在Windows 10上安装单机版的hadoop-3.3.5

1、Hadoop是一个由Apache基金会所开发的分布式系统基础架构。用户可以不需要了解分布式底层细节的情况下，开发分布式程序。充分利用集群进行高速运算和存储。

2、下载Hadoop，我们在清华大学的镜像站下载

Index of /apache/hadoop/core/hadoop-3.3.6 (tsinghua.edu.cn)

3、下载之后解压缩

​4、安装相应的环境

4.1、jdk1.8或者jdk11，

4.2、配置hadoop环境

​

​

5、修改hadoop配置

5.1、修改start-all.cmd中的配置

@rem start hdfs daemons if hdfs is present
if exist %HADOOP_HDFS_HOME%\sbin\start-dfs.cmd (
  call %HADOOP_HDFS_HOME%\sbin\start-dfs.cmd --config %HADOOP_CONF_DIR%
)

@rem start yarn daemons if yarn is present
if exist %HADOOP_YARN_HOME%\sbin\start-yarn.cmd (
  call %HADOOP_YARN_HOME%\sbin\start-yarn.cmd --config %HADOOP_CONF_DIR%
)

5.2、修改yarn-site.xml

<configuration>

<!-- Site specific YARN configuration properties -->
 <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.hostname</name>
        <value>localhost</value>
    </property>
</configuration>

5.3、mapred-site.xml

<configuration>
 <property>
       <name>mapreduce.framework.name</name>
       <value>yarn</value>
    </property>
</configuration>

5.4、hdfs-site.xml

<configuration>
	<property>
        <name>dfs.replication</name>
        <value>1</value>
    </property>
    <property>
        <name>dfs.namenode.name.dir</name>
        <value>/D:/bigdata/hadoop/data/namenode</value> //注意前面部分路径修改为自己的
    </property>
    <property>
        <name>dfs.datanode.data.dir</name>
        <value>/D:/bigdata/hadoop/data/datanode</value> //注意前面部分路径修改为自己的
    </property>
	<property>
	   <name>dfs.permissions.enabled</name>
	   <value>false</value>
	</property>
</configuration>

5.5、core-site.xml

<configuration>
	<property>
        <name>hadoop.tmp.dir</name>
        <value>/D:/bigdata/hadoop/data/tmp</value> //注意前面部分路径修改为自己的
    </property>
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://localhost:9000</value>
    </property>
	<property>
        <name>hadoop.http.authentication.simple.anonymous.allowed</name>
        <value>true</value>
    </property>
</configuration>

5.6、需要拷贝winutils下的winutils.exe，hadoop.dll到hadoop的bin下面

在/ect/hadoop/hadoop-env.cmd中设置set JAVA_HOME=D:/Java/jdk1.8.0_311，jdk的环境地址

修改start-yarn.cmd的配置

setlocal enabledelayedexpansion

echo starting yarn daemons

if not defined HADOOP_BIN_PATH ( 
  rem set HADOOP_BIN_PATH=%~dp0
  set HADOOP_BIN_PATH=%HADOOP_HOME%\bin
)

if "%HADOOP_BIN_PATH:~-1%" == "\" (
  set HADOOP_BIN_PATH=%HADOOP_BIN_PATH:~0,-1%
)

set DEFAULT_LIBEXEC_DIR=%HADOOP_BIN_PATH%\..\libexec
if not defined HADOOP_LIBEXEC_DIR (
  set HADOOP_LIBEXEC_DIR=%DEFAULT_LIBEXEC_DIR%
)

call %HADOOP_LIBEXEC_DIR%\yarn-config.cmd %*
if "%1" == "--config" (
  shift
  shift
)

@rem start resourceManager
start "Apache Hadoop Distribution" %HADOOP_HOME%\bin\yarn resourcemanager
@rem start nodeManager
start "Apache Hadoop Distribution" %HADOOP_HOME%\bin\yarn nodemanager
@rem start proxyserver
@rem start "Apache Hadoop Distribution" %HADOOP_HOME%\yarn proxyserver

endlocal

5.7、输入hdfs namenode -format格式化

hdfs namenode -format

5.8、进入hadoop/sbin目录执行start-all.cmd

D:\bigdata\hadoop\sbin>start-all.cmd
This script is Deprecated. Instead use start-dfs.cmd and start-yarn.cmd
starting yarn daemons

5.9、jps查看

D:\bigdata\hadoop\sbin>jps
8448 Jps
28360 NameNode
29592 ResourceManager
18108 NodeManager
20940 DataNode

5.10、启动成功后界面

http://localhost:8088/cluster

http://localhost:9870/

单机版的hadoop就启动成功