安装JDK(JRE)
-
查看java版本
java -version
-
查询jdk安装路径
update-alternatives --display java
-
安装jdk
sudo apt install openjdk-8-jdk-headless
设置SSH免密码登录
-
安装openssh-server
sudo apt-get install openssh-server
-
配置认证
ssh localhost #选择yes即可连接成功 exit #退出ssh连接 cd ~/.ssh/ ssh-keygen -t rsa # 会有提示,都按回车就可以 cat ./id_rsa.pub >> ./authorized_keys # 加入授权
下载安装Hadoop
-
进入Hadoop官网
-
点击Releases
-
找到想要的版本
如hadoop-2.9.0.tar.gz的下载链接:
http://mirrors.tuna.tsinghua.edu.cn/apache/hadoop/common/hadoop-2.9.0/hadoop-2.9.0.tar.gz
-
下载Hadoop
wget http://mirrors.tuna.tsinghua.edu.cn/apache/hadoop/common/hadoop-2.9.0/hadoop-2.9.0.tar.gz
-
解压,移动到安装目录
tar -zxvf hadoop-2.9.0.tar.gz #解压 sudo mv ./hadoop-2.9.0 /usr/local/hadoop/ #移动到安装目录
-
设置Hadoop环境变量
-
编辑~/.bashrc文件
#设置JDK安装路径 export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64 #设置HADOOP_HOME为Hadoop的安装路径 export HADOOP_HOME=/usr/local/hadoop #设置PATH export PATH=$PATH:$HADOOP_HOME/bin export PATH=$PATH:$HADOOP_HOME/sbin #设置Hadoop其他环境变量 export HADOOP_MAPRED_HOME=$HADOOP_HOME export HADOOP_COMMON_HOME=$HADOOP_HOME export HADOOP_HDFS_HOME=$HADOOP_HOME export YARN_HOME=$HADOOP_HOME export HADOOP_COMMON_HOME=$HADOOP_HOME export HADOOP_HDFS_HOME=$HADOOP_HOME export YARN_HOME=$HADOOP_HOME #链接库相关设置 export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native export HADOOP_OPTS="-Djava.library.path=$HADOOP_HOME/lib" export JAVA_LIBRARY_PATH=$HADOOP_HOME/lib/native:$JAVA_LIBRARY_PATH
-
-
使环境变量生效
source ~/.bashrc
配置Hadoop
-
hadoop-env.sh
export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64
-
core-site.xml
<configuration> <property> <name>fs.default.name</name> <value>hdfs://localhost:9000</value> </property> </configuration>
-
yarn-site.xml
<configuration> <!-- Site specific YARN configuration properties --> <property> <name>yarn.nodemanager.aux-services</name> <value>mapreduce_shuffle</value> </property> <property> <name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name> <value>org.apache.hadoop.mapred.ShuffleHandler</value> </property> </configuration>
-
mapred-site.xml (从mapred-site.xml.template里面复制)
<configuration> <property> <name>mapreduce.framework.name</name> <value>yarn</value> </property> </configuration>
-
hdfs-site.xml
<configuration> <property> <name>dfs.replication</name> <value>1</value> </property> <property> <name>dfs.namenode.name.dir</name> <value>file:/usr/local/hadoop/hadoop_data/hdfs/namenode</value> </property> <property> <name>dfs.datanode.data.dir</name> <value>file:/usr/local/hadoop/hadoop_data/hdfs/datanode</value> </property> </configuration>
创建并格式化HDFS目录
#创建namenode目录
sudo mkdir -p /usr/local/hadoop/hadoop_data/hdfs/namenode
#创建datanode目录
sudo mkdir -p /usr/local/hadoop/hadoop_data/hdfs/datanode
#将Hadoop目录的所有者改为hduser
sudo chown hduser:hduser -R /usr/local/hadoop
#将HDFS格式化
hadoop namenode -format
启动Hadoop
#启动HDFS
start-dfs.sh
#启动Yarn
start-yarn.sh
#同时启动HDFS和YARN
start-all.sh
#查看Hadoop是否启动
jps
Hadoop Web 界面
-
Resource-Manager 界面
-
Namenode HDFS界面
网友评论