【大数据】一键安装hadoop（伪集群）

大数据选型中，很多都要依赖使用hadoop，工作中需要快速的构建hadoop测试环境。可以使用下面脚本快速安装hadoop环境。

#!/bin/bash
#################################################################################
# 作者：cxy@toc-2022-12-05                                                           
# 功能：自动搭建hadoop 伪集群模式（用于测试）
# https://hadoop.apache.org/docs/stable/hadoop-project-dist/hadoop-common/SingleCluster.html#Standalone_Operation                                           
#                                                                               
#################################################################################

proj_dir=/cxy
proj_bao_dir="${proj_dir}/bao"
proj_jdk_dir="${proj_dir}/jdk"
proj_bd_dir="${proj_dir}/bigdata"
proj_bd_data_dir="/cxy/bigdata/data/hadoop"

mkdir -p ${proj_bao_dir}
mkdir ${proj_jdk_dir}
mkdir ${proj_bd_dir}

install_jdk(){
cd ${proj_bao_dir}
wget https://repo.huaweicloud.com/java/jdk/8u151-b12/jdk-8u151-linux-x64.tar.gz

tar xf ${proj_bao_dir}/jdk-8u151-linux-x64.tar.gz -C ${proj_jdk_dir}
cat >> /etc/profile <<EOF

export JAVA_HOME=${proj_jdk_dir}/jdk1.8.0_151
export JRE_HOME=\${JAVA_HOME}/jre
export CLASSPATH=.:\${JAVA_HOME}/lib:\${JRE_HOME}/lib
export PATH=.:\${JAVA_HOME}/bin:\$PATH
EOF

source /etc/profile
}

echo "0、安装JDK（如需要，解开注释）"
install_jdk

echo "1、创建目录、下载tar包、解压"
mkdir ${proj_bd_dir}
cd ${proj_bd_dir}
wget https://repo.huaweicloud.com/apache/hadoop/common/hadoop-3.3.2/hadoop-3.3.2.tar.gz --no-check-certificate
mkdir
tar zxvf hadoop-3.3.2.tar.gz


echo "2、写入环境变量"
cat >> /etc/profile <<EOF

#Hadoop
export HADOOP_HOME=${proj_bd_dir}/hadoop-3.3.2
export PATH=\$PATH:\$HADOOP_HOME/bin
export PATH=\$PATH:\$HADOOP_HOME/sbin

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
EOF

source /etc/profile
hadoop version


echo "3、修改hadoop相关配置文件"
cd ${proj_bd_dir}/hadoop-3.3.2

#备份要改动的文件
cp etc/hadoop/hadoop-env.sh etc/hadoop/hadoop-env.sh.bak
cp etc/hadoop/core-site.xml etc/hadoop/core-site.xml.bak
cp etc/hadoop/hdfs-site.xml etc/hadoop/hdfs-site.xml.bak

#修改配置文件
sed -i '42aexport JAVA_HOME='${proj_jdk_dir}'/jdk1.8.0_151' etc/hadoop/hadoop-env.sh

rm -f etc/hadoop/core-site.xml
touch etc/hadoop/core-site.xml
cat >> etc/hadoop/core-site.xml <<EOF
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<configuration>
	<property>
   		<name>fs.defaultFS</name>
   		<value>hdfs://localhost:9000</value>
 	</property>

 	<!-- 数据存储目录 -->
  	<property>
   		<name>hadoop.tmp.dir</name>
   		<value>${proj_bd_data_dir}/tmp</value>
 	</property>

 	<!-- 仅限测试环境下使用 -->
 	<property>
        <name>hadoop.http.staticuser.user</name>
        <value>root</value>
    </property>
</configuration>
EOF

rm -f etc/hadoop/hdfs-site.xml
touch etc/hadoop/hdfs-site.xml
cat >> etc/hadoop/hdfs-site.xml <<EOF
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<configuration>
	<property>
		<name>dfs.namenode.name.dir</name>
		<value>file:${proj_bd_data_dir}/hdfs/name</value>
	</property>

	<property>
	    <name>dfs.datanode.data.dir</name>
	    <value>file:${proj_bd_data_dir}/hdfs/data</value>
	</property>

	<property>
	     <name>dfs.replication</name>
	     <value>1</value>
	</property>
</configuration>
EOF

echo "4、配置自登陆"
ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa
cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys
chmod 0600 ~/.ssh/authorized_keys

echo "5、初始化文件系统"
#Format the filesystem
bin/hdfs namenode -format

echo "6、启动服务"
sbin/start-dfs.sh

echo "7、验证"
jps

echo "安装完成，访问：http://ip:9870/"

#上传测试命令：hadoop fs -put ~/install_hadoop.sh /aaa

保存该文件：install_hadoop.sh

执行：

chmod +x install_hadoop.sh
 
./install_hadoop.sh