Linux Hadoop平台伪分布式安装

Linux Hadoop 伪分布式安装

    • [1. JDK](#1. JDK)
    • [2. Hadoop](#2. Hadoop)
    • [3. Mysql+Hive](#3. Mysql+Hive)
      • [3.1 Mysql8安装](#3.1 Mysql8安装)
      • [3.2 Hive安装](#3.2 Hive安装)
    • [4. Spark](#4. Spark)
      • [4.1 Maven安装](#4.1 Maven安装)
      • [4.2 Scala安装](#4.2 Scala安装)
      • [4.3 Spark编译并安装](#4.3 Spark编译并安装)
    • [5. Zookeeper](#5. Zookeeper)
    • [6. HBase](#6. HBase)

版本概要:

  • jdk: jdk-8u391-linux-x64.tar.gz
  • hadoop:hadoop-3.3.1.tar.gz
  • hive:apache-hive-3.1.2-bin.tar.g
  • mysql:mysql-8.0.27-1.el7.x86_64.rpm-bundle.tar
  • maven:apache-maven-3.5.4-bin.tar.gz
  • scala:scala-2.11.12.tgz
  • spark:spark-2.4.5.tgz
  • zookeeper:zookeeper-3.4.10.tar.gz
  • hbase:hbase-2.4.12-bin.tar.gz

1. JDK

JDK下载:https://www.oracle.com/java/technologies/downloads/

shell 复制代码
# 解压
[root@sole install]# tar -zxvf jdk-8u391-linux-x64.tar.gz -C /opt/software/
##########################################################################################
# 编辑环境变量
[root@sole ~]# vi /etc/profile.d/my.sh
# JAVA_HOME
export JAVA_HOME=/opt/software/jdk1.8.0_391
export JRE_HOME=${JAVA_HOME}/jre
export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib:$CLASSPATH
export JAVA_PATH=${JAVA_HOME}/bin:${JRE_HOME}/bin
export PATH=$PATH:${JAVA_PATH}

# 重新加载
[root@sole ~]# source /etc/profile

2. Hadoop

下载地址:https://archive.apache.org/dist/

shell 复制代码
# 解压
[root@sole install]# tar -zxvf hadoop-3.3.1.tar.gz -C /opt/software/
##########################################################################################
# 编辑环境变量
[root@sole ~]# vi /etc/profile.d/my.sh
# HADOOP_HOME
export HADOOP_HOME=/opt/software/hadoop-3.3.1
export PATH=$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$PATH
# 重新加载
[root@sole ~]# source /etc/profile
shell 复制代码
# Hadoop配置修改
[root@sole software]# cd hadoop-3.3.1/etc/hadoop/

[root@sole hadoop]# vi hadoop-env.sh
export JAVA_HOME=/opt/software/jdk1.8.0_391
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
shell 复制代码
[root@sole hadoop]# vi core-site.xml
xml 复制代码
<configuration>
<!-- 指定Hadoop所使用的文件系统schema(URL),HDFS的老大(NameNode)的地址 -->
<property>
    <name>fs.defaultFS</name>
    <value>hdfs://sole:9000</value>
</property>
<!-- 指定Hadoop运行时产生文件的储存目录,默认是/tmp/hadoop-${user.name} -->
<property>
    <name>hadoop.tmp.dir</name>
    <value>/opt/software/hadoop-3.3.1/hadoopdata</value>  
</property>
</configuration>
shell 复制代码
[root@sole hadoop]# vi hdfs-site.xml 
xml 复制代码
<configuration>
<!-- 指定HDFS副本的数量 -->
<property>
    <name>dfs.replication</name>
    <value>1</value>
</property>
<property>
    <name>dfs.namenode.name.dir</name>
    <value>/opt/software/hadoop-3.3.1/tmp/name</value>
</property>
<property>
    <name>dfs.datanode.data.dir</name>
    <value>/opt/software/hadoop-3.3.1/tmp/data</value>
</property>
</configuration>
shell 复制代码
[root@sole hadoop]# vi yarn-site.xml 
xml 复制代码
<configuration>
<!-- Site specific YARN configuration properties -->
<property>
    <name>yarn.nodemanager.aux-services</name>
    <value>mapreduce_shuffle</value>
</property>
<property>
    <name>yarn.resourcemanager.address</name>
    <value>sole:18040</value>
</property>
<property>
    <name>yarn.resourcemanager.scheduler.address</name>
    <value>sole:18030</value>
</property>
<property>
    <name>yarn.resourcemanager.resource-tracker.address</name>
    <value>sole:18025</value>
</property></property>
<property>
    <name>yarn.resourcemanager.admin.address</name>
    <value>sole:18141</value>
</property>
<property>
    <name>yarn.resourcemanager.webapp.address</name>
    <value>sole:18088</value>
</property>
</configuration>
shell 复制代码
[root@sole hadoop]# vi mapred-site.xml 
xml 复制代码
<configuration>
<!-- 指定mr运行时框架,这里指定在yarn上,默认是local -->
<property>
    <name>mapreduce.framework.name</name>
    <value>yarn</value>
</property>
</configuration>

shell 复制代码
# 初始化,进到${HADOOP_HOME}/sbin目录下
[root@sole sbin]# pwd
/opt/software/hadoop-3.3.1/sbin
[root@sole sbin]# hdfs namenode -format

# 启动服务
[root@sole sbin]# start-dfs.sh
[root@sole sbin]# start-yarn.sh

3. Mysql+Hive

3.1 Mysql8安装

shell 复制代码
# 卸载已有mariadb服务,如果已安装过MySQL,则将旧的MySQL服务全部卸载再安装
[root@sole ~]# rpm  -qa|grep mariadb
[root@sole ~]# yum remove mariadb-libs

MySQL 8.0.27 tar包下载:https://downloads.mysql.com/archives/community/


shell 复制代码
[root@sole ~]# tar -xvf mysql-8.0.27-1.el7.x86_64.rpm-bundle.tar

shell 复制代码
# 为了避免安装过程中报错,提前安装好以下依赖
[root@sole ~]#  -y install libaio
[root@sole ~]# yum install openssl-devel.x86_64 openssl.x86_64 -y
[root@sole ~]# yum -y install autoconf
[root@sole ~]# yum install perl.x86_64 perl-devel.x86_64 -y
[root@sole ~]# yum install perl-JSON.noarch -y
[root@sole ~]# yum install perl-Test-Simple
[root@sole ~]# yum install net-tools
shell 复制代码
# 安装mysql
[root@sole ~]# rpm -ivh mysql-community-common-8.0.27-1.el7.x86_64.rpm
[root@sole ~]# rpm -ivh mysql-community-client-plugins-8.0.27-1.el7.x86_64.rpm
[root@sole ~]# rmp -ivh mysql-community-libs-8.0.27-1.el7.x86_64.rpm
[root@sole ~]# rpm -ivh mysql-community-client-8.0.27-1.el7.x86_64.rpm
[root@sole ~]# rpm -ivh mysql-community-server-8.0.27-1.el7.x86_64.rpm
[root@sole ~]# rpm -ivh mysql-community-libs-compat-8.0.27-1.el7.x86_64.rpm
[root@sole ~]# rpm -ivh mysql-community-embedded-compat-8.0.27-1.el7.x86_64.rpm 
[root@sole ~]# rpm -ivh mysql-community-devel-8.0.27-1.el7.x86_64.rpm 
shell 复制代码
#启动MySQL
[root@sole ~]# mysqld --initialize --console
[root@sole ~]# chown -R mysql:mysql /var/lib/mysql/
[root@sole ~]# systemctl start mysqld.service
[root@sole ~]# systemctl status mysqld.service
[root@sole ~]# cat /var/log/mysqld.log |grep password  --查看临时密码
mysql 复制代码
# 修改密码&远程登录权限
mysql> alter user 'root'@'localhost' identified by 'root';
mysql> CREATE USER 'root'@'%' IDENTIFIED BY 'root';
mysql> GRANT ALL PRIVILEGES ON *.* TO 'root'@'%' WITH GRANT OPTION;
mysql> FLUSH PRIVILEGES;
shell 复制代码
# MySQL字符集修改,最后添加配置如下
[root@sole ~]# vi /etc/my.cnf

[mysql.server]
default-character-set = utf8
[client]
default-character-set = utf8


#添加完重启服务
[root@sole ~]# service mysqld restart

3.2 Hive安装

下载地址:https://archive.apache.org/dist/

shell 复制代码
# 解压
[root@sole install]# tar -zxvf apache-hive-3.1.2-bin.tar.gz -C /opt/software/
##########################################################################################
# 编辑环境变量
[root@sole ~]# vi /etc/profile.d/my.sh
# HIVE_HOME
export HIVE_HOME=/opt/software/apache-hive-3.1.2-bin
export PATH=$HIVE_HOME/bin:$PATH
# 重新加载
[root@sole ~]# source /etc/profile
shell 复制代码
# Hive配置修改,进入${HIVE_HOME}/conf
[root@sole conf]# cp hive-env.sh.template hive-env.sh
[root@sole conf]# vi hive-env.sh

export JAVA_HOME=/opt/software/jdk1.8.0_391
export HADOOP_HOME=/opt/software/hadoop-3.3.1
export HIVE_CONF_DIR=/opt/software/apache-hive-3.1.2-bin/conf
export HIVE_AUX_JARS_PATH=/opt/software/apache-hive-3.1.2-bin/lib
shell 复制代码
[root@sole conf]# vi hive-site.xml 
xml 复制代码
<configuration>
    <property>
        <name>hive.metastore.warehouse.dir</name>
        <value>/user/hive/warehouse</value>
    </property>
    <property>
        <name>hive.exec.scratchdir</name>
        <value>/tmp_local/hive</value>
    </property>
    <property>
        <name>hive.metastore.local</name>
        <value>true</value>
    </property>
    <property>
        <name>javax.jdo.option.ConnectionURL</name>
        <value>jdbc:mysql://sole:3306/hive?createDatabaseIfNotExist=true&amp;useSSL=false&amp;useUnicode=true&amp;characterEncoding=UTF-8&amp;allowPublicKeyRetrieval=true</value>
    </property>
    <property>
        <name>javax.jdo.option.ConnectionDriverName</name>
        <value>com.mysql.cj.jdbc.Driver</value>
    </property>
    <property>
        <name>javax.jdo.option.ConnectionUserName</name>
        <value>root</value>
    </property>
    <property>
        <name>javax.jdo.option.ConnectionPassword</name>
        <value>root</value>
    </property>
    <property>
        <name>hive.cli.print.header</name>
        <value>true</value>
    </property>
    <property>
        <name>hive.cli.print.current.db</name>
        <value>true</value>
    </property>    
    <property>
        <name>hive.exec.mode.local.auto</name>
        <value>true</value>
    </property>
    <property>
        <name>hive.exec.dynamic.partition</name>
        <value>true</value>
    </property>
    <property>
        <name>hive.exec.dynamic.partition.mode</name>
        <value>nonstrict</value>
    </property>
    <property>
        <name>hive.support.concurrency</name>
        <value>true</value>
    </property>
    <property>
        <name>hive.txn.manager</name>
        <value>org.apache.hadoop.hive.ql.lockmgr.DbTxnManager</value>
    </property>
    <property>
         <name>hive.compactor.initiator.on</name>
         <value>true</value>
    </property>
    <property>
          <name>hive.compactor.worker.threads</name>
          <value>1</value>
    </property>
</configuration>
shell 复制代码
# MySQL驱动
[root@sole install]# cp mysql-connector-j-8.0.33.jar /opt/software/apache-hive-3.1.2-bin/lib/

MySQL驱动网页下载:https://downloads.mysql.com/archives/c-j/

Maven下载:

xml 复制代码
<dependency>
  <groupId>com.mysql</groupId>
  <artifactId>mysql-connector-j</artifactId>
  <version>8.0.33</version>
</dependency>
shell 复制代码
# 解决Hadoop和Hive的两个guava.jar版本冲突问题:
# 删除${HIVE_HOME}/lib中的guava-19.0.jar
# 并将${HADOOP_HOME}/share/hadoop/common/lib/guava-27.0-jre.jar复制到${HIVE_HOME}/lib下

[root@sole install]# cd /opt/software/apache-hive-3.1.2-bin/lib/
[root@sole lib]# rm -f guava-19.0.jar 
[root@sole lib]# cp /opt/software/hadoop-3.3.1/share/hadoop/common/lib/guava-27.0-jre.jar ./

shell 复制代码
# 初始化元数据库
[root@sole bin]# ./schematool -dbType mysql -initSchema

# 启动服务 metastore & hiveserver2
[root@sole bin]# nohup hive --service metastore>hive.log 2>&1 &
[root@sole bin]# nohup hive --service hiveserver2>/dev/null 2>&1 &

4. Spark

下载地址:https://archive.apache.org/dist/

https://www.scala-lang.org/download/2.11.12.html




4.1 Maven安装

shell 复制代码
# 解压
[root@sole install]# tar -zxvf apache-maven-3.5.4-bin.tar.gz -C /opt/software
[root@sole software]# mv apache-maven-3.5.4/ maven-3.5.4
##########################################################################################
# 编辑环境变量
[root@sole ~]# vi /etc/profile.d/my.sh
# MAVEN_HOME
export MAVEN_HOME=/opt/software/maven-3.5.4
export PATH=$MAVEN_HOME/bin:$PATH

# 重新加载环境变量并测试maven
[root@sole ~]# source /etc/profile
[root@sole ~]# mvn -v
shell 复制代码
# 配置阿里云镜像
[root@sole software]# vi maven-3.5.4/conf/settings.xml
xml 复制代码
<mirror>
	<id>alimaven</id>
	<name>aliyun maven</name>
	<url>http://maven.aliyun.com/nexus/content/groups/public/</url>
	<mirrorOf>central</mirrorOf>
</mirror>

4.2 Scala安装

shell 复制代码
# 解压
[root@sole install]# tar -zxvf scala-2.11.12.tgz -C /opt/software
##########################################################################################
# 编辑环境变量
[root@sole ~]# vi /etc/profile.d/my.sh
#SCALA_HOME
export SCALA_HOME=/opt/software/scala-2.11.12
export PATH=$SCALA_HOME/bin:$PATH

# 重新加载并测试
[root@sole ~]# source /etc/profile
[root@sole ~]# scala -version

4.3 Spark编译并安装

shell 复制代码
# 解压
[root@sole install]# tar -zxvf spark-2.4.5.tgz -C /opt/software
# 编辑配置文件
[root@sole ~]# vi /opt/software/dev/make-distribution.sh
shell 复制代码
#以下内容注释,并添加以下配置
#VERSION=$("$MVN" help:evaluate -Dexpression=project.version $@ 2>/dev/null\
#    | grep -v "INFO"\
#    | grep -v "WARNING"\
#    | tail -n 1)
#SCALA_VERSION=$("$MVN" help:evaluate -Dexpression=scala.binary.version $@ 2>/dev/null\
#    | grep -v "INFO"\
#    | grep -v "WARNING"\
#    | tail -n 1)
#SPARK_HADOOP_VERSION=$("$MVN" help:evaluate -Dexpression=hadoop.version $@ 2>/dev/null\
#    | grep -v "INFO"\
#    | grep -v "WARNING"\
#    | tail -n 1)
#SPARK_HIVE=$("$MVN" help:evaluate -Dexpression=project.activeProfiles -pl sql/hive $@ 2>/dev/null\
#    | grep -v "INFO"\
#    | grep -v "WARNING"\
#    | fgrep --count "<id>hive</id>";\
    # Reset exit status to 0, otherwise the script stops here if the last grep finds nothing\
    # because we use "set -o pipefail"
    echo -n)

# 设置版本信息
VERSION=2.4.5
SCALA_VERSION=2.11.12
SPARK_HADOOP_VERSION=3.3.1
SPARK_HIVE=3.1.2
shell 复制代码
# 修改${SPARK_HOME}/poml.xml中得<hadoop.version>
# <hadoop.version>2.6.5</hadoop.version>  --> <hadoop.version>3.3.1</hadoop.version>
shell 复制代码
[root@sole dev]# ./make-distribution.sh --name build --tgz -Phadoop-3.3 -Dhadoop.version=3.3.1 -Dscala-2.11 -DskipTests -Pyarn -Phive -Phive-thriftserver

# --name --tgz :是最后生成的包名,以及采用上面格式打包,比如,编译的是spark-2.4.5,那么最后编译成功后就会在 spark-2.4.5这个目录下生成 spark--bin-build.tgz
# -Pyarn: 表示支持yarn
# --Phadoop-3.3 :指定hadoop的主版本号
# -Dhadoop.version: 指定hadoop的子版本号
# -Phive -Phive-thriftserver:开启HDBC和Hive功能
# -Dscala-2.11 :指定scala版本
# -DskipTests :忽略测试过程

#还可以加上:
#  clean package:clean和package是编译目标。clean执行清理工作,比如清除旧打包痕迹,package用于编译和打包

shell 复制代码
# 解压
[root@sole spark-2.4.5]# tar -zxvf spark--bin-build.tgz -C /opt/software
shell 复制代码
# 配置
[root@sole spark--bin-build]# vi /etc/profile.d/my.sh 

#SPARK_HOME
export SPARK_HOME=/opt/software/spark--bin-build
export SPARK_CLASSPATH=$SPARK_HOME/jars
export PATH=$SPARK_HOME/bin:$PATH
##########################################################################################
[root@sole conf]# vi spark-env.sh

export JAVA_HOME=/opt/software/jdk1.8.0_391
export HADOOP_HOME=/opt/software/hadoop-3.3.1
export HADOOP_CONF_DIR=/opt/software/hadoop-3.3.1/etc/hadoop
export SCALA_HOME=/opt/software/scala-2.11.12
export SPARK_HOME=/opt/software/spark--bin-build
export SPARK_MASTER_IP=192.168.229.130
export SPARK_MASTER_PORT=7077
##########################################################################################
[root@sole conf]# cp slaves.template slaves
##########################################################################################
# 将hive-site.xml拷贝至该目录下
[root@sole conf]# cp /opt/software/apache-hive-3.1.2-bin/conf/hive-site.xml ./
##########################################################################################
#spark-shell/spark-sql启动提示 Unrecognized Hadoop major version number: 3.3.1
[root@sole conf]# vi common-version-info.properties
version=2.7.6 #版本信息设置成2和3都可以

编译参考:https://blog.csdn.net/qq_43591172/article/details/126575084


shell 复制代码
# 启动&测试
[root@sole ~]# sh /opt/software/spark--bin-build/sbin/start-all.sh
[root@sole ~]# spark-sql



5. Zookeeper

下载地址:https://archive.apache.org/dist/zookeeper/zookeeper-3.4.10/

shell 复制代码
# 解压
[root@sole install]# tar -zxvf zookeeper-3.4.10.tar.gz -C /opt/software/
##########################################################################################
# 编辑环境变量
[root@sole ~]# vi /etc/profile.d/my.sh
# ZK_HOME
export ZK_HOME=/opt/software/zookeeper-3.4.10
export PATH=$ZK_HOME/bin:$ZK_HOME/sbin:$PATH
# 重新加载
[root@sole ~]# source /etc/profile
shell 复制代码
# 配置
[root@sole install]# cd /opt/software/zookeeper-3.4.10/
# 在zookeeper的根目录下新建文件夹mydata
[root@sole zookeeper-3.4.10]# mkdir mydata
[root@sole zookeeper-3.4.10]# touch myid
[root@sole zookeeper-3.4.10]# echo "1" >> myid
##########################################################################################
[root@sole zookeeper-3.4.10]# cd /opt/software/zookeeper-3.4.10/conf
[root@sole conf]# cp zoo_sample.cfg zoo.cfg
[root@sole conf]# vi zoo.cfg

# 在zoo.cfg这个文件中,配置集群信息是存在一定的格式:service.N =YYY:A:B
# N:代表服务器编号(也就是myid里面的值);
# YYY:服务器地址/hostname;
# A:表示 Flower 跟 Leader的通信端口,简称服务端内部通信的端口(默认2888);
# B:表示 是选举端口(默认是3888);
dataDir=/opt/software/zookeeper-3.4.10/mydata
server.1=sole:2888:3888
shell 复制代码
# 启动服务
[root@sole ~]# zkServer.sh start

6. HBase

下载地址:https://archive.apache.org/dist/zookeeper/zookeeper-3.4.10/

shell 复制代码
# 解压
[root@sole install]# tar -zxvf hbase-2.4.12-bin.tar.gz -C /opt/software/
##########################################################################################
# 编辑环境变量
[root@sole ~]# vi /etc/profile.d/my.sh
#HBASE_HOME
export HBASE_HOME=/opt/software/hbase-2.4.12
export PATH=$HBASE_HOME/bin:$PATH
# 重新加载
[root@sole ~]# source /etc/profile
shell 复制代码
# 配置
[root@sole ~]# cd /opt/software/hbase-2.4.12/conf/
[root@sole conf]# vi hbase-env.sh

export JAVA_HOME=/opt/software/jdk1.8.0_391
shell 复制代码
[root@sole conf]# vi hbase-site.xml
xml 复制代码
<configuration>
  <property>
    <name>hbase.rootdir</name>
    <value>hdfs://sole:9000/hbase</value>
  </property>
  <property>
    <name>hbase.cluster.distributed</name>
    <value>true</value>
  </property>
  <property>
    <name>hbase.tmp.dir</name>
    <value>./tmp</value>
  </property>
  <property>
    <name>hbase.zookeeper.property.clientPort</name>
    <value>2181</value>
  </property>
  <property>
    <name>hbase.zookeeper.property.dataDir</name>
    <value>/opt/software/zookeeper-3.4.10/mydata</value>
  </property>
  <property>
    <name>hbase.unsafe.stream.capability.enforce</name>
    <value>false</value>
  </property>
</configuration>
shell 复制代码
# 启动服务
[root@sole ~]# start-hbase.sh 

PS:如果有写错或者写的不好的地方,欢迎各位大佬在评论区留下宝贵的意见或者建议,敬上!如果这篇博客对您有帮助,希望您可以顺手帮我点个赞!不胜感谢!

|-------------------------------------------------------|
| 原创作者:wsjslient |


相关推荐
scoone6 分钟前
ssh登陆服务器后支持Tab键命令补全
linux·shell
Hsu_kk18 分钟前
Kafka 安装教程
大数据·分布式·kafka
苍老流年20 分钟前
1. kafka分布式环境搭建
分布式·kafka
sj116373940321 分钟前
Kafka参数了解
数据库·分布式·kafka
Hsu_kk23 分钟前
Kafka Eagle 安装教程
分布式·kafka
CodingBrother26 分钟前
Kafka 与 RabbitMQ 的联系
分布式·kafka·rabbitmq
pblh12339 分钟前
2023_Spark_实验十五:SparkSQL进阶操作
大数据·分布式·spark
运维佬1 小时前
CentOS 9 配置网卡
linux·centos
轩轩曲觞阁2 小时前
Linux网络——网络初识
linux·网络
2401_840192272 小时前
python基础大杂烩
linux·开发语言·python