大数据之---hadoop伪分布式部署(HDFS)全网终极篇

在吉安等地区，都构建了全面的区域性战略布局，加强发展的系统性、市场前瞻性、产品创新能力，以专注、极致的服务理念，为客户提供网站建设、做网站网站设计制作按需定制开发,公司网站建设,企业网站建设,品牌网站设计,全网整合营销推广,外贸网站建设,吉安网站建设费用合理。

1、软件环境

RHEL6	jdk-8u45
hadoop-2.8.1.tar.gz	ssh
xx.xx.xx.xx ip地址	hadoop1
xx.xx.xx.xx ip地址	hadoop2
xx.xx.xx.xx ip地址	hadoop3
xx.xx.xx.xx ip地址	hadoop4
xx.xx.xx.xx ip地址	hadoop5

本次部署只涉及伪分布式部署只是要主机hadoop1

2.伪分布式部署

伪分布式部署文档参考官方网站hadoop
Apache > Hadoop > Apache Hadoop Project Dist POM > Apache Hadoop 2.8.3 > Hadoop: Setting up a Single Node Cluster
添加hadoop用户

[root@hadoop1 ~]# useradd hadoop
[root@hadoop1 ~]# vi /etc/sudoers
# 找到root     ALL=(ALL)     ALL，添加
hadoop     ALL=(ALL)       NOPASSWD:ALL
上传并解压
[root@hadoop1 software]# rz #上传hadoop-2.8.1.tar.gz
[root@hadoop1 software]# tar -xzvf hadoop-2.8.1.tar.gz
软连接
[root@hadoop1 software]# ln -s /opt/software/hadoop-2.8.1 /opt/software/hadoop
设置环境变量
[root@hadoop1 software]# vi /etc/profile
export HADOOP_HOME=/opt/software/hadoop
export PATH=$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$PATH
[root@hadoop1 software]# source /etc/profile
设置用户、用户组
[root@hadoop1 software]# chown -R hadoop:hadoop hadoop
[root@hadoop1 software]# chown -R hadoop:hadoop hadoop/*
[root@hadoop1 software]# chown -R hadoop:hadoop hadoop-2.8.1
[root@hadoop1 software]# cd hadoop
[root@hadoop1 hadoop]# rm -f *.txt
[root@hadoop1 software]# su - hadoop
[root@hadoop1 hadoop]# ll
total 32
drwxrwxr-x. 2 hadoop hadoop 4096 Jun 2 14:24 bin
drwxrwxr-x. 3 hadoop hadoop 4096 Jun 2 14:24 etc
drwxrwxr-x. 2 hadoop hadoop 4096 Jun 2 14:24 include
drwxrwxr-x. 3 hadoop hadoop 4096 Jun 2 14:24 lib
drwxrwxr-x. 2 hadoop hadoop 4096 Aug 20 13:59 libexec
drwxr-xr-x. 2 hadoop hadoop 4096 Aug 20 13:59 logs
drwxrwxr-x. 2 hadoop hadoop 4096 Jun 2 14:24 sbin
drwxrwxr-x. 4 hadoop hadoop 4096 Jun 2 14:24 share

# bin:        可执行文件
# etc:         配置文件
# sbin:        shell脚本，启动关闭hdfs,yarn等配置文件
[hadoop@hadoop1 ~]# cd /opt/software/hadoop
[hadoop@hadoop1 hadoop]# vi etc/hadoop/core-site.xml


        fs.defaultFS
        hdfs://172.168.18.133:9000    # 配置自己机器的IP



[hadoop@hadoop1 hadoop]# vi etc/hadoop/hdfs-site.xml


        dfs.replication
        1

---红色部分新增
配置hadoop用户的ssh信任关系
# 公钥/密钥配置无密码登录
[hadoop@hadoop1 ~]# ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa
[hadoop@hadoop1 ~]# cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys
[hadoop@hadoop1 ~]# chmod 0600 ~/.ssh/authorized_keys
# 查看日期，看是否配置成功
[root@hadoop1 ~]# ssh hadoop1 date
Wed Apr 25 15:22:58 CST 2018

[root@hadoop1 ~]# ssh localhost date
Wed Apr 25 15:23:25 CST 2018

# 第一次执行命令有交互选择输入yes
格式化和启动
[hadoop@hadoop1 hadoop]# bin/hdfs namenode -format
[hadoop@hadoop1 hadoop]# sbin/start-dfs.sh
ERROR:
hadoop1: Error: JAVA_HOME is not set and could not be found.
localhost: Error: JAVA_HOME is not set and could not be found.
解决方法:添加环境变量
[hadoop@hadoop1 hadoop]# vi etc/hadoop/hadoop-env.sh
# 将export JAVA_HOME=${JAVA_HOME}改为
export JAVA_HOME=/usr/java/jdk1.8.0_45
# 继续启动
[hadoop@hadoop1 hadoop]# sbin/start-dfs.sh
检查是否成功
[hadoop@hadoop1 hadoop]# jps
8026 Jps
7485 NameNode
7597 DataNode
7807 SecondaryNameNode
访问： http://192.168.137.130:50070

修改dfs启动的进程，以hadoop1启动启动的三个进程：
namenode: hadoop1 bin/hdfs getconf -namenodes
datanode: localhost datanodes (using default slaves file) etc/hadoop/slaves
secondarynamenode: 0.0.0.0

[hadoop@hadoop1 ~]# cd /opt/software/hadoop
[hadoop@hadoop1 hadoop]# echo "hadoop1" > ./etc/hadoop/slaves
[hadoop@hadoop1 hadoop]# cat ./etc/hadoop/slaves
hadoop1
[hadoop@hadoop1 hadoop]# vi ./etc/hadoop/hdfs-site.xml

    dfs.namenode.secondary.http-address
    hadoop1:50090

    dfs.namenode.secondary.https-address
    hadoop1:50091

[hadoop@hadoop1 hadoop]# sbin/stop-dfs.sh
[hadoop@hadoop1 hadoop]# sbin/start-dfs.sh