使用 Docker 搭建离线数仓环境_docker数仓

yum clean all
yum -y install unzip bzip2-devel vim bashname
yum install kde-l10n-Chinese -y
yum install glibc-common -y
localedef -c -f UTF-8 -i zh_CN zh_CN.utf8
echo "export LANG=zh_CN.UTF-8" >> /etc/locale.conf
echo "LC_ALL zh_CN.UTF-8" >> ~/.bashrc

3.2 配置SSH免密登录

# 修改root密码passwd root  # 输入两次密码# 安装必要SSH服务yum install -y openssh openssh-server openssh-clients openssl openssl-devel # 生成秘钥ssh-keygen -t rsa -f ~/.ssh/id_rsa -P '' # 配置免密cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys# 方式2: ssh-copy-id# 启动SSH服务systemctl start sshd

3.3 设置时区

cp /usr/share/zoneinfo/Asia/Shanghai /etc/localtime

3.4 关闭防火墙

yum -y install firewalldsystemctl stop firewalldsystemctl disable firewalld

3.5 时间同步、静态ip、主机映射

• 由于本次课使用docker进行环境搭建，所以对于静态ip和主机映射可以不用配置
• 由于本次课搭建的是单节点的伪分布式集群，所以时间同步可以用不设置
• 如果在物理机上搭建多节点的完全分布式集群则必须配置

四、MySQL安装

4.1 上传解压安装包

cd /opt/software/tar xvf MySQL-5.5.40-1.linux2.6.x86_64.rpm-bundle.tar

4.2 安装必要依赖

yum -y install libaio perl

4.3 安装服务端和客户端

rpm -ivh MySQL-server-5.5.40-1.linux2.6.x86_64.rpmrpm -ivh MySQL-client-5.5.40-1.linux2.6.x86_64.rpm 

4.4 启动并配置MySQL

方式一

# 启动服务systemctl start mysql# 修改MySQL密码/usr/bin/mysqladmin -u root password 'root'# 登陆MySQL设置权限mysql -uroot -proot > update mysql.user set host='%' where host='localhost';> delete from mysql.user where host<>'%' or user='';> flush privileges;

方式二

# 启动服务systemctl start mysql# 执行MySQL的初始化/usr/bin/mysql\_secure\_installation# 输入一次回车, 两次相同的密码进行修改密码# Remove anonymous users? [Y/n] 是否移除掉anonymous用户 n# Disallow root login remotely? [Y/n] 是否允许root用户远程登录 y# Remove test database and access to it? [Y/n] 是否移除掉test数据库 n# Reload privilege tables now? [Y/n] 是否现在刷新权限 y# 登陆MySQL设置权限mysql -uroot -proot > update mysql.user set host='%' where host='localhost';> delete from mysql.user where host<>'%' or user='';> flush privileges;

五、安装JDK

5.1 上传并解压

tar zxvf /opt/software/jdk-8u171-linux-x64.tar.gz -C /opt/install/ln -s /opt/install/jdk1.8.0_171 /opt/install/java

5.2 配置环境变量

环境变量配置在 ~/.bashrc 里

vi ~/.bashrc-------------------------------------------export JAVA_HOME=/opt/install/javaexport PATH=$JAVA_HOME/bin:$PATH-------------------------------------------source ~/.bashrc

5.3 查看版本

java -version

六、Hadoop安装

6.1 上传并解压

tar zxvf hadoop-3.2.1.tar.gz -C /opt/install/ln -s /opt/install/hadoop-3.2.1/ /opt/install/hadoop

6.2 修改配置

# 进入路径cd /opt/install/hadoop/etc/hadoop/

6.2.1 配置core-site.xml

vi core-site.xml-------------------------------------------<configuration>    <property>        <name>fs.defaultFS</name>        <value>hdfs://singleNode:8020</value>    </property>    <property>        <name>hadoop.tmp.dir</name>        <value>/opt/install/hadoop/data</value>    </property>    <property>        <name>hadoop.proxyuser.root.hosts</name>        <value>*</value>    </property>    <property>        <name>hadoop.proxyuser.root.groups</name>        <value>*</value>    </property>    <property>        <name>hadoop.http.staticuser.user</name>        <value>root</value>    </property></configuration>-------------------------------------------

6.2.2 配置hdfs-site.xml

vi hdfs-site.xml-------------------------------------------<configuration>    <property>        <name>dfs.replication</name>        <value>1</value>    </property>    <property>        <name>dfs.namenode.secondary.http-address</name>        <value>singleNode:9868</value>    </property></configuration>-------------------------------------------

6.2.3 配置mapred-site.xml

vi mapred-site.xml-------------------------------------------<configuration>  <property>    <name>mapreduce.framework.name</name>    <value>yarn</value>  </property>  <property>    <name>mapreduce.jobhistory.address</name>    <value>singleNode:10020</value>  </property>  <property>    <name>mapreduce.jobhistory.webapp.address</name>    <value>singleNode:19888</value>  </property></configuration>-------------------------------------------

6.2.4 配置yarn-site.xml

vi yarn-site.xml-------------------------------------------<configuration>    <property>        <name>yarn.nodemanager.aux-services</name>        <value>mapreduce_shuffle</value>    </property>    <property>        <name>yarn.resourcemanager.hostname</name>        <value>singleNode</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_MAPRED_HOME</value>    </property>    <property>        <name>yarn.scheduler.minimum-allocation-mb</name>        <value>512</value>    </property>    <property>        <name>yarn.scheduler.maximum-allocation-mb</name>        <value>4096</value>    </property>    <property>        <name>yarn.nodemanager.resource.memory-mb</name>        <value>4096</value>    </property>    <property>        <name>yarn.nodemanager.pmem-check-enabled</name>        <value>false</value>    </property>    <property>        <name>yarn.nodemanager.vmem-check-enabled</name>        <value>false</value>    </property>    <property>        <name>yarn.log-aggregation-enable</name>        <value>true</value>    </property>    <property>          <name>yarn.log.server.url</name>          <value>http://${yarn.timeline-service.webapp.address}/applicationhistory/logs</value>    </property>    <property>        <name>yarn.log-aggregation.retain-seconds</name>        <value>604800</value>    </property>    <property>        <name>yarn.timeline-service.enabled</name>        <value>true</value>    </property>    <property>        <name>yarn.timeline-service.hostname</name>        <value>${yarn.resourcemanager.hostname}</value>    </property>    <property>        <name>yarn.timeline-service.http-cross-origin.enabled</name>        <value>true</value>    </property>    <property>        <name>yarn.resourcemanager.system-metrics-publisher.enabled</name>        <value>true</value>    </property></configuration>-------------------------------------------

6.2.5 配置hadoop-env.sh

vi hadoop-env.sh-------------------------------------------export JAVA_HOME=/opt/install/java-------------------------------------------

6.2.6 配置mapred-env.sh

vi mapred-env.sh-------------------------------------------export JAVA_HOME=/opt/install/java-------------------------------------------

6.2.7 配置yarn-env.sh

vi yarn-env.sh-------------------------------------------export JAVA_HOME=/opt/install/java-------------------------------------------

6.2.8 配置works

vi works-------------------------------------------singleNode-------------------------------------------

6.3 添加变量

vi ~/.bashrc------------------------------------------------export HADOOP_HOME=/opt/install/hadoopexport HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoopexport PATH=$HADOOP_HOME/bin:$PATH------------------------------------------------vi $HADOOP_HOME/sbin/start-dfs.shvi $HADOOP_HOME/sbin/stop-dfs.sh------------------------------------------------HDFS_NAMENODE_USER=root HDFS_DATANODE_USER=root HDFS_SECONDARYNAMENODE_USER=root YARN_RESOURCEMANAGER_USER=root YARN_NODEMANAGER_USER=root------------------------------------------------vi $HADOOP_HOME/sbin/start-yarn.shvi $HADOOP_HOME/sbin/stop-yarn.sh------------------------------------------------YARN_RESOURCEMANAGER_USER=root HADOOP_SECURE_DN_USER=yarn YARN_NODEMANAGER_USER=root------------------------------------------------

6.4 HDFS格式化

hdfs namenode -format

6.5 启动Hadoop服务

# 启动HDFS$HADOOP_HOME/sbin/start-dfs.sh# 启动yarn$HADOOP_HOME/sbin/start-yarn.sh# 启动历史服务器mapred --daemon start historyserver

6.6 Web端查看

查看9870端口

查看8088端口

七、Hive安装

7.1 上传并解压

tar zxvf /opt/software/apache-hive-3.1.2-bin.tar.gz -C /opt/install/ln -s /opt/install/apache-hive-3.1.2-bin/ /opt/install/hive

7.2 修改配置

# 进入路径cd /opt/install/hive/conf/

7.2.1 修改hive-site.xml

cp hive-default.xml.template hive-site.xmlvi hive-site.xml-------------------------------------------<configuration>    <property>        <name>javax.jdo.option.ConnectionURL</name>        <value>jdbc:mysql://singleNode:3306/metastore?createDatabaseIfNotExist=true&amp;useUnicode=true&amp;characterEncoding=UTF-8</value>    </property>    <property>        <name>javax.jdo.option.ConnectionDriverName</name>        <value>com.mysql.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.metastore.warehouse.dir</name>        <value>/user/hive/warehouse</value>    </property>    <property>        <name>hive.metastore.schema.verification</name>        <value>false</value>    </property>    <property>        <name>hive.metastore.uris</name>        <value>thrift://singleNode:9083</value>    </property>    <property>        <name>hive.server2.thrift.port</name>        <value>10000</value>    </property>    <property>        <name>hive.server2.thrift.bind.host</name>        <value>singleNode</value>    </property>    <property>        <name>hive.metastore.event.db.notification.api.auth</name>        <value>false</value>    </property></configuration>-------------------------------------------

7.2.2 修改hive-env.sh

cp hive-env.sh.template hive-env.shvi hive-env.sh-------------------------------------------HADOOP_HOME=/opt/install/hadoop-------------------------------------------

7.3 添加依赖包

cp /opt/software/mysql-connector-java-5.1.31.jar /opt/install/hive/lib/

7.4 添加环境变量

vi ~/.bashrc------------------------------------------------export HIVE_HOME=/opt/install/hiveexport PATH=$HIVE_HOME/bin:$PATH------------------------------------------------

7.5 启动服务

# 初始化元数据表schematool -dbType mysql -initSchema# 启动hiveserver2服务nohup hive --service hiveserver2 &#############报错 Exception in thread "main" java.lang.NoSuchMethodError ################# jar 包冲突, 需要删除低版本包rm -rf /opt/install/hive/lib/guava-19.0.jarcp /opt/install/hadoop/share/hadoop/common/lib/guava-27.0-jre.jar /opt/install/hive/lib/

7.6 Jps查看

八、Sqoop安装

8.1 上传并解压

tar zxvf sqoop-1.4.7.bin__hadoop-2.6.0.tar.gz -C /opt/install/ln -s /opt/install/sqoop-1.4.7.bin__hadoop-2.6.0/ /opt/install/sqoop

8.2 修改sqoop-env.sh

cd /opt/install/sqoop/conf/cp sqoop-env-template.sh sqoop-env.shvi sqoop-env.sh-------------------------------------------#Set path to where bin/hadoop is availableexport HADOOP_COMMON_HOME=/opt/install/hadoop#Set path to where hadoop-*-core.jar is availableexport HADOOP_MAPRED_HOME=/opt/install/hadoop#Set the path to where bin/hive is availableexport HIVE_HOME=/opt/install/hive-------------------------------------------

8.3 添加依赖包

cp /opt/software/mysql-connector-java-5.1.31.jar /opt/install/sqoop/lib/cp /opt/software/commons-lang-2.6.jar /opt/install/sqoop/lib/cp /opt/software/java-json.jar /opt/install/sqoop/lib/

8.4 添加环境变量

vi ~/.bashrc------------------------------------------------export SQOOP_HOME=/opt/install/sqoopexport PATH=$SQOOP_HOME/bin:$PATH------------------------------------------------

8.5 查看版本

网上学习资料一大堆，但如果学到的知识不成体系，遇到问题时只是浅尝辄止，不再深入研究，那么很难做到真正的技术提升。

需要这份系统化资料的朋友，可以戳这里获取

一个人可以走的很快，但一群人才能走的更远！不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人，都欢迎加入我们的的圈子（技术交流、学习资源、职场吐槽、大厂内推、面试辅导），让我们一起学习成长！

---

#### 8.5 查看版本




[外链图片转存中...(img-gWyNJsgH-1714182464283)]
[外链图片转存中...(img-q6q1iX2I-1714182464283)]

**网上学习资料一大堆，但如果学到的知识不成体系，遇到问题时只是浅尝辄止，不再深入研究，那么很难做到真正的技术提升。**

**[需要这份系统化资料的朋友，可以戳这里获取](https://bbs.csdn.net/topics/618545628)**


**一个人可以走的很快，但一群人才能走的更远！不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人，都欢迎加入我们的的圈子（技术交流、学习资源、职场吐槽、大厂内推、面试辅导），让我们一起学习成长！**