分类： 系统运维
2013-05-10 16:28:06
添加标记
vi /etc/portage/package.use
media-libs/gd jpeg png
uuwatch_liwei ~ # emerge gd
uuwatch_liwei ~ # emerge nagios
安装成功后，会自动新建用户nagios。
修改这个新用户的注释信息，以后此用户发送报警邮件中就不会带有注释信息
nano /etc/passwd
删除nagios那一行中的added by portage for nagios-plugins
保存为nagios:x:101:101::/var/nagios/home:/bin/bash
添加nagios使这个用户可以发邮件
nano /etc/ssmtp/revaliases
nagios:deamon@uuwatch.com:smtp.uuwatch.com
修改配置文件：
uuwatch_liwei ~ # vi /etc/nagios/objects/contacts.cfg
uuwatch_liwei ~ # emerge nagios-plugins
uuwatch_liwei ~ # nagios -v /etc/nagios/nagios.cfg
uuwatch_liwei ~ # /etc/init.d/nagios start
1.6．修改Apache配置文件(创建nagios虚拟主机，从源码包拷贝模版)：uuwatch_liwei ~ # cp nagios-3.2.3/sample-config/httpd.conf /etc/apache2/vhosts.d/nagios.uuwatch.com.include
内容修改如下：
ScriptAlias /nagios/cgi-bin "/etc/nagios/sbin"
ServerName test.nagios.uuwatch.com
Options ExecCGI
AllowOverride None
Order allow,deny
Allow from all
AuthName "Nagios Access"
AuthType Basic
AuthUserFile /usr/lib/nagios/htpasswd.user
Require valid-user
Alias /nagios "/etc/nagios/share"
DocumentRoot "/etc/nagios/share"
Options None
AllowOverride None
Order allow,deny
Allow from all
AuthName "Nagios Access"
AuthType Basic
AuthUserFile /usr/lib/nagios/htpasswd.user
Require valid-user
1.7.创建登陆账号：
uuwatch_liwei ~ # htpasswd -c /usr/lib/nagios/htpasswd.user nagios
登陆后如出现以下情况：
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.
解决方法：
uuwatch_liwei ~ # vi /etc/nagios/cgi.cfg
default_user_name=nagios
authorized_for_system_information=nagiosadmin,nagios
authorized_for_configuration_information=nagiosadmin,nagios
authorized_for_system_commands=nagiosadmin,nagios
authorized_for_all_services=nagiosadmin,nagios
authorized_for_all_hosts=nagiosadmin,nagios
authorized_for_all_service_commands=nagiosadmin,nagios
authorized_for_all_host_commands=nagiosadmin,nagios
或者：
uuwatch_liwei ~ # cp /etc/nagios/ /etc/nagios_bak -r
uuwatch_liwei ~ # sed s/nagiosadmin/nagiosadmin\,nagios/g /etc/nagios _bak/cgi.cfg |grep -v "#" |grep -v "^$" >/etc/nagios/cgi.cfg
uuwatch_liwei ~ # /etc/init.d/nagios restart
六、汉化：
uuwatch_liwei ~ # tar vjxf nagios-cn-3.2.3.tar.bz2
uuwatch_liwei ~ # cd nagios-cn-3.2.3
uuwatch_liwei nagios-cn-3.2.3 # ./configure
uuwatch_liwei nagios-cn-3.2.3 # make && make install
问题：whoops! Error: could not open CGI config file '/etc/nagios/cgi.cfg'
解决方法：usermod -a -G nagios apache
uuwatch_liwei ~ # vi /etc/conf.d/apache2
APACHE2_OPTS="-D PHP5 -D DEFAULT_VHOST -D INFO -D SSL -D SSL_DEFAULT_VHOST -D LANGUAGE"
uuwatch_liwei ~ # emerge nrpe
uuwatch_liwei ~ # emerge openrc
修改nagios配置，让其可以使用check_nrpe插件：
uuwatch_liwei ~ # vi /etc/nagios/objects/commands.cfg
添加如下行：
#'check_nrpe' command definition from liwei at 2013/04/17
define command{
command_name check_nrpe
command_line $USER1$/check_nrpe -H $HOSTADDRESS$ -c $ARG1$
}
到此服务器端全部安装成功；
Cgi.cfg 控制CGI访问的配置文件（比如，指定nagios主配置文件及添加用户访问权限等）
nagios.cfg nagios主配置文件
resource.cfg 变量定义文件，又称为资源文件，在些文件中定义变量，以便由其他配置文件引用，如$USER1$
objects 这是一个目录，在这个目录下有很多配置文件模版，用于定义nagios对像
objects/commands.cfg 命令定义配置文件，其中定义的命令可以被其他配置文件引用
objects/contacts.cfg 定义联系人和联系人组的配置文件
objects/localhost.cfg 定义监控本地主机的配置文件
objects/printer.cfg 定义监控打印机的一个配置文件模版，默认没有启用此文件
objects/switch.cfg 监控路由器的一个配置文件模版，默认没有启用此文件
objects/templates.cfg 定义主机和服务的一个模版配置文件，可以在其他文件中引用
objects/timeperiods.cfg 定义nagios监控时间段的配置文件
objects/windows.cfg 监控Windows主机的一个配置文件模版，默认未启用
2.2．配置实例：自定义hosts.cfg里存放要监控的主机及主机组，services.cfg里存放监控这些主机的哪些服务：
Hosts.cfg:
define host{
use linux-server
host_name localhost
alias localhost
address 127.0.0.1
}
define host{
use linux-server
host_name db2
alias db2
address 192.168.0.88
}
define hostgroup{
hostgroup_name sa-server
alias sa server
members localhost,db2
}
Services.cfg:
define service{
use local-service
host_name localhost,db2
service_description PING
check_command check_ping!100.0,20%!500.0,60%
}
define service{
use local-service
host_name localhost,db2
service_description SSH
check_command check_ssh
}
define service{
use local-service
host_name localhost,db2
service_description SSHD
check_command check_tcp!22
}
define service{
use local-service
host_name localhost,db2
service_description http
check_command check_http
}
然后修改主配置文件nagios.cfg，添加以下两行：
cfg_file=/etc/nagios/objects/hosts.cfg
cfg_file=/etc/nagios/objects/services.cfg
修改contacts.cfg配置文件：
define contact{
contact_name nagiosadmin
use generic-contact
alias Nagios Admin
email liwei@uuwatch.com
}
define contactgroup{
contactgroup_name admins
alias Nagios Administrators
members nagiosadmin
}
遇到问题：监控的主机不停的动，时好时坏；
解决：ps –ef ｜grep nagios查看是否有多个nagios进程，全部Kill掉后，重启nagios解决。
3.客户端配置：3.1．安装nrpe:
uuwatch_client ~ # emerge nrpe
uuwatch_client ~ # emerge openrc (不安装提示function问题)
3.2．修改nrpe配置文件：
uuwatch_client ~ # vi /etc/nagios/nrpe.cfg
可以把nrpe服务加入到/etc/service文件里 nrpe 5666/tcp #nrpe
把allowed_hosts=127.0.0.1 修改为 allowed_hosts=127.0.0.1,192.168.0.45（服务器端IP）
3.3．启动nrpe：
uuwatch_client ~ # /etc/init.d/nrpe start
uuwatch_client ~ # netstate -auntp |grep nrpe
tcp 0 0 0.0.0.0:5666 0.0.0.0:* LISTEN 24070/nrpe
4．客户端配置实例：
通过check_nrpe监控客户端磁盘状态、登陆用户数、swap使用状况、CPU负载等
4.1.修改客户端nrpe.cfg文件，如下：
log_facility=daemon
pid_file=/var/run/nrpe.pid
server_port=5666
server_address=192.168.0.88（客户端本机地址）
nrpe_user=nagios
nrpe_group=nagios
allowed_hosts=127.0.0.1,192.168.0.45（后面跟nagios服务器的IP地址）
dont_blame_nrpe=0
debug=0
command_timeout=60
connection_timeout=300
command[check_users]=/usr/lib64/nagios/plugins/check_users -w 5 -c 10
command[check_load]=/usr/lib64/nagios/plugins/check_load -w 15,10,5 -c 30,25,20
command[check_md125]=/usr/lib64/nagios/plugins/check_disk -w 20% -c 10% -p /dev/md125
command[check_zombie_procs]=/usr/lib64/nagios/plugins/check_procs -w 5 -c 10 -s Z
command[check_total_procs]=/usr/lib64/nagios/plugins/check_procs -w 150 -c 200
command[check_swap]=/usr/lib64/nagios/plugins/check_swap -w 20 -c 10
command[check_md125]=/usr/lib64/nagios/plugins/check_disk -w 20% -c 10% -p /dev/md127
command[xxxx]指要监控服务的指令与参数
4.2．修改服务器上的services.cfg文件，添加如下文件：
define service{
use local-service
host_name db2
service_description users
check_command check_nrpe!check_users
}
define service{
use local-service
host_name db2
service_description load
check_command check_nrpe!check_load
}
define service{
use local-service
host_name db2
service_description disk
check_command check_nrpe!check_md127
}
define service{
use local-service
host_name db2
service_description swap
check_command check_nrpe!check_swap
}
define servicegroup{
servicegroup_name servergroup
alias server-group
members db2,PING,db2,SSH,db2,SSHD,db2,http,db2,users,db2,disk,db2,swap,db2,load,localhost,PING,localhost,SSH,localhost,SSHD
}
其中services.cfg中check_command check_nrpe!xxxx的参数要与客户端nrpe.cfg里command[xxxx]选项中的xxxx是相对应的。
重启nagios服务器，/etc/init.d/nagios restart
5.报警配置：
5.1.邮件报警：
5.1.1.安装sendMail软件：
uuwatch_liwei ~ # wget
uuwatch_liwei ~ # tar vzxf sendEmail-v1.56.tar.gz
uuwatch_liwei ~ # cp –a sendEmail-v1.56/sendEmail /bin/
uuwatch_liwei ~ # chmod 755 /bin/sendEmail
uuwatch_liwei~ # vi /etc/nagios/objects/commands.cfg
# 'notify-host-by-email' command definition ----------modify by liwei at 2013/04/17
define command{
command_name notify-host-by-email
command_line /usr/bin/printf "%b" "Host:
$HOSTNAME$
Notification: $HOSTNOTIFICATIONNUMBER$
Command:
$HOSTCHECKCOMMAND$
Datetime: $LONGDATETIME$
Info:
$HOSTOUTPUT$
$LONGHOSTOUTPUT$" | /usr/local/bin/sendEmail -f
liwei_linux@hotmail.com -t $CONTACTEMAIL$ -s smtp.live.com -u "Host
$HOSTSTATE$: $HOSTADDRESS$" -xu liwei_linux@hotmail.com -xp xxxxxxx -o
message-content-type=html -o message-charset=utf8
}
# 'notify-service-by-email' command definition-------modify by liwei at 2013/04/17
define command{
command_name notify-service-by-email
command_line /usr/bin/printf "%b" "Host:
$HOSTALIAS$
NotifyTimes: $SERVICENOTIFICATIONNUMBER$
Command:
$SERVICECHECKCOMMAND$
Datetime:
$LONGDATETIME$
Additional
Info:
$SERVICEOUTPUT$
$LONGSERVICEOUTPUT$" | /usr/local/bin/sendEmail
-f liwei_linux@hotmail.com -t $CONTACTEMAIL$ -s smtp.live.com -u "Service
$SERVICESTATE$: $HOSTADDRESS$ | $SERVICEDESC$" -xu liwei_linux@hotmail.com
-xp xxxx -o message-content-type=html -o message-charset=utf8
}
修改完后重启nagios服务器，然后关闭客户端的nrpe测试一下能否收到邮件。
5.2.手机短信报警（限移动手机用户）：
下载安装包：
uuwatch_liwei ~ # wget
下载最新主程序fetion:
到“nagios所需”里找到fetion或者到下载fetion程序(Linux版)
下载机器人支持库：
uuwatch_liwei ~ # wget
uuwatch_liwei ~ # tar vzxf fetion20091117-linux.tar.gz
uuwatch_liwei ~ # mv fx/ /etc/fetion
将linuxso_20101113.rar在windows机器解压，然后上传到服务器/usr/local/fetion/目录下，或者直接解压我自己压缩进去的包，fetion-so.tar.gz
uuwatch_liwei ~ # tar vzxf fetion-so.tar.gz –C /usr/local/fetion
将fetion-so里的文件拷贝到/usr/local/fetion目录下。
uuwatch_liwei ~ # chmod 755 /usr/local/fetion/fetion
uuwatch_liwei ~ # cp /usr/local/fetion/libcrypto.so.4 libssl.so.4 /usr/lib/
uuwatch_liwei ~ # cp /usr/local/fetion/libACE* /usr/lib/
uuwatch_liwei ~ # vi /etc/ld.so.conf
添加：
/etc/fetion
uuwatch_liwei ~ # ldd /usr/local/fetion/fetion (测试是否正常，如没not found则正确)
测试是否能发送短信：
uuwatch_liwei ~ # /usr/local/fetion/fetion --mobile=13661133354 --pwd=password--to 13661133354 --msg-utf8="test" –debug
此处会出现验证码，解决方法：到/usr/local/fetion目录下找到图片，下载到wiondows客户端上查看验证码为多少，然后输入，输入一次后，以后不需要再输入，除非重装。
5.2.2．修改nagios配置文件command.cfg，定义fetion发送指令：
uuwatch_liwei ~ # vi /etc/nagios/objects/commands.cfg
#'notify-host-by-sms' command definition-------- from liwei at 2013/04/17
define command{
command_name notify-host-by-sms
command_line /usr/local/fetion/fetion --mobile=13661133354 --pwd=passwd --to=$CONTACTPAGER$ --msg-utf8="Host $HOSTSTATE$ alert for $HOSTNAME$! on '$DATETIME$'"
}
#'notify-service-by-sms' command definition-------- from liwei at 2013/04/17
define command{
command_name notify-service-by-sms
command_line /usr/local/fetion/fetion --mobile=13661133354 --pwd=passwd --to=$CONTACTPAGER$ --msg-utf8="$HOSTADDRESS$' $HOSTALIAS$/$SERVICEDESC$ is $SERVICESTATE$"
}
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-sms
host_notification_commands notify-host-by-email,notify-host-by-sms
register 0
}
uuwatch_liwei ~ # vi /etc/nagios/objects/contacts.cfg
define contact{
contact_name nagiosadmin
use generic-contact
alias Nagios Admin
email liwei@uuwatch.com
pager 13661133354
}
