Hadoop 之 HDFS 分布式集群配置与使用（三）

一.集群实例创建

以三个 Hadoop 实例创建集群，可以用虚拟机，或者Docker容器来实现。本教程直接使用虚拟机演示
集群架构可参考下图：客户端、命名节点和数据节点

查看 Hadoop 配置文件目录：ll $HADOOP_HOME/etc/hadoop

Hadoop 基本概念与含义

名称	含义
HDFS	Hadoop Distributed File System，Hadoop 分布式文件系统的简称
NameNode	指挥其它节点存储的节点，用于映射文件在集群存储的位置
Secondary NameNode	副命名节点，用于备份命名节点数据，并协助命名节点进行管理工作；命名节点崩溃后可以用来恢复其数据，可以有多个
DataNode	用来储存数据块的节点，HDFS基础存储单位，受命名节点协调管理
core-site.xml	Hadoop 核心配置
hdfs-site.xml	HDFS 配置项
mapred-site.xml	MapReduce 配置项，映射和规约，对大型任务分治处理
yarn-site.xml	YARN 配置项
workers	记录所有的数据节点的主机名或 IP 地址

二.配置

1.创建三个虚拟机（Anolis）

虚拟机名称	地址	Host Name
hadoop_1	192.168.1.6	nn
hadoop_2	192.168.1.7	nd1
hadoop_3	192.168.1.8	nd2

1.修改 HostName

## 修改 192.168.1.6 服务器
hostnamectl set-hostname nn
echo "192.168.1.7 nd1" >> /etc/hosts
echo "192.168.1.8 nd2" >> /etc/hosts
## 修改 192.168.1.7 服务器
hostnamectl set-hostname nd1
echo "192.168.1.6 nn" >> /etc/hosts
echo "192.168.1.8 nd2" >> /etc/hosts
## 修改 192.168.1.8 服务器
hostnamectl set-hostname nd2
echo "192.168.1.6 nn" >> /etc/hosts
echo "192.168.1.7 nd1" >> /etc/hosts

以 192.168.1.6 为例

2.配置免密登录，配置前

ssh root@nd1

## 修改 192.168.1.6 服务器
ssh-keygen -t rsa -P "" -f ~/.ssh/id_rsa
ssh-copy-id -i ~/.ssh/id_rsa root@nd1
ssh-copy-id -i ~/.ssh/id_rsa root@nd2
## 修改 192.168.1.7 服务器
ssh-keygen -t rsa -P "" -f ~/.ssh/id_rsa
ssh-copy-id -i ~/.ssh/id_rsa root@nn
ssh-copy-id -i ~/.ssh/id_rsa root@nd2
## 修改 192.168.1.8 服务器
ssh-keygen -t rsa -P "" -f ~/.ssh/id_rsa
ssh-copy-id -i ~/.ssh/id_rsa root@nn
ssh-copy-id -i ~/.ssh/id_rsa root@nd1
## 分别配置本地登录
ssh-copy-id -i ~/.ssh/id_rsa root@localhost

以 192.168.1.6为例，免密访问 nd1

2.配置命名节点

1.在 nd1 / nd2 部署 hadoop

## 解压文件
mkdir -p /usr/local/java
mkdir -p /usr/local/hadoop
tar zxvf jdk-11.0.19_linux-x64_bin.tar.gz -C /usr/local/java/
tar zxvf hadoop-3.3.6.tar.gz -C /usr/local/hadoop/
## 设置环境变量
echo 'export JAVA_HOME=/usr/local/java/jdk-11.0.19' >> /etc/profile
echo 'export CLASSPATH=$JAVA_HOME/lib:$CLASSPATH' >> /etc/profile
echo 'export PATH=$JAVA_HOME/bin:$PATH' >> /etc/profile
echo 'export HADOOP_HOME=/usr/local/hadoop/hadoop-3.3.6' >> /etc/profile
echo 'export PATH=${PATH}:${HADOOP_HOME}/bin:${HADOOP_HOME}/sbin' >> /etc/profile
source /etc/profile

2.配置

## 1.进入
cd $HADOOP_HOME/etc/hadoop
## 2.修改配置 core-site.xml
vim core-site.xml
## 增加如下信息
   <property>
       <name>hadoop.http.staticuser.user</name>
       <value>root</value>
   </property>
   <property>
        <name>fs.defaultFS</name>
        <value>hdfs://nn:9000</value>
    </property>
    <property>
        <name>hadoop.tmp.dir</name>
        <value>file:///home/hadoop/tmp</value>
    </property>
## 3.修改配置 hdfs-site.xml
vim hdfs-site.xml
## 增加如下信息
    <property>
        <name>dfs.replication</name>
        <value>2</value>
    </property>
    <property>
        <name>dfs.namenode.name.dir</name>
        <value>file:///home/hadoop/hdfs/name</value>
    </property>
    <property>
        <name>dfs.namenode.data.dir</name>
        <value>file:///home/hadoop/hdfs/data</value>
    </property>
## 4.修改配置 yarn-site.xml
vim yarn-site.xml
## 增加如下信息
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>
    <property>
        <name>yarn.resourcemanager.hostname</name>
        <value>nn</value>
    </property>
## 5.修改配置 mapred-site.xml
vim mapred-site.xml
## 增加如下信息
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>
## 6.修改配置 workers
vim workers
## 增加如下信息
nn
nd1
nd2
## 7.将以上两个文件从 nn 复制到 nd1/nd2
scp core-site.xml hdfs-site.xml yarn-site.xml mapred-site.xml hadoop-env.sh workers root@nd1:$HADOOP_HOME/etc/hadoop
scp core-site.xml hdfs-site.xml yarn-site.xml mapred-site.xml hadoop-env.sh workers root@nd2:$HADOOP_HOME/etc/hadoop

core-site.xml

hdfs-site.xml

yarn-site.xml

mapred-site.xml

workers

## 格式化命名节点：$HADOOP_HOME/etc/hadoop
hdfs namenode -format
## 启动服务
start-dfs.sh

格式化结果

启动结果

## 启动 Yarn
start-yarn.sh

3.查看集群信息

集群信息：http://192.168.1.6:9870/dfshealth.html#tab-datanode

在 Windows 访问 http://nd1:9864 要关虚拟机防火墙，并添加 Host 解析，此处直接通过 IP 地址打开

Yarn 信息：http://192.168.1.6:8088/cluster

三.测试

1.Shell 命令

## 上传文件
hadoop fs -put /home/test.txt /log/
## 查看文件
hadoop fs -cat /log/test.txt

2.Java & MapReduce

Apache Hadoop 官网

单词统计代码

package org.example.controller;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;
import java.util.StringTokenizer;

/**
 * @author Administrator
 * @Description
 * @create 2023-07-17 23:22
 */
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);
        }
    }

}

测试类，测试地址：http://127.0.0.1:8080/test/wordCount

package org.example.controller;

import jakarta.annotation.PostConstruct;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
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.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RestController;

import java.io.IOException;

/**
 * @author Administrator
 * @Description
 * @create 2023-07-13 23:19
 */
@RestController
@RequestMapping("/test")
public class TestController {
    
    

    @PostConstruct
    public void init(){
    
    
        System.setProperty("HADOOP_USER_NAME","root");
    }

    @GetMapping("/wordCount")
    public void wordCount() throws IOException, InterruptedException, ClassNotFoundException {
    
    
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS", "hdfs://192.168.1.6:9000");
        // 打开文件并读取输出
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(WordCount.TokenizerMapper.class);
        job.setCombinerClass(WordCount.IntSumReducer.class);
        job.setReducerClass(WordCount.IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, new Path("/testData"));
        FileOutputFormat.setOutputPath(job, new Path("/output"));
        boolean result = job.waitForCompletion(true);
        // System.exit(result ? 0 : 1);
        // 打开文件并读取输出
        FileSystem fs = FileSystem.get(conf);
        Path path = new Path("/output/part-r-00000");
        FSDataInputStream ins = fs.open(path);
        StringBuilder builder = new StringBuilder();
        int ch = ins.read();
        while (ch != -1) {
    
    
            builder.append((char)ch);
            ch = ins.read();
        }
        System.out.println(builder.toString());
    }
}

测试结果