1.更新yum源
mv /etc/yum.repos.d/CentOS-Base.repo /etc/yum.repos .d/CentOS-Base.repo.backup wget -O /etc/yum.repos.d/CentOS-Base.repo http://mirrors.aliyun.com/repo/Centos-6.repo
2.调整字符集
echo 'export LC_ALL=C'>>/etc/profile source /etc/profile
3.关闭iptables与selinux
4.更新系统时间
/usr/sbin/ntpdate pool.ntp.org
然后放入定时任务
5.安装gcc(可以省略）
yum install gcc glibc glibc-common mysql* -y
6.添加用户
/usr/sbin/useradd -m nagios -s /sbin/nologin
7.安装插件
yum -y install perl-devel tar xf nagios-plugins-1.4.16.tar.gz cd nagios-plugins-1.4.16 ./configure --prefix=/usr/local/nagios --enable-perl-modules --enable-redhat-pthread-workaround make && make install cd ../ ls /usr/local/nagios/libexec/|wc -l
8.安装nrpe
tar xf nrpe-2.12.tar.gz cd nrpe-2.12 ./configure make all make install-plugin make install-daemon make install-daemon-config cd ../
9.安装soft与iostat
tar xf Params-Validate-0.91.tar.gz cd Params-Validate-0.91 perl Makefile.PL make make install cd ../
tar xf Class-Accessor-0.31.tar.gz cd Class-Accessor-0.31 perl Makefile.PL make make install cd ../
tar xf Config-Tiny-2.12.tar.gz cd Config-Tiny-2.12 perl Makefile.PL make make install cd ../
tar xf Math-Calc-Units-1.07.tar.gz cd Math-Calc-Units-1.07 perl Makefile.PL make make install cd ../
tar xf Regexp-Common-2010010201.tar.gz cd Regexp-Common-2010010201 perl Makefile.PL make make install cd ../
tar xf Nagios-Plugin-0.34.tar.gz cd Nagios-Plugin-0.34 perl Makefile.PL make make install cd ../
yum install sysstat -y cp check_memory.pl /usr/local/nagios/libexec cp check_iostat /usr/local/nagios/libexec chmod 755 /usr/local/nagios/libexec/check_memory.pl chmod 755 /usr/local/nagios/libexec/check_iostat dos2unix /usr/local/nagios/libexec/check_memory.pl dos2unix /usr/local/nagios/libexec/check_iostat
10.修改nrpe.cfg
[root@Nagios tools]# vim /usr/local/nagios/etc/nrpe.cfg +79
修改79行：allowed_hosts=127.0.0.1
为：allowed_hosts=127.0.0.1,192.168.0.150 #允许哪个服务端(192.168.0.150)对它发送命令
删除199行到203行：
199 command[check_users]=/usr/local/nagios/libexec/check
_users -w 5 -c 10
200 command[check_load]=/usr/local/nagios/libexec/check_
load -w 15,10,5 -c 30,25,20
201 command[check_hda1]=/usr/local/nagios/libexec/check_
disk -w 20% -c 10% -p /dev/hda1
202 command[check_zombie_procs]=/usr/local/nagios/libexe
c/check_procs -w 5 -c 10 -s Z
203 command[check_total_procs]=/usr/local/nagios/libexec
/check_procs -w 150 -c 200
echo "command[check_load]=/usr/local/nagios/libexec/check_load -w 15,10,6 -c 30,25,20">>/usr/local/nagios/etc/nrpe.cfg
echo "command[check_mem]=/usr/local/nagios/libexec/check_memory.pl -w 6% -c 3%">>/usr/local/nagios/etc/nrpe.cfg
echo "command[check_disk]=/usr/local/nagios/libexec/check_disk -w 20% -c 8% -p /">>/usr/local/nagios/etc/nrpe.cfg
echo "command[check_swap]=/usr/local/nagios/libexec/check_swap -w 20% -c 10%">>/usr/local/nagios/etc/nrpe.cfg
echo "command[check_iostat]=/usr/local/nagios/libexec/check_iostat -w 6 -c 10">>/usr/local/nagios/etc/nrpe.cfg
11.启动nagios客户端
pkill nrpe
/usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
echo "#nagios nrpe process cmd by oldboy 2012-6-7" >> /etc/rc.local
echo "/usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d">>/etc/rc.local
[root@Nagios tools]# netstat -lnt|grep 5666 && echo "nagios client is ok"
tcp 0 0 0.0.0.0:5666 0.0.0.0:* LISTEN
nagios client is ok
配置服务端主配置文件：
[root@Nagios etc]# vim nagios.cfg
在34行增加如下两行：
cfg_file=/usr/local/nagios/etc/objects/services.cfg
cfg_file=/usr/local/nagios/etc/objects/hosts.cfg
注释掉38行：
cfg_file=/usr/local/nagios/etc/objects/localhost.cfg
在38行最前面输入"#"
#cfg_file=/usr/local/nagios/etc/objects/localhost.cfg
按服务的目录功能分(演示)：
54行：#cfg_dir=/usr/local/nagios/etc/services
修改为：cfg_dir=/usr/local/nagios/etc/services
[root@Nagios etc]# mkdir services
[root@Nagios etc]# chown -R nagios.nagios services/
[root@Nagios etc]# cd objects
[root@Nagios objects]# ls
commands.cfg localhost.cfg switch.cfg timeperiods.cfg
contacts.cfg printer.cfg templates.cfg windows.cfg
[root@Nagios objects]# head -51 localhost.cfg>hosts.cfg
[root@Nagios objects]# chown nagios.nagios hosts.cfg
[root@Nagios objects]# ls
commands.cfg localhost.cfg templates.cfg
contacts.cfg printer.cfg timeperiods.cfg
hosts.cfg switch.cfg windows.cfg
[root@Nagios objects]# touch services.cfg
[root@Nagios objects]# chown nagios.nagios services.cfg
Nagios监控模式的定义和约定:
1.按监控行为分类：
主动监控
和nrpe无关，就是利用服务端本地插件直接获取信息。
被动监控
主程序通过check_nrpe插件，和客户端nrpe进程沟通，调用本地插件获取数据。
2.如何选择主动模式和被动模式
1）对于本地的资源性能等的监控，一般用被动模式，如负载，内存，硬盘，虚拟内存，磁盘IO，温度，风扇等的监控（我们也可以通过snmp实现监控）
2）对于web服务，数据库服务这种能对外提供服务的监控，一般用主动模式，如监控httpd,sshd,mysqld,rsyncd等的服务
3）主动模式和被动模式是相对的，并且是可以互相转换的，即主动模式的服务，可以改成被动模式，被动模式的服务有时也可以改为主动模式。
实战配置Nagios主机及服务实战：
[root@Nagios etc]# cd objects
[root@Nagios objects]# vim hosts.cfg
define host{ #定义主机
use linux-server #使用的模板
host_name 151-web01 #被监控的主机名
alias 151-web01 #被监控的主机别名
address 192.168.0.151 #被监控的主机IP地址
}
define host{
use linux-server
host_name 150-nagios_server
alias 150-nagios_server
address 192.168.0.150
}
define hostgroup{ #定义主机组
hostgroup_name linux-servers
alias Linux Servers
members 151-web01,150-nagios_server #把上面定义的主机加到这一行，多个主机之间用逗号（，）分隔。
}
[root@Nagios objects]# /etc/init.d/nagios checkconfig #检查配置语法
Running configuration check... CONFIG ERROR! Check your Nagios configuration.
[root@Nagios objects]# /usr/local/nagios/bin/nagios -v /usr/local/nagios/etc/nagios.cfg #检查配置语法
。。。。。。。。。。。。。。。。。。。。。。。。。
Read object config files okay...
Running pre-flight check on configuration data...
Checking services...
Error: There are no services defined! #错误原因，没有定义服务
Checked 0 services.
。。。。。。。。。。。。。。。。。。。。。。。。。
Total Warnings: 2
Total Errors: 1
。。。。。。。。。。。。。。。。。。。。。。。。。。
[root@Nagios objects]# vim /etc/init.d/nagios +183
183 $NagiosBin -v $NagiosCfgFile > /dev/null 2>&1;
修改为：
$NagiosBin -v $NagiosCfgFile
[root@Nagios objects]# /etc/init.d/nagios checkconfig #检查配置语法
。。。。。。。。。。。。。。。。。。。。。。。。。
Read object config files okay...
Running pre-flight check on configuration data...
Checking services...
Error: There are no services defined!
Checked 0 services.
。。。。。。。。。。。。。。。。。。。。。。。。。
Total Warnings: 2
Total Errors: 1
。。。。。。。。。。。。。。。。。。。。。。。。。。
[root@Nagios objects]# vim services.cfg #编辑services.cfg服务配置文件，定义一个服务
define service {
use generic-service
host_name 151-web01
service_description Disk Partition
check_command check_nrpe!check_disk
}
[root@Nagios objects]# /etc/init.d/nagios checkconfig
。。。。。。。。。。。。。。。。。。。。。。。。。
Checking services...
Error: Service check command 'check_nrpe' specified in service 'Disk Partition' for host '151-web01' not defined anywhere! #错误原因，没有定义服务检测（check_nrpe）命令
Checked 1 services.
Checking hosts...
Warning: Host '150-nagios_server' has no services associated with it!
Checked 2 hosts.
Checking host groups...
Checked 1 host groups.
Checking service groups...
。。。。。。。。。。。。。。。。。。。。。。。。。
Total Warnings: 1
Total Errors: 1
。。。。。。。。。。。。。。。。。。。。。。。。。。
CONFIG ERROR! Check your Nagios configuration.
[root@Nagios objects]# vim commands.cfg
在39行增加如下内容，定义服务检测命令
39 # 'check_nrpe' command definition
40 define command {
41 command_name check_nrpe
42 command_line $USER1$/check_nrpe -H $HOSTADDRESS$ -c $ARG1$
43 }
[root@Nagios objects]# /etc/init.d/nagios checkconfig
。。。。。。。。。。。。。。。。。。。。。。。。。。
Read object config files okay...
Running pre-flight check on configuration data...
Checking services...
Checked 1 services.
Checking hosts...
Warning: Host '150-nagios_server' has no services associated with it!
Checked 2 hosts.
Checking host groups...
Checked 1 host groups.
。。。。。。。。。。。。。。。。。。。。。。。。。。。。
Total Warnings: 1
Total Errors: 0
Things look okay - No serious problems were detected during the pre-flight check
OK.
[root@Nagios objects]# /usr/local/nagios/libexec/check_nrpe -H 192.168.0.151 -c check_disk
DISK OK - free space: / 8970 MB (69% inode=92%);| /=3855MB;10814;12436;0;13518
[root@Nagios objects]# /etc/init.d/nagios reload #重新加载nagios配置
Running configuration check...done.
Reloading nagios configuration...done
在服务端的web界面查看主机和服务时出现如下错误：
It appears as though you do not have permission to view information for any of the hosts you requested...
If you believe this is an error, check the HTTP server authentication requirements for accessing this CGI
and check the authorization options in your CGI configuration file.
或
It appears as though you do not have permission to view information for any of the services you requested...
If you believe this is an error, check the HTTP server authentication requirements for accessing this CGI
and check the authorization options in your CGI configuration file.
解决方法：
[root@Nagios etc]# vim cgi.cfg
修改：
157 authorized_for_all_services=nagiosadmin
158 authorized_for_all_hosts=nagiosadmin
为：
157 authorized_for_all_services=oldboy
158 authorized_for_all_hosts=oldboy
因为前面定义验证用户时，定义成oldboy用户了
[root@Nagios etc]# /etc/init.d/nagios reload
Running configuration check...done.
Reloading nagios configuration...done
以下为web正常结果：
Host Status Details For All Host Groups
Limit Results:
Host Sort by host name (ascending)Sort by host name (descending)Status Sort by host status (ascending)Sort by host status (descending)Last Check Sort by last check time (ascending)Sort by last check time (descending)Duration Sort by state duration (ascending)Sort by state duration time (descending)Status Information
150-nagios_server
View Service Details For This Host
UP 01-02-2016 21:46:40 0d 0h 1m 46s+ PING OK - Packet loss = 0%, RTA = 0.05 ms
151-web01
View Service Details For This Host
UP 01-02-2016 21:49:00 0d 0h 3m 12s PING OK - Packet loss = 0%, RTA = 0.27 ms
Service Status Details For All Hosts
Limit Results:
Host Sort by host name (ascending)Sort by host name (descending)Service Sort by service name (ascending)Sort by service name (descending)Status Sort by service status (ascending)Sort by service status (descending)Last Check Sort by last check time (ascending)Sort by last check time (descending)Duration Sort by state duration (ascending)Sort by state duration time (descending)Attempt Sort by current attempt (ascending)Sort by current attempt (descending)Status Information
151-web01
Disk Partition
OK 01-02-2016 21:46:10 0d 0h 4m 18s 1/3 DISK OK - free space: / 8970 MB (69% inode=92%):
Nagios排错及监控Nagios常用本地资源:
[root@Nagios objects]# vim services.cfg #增加如下服务
define service { #http服务自己增加的
use generic-service
host_name 150-nagios_server
service_description http
check_command check_http!check_http
}
define service {
use generic-service
host_name 150-nagios_server
service_description load
check_command check_nrpe!check_load
}
define service {
use generic-service
host_name 150-nagios_server
service_description mem
check_command check_nrpe!check_mem
}
define service {
use generic-service
host_name 150-nagios_server
service_description swap
check_command check_nrpe!check_swap
}
define service {
use generic-service
host_name 150-nagios_server
service_description iostat
check_command check_nrpe!check_iostat
}
[root@Nagios objects]# /etc/init.d/nagios checkconfig
。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。
Total Warnings: 0
Total Errors: 0
Things look okay - No serious problems were detected during the pre-flight check
OK.
[root@Nagios objects]# /etc/init.d/nagios reload Running configuration check...done.
Reloading nagios configuration...done
查看web中服务的状态（在浏览器中）：
service Status
150-nagios_server http PENDING
出现如上错误，等一会就好了
如下出现如下错误：
150-nagios_server http CRITICAL 01-03-2016 21:18:19 0d 0h 2m 51s 2/3 NRPE: Command 'check_http' not defined
解决方法如下：
[root@Nagios objects]# cd ..
[root@Nagios etc]# ls
cgi.cfg nagios.cfg nrpe.cfg.ori resource.cfg
htpasswd.users nrpe.cfg objects services
[root@Nagios etc]# vim nrpe.cfg
在最后一行后面加入如下内容：
command[check_http]=/usr/local/nagios/libexec/check_http -w $ARG1$ -c $ARG2$
[root@Nagios etc]# pkill nrpe
[root@Nagios etc]# ps -ef|grep nrpe
root 13431 12823 0 21:29 pts/0 00:00:00 grep nrpe
[root@Nagios etc]# /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
[root@Nagios etc]# ps -ef|grep nrpe nagios 13433 1 0 21:29 ? 00:00:00 /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
root 13435 12823 0 21:29 pts/0 00:00:00 grep nrpe
出现如下错误：
Status
CRITICAL
Status Information
HTTP CRITICAL: HTTP/1.1 403 Forbidden - 5159 bytes in 0.013 second response time
HTTP CRITICAL: HTTP/1.1 200 OK - 254 bytes in 0.001 second response time
解决方法如下：
http服务用后面的主动模式监控！！！！！！！！
Nagios(被动模式)实战配置过程总结说明：
1.添加主机和主机组，如果有多台机器，用逗号分隔
2.添加服务，可以定义多个服务（被动模式，用check_nrpe!check_http)
3.检查语法
4.重启nagios服务（重新加载配置，可以reload)
端口及url地址(主动模式）监控企业案例实战：
[root@Nagios nagios]# cd libexec
[root@Nagios libexec]# ./check_tcp --help
。。。。。。。。。。。。。。。
Usage:
check_tcp -H host -p port
[root@Nagios libexec]# ./check_tcp -H 192.168.0.151 -p 80
TCP OK - 0.001 second response time on port 80|time=0.000811s;;;0.000000;10.000000
[root@Nagios libexec]# ./check_http -H 192.168.0.151 -p 80
HTTP OK: HTTP/1.1 200 OK - 254 bytes in 0.001 second response time |time=0.000744s;;;0.000000 size=254B;;;0
[root@Nagios libexec]# ./check_http --help
。。。。。。。。。。。。。。。。。。。。。。。。
Usage:
check_http -H <vhost> | -I <IP-address> [-u <uri>] [-p <port>]
[root@Nagios etc]# cd services
[root@Nagios services]# vim http.cfg
define service {
use generic-service
host_name 150-nagios_server
service_description http
check_command check_weburl!-I 192.168.0.150
max_check_attempts 3
normal_check_interval 2
retry_check_interval 1
check_period 24x7
notification_interval 30
notification_period 24x7
notification_options w,u,c,r
contact_groups admins
}
define service {
use generic-service
host_name 151-web01
service_description http
check_command check_weburl!-I 192.168.0.151
max_check_attempts 3
normal_check_interval 2
retry_check_interval 1
check_period 24x7
notification_interval 30
notification_period 24x7
notification_options w,u,c,r
contact_groups admins
}
[root@Nagios objects]# vim commands.cfg
在'check_http' command 下面紧接着加入以下内容：
# 'check_weburl' command definition
define command{
command_name check_weburl
command_line $USER1$/check_http $ARG1$ -w 10 -c 30
}
[root@Nagios objects]# /etc/init.d/nagios checkconfig
.................................................
Total Warnings: 0
Total Errors: 0
Things look okay - No serious problems were detected during the pre-flight check
OK.
[root@Nagios objects]# /etc/init.d/nagios reload
Running configuration check...done.
Reloading nagios configuration...done
nagios 服务分组定义：
1.# vim nagios.cfg
cfg_file=/usr/local/nagios/etc/objects/servicegroups.cfg #添加这一行
2.在/usr/local/nagios/etc/objects/下建立servicegroups.cfg文件
3.# vim servicegroups.cfg
# check web
define servicegroup{
servicegroup_name check_web
alias check_web
members 155,check_w1,156,check_w2,157,check_w3
}
#注意：members 这里要写成：主机1，服务，主机2，服务...的形式，我之前就是这里出错了。
4.# checknagios #检测配置文件
5.# service nagios restart
url高级监控及MySQL-Rsync监控实战:
[root@Nagios services]# vim http.cfg
在最后面增加如下监控端口的服务：
define service {
use generic-service
host_name 151-web01
service_description port_80
check_command check_tcp!80
max_check_attempts 3
normal_check_interval 2
retry_check_interval 1
check_period 24x7
notification_interval 30
notification_period 24x7
notification_options w,u,c,r
contact_groups admins
}
define service {
use generic-service
host_name 151-web01
service_description port_3306
check_command check_tcp!3306
max_check_attempts 3
normal_check_interval 2
retry_check_interval 1
check_period 24x7
notification_interval 30
notification_period 24x7
notification_options w,u,c,r
contact_groups admins
}
URL监控：
define service {
use generic-service
host_name 151-web01
service_description URL
check_command check_weburl!-H www.test.com #此处定义的check_weburl和Nagios服务端自带的check_http等价，因此也可以在这用check_http
max_check_attempts 3
normal_check_interval 2
retry_check_interval 1
check_period 24x7
notification_interval 30
notification_period 24x7
notification_options w,u,c,r
contact_groups admins
}
[root@Nagios services]# vi /etc/hosts
添加解析www.test.com的主机，即做hosts映射（DNS解析）
192.168.0.151 www.test.com
保存退出
[root@Nagios services]# curl www.test.com
192.168.0.151:test1-web
[root@Nagios services]# /usr/local/nagios/libexec/check_http -H www.test.com
HTTP OK: HTTP/1.1 200 OK - 254 bytes in 0.001 second response time |time=0.000978s;;;0.000000 size=254B;;;0
[root@Nagios services]# /etc/init.d/nagios reload
重新加载服务端的配置后，监控www.test.com成功
高级URL监控：
[root@Nagios services]# vim http.cfg
define service {
use generic-service
host_name 151-web01
service_description URL_3
check_command check_http!-H www.test.com -u "/test/55.html"
max_check_attempts 3
normal_check_interval 2
retry_check_interval 1
check_period 24x7
notification_interval 30
notification_period 24x7
notification_options w,u,c,r
contact_groups admins
}
[root@Nagios services]# /usr/local/nagios/libexec/check_http -H www.test.com -u "/test/55.html"
HTTP OK: HTTP/1.1 200 OK - 236 bytes in 0.001 second response time |time=0.000924s;;;0.000000 size=236B;;;0
[root@Nagios services]# /etc/init.d/nagios reload
Running configuration check...done.
Reloading nagios configuration...done
重新加载服务端的配置后，监控www.test.com/test/55.html成功
集群节点监控-服务分组实例-被动监控实战详解一例:
方案：
利用别名实现对集群下面同样节点的URL监控
如：
web1 blog.etiantian.org,blog1.etiantian.org
web2 blog.etiantian.org,blog2.etiantian.org
被动模式监控80端口：
[root@web01 html]# cd /usr/local/nagios
[root@web01 nagios]# ls
bin etc include libexec perl share
[root@web01 nagios]# cd libexec
[root@web01 libexec]# ./check_tcp -H 192.168.0.151 -p 80
TCP OK - 0.000 second response time on port 80|time=0.000187s;;;0.000000;10.000000
[root@web01 libexec]# pwd
/usr/local/nagios/libexec
[root@web01 libexec]# /usr/local/nagios/libexec/check_tcp -H 192.168.0.151 -p 80
TCP OK - 0.000 second response time on port 80|time=0.000216s;;;0.000000;10.000000
[root@web01 nagios]# cd etc
[root@web01 etc]# ls
nrpe.cfg
[root@web01 etc]# ls
nrpe.cfg
[root@web01 etc]# vim nrpe.cfg
在最后面追加：
command[check_port]=/usr/local/nagios/libexec/
check_tcp -H 192.168.0.151 -p 80 -w 5 -c 10
[root@web01 etc]# /usr/local/nagios/libexec/check_tcp -H 192.168.0.151 -p 80 -w 5 -c 10
TCP OK - 0.000 second response time on port 80|time=0.000214s;5.000000;10.000000;0.000000;10.000000
[root@web01 etc]# ps -ef|grep nrpe
nagios 21090 1 0 04:20 ? 00:00:01 /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
root 21649 21201 0 07:05 pts/0 00:00:00 grep nrpe
[root@web01 etc]# pkill nrpe
[root@web01 etc]# /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
[root@web01 etc]# ps -ef|grep nrpe nagios 21652 1 0 07:06 ? 00:00:00 /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
root 21654 21201 0 07:06 pts/0 00:00:00 grep nrpe
[root@Nagios services]# cd /usr/local/nagios/libexec
[root@Nagios libexec]# ./check_nrpe -H 192.168.0.151 -c check_port
TCP OK - 0.000 second response time on port 80|time=0.000181s;5.000000;10.000000;0.000000;10.000000
[root@Nagios services]# vim http.cfg
define service {
use generic-service
host_name 151-web01
service_description port_80_beidong
check_command check_nrpe!check_port
max_check_attempts 3
normal_check_interval 2
retry_check_interval 1
check_period 24x7
notification_interval 30
notification_period 24x7
notification_options w,u,c,r
contact_groups admins
}
[root@Nagios services]# /etc/init.d/nagios reload
Running configuration check...done.
Reloading nagios configuration...done
呵呵，被动模式监控80端口成功
作业：监控mysql主从同步（check_mysql),请用主动及被动分别监控主从同步
自定义插件开发规范及监控密码文件变化案例实战详解：
给Nagios插件程序提供两个返回值：一个是插件的退出状态码，另一个是插件在控制台打印的第一行数据。
Nagios主程序可识别的状态码和说明如下：
OK ---退出代码 0-表示服务正常的工作
WARNING ---退出代码 1-表示服务处于警告状态
CRITICAL ---退出代码 2-表示服务处于紧急，严重状态
UNKNOWN ---退出代码 3-表示服务处于未知状态
[root@Nagios libexec]# head -7 utils.sh
#! /bin/sh
STATE_OK=0
STATE_WARNING=1
STATE_CRITICAL=2
STATE_UNKNOWN=3
STATE_DEPENDENT=4
Nagios被动模式自定义插件开发及应用：
[root@web01 ~]# md5sum /etc/passwd
97fac7fd2707bfd9a0edddf7083afc55 /etc/passwd
[root@web01 ~]# md5sum /etc/passwd >/etc/zkq.md5
[root@web01 ~]# md5sum -c /etc/zkq.md5
/etc/passwd: OK
[root@web01 ~]# vim check_passwd
#!/bin/sh
char=`md5sum -c /etc/zkq.md5 2>/dev/null|grep "OK"|wc -l`
if [ $char -eq 1 ];then
echo "passwd is ok"
exit 0
else
echo "passwd is changed"
exit 2
fi
[root@web01 libexec]# chmod +x check_passwd
[root@web01 libexec]# ll /usr/local/nagios/libexec/check_passwd
-rwxr-xr-x 1 root root 167 Jan 3 09:52 /usr/local/nagios/libexec/check_passwd
[root@web01 libexec]# cd ..
[root@web01 nagios]# cd etc
[root@web01 etc]# ls
nrpe.cfg
[root@web01 etc]# vim nrpe.cfg
在最后一行加入如下内容：
command[check_passwd]=/usr/local/nagios/libexec/check_
passwd
[root@web01 etc]# pkill nrpe
[root@web01 etc]# /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
[root@web01 etc]# ps -ef|grep nrpe
nagios 22735 1 0 10:00 ? 00:00:00 /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
root 22737 22269 0 10:00 pts/0 00:00:00 grep nrpe
[root@Nagios]# cd libexec
[root@Nagios libexec]# ./check_nrpe -H 192.168.0.151 -c check_passwd
passwd is ok
[root@Nagios libexec]# cd ..
[root@Nagios nagios]# cd etc
[root@Nagios etc]# ls
cgi.cfg nrpe.cfg resource.cfg
htpasswd.users nrpe.cfg.ori services
nagios.cfg objects
[root@Nagios etc]# cd objects
[root@Nagios objects]# ls
commands.cfg printer.cfg timeperiods.cfg
contacts.cfg services.cfg windows.cfg
hosts.cfg switch.cfg
localhost.cfg templates.cfg
[root@Nagios objects]# vim services.cfg
在最后加入以下内容：
define service {
use generic-service
host_name 151-web01
service_description check_passwd
check_command check_nrpe!check_passwd
}
[root@Nagios objects]# /etc/init.d/nagios checkconfig
。。。。。。。。。。。。。。。。。。。。。。。。
Total Warnings: 0
Total Errors: 0
Things look okay - No serious problems were detected during the pre-flight check
OK.
嘿嘿，被动模式自定义插件应用成功
Nagios图形显示介绍及实战安装:
#1、图形显示管理的依赖库
yum install cairo pango zlib zlib-devel freetype freetype-devel gd gd-devel -y
#2、rrdtools的依赖
[root@Nagios tools]# tar xf libart_lgpl-2.3.17.tar.gz
cd libart_lgpl-2.3.17
./configure
make
make install
/bin/cp -r /usr/local/include/libart-2.0 /usr/include
cd ../
#3、rrdtools轮询的数据库，专门画图
[root@Nagios tools]# tar xf rrdtool-1.2.14.tar.gz
cd rrdtool-1.2.14
./configure --prefix=/usr/local/rrdtool --disable-python --disable-tcl
#WARNING: The RRDs Perl Modules are not found on your System
#Using RRDs will speedup things in larger Installtions.
#configure后出现上面的提示可以不用理会。
make
make install
cd ../
ls -l /usr/local/rrdtool/bin
#4、PNP收集数据告诉rrdtools画图，PHP负责展示
tar zxf pnp-0.4.14.tar.gz
cd pnp-0.4.14
./configure \
--with-rrdtool=/usr/local/rrdtool/bin/rrdtool --with-perfdata-dir=/usr/local/nagios/share/perfdata/
#################
# WARNING: The RRDs Perl Modules are not found on your System
# Using RRDs will speedup things in larger Installtions.
#####################
make all
make install
make install-config
make install-init
ll /usr/local/nagios/libexec/ |grep process
问题：configure报错（一般不会发生）
checking for linker flags for loadable modules... -shared
checking for Perl Module Time::HiRes... no
configure: error: Perl Module Time::HiRes not available
解决：
yum install perl-Time-HiRes -y
配置出图
[root@Nagios ~]# cd /usr/local/nagios/etc
[root@Nagios etc]# vim nagios.cfg
833 process_performance_data=1<==========
834
835
836
837 # HOST AND SERVICE PERFORMANCE DATA PROCESSING COMMANDS
838 # These commands are run after every host and service check is
839 # performed. These commands are executed only if the
840 # enable_performance_data option (above) is set to 1. The command
841 # argument is the short name of a command definition that you
842 # define in your host configuration file. Read the HTML docs for
843 # more information on performance data.
844
845 host_perfdata_command=process-host-perfdata<==========
846 service_perfdata_command=process-service-perfdata<==========
2.执行编辑命令 vi /usr/local/nagios/etc/objects/commands.cfg +227，修改commands.cfg配置文件。
#修改commands.cfg 配置文件，约227-238行
#默认配置为（如果没有直接添加即可）
#-----------------------------------------------------------------
# 'process-host-perfdata' command definition
define command{
command_name process-host-perfdata
command_line /usr/bin/printf "%b" "$LASTHOSTCHECK$\t$HOSTNAME$\t$HOSTSTATE$\t$HOSTATTEMPT$\t$HOSTSTATETYPE$\t$HOSTEXECUTIONTIME$\t$HOSTOUTPUT$\t$HOSTPERFDATA$\n" >> /usr/local/nagios/var/host-perfdata.out
}
# 'process-service-perfdata' command definition
define command{
command_name process-service-perfdata
command_line /usr/bin/printf "%b" "$LASTSERVICECHECK$\t$HOSTNAME$\t$SERVICEDESC$\t$SERVICESTATE$\t$SERVICEATTEMPT$\t$SERVICESTATETYPE$\t$SERVICEEXECUTIONTIME$\t$SERVICELATENCY$\t$SERVICEOUTPUT$\t$SERVICEPERFDATA$\n" >> /usr/local/nagios/var/service-perfdata.out
}
修改成如下配置
# 'process-host-perfdata' command definition
define command{
command_name process-host-perfdata
command_line /usr/local/nagios/libexec/process_perfdata.pl
}
# 'process-service-perfdata' command definition
define command{
command_name process-service-perfdata
command_line /usr/local/nagios/libexec/process_perfdata.pl
}
也可以用nagios变量$USER1$替代/usr/local/nagios/libexec/路径
执行检查语法命令/etc/init.d/nagios checkconfig
Total Warnings: 0
Total Errors: 0
根据提示，配置通过。重启。
3、主机出图的配置，模板或主机配置里hosts.cfg
action_url /nagios/pnp/index.php?host=$HOSTNAME$
4、服务出图，模板或服务配置里hosts.cfg
action_url /nagios/pnp/index.php?host=$HOSTNAME$&srv=$SERVICEDESC$
snmp协议（cacti）,客户端安装或开启SNMP
nrpe(nlient++)
网络设备（路由器，交换机），开启SNMP
短信报警的脚本开发及实战配置：
1、添加联系人及联系组contacts.cfg
define contact{
contact_name oldboy-pager
use generic-contact
alias Nagios users
pager 18901398229
}
2、添加报警的命令commands.cfg
#command.cfg
# 'notify-host-by-pager' command definition
define command{
command_name notify-host-by-pager
command_line $USER1$/sms_send "Host $HOSTSTATE$ alert for $HOSTNAME$" $CONTACTPAGER$
}
# 'notify-service-by-pager' command definition
define command{
command_name notify-service-by-pager
command_line $USER1$/sms_send "$HOSTALIAS$/$SERVICEDESC$ is $SERVICESTATE$" $CONTACTPAGER$
}
3、调整联系人模板，添加报警的命令（来自于commands.cfg）
编辑templates.cfg里的定义内容为：
define contact{
name generic-contact
service_notification_period 24x7
host_notification_period 24x7
service_notification_options w,u,c,r,f,s
host_notification_options d,u,r,f,s
service_notification_commands notify-service-by-email,notify-service-by-fetion,notify-service-by-msn, notify-service-by-pager
host_notification_commands notify-host-by-email,notify-service-by-fetion,notify-host-by-msn, notify-host-by-pager
register 0
}
4、hosts.cfg,services.cfg添加报警联系人及组，或者对应模板加
contact_groups admins,groups1,groups2,user01
开发短信报警脚本（短信网关是收费的）
[root@oldboy-A libexec]# pwd
/usr/local/nagios/libexec
[root@oldboy-A libexec]# cat sms_send
#!/bin/sh
alert_date=$(date +%y-%m-%d" "%H:%M)
TITLE=$1 #FORMAT "Host $HOSTSTATE$ alert for $HOSTNAME$"
CONTACT=$2 #$2为手机号
#curl方式
curl -d cdkey=3RTY-EMY-0980-MTUQ2 -d password=189162 -d phone=$CONTACT -d message="$TITLE[${alert_date} oldboysa]" http://sdkhttp.eucp.b2m.cn/sdkproxy/sendsms.action
#wget --quiet "http://s.ccme.cc/qxt/send.jsp?circle=159net_131&pwd=oldboy123&mobile=18911718229&service=f1fb0546-ebb6-0987-8f20-560524c1f88d&msgid=3956724&message=$TITLE[${alert_date} oldboysa n]"
1、添加联系人及联系组contacts.cfg
define contact{
contact_name oldboy-pager
use generic-contact
alias Nagios users
pager 18901398229
}
2、添加报警的命令commands.cfg
#command.cfg
# 'notify-host-by-pager' command definition
define command{
command_name notify-host-by-pager
command_line $USER1$/sms_send "Host $HOSTSTATE$ alert for $HOSTNAME$" $CONTACTPAGER$
}
# 'notify-service-by-pager' command definition
define command{
command_name notify-service-by-pager
command_line $USER1$/sms_send "$HOSTALIAS$/$SERVICEDESC$ is $SERVICESTATE$" $CONTACTPAGER$
}
3、调整联系人模板，添加报警的命令（来自于commands.cfg）
编辑templates.cfg里的定义内容为：
define contact{
name generic-contact
service_notification_period 24x7
host_notification_period 24x7
service_notification_options w,u,c,r,f,s
host_notification_options d,u,r,f,s
service_notification_commands notify-service-by-email,notify-service-by-fetion,notify-service-by-msn, notify-service-by-pager
host_notification_commands notify-host-by-email,notify-service-by-fetion,notify-host-by-msn, notify-service-by-pager
register 0
}
4、hosts.cfg,services.cfg添加报警联系人及组，或者对应模板加
contact_groups admins,groups1,groups2,user01
开发脚本批量生成Nagios配置文件实战：
########################
批量建立nagios配置文件：
########################
好多兄弟们都说nagios配置麻烦，都来问过我如何管理，为了提高解答效率，所以这里统一总结下，供大家参考。呵呵。
这是 以前的一个例子，抛砖引玉下，你可以拓展做成菜单式等更详细的配置,如果你足够努力，可以做到一键 部署几百
台服务器的服务监控，是没有问题的（包括host.cfg,service.cfg等），如果配置支持目录就更简单了。。欢迎随时交流。
1.建立 机器名和IP对应列表
cat >host.list <<EOFoldboy oldboyVM-001 192.168.1.1 oldboyVM-002 192.168.1.2 oldboyVM-003 192.168.1.3 oldboyVM-004 192.168.1.4 EOFoldboy
#提示：上面列表可以手工编辑或者脚本批量去取
2.批量生成 nagios host配置文件
rm -f new.host
exec <host.list
while read line
do
echo 'define host {' >>new.host
echo ' use linux-server' >>new.host
echo " host_name `echo $line|awk '{print $1}'`" >>new.host
echo " alias `echo $line|awk '{print $1}'` " >>new.host
echo " address `echo $line|awk '{print $2}'` " >>new.host
echo "}" >>new.host
done
3.最终host内容
$ cat new.host
define host {
use linux-server
host_name oldboyVM-001
alias oldboyVM-001
address 192.168.1.1
}
define host {
use linux-server
host_name oldboyVM-002
alias oldboyVM-002
address 192.168.1.2
}
define host {
use linux-server
host_name oldboyVM-003
alias oldboyVM-003
address 192.168.1.3
}
define host {
use linux-server
host_name oldboyVM-004
alias oldboyVM-004
address 192.168.1.4
}
转载于:https://blog.51cto.com/butterflykiss/1950670
扫一扫
195
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
