NFS双机热备高可用环境 - 运维笔记

关闭防火墙
# systemctl stop firewalld.service
# systemctl disable firewalld.service
# firewall-cmd --state
not running

关闭selinux
# cat /etc/sysconfig/selinux
SELINUX=disabled

# setenforce 0
# getenforce
Disabled
# reboot

1）安装keepalived
# yum -y install keepalived

2）Master节点的keepalived.conf配置
这里特别需要注意：
一定要设置keepalived为非抢占模式，如果设置成抢占模式会在不断的切换主备时容易造成NFS数据丢失。

# cp /etc/keepalived/keepalived.conf /etc/keepalived/keepalived.conf_bak
# >/etc/keepalived/keepalived.conf
# vim /etc/keepalived/keepalived.conf
! Configuration File for keepalived
global_defs {
    router_id master   #id可以随便设
}
vrrp_script chk_nfs {
    script "/etc/keepalived/nfs_check.sh"    #监控脚本
    interval 2
    weight -20   #keepalived部署了两台，所以设为20，如果三台就设为30
}
vrrp_instance VI_1 {
    state BACKUP    #两台主机都设为backup非抢占模式
    interface eth0  #网卡名写自己的，不要照抄
    virtual_router_id 51
    priority 100    #master设为100，backup设为80，反正要比100小
    advert_int 1
    nopreempt       #设置为非抢占模式必须要该参数
    authentication {
        auth_type PASS
        auth_pass 1111
    }   
    track_script {
        chk_nfs
    }
    virtual_ipaddress {
        172.16.60.244      #虚拟ip
    }
}

3）Slave节点的keepalived.conf配置
只需将priority参数项修改为80，其他配置的和master节点一样，脚本也一样。

# cp /etc/keepalived/keepalived.conf /etc/keepalived/keepalived.conf_bak
# >/etc/keepalived/keepalived.conf
# vim /etc/keepalived/keepalived.conf
! Configuration File for keepalived
global_defs {
    router_id master   
}
vrrp_script chk_nfs {
    script "/etc/keepalived/nfs_check.sh"    
    interval 2
    weight -20   
}
vrrp_instance VI_1 {
    state BACKUP    
    interface eth0  
    virtual_router_id 51
    priority 80   
    advert_int 1
    nopreempt       
    authentication {
        auth_type PASS
        auth_pass 1111
    }   
    track_script {
        chk_nfs
    }
    virtual_ipaddress {
        172.16.60.244      
    }
}


4）编辑nfs_check.sh监控脚本
# vim /etc/keepalived/nfs_check.sh
#!/bin/bash
A=`ps -C nfsd --no-header | wc -l`
if [ $A -eq 0 ];then
        systemctl restart nfs-server.service
        sleep 2
        if [ `ps -C nfsd --no-header| wc -l` -eq 0 ];then
            pkill keepalived
        fi
fi

设置脚本执行权限
# chmod 755 /etc/keepalived/nfs_check.sh

5）启动keepalived服务
# systemctl restart keepalived.service && systemctl enable keepalived.service

查看服务进程是否启动
# ps -ef|grep keepalived

6）检查vip是否存在
在两台节点机器上执行"ip addr"命令查看vip，其中会在一台机器上产生vip地址。
# ip addr|grep 172.16.60.244
    inet 172.16.60.244/32 scope global eth0
    
测试vip地址要能被ping通  
# ping 172.16.60.244
PING 172.16.60.244 (172.16.60.244) 56(84) bytes of data.
64 bytes from 172.16.60.244: icmp_seq=1 ttl=64 time=0.063 ms
64 bytes from 172.16.60.244: icmp_seq=2 ttl=64 time=0.042 ms
64 bytes from 172.16.60.244: icmp_seq=3 ttl=64 time=0.077 ms

7）keepalived故障测试
停掉vip所在的Master节点机器上的keepalived服务后，发现vip会自动飘移到另一台Backup机器上才算测试成功。
当该Master节点的keepalived服务重新启动后，vip不会重新飘移回来。因为keepalived采用了非抢占模式。

如果keepalived设置为抢占模式，vip会在Master节点的keepalived重启恢复后自动飘回去，
但是这样一直来回切换可能会造成NFS数据不完整，因为这里必须设置成非抢占模式。

由于配置了nfs的nfs_check.sh监控脚本，所以当其中一台节点机器上的NFS服务宕停后会自动重启NFS。
如果NFS服务重启失败，则会自动关闭该节点机器上的keepalived服务，如果该节点有vip则会自动飘移到另外一台节点上。

#!/bin/bash
VIP_NUM=`ip addr|grep 244|wc -l`
RSYNC_INOTIRY_NUM=`ps -ef|grep /usr/bin/inotifywait|grep -v grep|wc -l`
if [ ${VIP_NUM} -ne 0 ];then
   echo "VIP在当前NFS节点服务器上" >/dev/null 2>&1
   if [ ${RSYNC_INOTIRY_NUM} -ne 0 ];then
      echo "rsync_inotify.sh脚本已经在后台执行中" >/dev/null 2>&1
   else
      echo "需要在后台执行rsync_inotify.sh脚本" >/dev/null 2>&1
      nohup sh /opt/rsync_inotify.sh &
  fi
else
   echo "VIP不在当前NFS节点服务器上" >/dev/null 2>&1
   if [ ${RSYNC_INOTIRY_NUM} -ne 0 ];then
      echo "需要关闭后台执行的rsync_inotify.sh脚本" >/dev/null 2>&1
      ps -ef|grep rsync_inotify.sh|grep -v grep|awk '{print $2}'|xargs kill -9
      ps -ef|grep inotifywait|grep -v grep|awk '{print $2}'|xargs kill -9
   else
      echo "rsync_inotify.sh脚本当前未执行" >/dev/null 2>&1
   fi
fi