55_03_2_实验:Nagios的配置及邮件报警

2016-02-05

监控端：192.168.122.115
被监控端：192.168.122.102

被监控端安装的软件包

# yum -y install nrpe nagios-plugins-all nagios-plugins


# egrep -v "^$|#" /etc/nagios/nrpe.cfg 

log_facility=daemon
pid_file=/var/run/nrpe/nrpe.pid
server_port=5666
nrpe_user=nrpe
nrpe_group=nrpe
allowed_hosts=192.168.122.115
 
dont_blame_nrpe=0
allow_bash_command_substitution=0
debug=0
command_timeout=60
connection_timeout=300
command[check_users]=/usr/lib64/nagios/plugins/check_users -w 5 -c 10
command[check_load]=/usr/lib64/nagios/plugins/check_load -w 15,10,5 -c 30,25,20
command[check_vda]=/usr/lib64/nagios/plugins/check_disk -w 20% -c 10% -p /dev/vda
command[check_zombie_procs]=/usr/lib64/nagios/plugins/check_procs -w 5 -c 10 -s Z
command[check_total_procs]=/usr/lib64/nagios/plugins/check_procs -w 150 -c 200 
command[check_mysql_alive]=/usr/lib64/nagios/plugins/check_mysql -H localhost -uroot -peasyheart -P3306 
include_dir=/etc/nrpe.d/

# chkconfig nrpe on && service nrpe start

监控端

安装依赖包

# yum -y install epel-release httpd gcc glibc glibc-common gd gd-devel php mysql mysql-server php-mysql mysql-devel php-snmp php-xml php-gd 
# yum -y install nagios
# yum -y install nagios-plugins nagios-plugins-all nagios-plugins-mysql
# yum -y install nagios-plugins-nrpe  #用来以nrpe的方式进行监控，也就是在/usr/lib64/nagios/plugins/增加了check_nrpe命令;
# chkconfig nagios on
# chkconfig --list nagios
# cp /etc/nagios/passwd /etc/nagios/passwd.bak
# htpasswd -c /etc/nagios/passwd nagiosadmin
# service nagios start
# service httpd reload

这个时候可以登录web查看localhost可以正常运行了;

执行如下命令，确保可以正常执行

1 2	# /usr/lib64/nagios/plugins/check_nrpe -H 192.168.122.102 NRPE v2.15

添加commands

# vim /etc/nagios/objects/commands.cfg　　　　　　//添加
define command{
        command_name check_nrpe
        command_line $USER1$/check_nrpe -H $HOSTADDRESS$ -c $ARG1$
}

node1

# cp /etc/nagios/objects/localhost.cfg /etc/nagios/objects/node1.cfg //关于命名，最好对应不同的hostname
# egrep -v "^$|#" /etc/nagios/objects/node1.cfg 
define host{
        use                     linux-server            ; Name of host template to use
                    ; This host definition will inherit all variables that are defined
                    ; in (or inherited by) the linux-server host template definition.
        host_name               node1
        alias                   My Linux Host
        address                 192.168.122.102
        }
define service{
        use                             generic-service         ; Name of service template to use
        host_name                       node1
        service_description             users
    check_command            check_nrpe!check_users
        }
define service{
        use                             generic-service         ; Name of service template to use
        host_name                       node1
        service_description             vda
    check_command            check_nrpe!check_vda
        }
define service{
        use                             generic-service         ; Name of service template to use
        host_name                       node1
        service_description             zombie_proc
    check_command            check_nrpe!check_zombie_procs
        }
define service{
        use                             generic-service         ; Name of service template to use
        host_name                       node1
        service_description             Total Processes
    check_command            check_nrpe!check_total_procs
        }
define service{
        use                             generic-service
        host_name                       node1
        service_description             MySQL Server
        check_command                   check_nrpe!check_mysql_alive
}

启动这个配置文件

# vim /etc/nagios/nagios.cfg
cfg_file=/etc/nagios/objects/node1.cfg

# service nagios restart

有多少主机就这样定义即可；

关于收取邮件需要注意的地方

hostname这个地方，另外就是上面提及到的自定义的host_name,一定要和主机的hostname一致;
配置监控机邮件服务：

# vim /etc/nagios/objects/contacts.cfg

注意：由于本地没有nagiosadmin用户，所以是没有办法发送邮件的，这个时候：
# useradd -r -s /sbin/nologin nagiosadmin

email那最好对应163邮箱;

# iptables -F
# service postfix restart
即可；

补充

-w 表示warning阀值
-c 表示critical阀值
应该根据实际定义这个值