一键搭建nagios监控系统之二 脚本解释篇

由于发布文章字数有限制。脚本解释将在这一篇文章里讲解。如下：

#! /bin/bash
##  QQ:410018348

##################  nagios server configure ########################

installserver() {   #定义安装nagios函数
read -p " Please input the alarm  email address : " email   #报警邮箱
read -p " Please input the login nagios user: " loginuser   #网页登录时帐户
read -p " Please input the login nagios pass: " loginpass   #网页登录时的密码

echo  "###############  Install nagios server #################"
yum -y install httpd php php-gd php-xml php-mbstring php-ldap php-pear php-xmlrpc httpd-manual mod_ssl mod_perl  zlib libpng  freetype  libart_lgpl libart_lgpl-devel libxml*   pango*
#安装 apache php 及其他

wget http://prdownloads.sourceforge.net/sourceforge/nagios/nagios-3.2.3.tar.gz useradd nagios -s /sbin/nologin
tar -xvf  nagios-3.2.3.tar.gz
cd nagios-3.2.3
./configure --prefix=/usr/local/nagios
make all
make install
make install-init
make install-config
make install-commandmode
make install-webconf
cd  ..      #安装nagios软件

wget http://prdownloads.sourceforge.net/sourceforge/nagiosplug/nagios-plugins-1.4.15.tar.gz tar -xvf  nagios-plugins-1.4.15.tar.gz
cd nagios-plugins-1.4.15
./configure
make
make install
cd ..      #安装nagios监控插件

wget http://nchc.dl.sourceforge.net/sourceforge/nagios/nrpe-2.12.tar.gz tar -xvf  nrpe-2.12.tar.gz
cd nrpe-2.12
./configure
make all
make install
make install-plugin
make install-daemon
make install-daemon-config
cd ..      #安装nrpe插件

wget http://oss.oetiker.ch/rrdtool/pub/rrdtool-1.4.7.tar.gz tar -xvf  rrdtool-1.4.7.tar.gz
cd rrdtool-1.4.7
./configure --prefix=/usr/local/rrdtool/ &&make &&make install
cd ..     #安装绘图工具

wget http://pkgs.fedoraproject.org/repo/pkgs/pnp4nagios/pnp-0.4.12.tar.gz/eb833a4769a5b58aad0ac53cae3e3e9f/pnp-0.4.12.tar.gz tar -xvf  pnp-0.4.12.tar.gz
cd pnp-0.4.12
./configure --with-nagios-user=nagios --with-nagios-group-nagios --with-rrdtool=/usr/local/rrdtool/bin/rrdtool
make
make all
make install
make install-config
make install-init
cd ..       #安装绘图工具
## 以上为安装nagios服务的一些软件。

wget http://218.6.16.170/somenagios.tar      #这里的我个人找的一些 cpu ,内存，及mysql的插件。 打包在这。
tar -xvf somenagios.tar -C /usr/local/nagios/libexec/

echo  "################install nagios server  completed#############"   #nagios安装完成。

echo "################# configure nagios server start###############"   #下面是常规的一些配置。
htpasswd -bc /usr/local/nagios/etc/htpasswd.users  $loginuser $loginpass   #创建用户密码，就是上面要求输入的内容。

# cgi.cfg configure#
sed -i "s#use_authentication=1#use_authentication=0#g" /usr/local/nagios/etc/cgi.cfg   #更改use_authentication参数

#nagios.cfg configure#
sed -i '35i\cfg_file=/usr/local/nagios/etc/objects/hosts.cfg' /usr/local/nagios/etc/nagios.cfg   #在nagios.cfg里添加 host.cfg
sed -i '35i\cfg_file=/usr/local/nagios/etc/objects/services.cfg' /usr/local/nagios/etc/nagios.cfg  #在nagios.cfg里添加 services.cfg
sed -i '35i\cfg_file=/usr/local/nagios/etc/objects/hostgroup.cfg' /usr/local/nagios/etc/nagios.cfg  #在nagios.cfg里添加 hostgroup.cfg
sed -i "s#cfg_file=/usr/local/nagios/etc/objects/localhost.cfg#\#cfg_file=/usr/local/nagios/etc/objects/localhost.cfg#g"  /usr/local/nagios/etc/nagios.cfg  #禁用监控本地的配置文件
sed -i "s#process_performance_data=0#process_performance_data=1#g" /usr/local/nagios/etc/nagios.cfg  #更改 process_performance_data 为1
sed -i "s/#host_perfdata_command=process-host-perfdata/host_perfdata_command=process-host-perfdata/g" /usr/local/nagios/etc/nagios.cfg #开启 host_perfdata_commandsed -i "s/#service_perfdata_command=process-service-perfdata/service_perfdata_command=process-service-perfdata/g" /usr/local/nagios/etc/nagios.cfg   #开启service_perfdata_command

#command.cfg configure#

line1=`sed -n '/process-host-perfdata$/=' /usr/local/nagios/etc/objects/commands.cfg`  #查找commands.cfg里 process-host-perfdata的行
line2=`sed -n '/process-service-perfdata$/=' /usr/local/nagios/etc/objects/commands.cfg`  #同上

sed -i "$(($line1+1))"d /usr/local/nagios/etc/objects/commands.cfg  #删除上面找的行的下一行
sed -i "$(($line1+1))i\        command_line /usr/local/nagios/libexec/process_perfdata.pl"  /usr/local/nagios/etc/objects/commands.cfg  #插入新的命令
sed -i "$(($line2+1))"d /usr/local/nagios/etc/objects/commands.cfg  #删除上面找的行的下一行
sed -i "$(($line2+1))i\        command_line /usr/local/nagios/libexec/process_perfdata.pl"  /usr/local/nagios/etc/objects/commands.cfg  #插入新的命令

echo '
define command{
command_name    check_nrpe
command_line    $USER1$/check_nrpe -H $HOSTADDRESS$ -c $ARG1$ -t 30
}

define command {
command_name  check_mysql
command_line    $USER1$/check_mysql -H $HOSTADDRESS$ -unagdb -pnagdb -d nagdb

}
'>>/usr/local/nagios/etc/objects/commands.cfg  # 在commands.cfg里添加两条命令。 nrpe及监控mysql

#templates.cfg configure#

echo '
define host {
name       hosts-pnp
register   0
action_url /nagios/pnp/index.php?host=$HOSTNAME$
process_perf_data               1

}
define service {
name       services-pnp
register   0
action_url /nagios/pnp/index.php?host=$HOSTNAME$&srv=$SERVICEDESC$
process_perf_data               1

}'>>/usr/local/nagios/etc/objects/templates.cfg
# 上面是在templates.cfg里添加性能分析图表的功能

#pnp configure#

cp  /usr/local/nagios/etc/pnp/process_perfdata.cfg-sample  /usr/local/nagios/etc/pnp/process_perfdata.cfg
cp  /usr/local/nagios/etc/pnp/npcd.cfg-sample  /usr/local/nagios/etc/pnp/npcd.cfg
cp  /usr/local/nagios/etc/pnp/rra.cfg-sample  /usr/local/nagios/etc/pnp/rra.cfg
chown -R nagios:nagios  /usr/local/nagios/etc/pnp/*
#上面把pnp的模板文件改成真的配置文件 并授权
sed -i 's#LOG_LEVEL = 0#LOG_LEVEL = 2#g'  /usr/local/nagios/etc/pnp/process_perfdata.cfg
#更改 LOG_LEVEL 为2

#contacts.cfg configure#
sed -i  "s#nagios@localhost#$email#g" /usr/local/nagios/etc/objects/contacts.cfg
clear
#更改contacts.cfg里面的联系人为所输入的联系人

echo "################### nagios server install and  configure completed,plase add hosts and services  then start it ##################"

} #以上nagios安装及配置完成。

restartnagios(){   # 这里是定义nagios，nrpe,及apache重启的函数
echo "stopping ......"
service nagios stop   #nagios stop
killall -9 nrpe   #nrpe stop
service httpd stop   #apache stop
echo "starting ......"
service nagios start   #nagios start
/usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d  # nrpe start
service httpd start   #apache start
}

addservices(){   #这里定义了在nagios端添加客户机的函数

read -p "please input the alias name : "  host   #输入添加机器别名
read -p "please input the clint ip : "  ip   #输入添加机器的ip
echo "define host {
host_name                 $host
use            linux-server,hosts-pnp
alias                      nagios server
address                   $ip
contact_groups             admins
check_command              check-host-alive
max_check_attempts         5
notification_interval      10
notification_period        24x7
notification_options        d,u,r
}" >> /usr/local/nagios/etc/objects/hosts.cfg   #在hosts.cfg里添加一个主机 (参数的意思可以在网上看下)

echo "define hostgroup {
hostgroup_name myserver
alias          myserver
members        $host
}" >>/usr/local/nagios/etc/objects/hostgroup.cfg   #在hostgroup.cfg里添中一个主机组，$host就是添加的别名

是添加监控的具体服务。
echo "define service {
host_name     $host
use local-service,services-pnp
service_description   CPU
check_period          24x7
max_check_attempts    4
normal_check_interval 1
retry_check_interval 1
contact_groups        admins
notification_interval   10
notification_period     24x7
notification_options    w,u,c,r
check_command    check_nrpe!check_cpu
}   #监控客户机CPU
define service {
host_name     $host
use local-service,services-pnp
service_description   CPU_load
check_period          24x7
max_check_attempts    4
normal_check_interval 1
retry_check_interval 1
contact_groups        admins
notification_interval   10
notification_period     24x7
notification_options    w,u,c,r
check_command    check_nrpe!check_load
}  #监控客户机负载
define service {
host_name     $host
use local-service,services-pnp
service_description   HTTP
check_period          24x7
max_check_attempts    4
normal_check_interval 1
retry_check_interval 1
contact_groups        admins
notification_interval   10
notification_period     24x7
notification_options    w,u,c,r
check_command    check_nrpe!check_http
}  #监控客户机http服务
define service {
host_name     $host
use local-service,services-pnp
service_description   MEMORY
check_period          24x7
max_check_attempts    4
normal_check_interval 1
retry_check_interval 1
contact_groups        admins
notification_interval   10
notification_period     24x7
notification_options    w,u,c,r
check_command    check_nrpe!check_mem
}  #监控客户机的内存使用情况
define service {
host_name     $host
service_description   connect-count
check_period          24x7
max_check_attempts    4
normal_check_interval 1
retry_check_interval 1
contact_groups        admins
notification_interval   10
notification_period     24x7
notification_options    w,u,c,r
check_command    check_nrpe!check_ips
}  #监控客户机的连接情况
define service {
host_name     $host
service_description   DISK
check_period          24x7
max_check_attempts    4
normal_check_interval 1
retry_check_interval 1
contact_groups        admins
notification_interval   10
notification_period     24x7
notification_options    w,u,c,r
check_command    check_nrpe!check_disk
}  #监控客户机的硬盘分区使用情况
define service {
host_name     $host
service_description   mysql
check_period          24x7
max_check_attempts    4
normal_check_interval 1
retry_check_interval 1
contact_groups        admins
notification_interval   10
notification_period     24x7
notification_options    w,u,c,r
check_command   check_mysql
}  #监控客户机的mysql监控状态
define service {
host_name     $host
service_description   PING
use local-service,services-pnp
check_period          24x7
max_check_attempts    4
normal_check_interval 1
retry_check_interval 1
contact_groups        admins
notification_interval   10
notification_period     24x7
notification_options    w,u,c,r
check_command    check_ping!100.0,20%!500.0,60%
}  #监控客户机的ping是否正常
define service {
host_name     $host
use local-service,services-pnp
service_description  FTP
check_period          24x7
max_check_attempts    4
normal_check_interval 60
retry_check_interval 10
contact_groups        admins
notification_interval   10
notification_period     24x7
notification_options    w,u,c,r
check_command    check_nrpe!check_ftp
}  #监控客户机的ftp服务

" >>/usr/local/nagios/etc/objects/services.cfg   #把上面内容添加到services.cfg里面 (参数的意思可以在网上看下)
echo "###############  Add services completed ########"
}
######################### nagios  configure  completed ########################
#以上为nagios服务端配置。

####################### client  server configure ########################
#以下为被监控端配置
clientnagios() {   #定义客户机的安装配置

### install soft###
read -p "Please input the nagios server ip : " nagiosip   #输入naiogs服务端ip

read -p "Please input the mysql password : " mysqlpass   #输入本机的mysql密码。

useradd nagios
yum install zlib libpng  freetype  libart_lgpl libart_lgpl-devel libxml*   pango*
#安装所需要的包

wget http://prdownloads.sourceforge.net/sourceforge/nagiosplug/nagios-plugins-1.4.15.tar.gz tar -xvf  nagios-plugins-1.4.15.tar.gz
cd nagios-plugins-1.4.15
./configure
make
make install
cd ..

wget http://nchc.dl.sourceforge.net/sourceforge/nagios/nrpe-2.12.tar.gz tar -xvf  nrpe-2.12.tar.gz
cd nrpe-2.12
./configure
make all
make install
make install-plugin
make install-daemon
make install-daemon-config
cd ..
#以上为安装被监控机所需要的软件
wget http://218.6.16.170/somenagios.tar tar -xvf somenagios.tar -C /usr/local/nagios/libexec/  #这里是个人找的几个监控插件
### install completed ###
### configure ####

rm /usr/local/nagios/etc/nrpe.cfg   #删除安装的nrpe.cfg配置文件

cat >>/usr/local/nagios/etc/nrpe.cfg<<EOF  #添加以下内容到nrpe.cfg配置文件里。主要就是一些监控本机的命令，供nagios服务端调用
log_facility=daemon
pid_file=/var/run/nrpe.pid
server_port=5666
nrpe_user=nagios
nrpe_group=nagios
allowed_hosts=$nagiosip
dont_blame_nrpe=1
debug=1
command_timeout=30
connection_timeout=300
command[check_http]=/usr/local/nagios/libexec/check_http -H  -u 127.0.0.1 /index.php -t 60
command[check_disk]=/usr/local/nagios/libexec/check_disk -w 15% -c 10% -A -i '/dev/shm'
command[check_cpu]=/usr/local/nagios/libexec/check_cpu.sh
command[check_mem]=/usr/local/nagios/libexec/check_mem.sh
command[check_ips]=/usr/local/nagios/libexec/ip_conn.sh  400 600
command[check_load]=/usr/local/nagios/libexec/check_load -w 14,12,10 -c 18,15,12
command[check_ftp]=/usr/local/nagios/libexec/check_ftp 127.0.0.1 -w 10 -c 60
EOF

mysql -uroot -p"$mysqlpass" <<EOF
create database nagdb;
grant all on nagdb.* to nagdb@"$nagiosip" identified by 'nagdb';
flush privileges;
\q
EOF #这里是创建一个只能是nagios服务端访问的库。监控mysql状态是需有的。

killall -9 nrpe
/usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d   #重启被监控机的nrpe服务

############ configure completed ############
}
#客户机配置完成

real=`grep -l '\^H' /root/.bash_profile`
if [ $? -eq 1 ];then
echo  'stty erase ^H' >> /root/.bash_profile
source /root/.bash_profile   #这几行主要就是让在使用read键时能使用回删键。写错了，回删了，重启写。不用这段的话，回删键会变成乱码。
fi
echo -e '\033[0;33;1m #################nagios################## \033[0m' #让echo能弄点颜色出来好看点。。。
echo "nagios server install and configure or addserver          please input : 1"
echo "  clint server install or configure               please input : 2"
echo "      exit                            please input : 3"
echo -e '\033[0;33;1m ######################################### \033[0m'

read -p "please chose : " frist   #定义输入的值

if [ $frist -eq 1 ];then   #值等于1时执行nagios服务器配置

echo -e '\033[0;33;1m #################nagios################## \033[0m'
echo "nagios server install and configue                    please input : 1"
echo "  Add server and services                     please input : 2"
echo "      exit                            please input : 3"
echo -e '\033[0;33;1m ######################################### \033[0m'
read -p "please chose : " nagiosfrist  #定义nagiosfrist输入的值
if [ $nagiosfrist -eq 1 ];then   #当nagiosfrist等于1时，执行下面 安装，添加服务 入重启服务的函数
installserver
addservices
restartnagios
elif [ $nagiosfrist -eq 2 ];then   #当nagiosfrist等于2时，执行添加服务，重启服务函数
addservices
restartnagios
elif [  $nagiosfrist -eq 3 ];then  #nagiosfrist等于3，就退出
clear
exit
else
echo "plase chose [1|2|3]"   #都不等于的话，打印这个
fi

elif [ $frist -eq 2 ];then   # 当frist等于2时 执行被监控端的函数
clientnagios

elif [ $frist -eq 3 ];then  #等于3时退出
clear
exit
else
echo "plase chose [1|2|3]"   #都不等的话，就打印这个
fi

脚本解析完成。本人也做了一系列的测试。看脚本是否能正常运行。答案是可以的。在测试当中，本人也装一些图抓了下来，在下篇博客 《一键搭建nagios监控系统之三 测试篇 》中我们来看下。

QQ:410018348