @throws IOException
         * @throws InterruptedException
         */
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            //获取第一行的第一个数据
            String ip = value.toString().split(" ")[0];
            context.write(new Text(ip),new IntWritable(1));
        }
    }

**ReducerDemo，规定了如何计算数据。**

import org.apache.hadoop.io.IntWritable;
    import org.apache.hadoop.io.Text;
    import org.apache.hadoop.mapreduce.Reducer;
    
    import java.io.IOException;
    
    public class ReducerDemo extends Reducer<Text, IntWritable,Text,IntWritable> {
        /**
         *
         * @param key :ip
         * @param values :Int[]{1,1,1,...}
         * @param context
         * @throws IOException
         * @throws InterruptedException
         */
        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int total=0;
            for (IntWritable value : values) {
                total+=value.get();
            }
            context.write(key,new IntWritable(total));
        }
    }

**CustomJobSubmiter，规约提交给hadoop做计算。**

import org.apache.hadoop.conf.Configured;
    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.lib.input.TextInputFormat;
    import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
    import org.apache.hadoop.util.Tool;
    import org.apache.hadoop.util.ToolRunner;
    
    import javax.swing.*;
    
    public class CustomJobSubmiter extends Configured implements Tool {
        public static void main(String[] args) throws Exception {
            ToolRunner.run(new CustomJobSubmiter(),args);
        }
    
        public int run(String[] args) throws Exception {
            //1 封装job
            Job job = Job.getInstance(getConf());
    
            //附加：jar类加载器
            job.setJarByClass(CustomJobSubmiter.class);
    
            //2 设置数据读入与写出格式
            job.setInputFormatClass(TextInputFormat.class);
            job.setOutputFormatClass(TextOutputFormat.class);
    
            //3 设置处理数据的路径
            TextInputFormat.addInputPath(job,new Path("/demo/input"));
            TextOutputFormat.setOutputPath(job,new Path("/demo/output"));
    
            //4 设置计算数据使用得逻辑
            job.setMapperClass(MapperDemo.class);
            job.setReducerClass(ReducerDemo.class);
    
            //5 设置Mapper输出泛型
            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(IntWritable.class);
    
            //6 设置Reducer输出泛型
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(IntWritable.class);
    
            //7 提交任务
            job.submit();
    
            return 0;
        }
    }

**pom的配置：**

<?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>com.yun</groupId>
        <artifactId>mapreduce</artifactId>
        <version>1.0-SNAPSHOT</version>
        <dependencies>
            
            <dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-hdfs</artifactId>
                <version>2.6.0</version>
            </dependency>
            
            <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>
            </dependency>
            <dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
                <version>2.6.0</version>
            </dependency>
            <dependency>
                <groupId>org.clojure</groupId>
                <artifactId>clojure</artifactId>
                <version>RELEASE</version>
                <scope>compile</scope>
            </dependency>
        </dependencies>
    </project>

打成jar包：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI5NTE5MDQx_size_16_color_FFFFFF_t_70 1][]

找到maven工程，找到项目，点击package打包

然后会看见target中多了个jar包。

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI5NTE5MDQx_size_16_color_FFFFFF_t_70 2][]

找到这个jar包的路径，把它传送到 linux 中去。

如何把文件传输到linu，有很多办法，这里不赘述。

在linux根目录下，root目录下输入ls查看可找到

![20190111212447154.png][]

然后需要准备 输入的数据

这里为一个txt的文本

先创建一个文件

> \[root@CentOS ~\]\# vi newInput.txt

在文件中输入如下ip

> 139.212.122.190  
> 61.233.169.47  
> 61.235.118.135  
> 171.10.177.236  
> 210.44.124.58  
> 171.10.177.236  
> 210.38.128.203  
> 182.81.141.169  
> 106.91.10.155  
> 171.15.236.27  
> 36.61.91.146  
> 61.233.175.233  
> 139.205.123.246  
> 171.14.166.146  
> 171.14.166.146  
> 139.212.122.190  
> 139.212.122.190  
> 171.10.60.168  
> 210.44.124.58  
> 36.61.18.65  
> 36.63.76.3  
> 139.212.122.190  
> 106.91.10.155  
> 36.63.76.3  
> 123.234.253.167  
> 61.233.169.47  
> 171.10.177.236  
> 36.63.76.3  
> 36.63.76.3  
> 139.205.123.246  
> 123.234.253.167  
> 171.15.236.27  
> 210.44.124.58  
> 121.76.252.189  
> 171.14.166.146  
> 36.60.90.114  
> 123.234.253.167

把文件放进hdfs中：

**我们在  CustomJobSubmiter 类中定义了 数据输入及输出的路径，因此要把文件放入定义的输入路径下。**

> **\[root@CentOS ~\]\# hdfs dfs -put /root/newInput.txt /demo/input**

放好后，运行jar程序。hadoop jar命令 \+ jar包 \+ 需要运行的类

> **\[root@CentOS ~\]\# hadoop jar mapreduce-1.0-SNAPSHOT.jar com.yun.CustomJobSubmiter**

结果会输出到 **/demo/output**下，通过hadoop提供的浏览器访问文件系统的方式。

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI5NTE5MDQx_size_16_color_FFFFFF_t_70 3][]

点击下载：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI5NTE5MDQx_size_16_color_FFFFFF_t_70 4][]

获取运算结果：

![20190111213658908.png][]

看懂的 点个赞吧。

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI5NTE5MDQx_size_16_color_FFFFFF_t_70]: /images/20220327/191fd85a5c554c169236abfeda2e62ef.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI5NTE5MDQx_size_16_color_FFFFFF_t_70 1]: /images/20220327/9c5c431b4aa74920a9116a2032f2296f.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI5NTE5MDQx_size_16_color_FFFFFF_t_70 2]: /images/20220327/00f8da7b0c6649da884261cb6abed019.png
[20190111212447154.png]: /images/20220327/da0c2d7eebba4fd3b217ad06ed8e089a.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI5NTE5MDQx_size_16_color_FFFFFF_t_70 3]: /images/20220327/841bc9bd0d76408c960531e3fdc89db4.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI5NTE5MDQx_size_16_color_FFFFFF_t_70 4]: /images/20220327/3cdbbaa71ba34f789fffb3de2bd9afbd.png
[20190111213658908.png]: /images/20220327/d0b49ba14cd1422a9d0c90ccd1e52e10.png