Nagios远程监控
1.添加用户# useradd nagios
2.安装nagios-plugins
# tar zxf nagios-plugins-2.0.3.tar.gz
# ./configure --with-nagios-user=nagios --with
--with-apt-get-command:
--with-ping6-command: /bin/ping6 -n -U -w %d -c %d %s
--with-ping-command: /bin/ping -n -U -w %d -c %d %s
--with-ipv6: yes
--with-mysql: /usr/bin/mysql_config
--with-openssl: yes
--with-gnutls: no
--enable-extra-opts: yes
--with-perl: /usr/bin/perl
--enable-perl-modules: no
--with-cgiurl: /nagios/cgi-bin
--with-trusted-path: /bin:/sbin:/usr/bin:/usr/sbin
--enable-libtap: no
# make && make install
# pwd
/usr/local/nagios
# chown -R nagios.nagios *
3.安装 NRPE
# tar zxf nrpe-2.15.tar.gz
# ./configure
General Options:
-------------------------
NRPE port: 5666
NRPE user: nagios
NRPE group: nagios
Nagios user:nagios
Nagios group: nagios
# make all
4.安装插件、daemon和示例配置文件
#安装nrpe-plugin插件
# make install-plugin
#安装nrpe daemon
# make install-daemon
#安装daemon配置文件
# make install-daemon-config
#安装xinetd脚本,NRPE daemon是作为xinetd下的一个服务来运行的，所以先安装好xinetd
# yum install -y xinetd
# make install-xinetd
4.修改配置文件
# vim /etc/xinetd.d/nrpe #添加nagios服务端的地址
only_from = 172.25.16.2 #nagios 主机 ip 地址
# vim /usr/local/nagios/etc/nrpe.cfg
allowed_hosts=172.25.16.2 #允许监测主机的IP
5.编辑/etc/services文件，增加NRPE服务
nrpe 5666/tcp #nrpe
6.重启服务
# /etc/init.d/xinetd restart
# netstat -antlp | grep 5666 #NRPE已经启动
tcp 0 0 :::5666 :::* LISTEN 22872/xinetd
#在监控主机上
1.安装NRPE，只需要check_nrpe插件，可直接从被监测端copy
# scp check_nrpe 172.25.16.2:/usr/local/nagios/libexec/
# chown nagios.nagios check_nrpe
# ll check_nrpe
-rwxr-xr-x. 1 nagios nagios 76769 Aug 29 23:36 check_nrpe
# ./check_nrpe -H 172.25.16.3#输出nrpe的版本，说明监测机check_nrpe与被监测主机运行的nrpe daemon之间建立联系
NRPE v2.15
# vim /usr/local/nagios/etc/objects/commands.cfg
# 'check_nrpe'
define command{
command_name check_nrpe
command_line $USER1$/check_nrpe -H $HOSTADDRESS$ -c "$ARG1$"#-c后面的参数是传给被监测端nrpe daemon要执行的监测命令，这些命令在nrpe.cfg中要求已经定义
}
# grep -v '^#' /usr/local/nagios/etc/nrpe.cfg | sed '/^$/d'
log_facility=daemon
pid_file=/var/run/nrpe.pid
server_port=5666
nrpe_user=nagios
nrpe_group=nagios
allowed_hosts=172.25.16.2
dont_blame_nrpe=0
allow_bash_command_substitution=0
debug=0
command_timeout=60
connection_timeout=300
command=/usr/local/nagios/libexec/check_users -w 5 -c 10
command=/usr/local/nagios/libexec/check_load -w 15,10,5 -c 30,25,20
command=/usr/local/nagios/libexec/check_disk -w 20% -c 10% -p /
command=/usr/local/nagios/libexec/check_procs -w 5 -c 10 -s Z
command=/usr/local/nagios/libexec/check_procs -w 150 -c 200
# vim /usr/local/nagios/etc/objects/services.cfg#在这个里面定义的服务命令完全根据在被监控端nrpe.cfg中内置命令定义的，如上面命令所示
define service{
use generic-service
host_name server3.example.com
service_description CPU Load
check_command check_nrpe!check_load
}
define service{
use generic-service
host_name server3.example.com
service_description Current Users
check_command check_nrpe!check_users
}
define service{
use generic-service
host_name server3.example.com
service_description/ Free Space
check_command check_nrpe!check_disk
}
define service{
use generic-service
host_name server3.example.com
service_description Total Processes
check_commandcheck_nrpe!check_total_procs
}
define service{
use generic-service
host_name server3.example.com
service_descriptionZombie Processes
check_command check_nrpe!check_zombie_procs
}
#监测是否有语法错误并测试
# /usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg
#/usr/local/nagios/libexec/check_nrpe -H 172.25.16.3 -c check_load
OK - load average: 0.08, 0.02, 0.01|load1=0.080;15.000;30.000;0; load5=0.020;10.000;25.000;0; load15=0.010;5.000;20.000;0;
# /usr/local/nagios/libexec/check_nrpe -H 172.25.16.3 -c check_users
USERS OK - 1 users currently logged in |users=1;5;10;0
页:
[1]