nagios监控配置与邮件告警
ip | 主机名 | 备注 |
---|---|---|
172.16.121.227 | nagios | 服务端 |
172.16.121.228 | client | 客户端 |
这里还需要安装nagios服务以及插件可以参考我之前的博客:https://blog.csdn.net/miss_miss6/article/details/105061694
1.先设置服务端
[root@nagios ~]# vi /usr/local/nagios/etc/nrpe.cfg
修改和添加2条命令
allowed_hosts=127.0.0.1,::1,172.16.121.0/24 加上监控网段
command[check_nagios]=/usr/local/nagios/libexec/check_nagios -e 5 -F /usr/local/nagios/var/status.dat -C /usr/local/nagios/bin/nagios
2.配置客户端
这里先测试服务端配置是否正常
[root@client ~]# cd /usr/local/nagios/libexec/
[root@client libexec]# ./check_nrpe -H 172.16.121.227
NRPE v3.1.0-rc1
[root@client libexec]# ./check_nrpe -H 172.16.121.227 -c check_nagios
NAGIOS OK: 6 processes, status log updated 1 second ago
复制相关文档到/usr/local/nagios/libexec/eventhandlers/下
cd /root/wjh/nagios-4.3.1/contrib/eventhandlers/
cp enable_notifications /usr/local/nagios/libexec/eventhandlers/
cp disable_notifications /usr/local/nagios/libexec/eventhandlers/
cp redundancy-scenario1/handle-master-host-event /usr/local/nagios/libexec/eventhandlers/
cp redundancy-scenario1/handle-master-proc-event /usr/local/nagios/libexec/eventhandlers/
sed -i 's/active_service_checks/notifications/g' /usr/local/nagios/libexec/eventhandlers/handle-master-proc-event
chown nagios.nagios /usr/local/nagios/libexec/eventhandlers/*
chmod 755 /usr/local/nagios/libexec/eventhandlers/*
修改/usr/local/nagios/etc/objects/commands.cfg文件
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 $ARG1$
}
修改主机文件/usr/local/nagios/etc/objects/localhost.cfg
define host {
use critical-host
host_name nagiosMaster
alias nagios master
address 172.16.121.227
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
}
修改模板文件 /usr/local/nagios/etc/objects/templates.cfg
[root@client eventhandlers]# vi /usr/local/nagios/etc/objects/templates.cfg
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
}
修改 /usr/local/nagios/etc/nagios.cfg
enable_notifications=0
use_retained_program_state=0
到这里监控服务端的配置基本完成重启两台的nagios服务
告警配置失败