CentOS 6.5+Nagios4.0.2+Msmtp+Mutt邮箱报警

环境：

Nagios Server  Nagios 6.5

IP：192.168.0.58

Nagios Clint   Nagios 6.5

IP：192.168.0.83

另注意：

Nagios需要PHP支持，安装Apache+PHP步骤略....

------------------------------------------------------

——安装Nagios

1）下载Nagios

[root@Nagios ~]# cd /Linux
[root@Nagios Linux]#  http://jaist.dl.sourceforge.net/project/nagios/nagios-4.x/nagios-4.0.2/nagios-4.0.2.tar.gz

2）编译安装

[root@Nagios Linux]# tar fzvx nagios-4.0.2.tar.gz
[root@Nagios Linux]# cd nagios-4.0.2
[root@Nagios nagios-4.0.2]# useradd -M -s /sbin/nologin nagios
[root@Nagios nagios-4.0.2]# mkdir /usr/local/nagios
[root@Nagios nagios-4.0.2]# chown -R nagios:nagios /usr/local/nagios/
[root@Nagios nagios-4.0.2]# ./configure --prefix=/usr/local/nagios/
[root@Nagios nagios-4.0.2]# make all
[root@Nagios nagios-4.0.2]# make install
[root@Nagios nagios-4.0.2]# make install-init
[root@Nagios nagios-4.0.2]# make install-commandmode
[root@Nagios nagios-4.0.2]# make install-config
[root@Nagios nagios-4.0.2]# chkconfig --add nagios
[root@Nagios nagios-4.0.2]# chkconfig --level 35 nagios on
[root@Nagios nagios-4.0.2]# chkconfig --list nagios
nagios          0:关闭  1:关闭  2:关闭  3:启用  4:关闭  5:启用  6:关闭
[root@Nagios nagios-4.0.2]# service nagios restart

3）服务端安装Nagios插件plugins

[root@Nagios Linux]# tar zfvx nagios-plugins-1.5.tar.gz
[root@Nagios Linux]# cd nagios-plugins-1.5
[root@Nagios nagios-plugins-1.5]# ./configure --prefix=/usr/local/nagios/
[root@Nagios nagios-plugins-1.5]# make && make install

----------------------------------------------------------------------------

4）服务端安装nrpe

[root@Nagios Linux]# tar zfvx nrpe-2.15.tar.gz
[root@Nagios Linux]# cd nrpe-2.15
[root@Nagios nrpe-2.15]# ./configure
[root@Nagios nrpe-2.15]# make all
[root@Nagios nrpe-2.15]# make install-plugin

——Apache配置修改

1）使apache支持nagios

[root@Nagios nagios-plugins-1.5]# vi /usr/local/apache-2.4/conf/httpd.conf
ScriptAlias /nagios/cgi-bin "/usr/local/nagios/sbin"

     AuthType Basic
     Options ExecCGI
     AllowOverride None
     Order allow,deny
     Allow from all
     AuthName "Nagios Access"
     AuthUserFile /usr/local/nagios/etc/htpasswd
     Require valid-user

Alias /nagios "/usr/local/nagios/share"

     AuthType Basic
     Options None
     AllowOverride None
     Order allow,deny
     Allow from all
     AuthName "nagios Access"
     AuthUserFile /usr/local/nagios/etc/htpasswd
     Require valid-user

2）添加nagios登陆用户

[root@Nagios nagios-plugins-1.5]# /usr/local/apache-2.4/bin/htpasswd -c  /usr/local/nagios/etc/htpasswd nagios
New password:
Re-type new password:
Adding password for user nagios

3）修改apache的用户和用户组

[root@Nagios nagios-plugins-1.5]# vi /usr/local/apache-2.4/conf/httpd.conf
User nagios
Group nagios

--------------------------------------------------------------------------

4）解决Nagios乱码问题

[root@Nagios nagios-plugins-1.5]# vi /usr/local/apache-2.4/conf/httpd.conf
LoadModule cgid_module modules/mod_cgid.so
LoadModule actions_module modules/mod_actions.so
[root@Nagios nagios-plugins-1.5]# service httpd restart

5）测试访问

——客户端配置

1）客户端安装nagios-plugins

[root@CentOS ~]# cd /Linux
[root@CentOS Linux]# useradd -M -s /sbin/nologin nagios
[root@CentOS Linux]# tar zfvx nagios-plugins-1.5.tar.gz
[root@CentOS Linux]# cd nagios-plugins-1.5
[root@CentOS nagios-plugins-1.5]# ./configure --prefix=/usr/local/nagios/
[root@CentOS nagios-plugins-1.5]# make && make install

2）客户端安装nrpe

[root@CentOS nagios-plugins-1.5]# cd ..
[root@CentOS Linux]# tar zfvx nrpe-2.15.tar.gz
[root@CentOS Linux]# cd nrpe-2.15
[root@CentOS nrpe-2.15]# ./configure
[root@CentOS nrpe-2.15]# make all
[root@CentOS nrpe-2.15]# make install-plugin
[root@CentOS nrpe-2.15]# make install-daemon
[root@CentOS nrpe-2.15]# make install-daemon-config
[root@CentOS nrpe-2.15]# vi /usr/local/nagios/etc/nrpe.cfg
allowed_hosts=127.0.0.1,192.168.0.58

3）启动nrpe

[root@CentOS nrpe-2.15]# /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
[root@CentOS nrpe-2.15]# echo "/usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d" /etc/rc.local

4）检查是否启动

[root@CentOS nrpe-2.15]# netstat -antup |grep 5666
tcp        0      0 0.0.0.0:5666                0.0.0.0:*                   LISTEN      48456/nrpe         
tcp        0      0 :::5666                     :::*                        LISTEN      48456/nrpe

5）在服务端检查 [如果返回NRPE版本及成功，相反则检查配置]

[root@Nagios ~]# /usr/local/nagios/libexec/check_nrpe -H 192.168.0.83
NRPE v2.15

=========================================================================================

——配置nagios

[root@Nagios nrpe-2.15]# cd /usr/local/nagios/etc/

1）编辑nagios.cfg

[root@Nagios etc]# vi nagios.cfg
注释下面的内容
#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
#cfg_file=/usr/local/nagios/etc/objects/localhost.cfg
#cfg_file=/usr/local/nagios/etc/objects/windows.cfg
#cfg_file=/usr/local/nagios/etc/objects/switch.cfg
#添加监控主机目录
cfg_dir=/usr/local/nagios/etc/objects/hosts
#添加模板目录
cfg_dir=/usr/local/nagios/etc/objects/templates

2）创建相关目录

[root@Nagios etc]# mdkir  objects/templates
[root@Nagios etc]# mdkir  objects/hosts

3）复制所需文件

[root@Nagios etc]# cp objects/commands.cfg objects/templates/
[root@Nagios etc]# cp objects/timeperiods.cfg objects/templates/

4）创建自定义模板

[root@Nagios etc]# vi objects/templates/templates.cfg
#联系人模板
define contact{
        #联系人名称
        name                            tao
        #当服务出现异常时 发送通知的时间段
        service_notification_period     24x7
        #当主机出现异常时 发送通知的时间段
        host_notification_period        24x7
        #w 表示警告 u 表示不明 c 表示紧急 r 表示恢复
        service_notification_options    w,u,c,r
        #d 表示宕机 u 表示不可达 r 表示重新恢复
        host_notification_options       d,u,r
        #服务故障时 发送通知的方式[邮件]
        service_notification_commands   notify-service-by-email
        #主机故障时 发送通知的方式[邮件]
        host_notification_commands      notify-host-by-email
        register                        0
        }
#主机模板
define host{
        #定义主机名
        name                            linux-host
        #其值为1 Nagios将收集的数据写入某个文件中 以备提取
        process_perf_data               1
        passive_checks_enabled          0
        #主机与服务的刷新检测 0为关闭
        check_freshness                 0
        #事件处理开启
        event_handler_enabled           1
        #打开抖动感知
        flap_detection_enabled          1
        active_checks_enabled           1
        #发送通知的时间段
        notification_period             24x7
        #检查主机的时间段
        check_period                    24x7
        #对主机的检查时间间隔/分钟
        check_interval                  5
        #如果宕机重试检查时间/分钟
        retry_interval                  1
        #宕机后对主机的最大检查次数
        max_check_attempts                  2
        #检查主机状态指令[在commands.cfg中定义]
        check_command                   check-host-alive
        #在主机出现异常后 故障一直没有解决 再次发送通知的时间/分钟
        notification_interval           5
        #d 表示宕机 u 表示不可达 r 表示重新恢复
        notification_options            d,u,r
        #1为开启报警信息
        notifications_enabled           0
        #指定联系人组[在contacts.cfg中定义]
        contact_groups                  admins
        #处理性能数据
        #一天刷新检测一次，以防止检测结果不是实时的
        freshness_threshold             86400
        #0为不注册，意思是这个作为模板
        register                        0
        }
#服务模板
define service{
        #定义一个服务名称
        name                            linux-service
        #启用主动服务检查
        active_checks_enabled           1
        #启用被动服务检查
        passive_checks_enabled          0
        #主机与服务的刷新检测
        check_freshness                 0
        #开启报警信息
        notifications_enabled           1
        #重新发送报警信息的间隔
        notification_interval           5
        #事件处理开启
        event_handler_enabled           1
        #启用抖动感知
        flap_detection_enabled          1
        #处理性能数据
        process_perf_data               1
        #发送通知的时间段
        notification_period             24x7
        #检查时间段
        check_period                    24x7
        #如果宕机最大检查次数
        max_check_attempts              5
        #检查服务时间间隔/分钟
        normal_check_interval           1
        #如果宕机再次检查的间隔时间/分钟
        retry_check_interval            1
        #一天刷新检测一次，以防止检测结果不是实时的
        freshness_threshold             86400
        #0为不注册，意思是这个作为模板
        register                        0
        }
define service  {
        name                                    test
        #1为开启报警信息
        notifications_enabled                   0
        #重新发送报警信息的间隔
        notification_interval                   5
        notification_options                    w,u,c,
        #事件处理开启
        event_handler_enabled                   1
        #打开抖动感知
        flap_detection_enabled                  1
        #发送通知的时间段
        notification_period                     24x7
        #检查时间段
        check_period                            24x7
        #每一次检测的间隔时间
        check_interval                          1
        #如果宕机再次检查的间隔时间
        retry_interval                          1
        #检测次数,如果2次都是宕机的话 就报警
        max_check_attempts                      2
        active_checks_enabled                   1
        passive_checks_enabled                  0
        #处理性能数据
        process_perf_data                       1
        #主机与服务的刷新检测 0为关闭
        check_freshness                         0
        #一天刷新检测一次，以防止检测结果不是实时的
        freshness_threshold                     86400
        #0为不注册，意思是这个作为模板
        register                                0
        }
[root@Nagios etc]# vi objects/templates/contacts.cfg
#联系人
define contact{
        #用户名称
        contact_name                    nagios
        #引用模板
        use                             tao
        #别名
        alias                           Nagios Admin
        #发送邮箱
        email                           [email protected]
        }
#联系人组
define contactgroup{
        #组名称
        contactgroup_name       admins
        #组别名
        alias                   Nagios Administrators
        #组用户成员
        members                 nagios
        }

5）添加监控主机

最好使用被监控机IP为名称、比如:被监控服务器为192.168.0.83 [后期服务器多的时候、容易维护]

这里为了省事、一台服务器监控多种服务。大家测试的时候、可以添加多个服务器监控不同服务。

[root@Nagios etc]# vi objects/hosts/192.168.0.83.cfg
#监控主机
define host {
                host_name                           192.168.0.83
                address                             192.168.0.83
                use                                 linux-host
}
#监控SSH
define service  {
                service_description                 check_ssh
                check_command                       check_ssh!-p 22
                host_name                           192.168.0.83
                use                                 linux-service
                register                            1
}
#监控登陆用户
define service  {
                service_description                 check_users
                check_command                       check_nrpe!check_users
                host_name                           192.168.0.83
                use                                 linux-service
                register                            1
}
#监控mysql [需要在被监控配置、下面有配置说明]
define service  {
                service_description                 check_mysql
                check_command                       check_mysql
                host_name                           192.168.0.83
                use                                 linux-service
                register                            1
}
#监控交换空间
define service  {
                service_description                 check_swap
                check_command                       check_nrpe!check_swap
                host_name                           192.168.0.83
                use                                 linux-service
                register                            1
}
#监控磁盘
define service  {
                service_description                 check_disk
                check_command                       check_nrpe!check_disk
                host_name                           192.168.0.83
                use                                 linux-service
                register                            1
}
#监控HTTP
define service  {
                service_description                 check_http
                check_command                       check_http!-p 80
                host_name                           192.168.0.83
                use                                 linux-service
                register                            1
}
#监控负载
define service  {
                service_description                 check_load
                check_command                       check_nrpe!check_load
                host_name                           192.168.0.83
                use                                 linux-service
                register                         
}

6）重启启动nagios、登陆WEB查看

网上很多人说配置后，执行命令检查是否有错误。个人感觉完全没必要、因为启动的时候Nagios默认会自动检查配置、如果有错误Nagios会提示。

[root@Nagios etc]# service nagios restart

——测试

1）在客户端 登陆nagios

注意：监控MySQL需要在被监控端配置如下：

1）客户端连接mysql添加nagios用户

mysql> create database nagios;
Query OK, 1 row affected (0.00 sec)
mysql> grant select on nagios.* to nagios@'192.168.1.18' identified by 'nagios';
Query OK, 0 rows affected (0.11 sec)
mysql> flush privileges;
Query OK, 0 rows affected (0.00 sec)
mysql> quit

2）Nagios服务器端添加mysql监控

[root@Nagios nrpe-2.15]# vi /usr/local/nagios/etc/objects/templates/commands.cfg
# 'check_mysql' command definition
define command{
        command_name    check_mysql
        command_line    $USER1$/check_nrpe -H $HOSTADDRESS$ -u nagios -d nagios -p nagios
        }

——安装msmtp

1）下载安装msmtp

[root@Nagios Linux]# wget http://jaist.dl.sourceforge.net/project/msmtp/msmtp/1.4.31/msmtp-1.4.31.tar.bz2
[root@Nagios Linux]# tar fvx msmtp-1.4.31.tar.bz2
[root@Nagios Linux]# cd msmtp-1.4.31
[root@Nagios msmtp-1.4.31]# ./configure --prefix=/usr/local/msmtp
[root@Nagios msmtp-1.4.31]# make && make install
[root@Nagios msmtp-1.4.31]# cd /usr/local/msmtp/

2）配置msmtp

[root@Nagios msmtp]# mkdir etc
[root@Nagios msmtp]# cd etc/
[root@Nagios etc]# vi msmtprc
account default
logfile /usr/local/msmtp/msmtp.log
host smtp.163.com
from [email protected]
auth login
user [email protected]
#邮箱密码
password xxxxxx

3）安装mutt

[root@Nagios etc]# yum install mutt -y

4）配置mutt

[root@Nagios etc]# vi /etc/Muttrc
set sendmail="/usr/local/msmtp/bin/msmtp"
set use_from=yes
set realname="YingTao"
set [email protected]
set envelope_from=yes
set editor="vim"
set record="/usr/local/msmtp/etc/sent"

5）Nagios默认使用sendmail发送邮件、只需要把 /bin/mail 改为 /usr/bin/mutt即可。

[root@Nagios etc]# vi objects/templates/commands.cfg
# 'notify-host-by-email' command definition
define command{
        command_name    notify-host-by-email
        command_line    /usr/bin/printf "%b" "***** Nagios *****\n\nNotification Type: $NOTIFICATIONTYPE$\nHost: $HOSTNAME$\nState: $HOSTSTATE$\nAddress: $HOSTADDRESS$\nInfo: $HOSTOUTPUT$\n\nDate/Time: $LONGDATETIME$\n" | /usr/bin/mutt -s "** $NOTIFICATIONTYPE$ Host Alert: $HOSTNAME$ is $HOSTSTATE$ **" $CONTACTEMAIL$
        }
# 'notify-service-by-email' command definition
define command{
        command_name    notify-service-by-email
        command_line    /usr/bin/printf "%b" "***** Nagios *****\n\nNotification Type: $NOTIFICATIONTYPE$\n\nService: $SERVICEDESC$\nHost: $HOSTALIAS$\nAddress: $HOSTADDRESS$\nState: $SERVICESTATE$\n\nDate/Time: $LONGDATETIME$\n\nAdditional Info:\n\n$SERVICEOUTPUT$\n" | /usr/bin/mutt -s "** $NOTIFICATIONTYPE$ Service Alert: $HOSTALIAS$/$SERVICEDESC$ is $SERVICESTATE$ **" $CONTACTEMAIL$
        }

——测试能否通过邮箱报警

1）在被监控端关闭mysql

[root@CentOS ~]# /etc/init.d/mysqld stop
Shutting down MySQL. SUCCESS!
[root@CentOS ~]# netstat -antup |grep 3306

2）登陆WEB Nagios查看MySQL状态

3）在服务端查看日志 [默认日志路径为/usr/local/nagios/var/]

[root@Nagios ~]# cd /usr/local/nagios/var/
[root@Nagios var]# tail -f nagios.log
#检查五次、如果五次服务还是无法检测到服务是正常的，则发邮件通知。
[1388002399] SERVICE ALERT: 192.168.0.83;check_mysql;CRITICAL;SOFT;1;Can't connect to MySQL server on '192.168.0.83' (111)
[1388002459] SERVICE ALERT: 192.168.0.83;check_mysql;CRITICAL;SOFT;2;Can't connect to MySQL server on '192.168.0.83' (111)
[1388002519] SERVICE ALERT: 192.168.0.83;check_mysql;CRITICAL;SOFT;3;Can't connect to MySQL server on '192.168.0.83' (111)
[1388002579] SERVICE ALERT: 192.168.0.83;check_mysql;CRITICAL;SOFT;4;Can't connect to MySQL server on '192.168.0.83' (111)
[1388002639] SERVICE ALERT: 192.168.0.83;check_mysql;CRITICAL;HARD;5;Can't connect to MySQL server on '192.168.0.83' (111)
[1388002639] SERVICE NOTIFICATION: nagios;192.168.0.83;check_mysql;CRITICAL;notify-service-by-email;Can't connect to MySQL server on '192.168.0.83' (111)

4）登陆邮箱查看是否收到邮件 [由于是虚拟机时间没有调整、和现实时间有差别]

5）重新启动MySQL

[root@CentOS ~]# /etc/init.d/mysqld start
Starting MySQL.. SUCCESS!
[root@CentOS ~]# netstat -antup |grep 3306
tcp        0      0 0.0.0.0:3306           0.0.0.0:*            LISTEN       51040/mysqld

6）检测服务恢复正常后，是否收到邮件通知