Hadoop也可以以伪分布式模式在单节点上运行，其中每个Hadoop守护程序都在单独的Java进程中运行。
hadoop简介
https://www.cnblogs.com/mh20131118/p/12146993.html

1.修改HOSTNAME

[root@localhost ~]# vim /etc/sysconfig/network
NETWORKING=yes
HOSTNAME=node00

2.修改/etc/hosts,追加内容

[root@localhost ~]# vim /etc/hosts
192.168.52.80 node00

3.关闭selinux

[root@localhost ~]# vim /etc/sysconfig/selinux
SELINUX=disabled
SELINUXTYPE=targeted

4.配置免秘钥登录

现在检查您是否可以在没有密码的情况下SSH到本地主机
如果没有密码就无法SSH到localhost，请执行以下命令
#ssh-keygen 秘钥生成器
#-t rsa 生成的类型为rsa
#-P 是否需要密码 ''不需要密码
#-f 文件存放位置
[root@localhost hadoop-3.2.1]# ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa
Generating public/private rsa key pair.
Your identification has been saved in /root/.ssh/id_rsa.
Your public key has been saved in /root/.ssh/id_rsa.pub.
The key fingerprint is:
8a:0d:c8:d4:08:1f:e1:4f:b2:b0:e5:31:f2:0b:d5:3b root@localhost.localdomain
The key's randomart image is:
+--[ RSA 2048]----+
|. o.             |
| + =             |
|o @ +            |
| @ O .           |
|o * E   S        |
| . . = .         |
|  . . o          |
|                 |
|                 |
+-----------------+
[root@localhost hadoop-3.2.1]# cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys
[root@localhost hadoop-3.2.1]# chmod 0600 ~/.ssh/authorized_keys

5. 修改主节点namenode配置

#默认值地址https://hadoop.apache.org/docs/stable/hadoop-project-dist/hadoop-common/core-default.xml
[root@localhost hadoop-3.2.1]# vim etc/hadoop/core-site.xml
<configuration>
<property>
      <name>fs.defaultFS</name>
      <value>hdfs://node00:9000</value>
</property>
<property>
      <name>hadoop.tmp.dir</name>
      <value>/opt/hadoop/pseudo</value>
</property>
</configuration>

6.修改workers

[root@localhost hadoop]# vim /opt/hadoop/hadoop-3.2.1/etc/hadoop/workers 
#改为
node00

7.修改从节点的配置

[root@localhost hadoop-3.2.1]# vim etc/hadoop/hdfs-site.xml
<configuration>
    <property>
        <name>dfs.replication</name>
        <value>1</value>
    </property>
    <property>
        <name>dfs.namenode.secondary.http-address</name>
        <value>node00:9868</value>
    </property>
</configuration>

8.格式化

[root@localhost hadoop]# hdfs namenode -format
#格式化后查看生成的信息
[root@localhost current]# view /opt/hadoop/pseudo/dfs/name/current/VERSION
#格式化时只生成namenode的信息，datanode和secondary-namenode的信息会在集群启动时生成

9.启动

[root@localhost pseudo]# start-dfs.sh
WARNING: HADOOP_SECURE_DN_USER has been replaced by HDFS_DATANODE_SECURE_USER. Using value of HADOOP_SECURE_DN_USER.
Starting namenodes on [node00]
Starting datanodes
Starting secondary namenodes [node00]
[root@localhost pseudo]# jps
67649 Jps
67313 DataNode
67488 SecondaryNameNode
67146 NameNode

问题

#2.启动NameNode守护程序和DataNode守护程序
若在启动时产生以下问题
[root@localhost hadoop-3.2.1]# sbin/start-dfs.sh
Starting namenodes on [localhost]
ERROR: Attempting to operate on hdfs namenode as root
ERROR: but there is no HDFS_NAMENODE_USER defined. Aborting operation.
Starting datanodes
ERROR: Attempting to operate on hdfs datanode as root
ERROR: but there is no HDFS_DATANODE_USER defined. Aborting operation.
Starting secondary namenodes [localhost.localdomain]
ERROR: Attempting to operate on hdfs secondarynamenode as root
ERROR: but there is no HDFS_SECONDARYNAMENODE_USER defined. Aborting operation.
2020-11-22 22:25:22,882 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
#出错，大概意思不允许root用户启动，修改启动命令
[root@localhost hadoop-3.2.1]# vim sbin/start-dfs.sh
#添加以下内容
HDFS_DATANODE_USER=root
HADOOP_SECURE_DN_USER=hdfs
HDFS_NAMENODE_USER=root
HDFS_SECONDARYNAMENODE_USER=root
#对sbin/stop-dfs.sh执行同样的操作
#重新启动
WARNING: HADOOP_SECURE_DN_USER has been replaced by HDFS_DATANODE_SECURE_USER. Using value of HADOOP_SECURE_DN_USER.
Starting namenodes on [localhost]
Starting datanodes
Starting secondary namenodes [localhost.localdomain]
localhost.localdomain: Warning: Permanently added 'localhost.localdomain' (RSA) to the list of known hosts.
2020-11-22 22:31:52,397 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
#解决Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
vim /etc/profile
#添加
export HADOOP_ROOT_LOGGER=DEBUG,console
source /etc/profile
#查看详细报错信息，有这样一条报错信息
2020-11-22 22:51:41,027 DEBUG util.NativeCodeLoader: Failed to load native-hadoop with error: java.lang.UnsatisfiedLinkError: /opt/hadoop/hadoop-3.2.1/lib/native/libhadoop.so.1.0.0: /lib64/libc.so.6: version `GLIBC_2.14' not found (required by /opt/hadoop/hadoop-3.2.1/lib/native/libhadoop.so.1.0.0)
`GLIBC_2.14' not found
#系统的glibc版本太低，查看当前系统的glibc支持的所有版本
[root@localhost bin]# strings /lib64/libc.so.6 |grep GLIBC_
GLIBC_2.2.5
GLIBC_2.2.6
GLIBC_2.3
GLIBC_2.3.2
GLIBC_2.3.3
GLIBC_2.3.4
GLIBC_2.4
GLIBC_2.5
GLIBC_2.6
GLIBC_2.7
GLIBC_2.8
GLIBC_2.9
GLIBC_2.10
GLIBC_2.11
GLIBC_2.12
GLIBC_PRIVATE
#下载glibc-2.17.tar.gz,地址
http://ftp.gnu.org/gnu/glibc/glibc-2.17.tar.gz
#安装的先决条件
yum install gcc libffi-devel python-devel openssl-devel wget -y
#使用默认的镜像下载会非常慢，改为阿里的镜像，下面是教程地址
https://developer.aliyun.com/mirror/centos?spm=a2c6h.13651102.0.0.3e221b11sciRdQ
从2020年12月以后，执行以下命令切换为阿里的源
sed -i "s|enabled=1|enabled=0|g" /etc/yum/pluginconf.d/fastestmirror.conf
mv /etc/yum.repos.d/CentOS-Base.repo /etc/yum.repos.d/CentOS-Base.repo.backup
curl -o /etc/yum.repos.d/CentOS-Base.repo https://www.xmpan.com/Centos-6-Vault-Aliyun.repo 
yum clean all
yum makecache
#解压
[root@localhost glibc]# tar -xvf glibc-2.17.tar.gz
[root@localhost glibc]# mkdir /opt/glibc/glibc-2.17/build
[root@localhost glibc]# cd /opt/glibc/glibc-2.17/build/
[root@localhost build]# ../configure --prefix=/usr --disable-profile --enable-add-ons --with-headers=/usr/include --with-binutils=/usr/bin
[root@localhost build]# make && make install
#先停止，再启动
[root@localhost sbin]# ./stop-dfs.sh
[root@localhost sbin]# ./start-dfs.sh
[root@localhost sbin]# jps
62514 Jps
62355 SecondaryNameNode
62149 DataNode
61981 NameNode

9.浏览器访问，默认端口9870

http://192.168.52.80:9870/dfshealth.html#tab-overview

2020-11-22_160416.jpg

10.创建执行MapReduce（计算框架）的HDFS（分布式存储系统）目录

#帮助命令
[root@localhost hadoop-3.2.1]# ./bin/hdfs dfs --help
#创建目录(默认)
[root@localhost hadoop-3.2.1]# ./bin/hdfs dfs -mkdir /user
[root@localhost hadoop-3.2.1]# ./bin/hdfs dfs -mkdir /user/root
#在浏览器上查看创建的目录
#删除目录
[root@localhost hadoop-3.2.1]# ./bin/hdfs dfs -rm -r /user/root

2020-11-22_163055.jpg

11.复制输入文件到HDFS

#默认到/user/root目录下
[root@localhost hadoop-3.2.1]# bin/hdfs dfs -mkdir input
[root@localhost hadoop-3.2.1]# bin/hdfs dfs -put etc/hadoop/*.xml input
#查看

2020-11-22_170253.jpg

12.运行一些例子

hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-3.2.1.jar grep input output 'dfs[a-z.]+'