阿里云安装 Hadoop

1.安装 jdk

修改

vi etc/profile

添加

# java env 
export JAVA_HOME=/java/jdk1.8.0_281
export CLASSPATH=.:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar
export PATH=$PATH:$JAVA_HOME/bin

生效

source /etc/profile

验证

java -version

2.免密登录

测试

ssh localhost

如果有问题 则安装 ssh

yum install openssh-clients openssh-server

取消输入密码

ssh-keygen -t rsa -P ‘’ -f ~/.ssh/id_rsa
cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys
chmod 0600 ~/.ssh/authorized_keys

验证是否免密

ssh localhost

3.安装 Hadoop

修改

vi etc/profile

添加

# hadoop env
export HADOOP_HOME=/hadoop/hadoop-3.3.0
export PATH=$PATH:$HADOOP_HOME/bin 
export HADOOP_HOME_WARN_SUPPRESS=1

export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native 
export HADOOP_OPTS=-Djava.library.path=$HADOOP_HOME/lib 

生效

source /etc/profile

4.修改配置文件

cd /hadoop/hadoop-3.3.0/etc/hadoop
vi core-site.xml
vi hdfs-site.xml

<configuration>
    <!-- 指定HDFS中NameNode的地址 -->
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://localhost:9000</value>
    </property>
    <!-- 指定hadoop临时目录 -->
    <property>
        <name>hadoop.tmp.dir</name>
        <value>/hadoop/tmp</value>
    </property>
</configuration>

<configuration>
    <!--<property>
        <name>fs.default.name</name>
        <value>localhost:9000</value>
    </property>
    <property>
        <name>mapred.job.tracker</name>
        <value>localhost:9001</value>
    </property>-->

    <!--官网只配了replication-->
    <property>
        <name>dfs.replication</name>
        <value>1</value>
    </property>
    <!--namenode和datanode的路径-->
    <property>
        <name>dfs.namenode.name.dir</name>
        <value>file:/hadoop/tmp/dfs/name</value>
    </property>
    <property>
        <name>dfs.datanode.data.dir</name>
        <value>file:/hadoop/tmp/dfs/data</value>
    </property>

    <!--指定可以通过web访问hdfs目录-->       
    <!--<property>
        <name>dfs.webhdfs.enabled</name>
        <value>true</value>
    </property>--> 
    <!-- 启用了50070的端口访问 -->
    <!-- 3.3版本启用了9870的端口访问 -->
    <!--<property>
        <name>dfs.namenode.http.address</name>
        <value>slave1:9870</value>
    </property>-->
</configuration>

5.启动 Hadoop (以及无法启动解决方案)

./sbin/stop-dfs.sh   # 关闭
rm -r ./tmp     # 删除 tmp 文件，注意这会删除 HDFS 中原有的所有数据
./bin/hdfs namenode -format   # 重新格式化 NameNode
./sbin/start-dfs.sh  # 重启

注：启动报错

vi start-dfs.sh
vi stop-dfs.sh

HDFS_DATANODE_USER=root
HADOOP_SECURE_DN_USER=hdfs
HDFS_NAMENODE_USER=root
HDFS_SECONDARYNAMENODE_USER=root

vi start-yarn.sh
vi stop-yarn.sh

YARN_RESOURCEMANAGER_USER=root
HADOOP_SECURE_DN_USER=yarn
YARN_NODEMANAGER_USER=root

6.访问 http://localhost:9870/