测试环境部署hadoop和hive网站首页 其他

测试环境部署hadoop和hive

yyyyjinying 2024-07-11 08:06:33

简介测试环境部署hadoop和hive

两台服务器的主机名

hostname

ssh ecs-qar1-0001
ssh ecs-qar1-0002

配置jdk

vim /etc/profile

旧有的
export JAVA_HOME=/usr/java/openjdk-8u41

export JAVA_HOME=/bigdata/server/jdk
export PATH= $P A T H :$ JAVA_HOME/bin

export MAVEN_HOME=/work/apache-maven-3.5.4
export PATH= $MAVEN_HOME/bin:$ PATH

rm -f /usr/bin/java
ln -s /bigdata/server/jdk/bin/java /usr/bin/java

查看系统

lsb_release -a
cat /etc/redhat-release

查看java版本

whereis java
which java （java执行路径）
echo $JAVA_HOME

如果配置没生效需要重启系统

reboot 重启系统

echo $PATH

# 配置hadoop
## 配置
ecs-qar1-0001
ecs-qar1-0002

＃＃　配置hadoop-env.sh
vim hadoop-env.sh
export JAVA_HOME=/bigdata/server/jdk
export HADOOP_HOME=/bigdata/server/hadoop
export HADOOP_CONF_DIR=${HADOOP_HOME}/etc/hadoop
export HADOOP_LOG_DIR=${HADOOP_HOME}/logs

配置core-site.xml

<configuration>
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://ecs-qar1-0002:8020</value>
        <description>hdfs默认地址与端口</description>
    </property>
    <property>
        <name>io.file.buffer.size</name>
        <value>131072</value>
    </property>
</configuration>

配置hdfs-site.xml

<configuration>
    <property>
        <name>dfs.namenode.name.dir</name>
        <value>/data/nn</value>
        <description>namenode上存储hdfs名字空间元数据</description>
    </property>
    <property>
        <name>dfs.datanode.data.dir</name>
        <value>/data/dn</value>
        <description>datanode上数据块的物理存储位置</description>
    </property>
    <property>
        <name>dfs.datanode.data.dir.perm</name>
        <value>755</value>
        <!--dn所使用的本地文件夹的路径权限，默认755-->
    </property>
    <property>
        <name>dfs.replication</name>
        <value>2</value>
        <!--数据需要备份的数量，不能大于集群的机器数量，默认为3-->
    </property>
    <property>
        <name>dfs.namenode.hosts</name>
        <value>ecs-qar1-0001,ecs-qar1-0002</value>
    </property>
    <property>
        <name>dfs.blocksize</name>
        <value>268435456</value>
    </property>
    <property>
        <name>dfs.namenode.handler.count</name>
        <value>100</value>
    </property>
</configuration>

vim /etc/profile
export JAVA_HOME=/bigdata/server/jdk
export HADOOP_HOME=/bigdata/server/hadoop
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
source /etc/profile

# 配置hadoop-env.sh、mapred-env.sh、yarn-env.sh文件中各添加javahome
export JAVA_HOME=/bigdata/server/jdk

配置mapred-site.xml

<configuration>
<property>
    <name>mapreduce.framework.name</name>
    <value>yarn</value>
    <description>Execution framework set to Hadoop YARN.</description>
</property>
<property>
       <name>mapreduce.jobhistory.address</name>
       <value>ecs-qar1-0002:10020</value>
</property>
<property>
       <name>mapreduce.jobhistory.webapp.address</name>
       <value>ecs-qar1-0002:19888</value>
</property>
<property>
    <name>yarn.app.mapreduce.am.env</name>
    <value>HADOOP_MAPRED_HOME=$HADOOP_HOME</value>
    <description>MAPREDUCE home设置为HADOOP_HOME</description>
</property>
<property>
    <name>mapreduce.map.env</name>
    <value>HADOOP_MAPRED_HOME=$HADOOP_HOME</value>
    <description>MAPREDUCE HOME 设置为HADOOP_HOME</description>
</property>
<property>
    <name>mapreduce.reduce.env</name>
    <value>HADOOP_MAPRED_HOME=$HADOOP_HOME</value>
    <description>mAPREDUCE HOME 设置为HADOOP_HOME</description>
</property>
</configuration>

配置yarn-site.xml

<configuration>
    <property>
        <name>yarn.resourcemanager.hostname</name>
        <value>ecs-qar1-0002</value>
        <description>ResourceManager host.</description>
    </property>
    <property>
        <name>yarn.nodemanager.local-dirs</name>
        <value>/data/nm-local</value>
        <description>中间数据存储</description>
    </property>
    <property>
        <name>yarn.nodemanager.log-dirs</name>
        <value>/data/nm-log</value>
        <description>日志存储</description>
    </property>
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
        <description>shuffle服务</description>
    </property>
    <property>
        <name>yarn.log.server.url</name>
        <value>http://ecs-qar1-0002:19888/jobhistory/logs</value>
        <description>历史服务器</description>
    </property>
    <property>
      <name>yarn.log.server.web-service.url</name>
      <value>http://ecs-qar1-0002:8188/ws/v1/applicationhistory</value>
    </property>
    <property>
        <name>yarn.log.aggregation.enable</name>
        <value>true</value>
        <description>开启日志聚合</description>
    </property>
    <property>
        <name>yarn.nodemanager.remote-app-log-dir</name>
        <value>/tmp/logs</value>
        <description>程序日志</description>
    </property>
    <property>
        <name>yarn.resourcemanager.scheduler.class</name>
        <value>org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler</value>
        <description>公平调度器</description>
    </property>
</configuration>

scp -r hadoop-3.3.4 ecs-qar1-0002:`pwd`/
ln -s hadoop
chown -R hadoop:hadoop hadoop*
chown -R hadoop:hadoop /data

# 设置hadoop用户的ssh免密登录
ssh-keygen -t rsa
ssh-copy-id ecs-qar1-0001
ssh-copy-id ecs-qar1-0002
## 重新配置
ssh-keygen
rm -rf .ssh/
ll .ssh/

su - hadoop
hadoop namenode -format

start-all.sh

安装docker

安装
https://docs.docker.com/engine/install/centos/#installation-methods
开机启动
systemctl enable docker.service
systemctl is-enabled docker.service

安装docker compose

https://github.com/docker/compose/releases/tag/v2.17.2
mv docker-compose-linux-x86_64 docker-compose
chmod +x docker-compose
cp docker-compose /usr/local/bin
docker-compose version

测试内网是否执行成功

ecs-QAR2
内网ip：172.16.0.72
公网IP：121.37.213.3
curl -fsSL ecs-qar1-0002:8088 --noproxy ‘’
curl -fsSL 172.16.0.72:8088 --noproxy '’
curl -fsSL 121.37.213.3:8088 --noproxy ‘’
curl -fsSL ecs-qar1-0002:9870 --noproxy '’
curl -fsSL localhost:8088 --noproxy ‘*’

测试mapreduce

hadoop jar /bigdata/server/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-examples-3.3.4.jar wordcount hdfs://ecs-qar1-0002/input hdfs://ecs-qar1-0002/output/bb

start-dfs.sh
start-yarn.sh

配置hive

su -
vim /etc/profile

export JAVA_HOME=/bigdata/server/jdk
export HADOOP_HOME=/bigdata/server/hadoop
export HIVE_HOME=/bigdata/server/hive
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$HIVE_HOME/bin

cd hadoop/etc/hadoop
vim core-site.xml
授权代理hadoop用户，可以支持hive访问

<configuration>
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://ecs-qar1-0002:8020</value>
    </property>
    <property>
        <name>io.file.buffer.size</name>
        <value>131072</value>
    </property>
    <property>
       <name>hadoop.proxyuser.hadoop.groups</name>
       <value>*</value>
    </property>
    <property>
       <name>hadoop.proxyuser.hadoop.hosts</name>
       <value>*</value>
    </property>
</configuration>

cd hive/conf
mv hive-env.sh.template hive-env.sh
vim hive-env.sh

export HADOOP_HOME=/bigdata/server/hadoop
export HIVE_CONF_DIR=/bigdata/server/hive/conf
export HIVE_AUX_JARS_PATH=/bigdata/server/hive/lib

mysql8
<configuration>
  <property>
    <name>javax.jdo.option.ConnectionURL</name>
    <value>jdbc:mysql://ecs-qar1-0002:3306/hive?createDatabaseIfNotExist=true&amp;useSSL=false&amp;useUnicode=true&amp;characterEncoding=UTF-8&amp;allowPublicKeyRetrieval=true</value>
    <description>JDBC connect string for a JDBC metastore</description>
  </property>
  <property>
    <name>javax.jdo.option.ConnectionDriverName</name>
    <value>com.mysql.cj.jdbc.Driver</value>
    <description>Driver class name for a JDBC metastore</description>
  </property>
  <property>
    <name>javax.jdo.option.ConnectionUserName</name>
    <value>root</value>
    <description>username to use against metastore database</description>
  </property>
  <property>
    <name>javax.jdo.option.ConnectionPassword</name>
    <value>123456</value>
    <description>password to use against metastore database</description>
  </property>
  <property>
        <name>hive.server2.thrift.bind.host</name>
        <value>ecs-qar1-0002</value>
    </property>
    <property>
        <name>hive.metastore.uris</name>
        <value>thrift://ecs-qar1-0002:9083</value>
    </property>
    <property>
        <name>hive.metastore.event.db.notification.api.auth</name>
        <value>false</value>
    </property>
</configuration>
mysql5.7
<configuration>
    <property>
        <name>javax.jdo.option.ConnectionURL</name>
        <value>jdbc:mysql://ecs-qar1-0002:3306/hive?createDatabaseIfNotExist=true&amp;useSSL=false&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>123456</value>
    </property>
    <property>
        <name>hive.server2.thrift.bind.host</name>
        <value>ecs-qar1-0002</value>
    </property>
    <property>
        <name>hive.metastore.uris</name>
        <value>thrift://ecs-qar1-0002:9083</value>
    </property>
    <property>
        <name>hive.metastore.event.db.notification.api.auth</name>
        <value>false</value>
    </property>
</configuration>

添加驱动

/bigdata/server/hive/lib
mysql-connector-java-5.1.49.jar
mysql-connector-java-8.0.21.jar
添加执行权限
chmod +x mysql-connector-java*
查看成功否
ll mysql*
修改组用户
chown -R hadoop:hadoop apache-hive-3.1.3-bin hive

创建mysql

docker mysql ……………………

测试

mkdir ./hive/logs
后台启动

nohup hive --service metastore >> /bigdata/server/hive/logs/metastore.log 2>&1 &

hive 交互式操作

必须启动hiveserver2,否则beeline无法使用

nohup hive --service hiveserver2 >> /bigdata/server/logs/hiveserver2.log 2>&1 &

beeline jdbc:hive2://ecs-qar1-0002:10000
hadoop
123456

文件存放位置

hadoop fs -cat /user/hive/warehouse/test/*
默认的数据库：default
show databases;
use default;
show tables;

启动

start-dfs.sh
start-yarn.sh
start-all.sh
stop-all.sh

风语者！平时喜欢研究各种技术，目前在从事后端开发工作，热爱生活、热爱工作。

上一篇
【Python实战】Python采集热榜数据...

下一篇
Java开发 - 让你少走弯路的Redis的主从复...

站长推荐

U8W/U8W-Mini使用与常见问题解决
U8W/U8W-Mini使用与常见问题解决
stm32使用HAL库配置串口中断收发数据（保姆级教程）
stm32使用HAL库配置串口中断收发数据（保姆级教程）
SpringSecurity实现前后端分离认证授权
SpringSecurity实现前后端分离认证授权
分享几个国内免费的ChatGPT镜像网址(亲测有效)
分享几个国内免费的ChatGPT镜像网址(亲测有效)
【社区图书馆】伴我前行的一本书《The C Programming Language》
【社区图书馆】伴我前行的一本书《The C Programming Language》

您现在的位置是：首页 >其他 >测试环境部署hadoop和hive网站首页其他