nagios部署+短信和郵件報警


操作系統 CentOS6.6 

服務端:10.0.0.20

客戶端:10.0.0.50

一.nagios的服務端安裝部署

1.nagios安裝

[root@manager src]# rz
rz waiting to receive.
Starting zmodem transfer. Press Ctrl+C to cancel.
Transferring nagios-cn-3.2.3.tar.bz2...
100% 9412 KB 9412 KB/sec 00:00:01 0 Errors

tar xf nagios-cn-3.2.3.tar.bz2 
cd nagios-cn-3.2.3
useradd -m -s /bin/bash nagios
groupadd nagcmd

  make install; make install-init;make install-commandmode;make install-config;make install-webconf
  ll /usr/local/nagios/  #出現以下文件代表成功

drwxrwxr-x 2 nagios nagios 4096 Mar 12 08:08 bin
drwxrwxr-x 3 nagios nagios 4096 Mar 12 08:08 etc
drwxrwxr-x 2 nagios nagios 4096 Mar 12 08:08 libexec
drwxrwxr-x 2 nagios nagios 4096 Mar 12 08:08 sbin
drwxrwxr-x 9 nagios nagios 4096 Mar 12 08:08 share
drwxrwxr-x 6 nagios nagios 4096 Mar 12 08:08 var

  chmod o+rwx /usr/local/nagios/var/rw

 2.nagios plugin 插件安裝

[root@manager src]# rz
rz waiting to receive.
Starting zmodem transfer.  Press Ctrl+C to cancel.
Transferring nagios-plugins-1.4.13.tar.gz...
  100%    2226 KB    2226 KB/sec    00:00:01       0 Errors 
[root@manager src]# tar xf nagios-plugins-1.4.13.tar.gz  
[root@manager src]# cd nagios-plugins-1.4.13

#安裝依賴

yum install make apr* autoconf automake curl curl-devel gcc gcc-c++ zlib-devel \
openssl openssl-devel pcre-devel gd gd-devel kernel keyutils patch perl perl-devel \
kernel keyutils kernel-headers compat* mpfr cpp glibc libgomp libstdc++-devel ppl \
cloog-ppl keyutils-libs-devel libcom_err-devel libsepol-devel libselinux-devel \
krb5-devel zlib-devel libXpm* freetype libjpeg* libpng* php-common php-gd ncurses* libtool* libxml2 libxml2-devel patch -y
./configure --prefix=/usr/local/nagios --with-mysql=/usr/local/mysql/
make
make install

  file /usr/lib64/libxcb-reply.so.1.0.0 from install of compat-xcb-util-0.4.0-2.2.el6.x86_64 conflicts with file from package xcb-util-0.3.6-5.el6.x86_64

有沖突卸載掉這個有沖突的

yum remove -y xcb-util-0.3.6-5.el6.x86_64

3.nrpe安裝

[root@manager src]# rz
rz waiting to receive.
Starting zmodem transfer.  Press Ctrl+C to cancel.
Transferring nrpe-2.12.tar.gz...
  100%     396 KB     396 KB/sec    00:00:01       0 Errors 
tar xf nrpe-2.12.tar.gz 
cd nrpe-2.12 ./configure make ./configure make all make install-plugin make install-daemon make install-daemon-config \cp src/check_nrpe /usr/local/nagios/libexec/ /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d echo '/usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d' >> /etc/rc.local
要重啟nrpe進行就先殺掉進行,然后重啟
kill `ps aux |grep nrpe |grep -v grep |awk '{print $2}'`
/usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
本機測試下:
/usr/local/nagios/libexec/check_nrpe -H localhost -c check_users

加入系統服務

加入系統服務並設為開機自動
chkconfig --add nagios
chkconfig nagios on
chown nagios.nagios /usr/local/nagios/var/rw
# 測試配置文件是否正確
/usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg

添加別名命令,方便測試配置文件

vi ~/.bashrc
在里面用alias 來自定義一個命令來代替,這里我用check
alias check='/usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg'
source ~/.bashrc
此時可以用check命令來檢測配置文件了

安裝 nginx  的FCGI模塊

  cd /usr/local/src/
  rz
  tar xf FCGI-0.74.tar.gz 
  cd FCGI-0.74
  perl Makefile.PL 
  make && make install

安裝IO  和IO-ALL模塊

[root@manager src]# tar xf IO-1.25.tar.gz 
[root@manager src]# cd IO-1.25
[root@manager IO-1.25]# perl Makefile.PL
[root@manager IO-1.25]# make && make install

[root@manager src]# tar xf IO-All-0.81.tar.gz
[root@manager src]# cd IO-All-0.81
[root@manager IO-All-0.81]# perl Makefile.PL

[root@manager IO-All-0.81]# make && make install

上傳fastcgi 的啟動腳本。

[root@manager src]# rz
rz waiting to receive.
Starting zmodem transfer. Press Ctrl+C to cancel.
Transferring perl-fcgi.zip...
100% 2 KB 2 KB/sec 00:00:01 0 Errors

[root@manager src]# unzip perl-fcgi.zip
Archive: perl-fcgi.zip
inflating: perl-fcgi.pl
[root@manager src]# cp perl-fcgi.pl /usr/local/nginx/

[root@manager IO-All-0.81]# chmod 755 /usr/local/nginx/perl-fcgi.pl

[root@manager nginx]# ./start_perl_cgi.sh start
start perl-fcgi done

[root@manager ~]# cat /usr/local/nginx/start_perl_cgi.sh
#!/bin/bash
#set -x
dir=/usr/local/nginx/
stop ()
{
#pkill  -f  $dir/perl-fcgi.pl
kill $(cat $dir/logs/perl-fcgi.pid)
rm $dir/logs/perl-fcgi.pid 2>/dev/null
rm $dir/logs/perl-fcgi.sock 2>/dev/null
echo "stop perl-fcgi done"
}
start ()
{
rm $dir/now_start_perl_fcgi.sh 2>/dev/null
chown nobody.root $dir/logs
echo "$dir/perl-fcgi.pl -l $dir/logs/perl-fcgi.log -pid $dir/logs/perl-fcgi.pid -S $dir/logs/perl-fcgi.sock" >>$dir/now_start_perl_fcgi.sh
chown nobody.nobody $dir/now_start_perl_fcgi.sh
chmod u+x $dir/now_start_perl_fcgi.sh
sudo -u nobody $dir/now_start_perl_fcgi.sh
echo "start perl-fcgi done"
}
case $1 in
stop)
stop
;;
start)
start
;;
restart)
stop
start
;;
esac

啟動fastcgi

[root@manager nginx]# ./start_perl_cgi.sh start
start perl-fcgi done

# 重復啟動會報這樣的錯 使用行參restart 或者stop 以后再start 就不會報這樣的錯。

 
         

[root@manager nginx]# ./start_perl_cgi.sh start

 
         

ERROR PID file /usr/local/nginx/logs/perl-fcgi.pid already exists

 
         

start perl-fcgi done

 

start_perl_cgi.sh文件中的nobody全部用nagios替換,nginx 目錄上的用戶

[root@manager ~]# sed -i 's#nobody#nagios#g' /usr/local/nginx/start_perl_cgi.sh 
[root@manager ~]# ps -ef |grep nagios
nagios     1695      1  0 05:52 ?        00:00:00 /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
nagios     1707      1  0 05:52 ?        00:00:00 /usr/local/nagios/bin/nagios -d /usr/local/nagios/etc/nagios.cfg
# 取消用戶認證(方便調試)
vi /usr/local/nagios/etc/cgi.cfg
找到use_authentication=1並把值改為0
#修改聯系人郵箱,修改為用於報警接收的郵件地址
vi /usr/local/nagios/etc/objects/contacts.cfg

email 13311802282@163.com (默認是nagios@localhost換成自己的郵箱)

產生這樣一個socket文件表示啟動成功了

[root@manager nginx]#  /etc/init.d/nagios start              
Starting nagios: done.

二,nagios的被監控端安裝部署

1.安裝nagios插件

[root@master ~]# groupadd nagios
[root@master ~]# useradd nagios -M -s /sbin/nologin -g nagios
[root@master ~]# rz
rz waiting to receive.
Starting zmodem transfer.  Press Ctrl+C to cancel.
Transferring nagios-plugins-1.4.13.tar.gz...
  100%    2226 KB    2226 KB/sec    00:00:01       0 Errors  
[root@master nagios-plugins-1.4.13]# ./configure --prefix=/usr/local/nagios --with-nagios-user=nagios --with-nagios-group=nagios --with-mysql=/usr/local/mysql && make && make install

2.安裝nrpe

[root@master nagios-plugins-1.4.13]# cd
[root@master ~]# rz
rz waiting to receive.
Starting zmodem transfer.  Press Ctrl+C to cancel.
Transferring nrpe-2.12.tar.gz...
  100%     396 KB     396 KB/sec    00:00:01       0 Errors  
[root@master nrpe-2.12]# ./configure && make all && make install-plugin && make install-daemon && make install-daemon-config

[root@master nrpe-2.12]# echo $? (0未報錯)
0

# 啟動nrpe 

[root@master nrpe-2.12]# /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
[root@master nrpe-2.12]# ps -ef |grep nrp
nagios 23592 1 0 09:28 ? 00:00:00 /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d

# 設置開機啟動進程

[root@master nrpe-2.12]# echo '/usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d' >> /etc/rc.local

 

監控服務端本機:自己監控自己不需要配置nrpe,服務端的nrpe只用於獲取客戶端的nrpe傳送過來的數據,在這里因為中文版的nagios已經默認有些配置,等會兒修改下直接用了

監控客戶端:監控的服務有:mysqlnginxmemoryip連接數、僵死的進程、磁盤空間、磁盤IO、登錄用戶數、進程總數、cpu負載、PINGSSH

有兩個紅色的不知道啥吊情況。

 

 3.操作數據庫mysql

mysql> create database nagios;
Query OK, 1 row affected (0.07 sec)

mysql> grant select on nagios.* to nagios@'%' identified by '123';
Query OK, 0 rows affected (0.05 sec)

mysql> flush privileges;
Query OK, 0 rows affected (0.00 sec)

mysql> select user,password,host from mysql.user;
+--------+-------------------------------------------+-----------+
| user   | password                                  | host      |
+--------+-------------------------------------------+-----------+
| root   | *23AE809DDACAF96AF0FD78ED04B6A265E05AA257 | localhost |
| root   | *23AE809DDACAF96AF0FD78ED04B6A265E05AA257 | master    |
| root   | *23AE809DDACAF96AF0FD78ED04B6A265E05AA257 | 127.0.0.1 |
| root   | *23AE809DDACAF96AF0FD78ED04B6A265E05AA257 | ::1       |
|        |                                           | localhost |
|        |                                           | master    |
| repl   | *23AE809DDACAF96AF0FD78ED04B6A265E05AA257 | 10.0.0.%  |
| root   | *23AE809DDACAF96AF0FD78ED04B6A265E05AA257 | 10.0.0.%  |
| nagios | *23AE809DDACAF96AF0FD78ED04B6A265E05AA257 | %         |
+--------+-------------------------------------------+-----------+
9 rows in set (0.03 sec)
# 添加mysql庫到系統搜索庫
vim /etc/ld.so.conf
/usr/local/mysql/lib
ldconfig
# 要監控磁盤io,還得安裝sysstat這個工具包
yum install sysstat -y
# 配置客戶端上面的nrpe
vim /usr/local/nagios/etc/nrpe.cfg

allowed_hosts=127.0.0.1,10.0.0.20; #允許server主機獲取信息
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_hda1]=/usr/local/nagios/libexec/check_disk -w 20% -c 10% -p /dev/hda1 (由於我的磁盤時scsii的硬盤所以不是hd是sd)
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 

#----------------------------------下面是后加的----------------------------------------------------
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_swap]=/usr/local/nagios/libexec/check_swap -w 20% -c 10%
command[check_iostat]=/usr/local/nagios/libexec/check_iostat.sh -d sda -w 6 -c 10
command[check_mysql]=/usr/local/nagios/libexec/check_mysql -H 192.168.0.22 -u nagios -p 123456 -d nagios
command[check_nginx]=/usr/local/nagios/libexec/check_nginx.sh -u 192.168.0.22 -p /status -w 4000 -c 5000
command[check_mem]=/usr/local/nagios/libexec/check_memory.pl -f -w 20 -c 10
command[check_ip_conn]=/usr/local/nagios/libexec/ip_conn.sh 200 250
command[check_ssh]=/usr/local/nagios/libexec/check_tcp -p 22 -w 1.0 -c 10.0

配置完重新啟動進程

[root@master ~]# kill `ps aux |grep nrpe |grep -v grep |awk '{print $2}'`
[root@master ~]# /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
[root@master ~]# ps -ef |grep nrpe
nagios     1598      1  0 10:04 ?        00:00:00 /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
root       1600   1491  0 10:04 pts/0    00:00:00 grep nrpe

服務端配置:

 

[root@manager ~]# cp /usr/local/nagios/etc/objects/localhost.cfg /usr/local/nagios/etc/objects/localhost.cfg.bak
[root@manager ~]# > /usr/local/nagios/etc/objects/localhost.cfg
[root@manager ~]# vim /usr/local/nagios/etc/objects/localhost.cfg
#這是自己監控自己的配置文件
define host{ use linux
-server host_name localhost alias localhost address 127.0.0.1 icon_image server.gif statusmap_image server.gd2 2d_coords 500,200 3d_coords 500,200,100 } define hostgroup{ hostgroup_name linux-servers ; The name of the hostgroup alias Linux Servers ; Long name of the group members * ; Comma separated list of hosts that belong to this group } define servicegroup{ servicegroup_name 全部聯通性檢查 alias 聯通性檢查 members localhost,PING,nagios-client,PING } define service{ use local-service ; Name of service template to use host_name * service_description PING check_command check_ping!100.0,20%!500.0,60% } define service{ use local-service ; Name of service template to use host_name localhost service_description 根分區 check_command check_local_disk!20%!10%!/ } define service{ use local-service ; Name of service template to use host_name localhost service_description 登錄用戶數 check_command check_local_users!20!50 } define service{ use local-service ; Name of service template to use host_name localhost service_description 進程總數 check_command check_local_procs!250!400!RSZDT } define service{ use local-service ; Name of service template to use host_name localhost service_description 系統負荷 check_command check_local_load!5.0,4.0,3.0!10.0,6.0,4.0 } define service{ use local-service ; Name of service template to use host_name localhost service_description 交換空間利用率 check_command check_local_swap!20!10 } define service{ use local-service ; Name of service template to use host_name localhost service_description SSH check_command check_tcp!22!1.0!10.0 notifications_enabled 0 }
服務器端監控被監控主機的配置文件:
 
cp /usr/local/nagios/etc/objects/localhost.cfg /usr/local/nagios/etc/objects/nagios-client.cfg
vim /usr/local/nagios/etc/objects/nagios-client.cfg   修改完成后的配置如下
define host{
        use                     linux-server
        host_name               nagios-client
        alias                   nagios-client
        address                 10.0.0.50
        icon_image              server.gif
        statusmap_image         server.gd2
        2d_coords       500,200
        3d_coords       500,200,100
        }
define service{
        use                             local-service         ; Name of service template to use
        host_name                       *
        service_description             PING
        check_command           check_ping!100.0,20%!500.0,60%
        }
define service{
        use                             local-service         ; Name of service template to use
        host_name                       nagios-client
        service_description             boot分區
        check_command           check_nrpe!check_sda1
        }
define service{
        use                             local-service         ; Name of service template to use
        host_name                       nagios-client
        service_description             根分區
        check_command           check_nrpe!check_sda2
        }
define service{
        use                             local-service         ; Name of service template to use
        host_name                       nagios-client
        service_description             登錄用戶數
        check_command           check_nrpe!check_users
        }
define service{
        use                             local-service         ; Name of service template to use
        host_name                       nagios-client
        service_description             進總程數
        check_command           check_nrpe!check_total_procs
        }
define service{
        use                             local-service         ; Name of service template to use
        host_name                       nagios-client
        service_description             CPU平均負載
        check_command           check_nrpe!check_load
        }
define service{
        use                             local-service         ; Name of service template to use
        host_name                       nagios-client
        service_description             虛擬內存
        check_command           check_nrpe!check_swap
        }
define service{
        use                             local-service         ; Name of service template to use
        host_name                       nagios-client
        service_description             SSH
        check_command           check_nrpe!check_ssh
        notifications_enabled       0
        }
define service{
        use                             local-service         ; Name of service template to use
        host_name                       nagios-client
        service_description             僵死進程數
        check_command           check_nrpe!check_zombie_procs
        }
define service{
        use                             local-service         ; Name of service template to use
        host_name                       nagios-client
        service_description             iostat
        check_command           check_nrpe!check_iostat
        }
define service{
        use                             local-service         ; Name of service template to use
        host_name                       nagios-client
        service_description             mysql
        check_command           check_nrpe!check_mysql
        }
define service{
        use                             local-service         ; Name of service template to use
        host_name                       nagios-client
        service_description             nginx
        check_command           check_nrpe!check_nginx
        }
define service{
        use                             local-service         ; Name of service template to use
        host_name                       nagios-client
        service_description             memory
        check_command           check_nrpe!check_mem
        }
define service{
        use                             local-service         ; Name of service template to use
        host_name                       nagios-client
        service_description             IP連接數
        check_command           check_nrpe!check_ip_conn
        }

出現問題會自動發送郵件到你設置的郵箱

這個部署的不太成功!網頁沒有顯示。。。。明天重新再來一遍,再好好理解理解,這些安裝包都特么好難找,這下我應該算是收集全了,在部署應該很快。


免責聲明!

本站轉載的文章為個人學習借鑒使用,本站對版權不負任何法律責任。如果侵犯了您的隱私權益,請聯系本站郵箱yoyou2525@163.com刪除。



 
粵ICP備18138465號   © 2018-2025 CODEPRJ.COM