页面历史

systemctl stop firewalld

systemctl disable firewalld

systemctl status firewalld

firewall-cmd --zone=public --add-port=9864/tcp --permanent
firewall-cmd --zone=public --add-port=9866/tcp --permanent
firewall-cmd --zone=public --add-port=9867/tcp --permanent
firewall-cmd --zone=public --add-port=9868/tcp --permanent
firewall-cmd --zone=public --add-port=9870/tcp --permanent

firewall-cmd --reload

firewall-cmd --list-all

setenforce 0

sed -i 's/=enforcing/=disabled/g'  /etc/selinux/config

vi /etc/security/limits.conf

* soft nofile 65536
* hard nofile 65536
* soft nproc 131072
* hard nproc 131072

vi /etc/hosts

10.10.204.248 10-10-204-248
10.10.204.249 10-10-204-249
10.10.204.250 10-10-204-250

ssh-keygen

cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys
chmod 0600 ~/.ssh/authorized_keys

ssh root@10-10-204-249

tar -zxvf jdk-8u181-linux-x64.tar.gz -C /data

vi /etc/profile

export JAVA_HOME=/data/jdk1.8.0_181
export JAVA_BIN=$JAVA_HOME/bin
export CLASSPATH=:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar
export PATH=$PATH:$JAVA_BIN

source /etc/profile

java -version

mkdir -p /data/hdfs/tmp

mkdir -p /data/hdfs/name

mkdir -p /data/hdfs/data

tar -zxvf hadoop-3.2.2.tar.gz -C /data

cd /data/hadoop-3.2.2/etc/hadoop
vi hadoop-env.sh

export JAVA_HOME=/data/jdk1.8.0_181

export HDFS_NAMENODE_OPTS="-XX:+UseParallelGC -Xmx4g"

export HDFS_DATANODE_USER=root
export HDFS_NAMENODE_USER=root
export HDFS_SECONDARYNAMENODE_USER=root

启动用户可根据实际环境替换成实际的用户名

cd /data/hadoop-3.2.2/etc/hadoop
vi core-site.xml

<configuration>
    <property>
        <name>fs.defaultFS</name>
        <!-- 注意替换成实际的主机名 -->
        <value>hdfs://10-10-204-249:9000</value>
    </property>
    <property>
        <name>hadoop.tmp.dir</name>
        <!-- 注意替换成实际的路径 -->
        <value>file:/data/hdfs/tmp</value>
    </property>
    <property>
        <name>fs.trash.interval</name>
        <value>100800</value>
    </property>
    <property>
        <name>hadoop.security.authorization</name>
        <value>true</value>
    </property>
</configuration>

cd /data/hadoop-3.2.2/etc/hadoop
vi hdfs-site.xml

<configuration>
    <property>
        <name>dfs.name.dir</name>
        <!-- 注意替换成实际的路径 -->
        <value>file:/data/hdfs/name</value> 
    </property>
    <property>
        <name>dfs.data.dir</name>
        <!-- 注意替换成实际的路径 -->
        <value>file:/data/hdfs/data</value>
    </property>
    <property>
        <name>dfs.replication</name>
        <value>1</value>
    </property>
    <property>
        <name>dfs.webhdfs.enabled</name>
        <value>false</value>
    </property>
    <property>
        <name>dfs.datanode.max.transfer.threads</name>
        <value>16384</value>
    </property>
</configuration>

dfs.data.dir尽量配置在空间比较大的目录，可以配置多个目录，中间用逗号分隔

cd /data/hadoop-3.2.2/etc/hadoop
vi hadoop-policy.xml

<configuration>
  <property>
    <name>security.client.protocol.acl</name>
    <value>*</value>
    <description>ACL for ClientProtocol, which is used by user code
    via the DistributedFileSystem.
    The ACL is a comma-separated list of user and group names. The user and
    group list is separated by a blank. For e.g. "alice,bob users,wheel".
    A special value of "*" means all users are allowed.</description>
  </property>
  
  <!-- 这里把实验引擎ip, python执行节点ip，spark部署机器ip，hadoop部署机器ip都加上--> 
  <!-- 增加以下配置 -->
  <property>
    <name>security.client.protocol.hosts</name>
    <value>10.10.204.248,10.10.204.249,10.10.204.250</value>
  </property>
  <!-- end -->

  <property>
    <name>security.client.datanode.protocol.acl</name>
    <value>*</value>
    <description>ACL for ClientDatanodeProtocol, the client-to-datanode protocol
    for block recovery.
    The ACL is a comma-separated list of user and group names. The user and
    group list is separated by a blank. For e.g. "alice,bob users,wheel".
    A special value of "*" means all users are allowed.</description>
  </property>
  
  <!-- 这里把实验引擎ip,python执行节点ip，spark部署机器ip，hadoop部署机器ip都加上-->
  <!-- 增加以下配置 -->
  <property>
    <name>security.client.datanode.protocol.hosts</name>
    <value>10.10.204.248,10.10.204.249,10.10.204.250</value>
  </property>
  <!-- end -->

  <property>
    <name>security.datanode.protocol.acl</name>
    <value>*</value>
    <description>ACL for DatanodeProtocol, which is used by datanodes to
    communicate with the namenode.
    The ACL is a comma-separated list of user and group names. The user and
    group list is separated by a blank. For e.g. "alice,bob users,wheel".
    A special value of "*" means all users are allowed.</description>
  </property>

  <!-- hadoop-policy.xml配置文件以上部分需要修改 -->
  <!-- hadoop-policy.xml后续配置无需修改和添加，此处省略，避免文档篇幅过长 -->
  <!-- ... -->

</configuration>

hadoop-policy.xml配置文件仅添加两处配置项；

新增的security.client.protocol.hosts，security.client.datanode.protocol.hosts两个配置项中的值，要替换成实际环境的IP地址；

此配置文件是限制可以访问hadoop节点的服务器ip，提高hadoop应用的安全性。

vi /etc/profile

export HADOOP_HOME=/data/hadoop-3.2.2
export PATH=$PATH:$HADOOP_HOME/bin

source /etc/profile

cd /data/hadoop-3.2.2/ 
./bin/hdfs namenode -format

仅第一次启动时需要执行格式化Hadoop操作，后续启动无需进行此操作

cd /data/hadoop-3.2.2/ 
./sbin/start-dfs.sh

hdfs dfs -mkdir /mining
hdfs dfs -chown mining:mining /mining

hdfs dfs -ls /    #显示创建的/mining即表示创建成功

cd /data/hadoop-3.2.2/
./sbin/stop-dfs.sh

cd /data/hadoop-3.2.2/
./sbin/start-dfs.sh

vi /etc/hosts

10.10.204.248 10-10-204-248
10.10.204.249 10-10-204-249
10.10.204.250 10-10-204-250