nagios的主从切换高可用部署并配置邮件告警

配置信息

IP	主机名	节点类型
192.168.100.41	z	主节点
192.168.100.43	nagios-client	从节点

建议关闭防火墙和selinux
nagios的部署：https://blog.csdn.net/Bilise/article/details/105057182
nagios自定义远程监控项:https://blog.csdn.net/Bilise/article/details/105077813

以下内容在主节点进行配置

一、在主节点上检查是否有nrpe进程

[root@z ~]# /usr/local/nagios/libexec//check_nagios -e 5 -F /usr/local/nagios/var/status.dat -C /usr/local/nagios/bin/nagios
NAGIOS OK: 6 processes, status log updated 8 seconds ago

二、修改两个节点的nrpe配置文件

[root@z ~]# vim /usr/local/nagios/etc/nrpe.cfg 

allowed_hosts=127.0.0.1,::1,192.168.100.43  //添加从节点的IP地址或网段
command[check_nagios]=/usr/local/nagios/libexec/check_nagios -e 5 -F /usr/local/nagios/var/status.dat -C /usr/local/nagios/bin/nagios

在从节点进行测试

[root@nagios-client ~]# /usr/local/nagios/libexec/check_nrpe -H 192.168.100.41 -c check_nagios
NAGIOS OK: 6 processes, status log updated 6 seconds ago

以下内容在从节点配置

一、修改nrpe.cfg文件

[root@z ~]# vim /usr/local/nagios/etc/nrpe.cfg 

allowed_hosts=127.0.0.1,::1,192.168.100.41  //添加主节点的IP地址或网段

二、复制相关文件到/usr/local/nagios/libexec/eventhandlers/下

[root@nagios-client eventhandlers]# cp enable_notifications /usr/local/nagios/libexec/eventhandlers/
[root@nagios-client eventhandlers]# cp disable_notifications /usr/local/nagios/libexec/eventhandlers/
[root@nagios-client eventhandlers]# cp redundancy-scenario1/handle-master-host-event /usr/local/nagios/libexec/eventhandlers/
[root@nagios-client eventhandlers]# cp redundancy-scenario1/handle-master-proc-event /usr/local/nagios/libexec/eventhandlers/
[root@nagios-client eventhandlers]# sed -i 's/active_service_checks/notifications/g' /usr/local/nagios/libexec/eventhandlers/handle-master-proc-event

授权

[root@nagios-client eventhandlers]# chown nagios.nagios /usr/local/nagios/libexec/eventhandlers/*
[root@nagios-client eventhandlers]# chmod 755 /usr/local/nagios/libexec/eventhandlers/*
[root@nagios-client eventhandlers]# ll /usr/local/nagios/libexec/eventhandlers/
total 16
-rwxr-xr-x 1 nagios nagios  759 Mar 25 15:28 disable_notifications
-rwxr-xr-x 1 nagios nagios  760 Mar 25 15:28 enable_notifications
-rwxr-xr-x 1 nagios nagios 2038 Mar 25 15:28 handle-master-host-event
-rwxr-xr-x 1 nagios nagios 1216 Mar 25 15:29 handle-master-proc-event

三、配置添加命令command

[root@nagios-client eventhandlers]# vim /usr/local/nagios/etc/objects/commands.cfg 

define command {
 command_name handle-master-host-event
 command_line $USER1$/eventhandlers/handle-master-host-event $HOSTSTATE$ $HOSTSTATETYPE$ $HOSTATTEMPT$
}

define command {
 command_name handle-master-proc-event
 command_line $USER1$/eventhandlers/handle-master-proc-event $SERVICESTATE$ $SERVICESTATETYPE$ $SERVICEATTEMPT$
}

define command {
 command_name check_nrpe
 command_line $USER1$/check_nrpe -H $HOSTADDRESS$ -c $ARG1$
}

四、修改本地主机文件

[root@nagios-client eventhandlers]# vim /usr/local/nagios/etc/objects/localhost.cfg 
define host {
        use                             critical-host
        host_name                       nagiosMaster
        alias                           nagios master
        address                         192.168.100.41
        event_handler                   handle-master-host-event
}

define service {
        use                              critical-service
        host_name                        nagiosMaster
        service_description              NAGIOS
        check_command                    check_nrpe!check_nagios
        event_handler                    handle-master-proc-event
}

五、修改模板文件

define host{
        name                            critical-host
        use                             generic-host
        check_period                    24x7
        check_interval                  5
        retry_interval                  1
        max_check_attempts              10
        check_command                   check-host-alive
        notification_period             workhours
        notification_interval           120
        notification_options            d,u,r
        contact_groups                  admins
        register                        0
        }

define service{
        name                            critical-service
        active_checks_enabled           1
        passive_checks_enabled          1
        parallelize_check               1
        obsess_over_service             1
        check_freshness                 0
        notifications_enabled           1
        event_handler_enabled           1
        flap_detection_enabled          1
        failure_prediction_enabled      1
        process_perf_data               1
        retain_status_information       1
        retain_nonstatus_information    1
        is_volatile                     0
        check_period                    24x7
        max_check_attempts              1
        normal_check_interval           1
        retry_check_interval            1
        contact_groups                  admins
        notification_options            w,u,c,r
        notification_interval           60
        notification_period             24x7
         register                        0
        }

六、修改 /usr/local/nagios/etc/nagios.cfg

[root@nagios-client eventhandlers]# vim /usr/local/nagios/etc/nagios.cfg 
# Values: 1 = enable notifications, 0 = disable notifications
enable_notifications=0
#改成不发告警
use_retained_program_state=0
#状态保持改成0，否则Nagios在启动和重启时将忽略notifications的设置，并采用最近的一个设置（比如你已经切换过一次发告警的状态）

七、重启nagios生效配置

[root@nagios-client eventhandlers]# systemctl restart nagios

八、配置邮件服务

[root@client ~]# vim /etc/mail.rc 
##添加以下内容，此前下载了mailx和sendmail
set from=1084373816@qq.com
set smtp=smtp.qq.com
set smtp-auth-user=XXXXXXX@qq.com		//此为QQ邮箱账号
set smtp-auth-password=XXXXXXX  	//此为QQ邮箱smtp授权码
set smtp-auth=login
[root@client ~]# vim /usr/local/nagios/etc/objects/contacts.cfg 
##修改此行，后为QQ邮箱账号
email			XXXXXX@qq.com

九、测试
如需发送邮件通知告警则需要开启邮件告警

[root@nagios-client eventhandlers]# vim /usr/local/nagios/etc/nagios.cfg 
s
enable_notifications=1 		 //1为开启，0为关闭

关闭主节点后，查看从节点的/var/log/message

[root@nagios-client eventhandlers]# tail -f /var/log/messages 
##可以在后面看到以下内容
Mar 25 23:16:37 nagios-client nagios: SERVICE ALERT: nagiosMaster;NAGIOS;CRITICAL;HARD;1;NAGIOS CRITICAL: Cannot open status log for reading!
Mar 25 23:16:37 nagios-client nagios: SERVICE EVENT HANDLER: nagiosMaster;NAGIOS;CRITICAL;HARD;1;handle-master-proc-event
Mar 25 23:16:37 nagios-client nagios: EXTERNAL COMMAND: ENABLE_NOTIFICATIONS;1585149397

QQ邮箱会收到邮件（或许会有稍许的延迟）