Debian 系统安装 Nagios 服务器监控端

1. 安装
   apt-get update
   apt-get install nagios* perl
   apt-get install --no-install-recommends pnp4nagios
   apt-get install apache2 apache2-utils php5 php-pear

2. 修改npcd设置
   # vim /etc/default/npcd
   Run="yes"
   # service npcd start

3. 添加process_perfdata.pl执行权限
   chmod +x /usr/lib/pnp4nagios/libexec/process_perfdata.pl
4. 修改commands.cfg设置(注释旧命令)
   vi /etc/nagios3/commands.cfg

   # '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" >> /var/lib/nagios3/host-perfdata.out
      command_line   /usr/bin/perl /usr/lib/pnp4nagios/libexec/process_perfdata.pl
      }
   
   # '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" >> /var/lib/nagios3/service-perfdata.out
      command_line   /usr/bin/perl /usr/lib/pnp4nagios/libexec/process_perfdata.pl
      }

   commands.cfg Code

5. 修改nagios.cfg配置
   vi /etc/nagios3/nagios.cfg 修改以下3行配置
   process_performance_data=1
   host_perfdata_command=process-host-perfdata
   service_perfdata_command=process-service-perfdata
   修改check_external_commands=1 (未修改可能导致web网站无法Re-schedule监控项)
   修改enable_flap_detection=0 (虽然文档里说默认是0，但实际为1.改为0之后就解决了flapping state)
6. 修改services_nagios2.cfg配置
   vi /etc/nagios3/conf.d/services_nagios2.cfg
   notification_interval 1
   vi /etc/nagios3/conf.d/generic-service_nagios2.cfg
   notification_interval 1

7. 删除install.php
   # cd /usr/share/pnp4nagios/html
   # mv install.php install.php.bak

8. Nagios插件目录: /usr/lib/nagios/plugins/
9. 添加pnp4nagios插件
   vi /etc/nagios3/conf.d/pnp4nagos.cfg 追加如下配置

   define host {
           name       host-pnp
           action_url /pnp4nagios/index.php/graph?host=$HOSTNAME$'class='tips'rel='/pnp4nagios/index.php/popup?host=$HOSTNAME$&srv=_HOST_
           register
           process_perf_data
   }
   
   define service {
           name       srv-pnp
           action_url /pnp4nagios/index.php/graph?host=$HOSTNAME$&srv=$SERVICEDESC$'class='tips'rel='/pnp4nagios/index.php/popup?host=$HOSTNAME$&srv=$SERVICEDESC$
           register
           process_perf_data
   }

   Code

10. 默认是没有监控内存的，若需要监控复制check_mem.sh文件到插件目录，再添加相关配置文件
    添加自定义执行命令
    vi /etc/nagios3/conf.d/custom_commond.cfg

    define command{
            command_name        check_mem
            command_line        $USER1$/check_mem.sh -w $ARG1$ -c $ARG2$
            }

    Code

    添加本机的check_mem服务
    vi /etc/nagios3/conf.d/localhost_nagios2.cfg  添加如下配置

    define service{
            use                             local-service,srv-pnp
            host_name                       localhost
            service_description             check_mem
            check_command                   check_mem!!
            }

    Code

11. 监控服务器网卡流量
    apt-get install snmpd snmp-mibs-downloader
    vi /etc/snmp/snmpd.conf（可备份snmpd.conf,修改下面的localhost－IP为服务器IP，保存此文件即可）

    com2sec notConfigUser 127.0.0.1 public
    com2sec notConfigUser localhost-IP public 
    
    group notConfigGroup v1 notConfigUser
    group notConfigGroup v2c notConfigUser 
    
    view systemview included .1.3.6.1.2.1.
    view systemview included .1.3.6.1.2.1.
    view systemview included .1.3.6.1.2.1.25.1.
    view all included . 
    
    access notConfigGroup "" any noauth exact all none none 

    Code

    重启snmpd服务
    下载check_traffic.sh到插件目录
    cd /usr/lib/nagios/plugins/
    测试执行
    ./check_traffic.sh -V 2c -C public -H your_ip -I 2 -w 1200,1500 -c 1700,1800 -K -B
    # vi /etc/nagios3/conf.d/custom_commond.cfg  追加

    define command{
            command_name    check_traffic
            command_line    $USER1$/check_traffic.sh -V 2c -C public -H $HOSTADDRESS$ -I $ARG1$ -w $ARG2$ -c $ARG3$ -M -b
    }

    Code

12. 当服务停止时重新监控失败，运行以下2行命令
    # dpkg-statoverride --update --add nagios www-data 2710 /var/lib/nagios3/rw
    # dpkg-statoverride --update --add nagios www-data 751 /var/lib/nagios3

13. 配置发送邮件功能
    apt-get install ssmtp   (备用：apt-get install sendmail-bin  sendmail)
    修改ssmpt.conf文件配置
    # vi /etc/ssmtp/ssmtp.conf  追加Google邮箱配置方式(勿开启2步验证)

    AuthUser=NagiosAdmin
    AuthPass=PassWord
    FromLineOverride=YES
    mailhub=smtp.gmail.com:
    UseSTARTTLS=YES

    Code

    service sendmail stop
    chkconfig sendmail off
    cd /usr/sbin
    mv sendmail sendmail.bak
    ln -s /usr/sbin/ssmtp /usr/sbin/sendmail
    测试发邮件即可

14. 添加被监控机需要注意
    监控其他主机，需要添加check_nrpe命令，但在Debian系统中，添加check_nrpe命令会提示重复，但是却找不到其他地方有配置。
    所以需要将check_nrpe改成其他名

    define command{
            command_name custom_check_nrpe
            command_line $USER1$/check_nrpe -H $HOSTADDRESS$ -c $ARG1$
            }

    Code

    举例监控客户机的CPU情况
    先添加主机
    # vi /etc/nagios3/conf.d/hosts.cfg

    define host{
        use                             generic-host               ; Inherit default values from a template
        host_name                       Dow1_Server                  ; The name we're giving to this server
        alias                           DriverServer               ; A longer name for the server
        address                         10.10.0.32            ; IP address of Remote Linux host
    }

    Code

    添加监控服务项，注意使用的命令是自定义的nrpe
    # vi /etc/nagios3/conf.d/custom_services.cfg

    define service{
            use                     generic-service
            host_name               Dow1_Server_198.27.75.
            service_description     CPU Load
            check_command           custom_check_nrpe!check_load
            }

    Code

    iptables -A INPUT -p tcp -m tcp --dport 5666 -j ACCEPT  
    service iptables save
    service iptables restart