Nagios监控工具

Nagios监控工具
不会显示具体的值，仅显示主机或服务的状态
强大的报警功能
高度插件化

Nagios监控主机/服务显示的4种状态
OK
WARNING
CRITICAL
UNKNOWN

Nagios对象：
主机，主机组
服务/资源，服务组
联系人，联系人组
时间段
命令(模板--->应用到某个被监控对象，以实现监控)

Nagios实现监控的方式：
check_by_ssh
check_by_nrpe：专用于监控Linux或Unix主机
check_by_nsclient++：用于监控Windows主机
check_by_snmp
check_by_nsca：实现被动方式的nagios，由被监控对象主动向nagios发送状态信息
check_by_xyz：自定义监控方式/脚本

安装nagios

1、安装依赖的软件
# yum install -y httpd php php-mysql mysql-devel mysql

2、创建nagios运行需要的用户和组
# groupadd nagcmd
# useradd -G nagcmd nagios

将运行apache进程的用户加入到nagcmd组中
# usermod -a -G nagcmd apache

3、安装nagios
# tar zxf nagios-3.3.1.tar.gz
# cd nagios
# ./configure --with-command-group=nagcmd --enable-event-broker --sysconfdir=/etc/nagios
# make all
# make install
# make install-init
# make install-commandmode
# make install-config
# make install-webconf

创建一个登录nagios web页面的用户，这个用户账号在以后通过web登录nagios时使用
# htpasswd -c /etc/nagios/htpasswd.users nagiosadmin
New password:
Re-type new password:
Adding password for user nagiosadmin

启动httpd服务
# service httpd start

4、安装nagios-plugins插件

# tar zxf nagios-plugins-1.5.tar.gz
# cd nagios-plugins-1.5
# ./configure --with-nagios-user=nagios --with-nagios-group=nagios
# make && make install

5、启动nagios服务
# chkconfig --add nagios
# service nagios start

6、访问nagios http://10.1.1.2/nagios
配置nagios
nagios配置文件保存在/etc/nagios目录下

nagios插件目录
/usr/local/nagios/libexec

nagios监控windows主机
SNMP
NSClient++
nagios通过check_nt插件与windows NSClient++通信
NSClient++可提供check_nt，check_nrpe及NSCA的能力
NSClient++监听在12489/tcp端口与check_nt插件通信

配置check_nt与NSClient++监控windows主机

1、定义命令command
# vim /etc/nagios/objects/commands.cfg

define command{
command_name check_nt
command_line $USER1$/check_nt -H $HOSTADDRESS$ -p 12489 -v $ARG1$ $ARG2$
}

2、定义主机host及服务service
# vim /etc/nagios/objects/windows.cfg

define host{
use windows-server ; Inherit default values from a template
host_name winhost; The name we're giving to this host
alias My Windows Server ; A longer name associated with the host
address 10.1.1.254 ; IP address of the host
}

define service{
use generic-service
host_name winhost
service_description Uptime
check_command check_nt!UPTIME
}

3、启用主机配置文件
# vim /etc/nagios/nagios.cfg
cfg_file=/etc/nagios/objects/windows.cfg

4、检测配置文件语法，并重启nagios服务
# /usr/local/nagios/bin/nagios -v /etc/nagios/nagios.cfg
# service nagios restart

浏览器访问http://10.1.1.2/nagios查看监控状态数据

配置check_nrpe监控Linux及windows主机

监控端通过check_nrpe与被监控端nrpe进程通信
nrpe监听在5666/tcp端口
监控端、被监控端都需要安装nrpe addon，被监控端需要启动nrpe服务

一、监控Linux 主机10.1.1.1

1、在被监控主机上安装nrpe并配置

1)创建nagios用户
# useradd -s /sbin/nologin nagios

2)nrpe依赖于nagios-plugins，安装nagios-plugins
# tar zxf nagios-plugins-1.4.14.tar.gz
# cd nagios-plugins-1.4.14
# ./configure --with-nagios-user=nagios --with-nagios-group=nagios
# make all
# make install

3)安装nrpe
# tar zxf nrpe-2.15.tar.gz
# cd nrpe-2.15
# ./configure --with-nrpe-user=nagios --with-nrpe-group=nagios --with-nagios-user=nagios --with-nagios-group=nagios --enable-command-args --enable-ssl
# make all
# make install-plugin
# make install-daemon
# make install-daemon-config

4）配置nrpe
# vim /usr/local/nagios/etc/nrpe.cfg

log_facility=daemon
pid_file=/var/run/nrpe.pid
server_port=5666
server_address=10.1.1.1
nrpe_user=nagios
nrpe_group=nagios
allowed_hosts=10.1.1.2
command_timeout=60

定义监控本地资源的命令
command[check_users]=/usr/local/nagios/libexec/check_users -w 5 -c 10
command[check_load]=/usr/local/nagios/libexec/check_load -w 15,10,5 -c 30,25,20
command[check_sda1]=/usr/local/nagios/libexec/check_disk -w 20% -c 10% -p /dev/sda1
command[check_sda2]=/usr/local/nagios/libexec/check_disk -w 20% -c 10% -p /dev/sda2
command[check_sda3]=/usr/local/nagios/libexec/check_disk -w 20% -c 10% -p /dev/sda3
command[check_zombie_procs]=/usr/local/nagios/libexec/check_procs -w 5 -c 10 -s Z
command[check_total_procs]=/usr/local/nagios/libexec/check_procs -w 150 -c 200

5)编写启动nrpe服务脚本
# vim /etc/rc.d/init.d/nrpe
#!/bin/bash
#
# chkconfig: 2345 88 12
# description: NRPE DAEMON
NRPE=/usr/local/nagios/bin/nrpe
NRPECONF=/usr/local/nagios/etc/nrpe.cfg

case $1 in
start)
echo -n "Starting NRPE damon...."
$NRPE -c $NRPECONF -d
echo "Done..."
;;
stop)
echo -n "Stopping NRPE daemon...."
pkill -u nagios nrpe
echo "Done...."
;;
restart)
$0 stop
sleep 2
$0 start
;;
*)
echo "Usage: $0 { start | stop | restart }"
;;
esac
exit 0

# chmod +x /etc/rc.d/init.d/nrpe
# chkconfig --add nrpe
# service nrpe start
# netstat -tnlp
Active Internet connections (only servers)
Proto Recv-Q Send-Q Local Address Foreign Address State PID/Program name
tcp 0 0 10.1.1.1:5666 0.0.0.0:* LISTEN 6826/nrpe

2、在监控端安装nrpe

1)安装nrpe
# tar zxf nrpe-2.15.tar.gz
# cd nrpe-2.15
# ./configure --with-nrpe-user=nagios --with-nrpe-group=nagios --with-nagios-user=nagios --with-nagios-group=nagios --enable-command-args --enable-ssl
# make all
# make install-plugin

安装完成后，在/usr/local/nagios/libexec目录下会产生check_nrpe插件
通过以下命令可测试插件是否工作正常
# ./check_nrpe -H 10.1.1.1
NRPE v2.15

3、配置监控Linux主机

1)定义命令command
# vim /etc/nagios/objects/commands.cfg
define command{
command_name check_nrpe
command_line $USER1$/check_nrpe -H $HOSTADDRESS$ -c $ARG1$
}

2)定义主机host及服务service
# cp /etc/nagios/objects/windows.cfg /etc/nagios/objects/linux.cfg
# vim /etc/nagios/objects/linux.cfg

define host{
use linux-server ; Inherit default values from a template
host_name linuxhost; The name we're giving to this host
alias My Linux Server ; A longer name associated with the host
address 10.1.1.1 ; IP address of the host
}

define service{
use generic-service
host_name linuxhost
service_description Users
check_command check_nrpe!check_users
}

define service{
use generic-service
host_name linuxhost
service_description Load
check_command check_nrpe!check_load
}

define service{
use generic-service
host_name linuxhost
service_description SDA1
check_command check_nrpe!check_sda1
}

define service{
use generic-service
host_name linuxhost
service_description SDA2
check_command check_nrpe!check_sda2
}

define service{
use generic-service
host_name linuxhost
service_description SDA3
check_command check_nrpe!check_sda3
}

define service{
use generic-service
host_name linuxhost
service_description Zombie procs
check_command check_nrpe!check_zombie_procs
}

define service{
use generic-service
host_name linuxhost
service_description total procs
check_command check_nrpe!check_total_procs
}

check_nrpe!check_total_procs
!后面为被监控端定义好的命令名称

3)启用主机配置文件
# vim /etc/nagios/nagios.cfg
cfg_file=/etc/nagios/objects/linux.cfg

4)检测配置文件语法，并重启nagios服务
# /usr/local/nagios/bin/nagios -v /etc/nagios/nagios.cfg
# service nagios restart

在10.1.1.1上分别安装web及mysql服务，配置监控端10.1.1.2监控这两个服务

1、在10.1.1.1上安装web及mysql
# yum install -y httpd mysql-server

需要在mysql服务器上创建允许远程登录的用户

2、编辑command.cfg分别定义监控web及mysql服务的命令
# vim /etc/nagios/objects/commands.cfg

define command{
command_name check_http
command_line $USER1$/check_http -I $HOSTADDRESS$ $ARG1$
}

define command{
command_name check_mysql
command_line $USER1$/check_mysql -H $HOSTADDRESS$ -u $ARG1$ -p $ARG2$
}

3、编辑linux.cfg配置文件，定义web及mysql服务
# vim /etc/nagios/objects/linux.cfg

define service{
use generic-service
host_name linuxhost
service_description Web Server
check_command check_http
}

define service{
use generic-service
host_name linuxhost
service_description Mysql Server
check_command check_mysql!admin!redhat
}

4、检测配置文件语法，并重启nagios服务
# /usr/local/nagios/bin/nagios -v /etc/nagios/nagios.cfg
# service nagios restart