systemctl-cmd --state //查看防火墙状态
systemctl stop firewalld.service
systemctl disable firewalld.service
修改主机名
vi /etc/hostname
静态ip
vi /etc/sysconfig/network-scripts/ifcfg-ens33
BOOTPROTO="static"
ONBOOT="yes"
IPADDR="192.168.110.101"
GATEWAY="192.168.110.2"
NETMASK="255.255.255.0"
DNS1="8.8.8.8"
syestemctl restart network
主机名映射
vi /etc/hosts
192.168.110.101 shmily
ssh免密配置
ssh-keygen -t rsa -P ' '
ssh-copy-id 节点2
ssh-copy-id 节点3
java环境配置
export JAVA_HOME=/usr/local
export PATH=$PATH:$JAVA_HOME/bin
source /etc/profile //更新系统环境变量
java -version //查看java版本
Hadoop环境配置
tar -zxvf 压缩包存放路径 -C /usr/local //解压hadoop压缩包
export HADOOP_HOME=/usr/local
export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
cd /usr/local/hadoop/etc/hadoop
修改配置文件
vi hadoop-env.sh
export JAVA_HOME=/usr/local
vi core-site.xml
<property>
<name>fs.defaultFS</name>
<value>hdfs://shmily:9000</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>/usr/local/hadoop/data/tmp</value> //手动创建/data/tmp文件夹mkdir -p /data/tmp
</property>
vi hdfs-site.xml
<property>
<name>dfs.namenode.name.dir</name>
<value>file:///home/hadoopdir/dfs/name</value>
<description>hdfs元数据存存储目录</description>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value> /home/hadoopdir/dfs/data,/home/hadoopdir/dfs/data1,/home/hadoopdir/dfs/data2</value>
<description>DataNode在本地文件系统中存放块的路径,会自动选用多个目录进行数据存储。如果是多个路径,请用逗号隔开。在企业生产环境中,数据量会非常大,请将这个目录设置到磁盘容量充足的目录。</description>
</property>
<property>
<name>dfs.replication</name>
<value>1</value>
<description>备份数量,伪分布式则将其配置成1</description>
</property>
vi mapred-site.xml
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
vi yarn-site.xml
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
<property>
scp -r /usr/hadoop shmily1:/usr
hadoop namenode -format //格式化namenode
hadoop version 查看Hadoop版本
start-all.sh //启动集群
stop-all.sh //关闭集群
shmily:50070 //hdfs网页UI
shmily:8088 //yarn网页UI
Hadoop伪分布式集群搭建
于 2022-06-17 16:08:02 首次发布