最新hadoop安装教程及hadoop的命令使用(亲测可用)

 cd /data
 tar -zxvf hadoop-2.7.7.tar.gz

[root@server11 hadoop]# vi hadoop-env.sh

# 指定JAVA_HOME
export JAVA_HOME=/usr/lib/jvm/TencentKona-8.0.1-242

[root@server19 hadoop]# vi core-site.xml

<configuration>
    <!-- 指定HDFS老大（namenode）的通信地址 -->
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://服务器的真实ip:9002</value>
    </property>
    <!-- 指定hadoop运行时产生文件的存储路径 -->
    <property>
        <name>hadoop.tmp.dir</name>
        <value>/data/hadoop/tmp</value>
    </property>
</configuration>

<configuration>
        <property>
                <name>dfs.namenode.name.dir</name>
                <value>/data/hadoop/hadoop/hdfs/nn</value>
        </property>
        <property>
                <name>fs.checkpoint.dir</name>
                <value>/data/hadoop/hdfs/snn</value>
        </property>
        <property>
                <name>fs.checkpoint.edits.dir</name>
                <value>/data/hadoop/hdfs/snn</value>
        </property>
        <property>
                <name>dfs.datanode.data.dir</name>
                <value>/data/hadoop/hdfs/dn</value>
        </property>

        <property>
            <name>dfs.name.dir</name>
            <value>/data/hadoop/name</value>
        </property>
        <property>
            <name>dfs.data.dir</name>
            <value>/data/hadoop/node</value>
        </property>
        <property>
            <name>dfs.replication</name>
            <value>1</value>
        </property>
        <property>
            <name>dfs.http.address</name>
            <value>服务器的真实ip:9000</value>
        </property>
        <property>
             <name>ipc.maximum.data.length</name>
             <value>134217728</value>
        </property>
</configuration>

<configuration>

<!-- Site specific YARN configuration properties -->
<property>
    <name>yarn.nodemanager.vmem-check-enabled</name>
    <value>false</value>
</property>
<property>
    <name>yarn.nodemanager.aux-services</name>
    <value>mapreduce_shuffle</value>
</property>
<property>
    <name>yarn.application.classpath</name>
    <value>
        /data/hadoop-2.7.7/etc/*,
        /data/hadoop-2.7.7/etc/hadoop/*,
        /data/hadoop-2.7.7/lib/*,
        /data/hadoop-2.7.7/share/hadoop/common/*,
        /data/hadoop-2.7.7/share/hadoop/common/lib/*,
        /data/hadoop-2.7.7/share/hadoop/mapreduce/*,
        /data/hadoop-2.7.7/share/hadoop/mapreduce/lib/*,
        /data/hadoop-2.7.7/share/hadoop/hdfs/*,
        /data/hadoop-2.7.7/share/hadoop/hdfs/lib/*,
        /data/hadoop-2.7.7/share/hadoop/yarn/*,
        /data/hadoop-2.7.7/share/hadoop/yarn/lib/*
    </value>
</property>

</configuration>

#到 root 目录下：
cd /root
#执行生成密钥命令：
ssh-keygen -t rsa
#然后三个回车
#然后复制公钥追加到第一台节点的公钥文件中：
ssh-copy-id -i /root/.ssh/id_rsa.pub root@master01
#选择 yes
#输入登录第一台节点的密码(操作完成该节点公钥复制到第一台节点中)

vi /etc/profile

### 配置内容如下：
export JAVA_HOME=/usr/lib/jvm/TencentKona-8.0.1-242
export CLASSPATH=.:$JAVA_HOME/jre/lib/rt.jar:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar
export HADOOP_HOME=/data/hadoop-2.7.7
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
export HADOOP_CLASSPATH=`hadoop classpath`
export HADOOP_CONF_DIR=/data/hadoop-2.7.7/etc/hadoop

### 生效配置
source /etc/profile

vi /etc/hosts

127.0.0.1 localhost.localdomain localhost
127.0.0.1 localhost4.localdomain4 localhost4
127.0.0.1 VM-xx-centos gp-master

::1 VM-xx-centos VM-xxx-centos
::1 localhost.localdomain localhost
::1 localhost6.localdomain6 localhost6

服务器的真实ip VM-xxx-centos localhost.localdomain gp-master 

./start-all.sh

jps

## 正在运行的任务
yarn application -list

## kill掉yarn正在运行的任务
yarn application -kill application_1654588814418_0003

## 查找yarn已经完成的任务列表
yarn application -appStates finished -list

## 查找yarn所有任务列表
yarn application -appStates ALL -list

## 查看容器日志
curl http://127.0.0.1:8042/node/containerlogs/container_1654588814418_0003_01_000001/root/jobmanager.out/?start=0

## 查看yarn内存使用情况
curl http://127.0.0.1:8042/cluster

# 因为在 HDFS 上没有为当前用户创建主目录，所以要先创建目录
$ hadoop fs -mkdir -p /user/root
# 目录只能一级级创建 ，不能一下子创建2个
$ hadoop fs -mkdir ./flink 
# 上传
$ hadoop fs -put /资源路径/相关资源 ./flink 
# 下载
$ hadoop fs -get ./flink 
# 查看
$ hadoop fs -ls ./flink 

# 删除整个文件夹
$ hadoop fs -rm -rf flink
# 此处为逐级删除
$ hadoop fs -rm  ./flink/资源
# 备注：上面的 `./bin/hadoop fs`等同于`./bin/hdfs dfs`

<property>
	<name>dfs.http.address</name>
	<value>11.41.140.96:9002</value>
</property>
<property>
	<name>dfs.secondary.http.address</name>
	<value>11.41.140.96:9002</value>
</property>

hdfs getconf -confKey fs.default.name