openEuler 单机部署 Hadoop SingleNode 模式

openEuler 单机部署 Hadoop SingleNode 模式

升级操作系统和软件

yum -y update

升级后建议重启

安装常用软件

yum -y install gcc gcc-c++ autoconf automake cmake make rsync openssh-server vim man zip unzip net-tools zlib zlib-devel openssl openssl-devel pcre-devel tcpdump lrzsz tar

修改主机名

hostnamectl set-hostname hadoop
或者
vim /etc/hostname 
hadoop
bash

修改IP地址

vim /etc/sysconfig/network-scripts/ifcfg-ens160

网卡 配置文件示例

TYPE=Ethernet
PROXY_METHOD=none
BROWSER_ONLY=no
BOOTPROTO=none
DEFROUTE=yes
IPV4_FAILURE_FATAL=no
IPV6INIT=yes
IPV6_AUTOCONF=yes
IPV6_DEFROUTE=yes
IPV6_FAILURE_FATAL=no
NAME=ens160
UUID=943779e9-249c-44bb-b272-d49ea5831ed4
DEVICE=ens160
ONBOOT=yes
IPADDR=192.168.28.10
PREFIX=24
GATEWAY=192.168.28.2
DNS1=192.168.28.2

保存后
nmcli con up ens160
重启网络服务

关闭防火墙

systemctl stop firewalld
systemctl disable firewalld
vim /etc/selinux/config
# This file controls the state of SELinux on the system.
# SELINUX= can take one of these three values:
# 	enforcing - SELinux security policy is enforced.
# 	permissive - SELinux prints warnings instead of enforcing.
# 	disabled - No SELinux policy is loaded.
# SELINUX=enforcing
# SELINUXTYPE= can take one of three two values:
# 	targeted - Targeted processes are protected,
# 	minimum - Modification of targeted policy. Only selected processes are protected. 
# 	mls - Multi Level Security protection.
# SELINUXTYPE=targeted 

SELINUX=disabled

执行下面命令

setenforce 0

或者

sed -i 's/SELINUX=enforcing/SELINUX=disabled/g' /etc/selinux/config
setenforce 0

创建软件安装目录并上传软件,配置环境变量

mkdir -p /opt/soft
cd /opt/soft

# 上传jdk zookeeper

tar -zxvf jdk-8u361-linux-x64.tar.gz
mv jdk1.8.0_361 jdk8
tar -zxvf hadoop-3.3.5.tar.gz
mv hadoop-3.3.5 hadoop3

vim /etc/profile
	
export JAVA_HOME=/opt/soft/jdk8
export CLASSPATH=.:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar
export PATH=$PATH:$JAVA_HOME/bin

export HADOOP_HOME=/opt/soft/hadoop3

export HADOOP_INSTALL=${HADOOP_HOME}
export HADOOP_MAPRED_HOME=${HADOOP_HOME}
export HADOOP_COMMON_HOME=${HADOOP_HOME}
export HADOOP_HDFS_HOME=${HADOOP_HOME}
export YARN_HOME=${HADOOP_HOME}
export PATH=${PATH}:${HADOOP_HOME}/bin:${HADOOP_HOME}/sbin
export HADOOP_CONF_DIR=${HADOOP_HOME}/etc/hadoop

export HDFS_NAMENODE_USER=root
export HDFS_DATANODE_USER=root
export HDFS_SECONDARYNAMENODE_USER=root
export YARN_RESOURCEMANAGER_USER=root
export YARN_NODEMANAGER_USER=root

编辑完成后使用source命令使文件~/.bash_profile生效执行以下命令
source /etc/profile
检查环境变量
printenv

修改域名映射

vim /etc/hosts
192.168.28.10 hadoop

修改后建议重启

修改Hadoop配置文件 在hadoop解压后的目录找到 etc/hadoop目录

cd /opt/soft/hadoop3

修改如下配置文件

hadoop-env.sh
core-site.xml
hdfs-site.xml
workers
mapred-site.xml
yarn-site.xml

hadoop-env.sh 文件末尾追加

export JAVA_HOME=/opt/soft/jdk8
export HDFS_NAMENODE_USER=root
export HDFS_DATANODE_USER=root
export HDFS_ZKFC_USER=root
export HDFS_JOURNALNODE_USER=root

export YARN_RESOURCEMANAGER_USER=root
export YARN_NODEMANAGER_USER=root

core-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://hadoop:9000</value>
    </property>
    <property>
    	<name>hadoop.tmp.dir</name>
    	<value>/home/hadoop_data</value>
    </property>
    <property>
    	<name>hadoop.http.staticuser.user</name>
    	<value>root</value>
    </property>
</configuration>

hdfs-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <property>
        <name>dfs.replication</name>
        <value>1</value>
    </property>
</configuration>

workers

hadoop

mapred-site.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>
    <property>
        <name>mapreduce.application.classpath</name>
        <value>$HADOOP_MAPRED_HOME/share/hadoop/mapreduce/*:$HADOOP_MAPRED_HOME/share/hadoop/mapreduce/lib/*</value>
    </property>
</configuration>

yarn-site.xml

<?xml version="1.0"?>
<configuration>
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>
    <property>
        <name>yarn.nodemanager.env-whitelist</name>
        <value>JAVA_HOME,HADOOP_COMMON_HOME,HADOOP_HDFS_HOME,HADOOP_CONF_DIR,CLASSPATH_PREPEND_DISTCACHE,HADOOP_YARN_HOME,HADOOP_HOME,PATH,LANG,TZ,HADOOP_MAPRED_HOME</value>
    </property>
</configuration>

配置ssh免密钥登录

创建本地秘钥并将公共秘钥写入认证文件

ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa
cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys

# 或者

ssh-copy-id hadoop
#远程登录自己
ssh hadoop
#Are you sure you want to continue connecting (yes/no)? 此处输入yes
#登录成功后exit或者logout返回
exit

Hadoop初始化

# 创建数据目录
mkdir -p /home/hadoop_data
# 格式化文件系统
hdfs namenode -format
# 启动 NameNode SecondaryNameNode DataNode 
start-dfs.sh
# 查看启动进程
jps
# 看到 DataNode SecondaryNameNode NameNode 三个进程代表启动成功
# 启动 ResourceManager daemon 和 NodeManager
start-yarn.sh
# 看到 DataNode NodeManager SecondaryNameNode NameNode ResourceManager 五个进程代表启动成功

重点提示:

# 关机之前 依关闭服务
stop-yarn.sh
stop-dfs.sh
# 开机后 依次开启服务
start-dfs.sh
start-yarn.sh

或者

# 关机之前关闭服务
stop-all.sh
# 开机后开启服务
start-all.sh
#jps 检查进程正常后开启胡哦关闭在再做其它操作
posted @ 2023-04-11 21:43  JD_L  阅读(50)  评论(0编辑  收藏  举报