nagios监控安装及设置案例

[root@server1 nagios]# 1 安装yum install gd-devel -y
[root@server1 nagios]# 2 部署lamp环境yum install httpd mysql mysql-server php php-mysql gcc gcc-c++ -y
[root@server1 nagios]# 3 安装主程序nagios
[root@server1 nagios]# tar fvxz nagios.tar.gz
[root@server1 nagios]# ./configure --prefix=/usr/local/nagios
[root@server1 nagios]# useradd nagios
[root@server1 nagios]# make all
[root@server1 nagios]# make install
make install
     - This installs the main program, CGIs, and HTML files

  make install-init
     - This installs the init script in /et c/rc.d/init.d

   make install-commandmode
     - This installs and configures permissions on the
       directory for holding the external command file

  make install-config
     - This installs *SAMPLE* config files in /usr/local/nagios/etc
       You'll have to modify these sample files before you can
       use Nagios.  Read the HTML documentation for more info
       on doing this.  Pay particular attention to the docs on
       object configuration files, as they determine what/how
       things get monitored!

  make install-webconf
     - This installs the Apache config file for the Nagios
       web interface

vim /etc/httpd/conf/httpd.conf
User nagios
Group nagios

重新启动apache
service httpd restart
                                                                                                                                     service nagios start
生成用户
[root@server1 nagios-3.2.0]# htpasswd -c /usr/local/nagios/etc/htpasswd.users nagiosm
New password: 
Re-type new password: 
Adding password for user nagios

给nagios用户开权限，让他能够查看信息！
[root@server1 nagios-3.2.0]# vim /usr/local/nagios/etc/cgi.cfg 
在所有的nagiosadmin后面添加nagios

本机为什么是down的状态？？？

监控分析控制台   －－－－－－－－－－－－－－－主程序
                插件
               －－－－－－－－－－－－－－被监控主机
nagios报错 无权查看任何主机的信息  解决方法

解决办法：

vi /usr/local/nagios/etc/cgi.cfg

将use_authentication的值改为0.

use_authentication=0

然后重启nagios服务

service nagios restart

[root@server1 libexec]# pwd
/usr/local/nagios/libexec
[root@server1 libexec]# ls
[root@server1 libexec]# 
插件目录下什么没有有阿！

安装插件
[root@server1 nagios-plugins-1.4.13]# ./configure --prefix=/usr/local/nagios/ -
可选的选项--with-gnutls --with-openssl --enable-extra-opts --enable-perl-modules 

make

make install

怎样监控的更多！

[root@server1 etc]# pwd
/usr/local/nagios/etc
[root@server1 etc]# vim nagios.cfg 
编辑主配置文件
cfg_file=/usr/local/nagios/etc/objects/commands.cfg
cfg_file=/usr/local/nagios/etc/objects/contacts.cfg
cfg_file=/usr/local/nagios/etc/objects/timeperiods.cfg
cfg_file=/usr/local/nagios/etc/objects/templates.cfg

通过上面的语句来调用那些配置文件
[root@server1 objects]# pwd
/usr/local/nagios/etc/objects

时间timeperiods.cfg
define timeperiod{
        timeperiod_name 24x7
        alias           24 Hours A Day, 7 Days A Week
        sunday          00:00-24:00
        monday          00:00-24:00
        tuesday         00:00-24:00
        wednesday       00:00-24:00
        thursday        00:00-24:00
        friday          00:00-24:00
        saturday        00:00-24:00
        }

插件commands.cfg
define command{
        command_name    check-host-alive
        command_line    $USER1$/check_ping -H $HOSTADDRESS$ -w 3000.0,80% -c 5000.0,100% -p 5
        }

监控谁localhost.cfg
define host {
        host_name       fudong
        alias           test
        address         192.168.18.50
        check_command   check-host-alive
        notification_options    d,u,r
        check_interval  1
        max_check_attempts      2
        contact_groups  admins
        notification_interval   10
        notification_period     24x7
}

联系人contacts.cfg

define contact {
        contact_name  kyo
        alias           kyo
        host_notification_period        24x7
        host_notification_options       d,u,r
        service_notification_period     24x7
        service_notification_options    w,u,c,r
        service_notification_commands   notify-service-by-email
        host_notification_commands      notify-host-by-email
        email   root@163.com
#通过飞信机器人发信报警！
}

define contactgroup{
        contactgroup_name       admins
        alias                   Nagios Administrators
        members                 nagiosadmin,kyo
        }

 检查错误
/usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg 

定义服务
define service {
        host_name       fudong
        service_description     apache
        check_period    24x7
        normal_check_interval   2
        retry_check_interval    1
        max_check_attempts      5 
        notification_period     24x7
        notification_options    w,u,c,r
        check_command   check_http

}

关于插件的返回状态
[root@server1 objects]# echo $?
2
[root@server1 objects]# /usr/local/nagios/libexec/check_http -I 192.168.18.50
HTTP OK HTTP/1.1 200 OK - 43306 bytes in 0.026 seconds |time=0.026288s;;;0.000000 size=43306B;;;0
[root@server1 objects]# echo $?
0
[root@server1 objects]# /usr/local/nagios/libexec/check_http -I 192.168.18.50 -u /a.html -s hello
HTTP WARNING: HTTP/1.1 404 Not Found
[root@server1 objects]# echo $?
1

0 成功  1 警告  2 严重错误  3 未知 
自己编写插件！！！！！！！！！！！！！！！！
#!/bin/bash

curl -I http://192.168.18.155 &> /dev/null

if [ $? -eq 0 ]; then
        ( curl -I http://192.168.18.155 | grep 'HTTP/1.1 200' ) &> /dev/null
        if [ $? -eq 0 ];then
                echo "OK!"
                exit 0
        else
                echo "warning!"
                exit 1
        fi
else
        echo "down!"
        exit 2
fi

自定义命令
define command {
        command_name    check_url
        command_line    $USER1$/check_http -I $HOSTADDRESS$ -u $ARG1$ -s $ARG2$
}

使用新定义的命令

define service {
        host_name       fudong
        service_description     apache
        check_period    24x7
        normal_check_interval   2
        retry_check_interval    1
        max_check_attempts      5
        notification_period     24x7
        notification_options    w,u,c,r
#       check_command   check_http
        check_command   check_url!/index.html!hello

}

########################################################################
check_mysql
vim /usr/local/nagios/libexec/check_mysql
#!/bin/bash
#check_mysql status
IP=$1

mysql -u test -h $IP -p123 -e 'show databases;' &> /dev/null

if [ $? -eq 0 ]; then
        echo "mysql OK!"
        exit 0;
else
        echo "mysql err!"                                                                                                                                          
        exit 2;
fi

vim /usr/local/nagios/etc/objects/commands.cfg
define command{
        command_name check_mysql
        command_line $USER1$/check_mysql $ARG1$
}

vim /usr/local/nagios/etc/objects/localhost.cfg
define service {
        host_name       mail.vfast.com
        service_description     mysql
        check_period    24x7
        normal_check_interval   2
        retry_check_interval    1
        max_check_attempts      2
        notification_period     24x7
        notification_options    w,u,c,r
        check_command   check_mysql!192.168.18.69
}

service nagios restart

###################################################################################

yum install expect -y

define command{
        command_name    notify-host-by-sms
        command_line    /usr/local/nagios/libexec/nagios-mail "$(/usr/bin/printf "%b" "***** Nagios *****\n\nNotification Type: $NOTIFICATIONTYPE$\nHost: $HOSTNAME$\nState: $HOSTSTATE$\nAddress: $HOSTADDRESS$\nInfo: $HOSTOUTPUT$\n\nDate/Time: $LONGDATETIME$\n")"  smtp.163.com  Y29vbHdhbmdjaG9uZ0AxNjMuY29t  UVE4MTBXQU5HODIwMCFA  coolwangchong@163.com $CONTACTEMAIL$  "** $NOTIFICATIONTYPE$ Host Alert: $HOSTNAME$ is $HOSTSTATE$ **"
        }

如果遇到host条目一会有，一会消失的问题，可以killall nagios 再重新启动nagios！

监控远程主机的系统信息
被监控主机
安装nrpe的server端
tar fvxz nrpe*.tar.gz
./configure --prefix=/usr/local/nagios
useradd nagios
make 

make install-daemon

make install-daemon-config

make install-xinetd

安装插件2
make install （这步不是必须的！）
把插件拷贝给监控主机nagios
scp /usr/local/nagios/libexec/check_nrpe   root@监控主机的ip:/usr/local/nagios/libexec

在被监控主机开启nrpe服务
vim /etc/xinetd.d/nrpe
# default: on
# description: NRPE (Nagios Remote Plugin Executor)
service nrpe

{
        flags           = REUSE
        socket_type     = stream    
        port            = 5666    
        wait            = no
        user            = nagios
        group           = nagios
        server          = /usr/local/nagios/bin/nrpe
        server_args     = -c /usr/local/nagios/etc/nrpe.cfg --inetd
        log_on_failure  += USERID
        disable         = no
        only_from       = 192.168.18.254  ＃监控主机的ip，保证他可以连接进来！
}

vim /etc/services 
nrpe 5666/tcp

service xinetd restart

[root@server1 objects]# /usr/local/nagios/libexec/check_nrpe -H 192.168.18.188
NRPE v2.12

#注意关闭防火墙！

在被监控主机安装插件

vim nrpe.cfg
command[check_users]=/usr/local/nagios/libexec/check_users -w 5 -c 10
command[check_u]=/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_hda1]=/usr/local/nagios/libexec/check_disk -w 20% -c 10% -p /dev/hda1
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 

通过以上字段来定义命令，以及接收命令后执行的插件

如果想不明白

定义服务，来检测一下
define host {
        host_name       zcg
        alias           nrpe-server
        address         192.168.18.188
        check_command   check-host-alive
        notification_options    d,u,r
        check_interval  1
        max_check_attempts      2
        contact_groups  admins
        notification_interval   10
        notification_period     24x7
}

define service {
        host_name       zcg
        service_description     nrpe
        check_period    24x7
        normal_check_interval   2
        retry_check_interval    1
        max_check_attempts      5
        notification_period     24x7
        notification_options    w,u,c,r
        check_command   check_nrpe!check_users
＃这里定义的check_nrpe需要在command.cfg里面定义
}
别忘了，先定义好zcg这台主机！！

定义命令
define command {
        command_name    check_nrpe
        command_line    /usr/local/nagios/libexec/check_nrpe -H $HOSTADDRESS$ -c $ARG1$
}

重启nagios服务！