hadoop伪分布式部署

1. 上传jdk和hadoop安装包到服务器

2. 解压压缩包

shell 复制代码

tar xf jdk1.8.0_112.tgz -C /usr/local/
tar xf hadoop-3.3.6.tar.gz  -C /usr/local/

3. 关闭防火墙

shell 复制代码

#关闭防火墙
systemctl stop firewalld
#关闭防火墙开机自启
systemctl disable firewalld

4. 修改配置文件

core-site.xml、hadoop-env.sh、yarn-env.sh、mapred-site.xml、yarn-site.xml、hdfs-site.xml

vim /usr/local/hadoop-3.3.6/etc/hadoop/core-site.xml

shell 复制代码

<configuration>
  <property>
    <name>fs.defaultFS</name>
    <value>hdfs://master:8020</value>
  </property>
  <property>
    <name>hadoop.tmp.dir</name>
    <value>/var/log/hadoop/tmp</value>
  </property>
</configuration>

vim /usr/local/hadoop-3.3.6/etc/hadoop/mapred-site.xml

shell 复制代码

<configuration>
  <!-- Framework name -->
  <property>
    <name>mapreduce.framework.name</name>
    <value>yarn</value>
  </property>

  <!-- Job history properties -->
  <property>
    <name>mapreduce.jobhistory.address</name>
    <value>master:10020</value>
  </property>

  <property>
    <name>mapreduce.jobhistory.webapp.address</name>
    <value>master:19888</value>
  </property>

  <property>
    <name>yarn.app.mapreduce.am.env</name>
    <value>HADOOP_MAPRED_HOME=${HADOOP_HOME}</value>
  </property>

  <property>
    <name>mapreduce.map.env</name>
    <value>HADOOP_MAPRED_HOME=${HADOOP_HOME}</value>
  </property>

  <property>
    <name>mapreduce.reduce.env</name>
    <value>HADOOP_MAPRED_HOME=${HADOOP_HOME}</value>
  </property>

</configuration>

vim /usr/local/hadoop-3.3.6/etc/hadoop/yarn-site.xml

shell 复制代码

<configuration>

    <!-- Site specific YARN configuration properties -->

    <!-- 指定YARN ResourceManager的主机名，通常是集群的主节点 -->
    <property>
        <name>yarn.resourcemanager.hostname</name>
        <value>master</value>
    </property>

    <!-- ResourceManager的RPC服务地址 -->
    <property>
        <name>yarn.resourcemanager.address</name>
        <value>${yarn.resourcemanager.hostname}:8032</value>
    </property>

    <!-- ResourceManager的调度器地址，用于任务调度 -->
    <property>
        <name>yarn.resourcemanager.scheduler.address</name>
        <value>${yarn.resourcemanager.hostname}:8030</value>
    </property>

    <!-- ResourceManager的Web应用程序地址，用于浏览集群状态 -->
    <property>
        <name>yarn.resourcemanager.webapp.address</name>
        <value>${yarn.resourcemanager.hostname}:8088</value>
    </property>

    <!-- ResourceManager的Web应用程序HTTPS地址，启用安全连接时使用 -->
    <property>
        <name>yarn.resourcemanager.webapp.https.address</name>
        <value>${yarn.resourcemanager.hostname}:8090</value>
    </property>

    <!-- ResourceManager的资源跟踪服务地址，节点管理器向该地址报告资源信息 -->
    <property>
        <name>yarn.resourcemanager.resource-tracker.address</name>
        <value>${yarn.resourcemanager.hostname}:8031</value>
    </property>

    <!-- ResourceManager的管理接口地址，用于管理和控制集群 -->
    <property>
        <name>yarn.resourcemanager.admin.address</name>
        <value>${yarn.resourcemanager.hostname}:8033</value>
    </property>

    <!-- NodeManager本地存储临时文件的目录 -->
    <property>
        <name>yarn.nodemanager.local-dirs</name>
        <value>/data/hadoop/yarn/local</value>
    </property>

    <!-- 是否启用日志聚合，将节点上的日志收集到一个中心位置 -->
    <property>
        <name>yarn.log-aggregation-enable</name>
        <value>true</value>
    </property>

    <!-- 存储应用程序日志的远程目录 -->
    <property>
        <name>yarn.nodemanager.remote-app-log-dir</name>
        <value>/data/tmp/logs</value>
    </property>

    <!-- 日志服务器的URL，用于访问应用程序的历史日志 -->
    <property>
        <name>yarn.log.server.url</name>
        <value>http://master:19888/jobhistory/logs/</value>
    </property>

    <!-- 是否启用虚拟内存检查，可以防止内存超用，但可能会影响任务运行 -->
    <property>
        <name>yarn.nodemanager.vmem-check-enabled</name>
        <value>false</value>
    </property>

    <!-- 定义NodeManager的辅助服务，mapreduce_shuffle是MapReduce任务所需的服务 -->
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>

    <!-- 配置ShuffleHandler类，处理MapReduce Shuffle操作 -->
    <property>
        <name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>
        <value>org.apache.hadoop.mapred.ShuffleHandler</value>
    </property>

    <!-- 配置NodeManager节点上可用的内存（以MB为单位） -->
    <property>
        <name>yarn.nodemanager.resource.memory-mb</name>
        <value>2048</value>
    </property>

    <!-- 调度器允许分配的最小内存大小 -->
    <property>
        <name>yarn.scheduler.minimum-allocation-mb</name>
        <value>512</value>
    </property>

    <!-- 调度器允许分配的最大内存大小 -->
    <property>
        <name>yarn.scheduler.maximum-allocation-mb</name>
        <value>4096</value>
    </property>

    <!-- Map任务分配的内存大小 -->
    <property>
        <name>mapreduce.map.memory.mb</name>
        <value>2048</value>
    </property>

    <!-- Reduce任务分配的内存大小 -->
    <property>
        <name>mapreduce.reduce.memory.mb</name>
        <value>2048</value>
    </property>

    <!-- 配置NodeManager可用的CPU核心数 -->
    <property>
        <name>yarn.nodemanager.resource.cpu-vcores</name>
        <value>1</value>
    </property>
</configuration>

vim /usr/local/hadoop-3.3.6/etc/hadoop/hdfs-site.xml

shell 复制代码

<configuration>

  <!-- NameNode directory -->
  <property>
    <name>dfs.namenode.name.dir</name>
    <value>file:///data/hadoop/hdfs/name</value>
  </property>

  <!-- DataNode directory -->
  <property>
    <name>dfs.datanode.data.dir</name>
    <value>file:///data/hadoop/hdfs/data</value>
  </property>

  <!-- Allow HTTP access to NameNode -->
  <property>
    <name>dfs.namenode.secondary.http-address</name>
    <value>master:50090</value>
  </property>

  <!-- Replication factor -->
  <property>
    <name>dfs.replication</name>
    <value>3</value>
  </property>
</configuration>

vim /usr/local/hadoop-3.3.6/etc/hadoop/hadoop-env.sh

vim /usr/local/hadoop-3.3.6/etc/hadoop/yarn-env.sh

vim /etc/hosts

5. 创建ssh免密

shell 复制代码

ssh-keygen -t rsa

回车回车回车

shell 复制代码

ssh-copy-id master

6. 配置java和hadoop环境变量

vi /etc/profile

shell 复制代码

export JAVA_HOME=/usr/local/jdk1.8.0_112
export HADOOP_HOME=/usr/local/hadoop-3.3.6
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin

source /etc/profile

验证是否成功

java -version

hadoop version

7. 格式化namenode

hdfs namenode -format

8. 修改启动、停止脚本

vi /usr/local/hadoop-3.3.6/sbin/start-dfs.sh

增加配置

shell 复制代码

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

vi /usr/local/hadoop-3.3.6/sbin/stop-dfs.sh

shell 复制代码

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

vi /usr/local/hadoop-3.3.6/sbin/start-yarn.sh

shell 复制代码

YARN_RESOURCEMANAGER_USER=root
HADOOP_SECURE_DN_USER=yarn
YARN_NODEMANAGER_USER=root

vi /usr/local/hadoop-3.3.6/sbin/stop-yarn.sh

shell 复制代码

YARN_RESOURCEMANAGER_USER=root
HADOOP_SECURE_DN_USER=yarn
YARN_NODEMANAGER_USER=root

9. 启动hadoop集群

shell 复制代码

start-dfs.sh
start-yarn.sh
mr-jobhistory-daemon.sh start historyserver

10. 界面查看

10.1 hdfs的web查看

输入自己IP地址加端口

http://192.168.100.110:9870

10.2 yarn的web查看

http://192.168.100.110:8088

10.3 Historyserver的web界面

http://192.168.100.110:19888