nagios批量添加监控

工作中往往需要对新上线的机器进行监控，如果对100台新机器手动添加监控的话真的是件体力活。提高工作效率的办法就是写脚本自动批量添加。本文将详细阐述nagios批量添加监控。
首先对要添加监控的机器分组，以5台机器为例，建立一个host_service列表，列表以空格隔开。第一列是功能分组，说明机器的主要功能；第二列是ip；第三列及后序列是要监控的服务。具体见下表所示：
cat nag_host_serv.txt
db 192.168.151.141 load cpu_idle disk disk_io ssh mysql
web 192.168.151.40 load cpu_idle disk disk_io ssh http
ad 192.168.151.2 load cpu_idle disk disk_io ssh
ad 192.168.151.23 load cpu_idle disk disk_io ssh
mcache 192.168.151.138 cpu_idle disk_io memcache_hits
接下来是编写监控脚本，在写脚本之前修改下templates.cfg这个文件，加上一些自己需要的东西。
more /usr/local/nagios/etc/objects/templates.cfg
#monitor  for all etnet linux hosts
define host{
        name                            etnet-host
        use                               generic-host
        check_period                   24x7
        check_interval                  5
        retry_interval                   1
        max_check_attempts        10
        check_command              check-host-alive
        notification_period             workhours
        notification_interval            120
        notification_options            d,u,r
        contact_groups                 admins
        register                           0
        }
#monitor for all etnet services
define service{
        name                            etnet-service
        use                               generic-service
        check_period                   24x7
        check_interval                  5
        retry_interval                   1
        max_check_attempts        10
        notification_period             workhours
        notification_interval           120
        notification_options            w,u,c,r,f
        contact_groups                admins
        register                           0
        }
以上是添加的一些主机模板和services模板，将模板的名字定义为自己喜欢的名字如etnet-host,etnet-service。不过在模板中要引用默认的generic-host,generic-service。
接下来要修改下command.cfg文件，添加一个check_nrpe命令，因为要通过nrpe监控远程机器的
tail -4 commands.cfg
define command{
    command_name check_nrpe
    command_line $USER1$/check_nrpe -H $HOSTADDRESS$ -c $ARG1$
}
注意这里的变量前后都要加$$，否则会监控不到服务的。
现在来监控服务吧，nrpe是C/S架构，所以先要配置下nrpe的服务端也就是被监控的机器。
安装nagios-plugin和nrpe在http://blog.itpub.net/27181165/viewspace-775807/中已经介绍过了，在此不介绍了，下面来说下nrpe的配置
cat etc/nrpe.cfg |grep -v \#|sed '/^$/d'
log_facility=daemon
pid_file=/var/run/nrpe.pid
server_port=5666
nrpe_user=nagios
nrpe_group=nagios
allowed_hosts=127.0.0.1,192.168.151.133
dont_blame_nrpe=0
debug=0
command_timeout=60
connection_timeout=300
command[check_users]=/usr/local/nagios/libexec/check_users -w 5 -c 10
command[check_load]=/usr/local/nagios/libexec/check_load -w 15,10,5 -c 30,25,20
command[check_disk]=/usr/local/nagios/libexec/check_disk -w 20% -c 10% -p /dev/mapper/VolGroup02-LogVol00
command[check_zombie_procs]=/usr/local/nagios/libexec/check_procs -w 5 -c 10 -s Z
command[check_total_procs]=/usr/local/nagios/libexec/check_procs -w 150 -c 200
command[check_ssh]=/usr/local/nagios/libexec/check_ssh -H 192.168.151.23 -p 22 -t 10
command[check_cpu_idle]=/usr/local/nagios/libexec/check_cpu_idle
command[check_disk_io]=/usr/local/nagios/libexec/check_disk_io
allowed_hosts允许被谁监控，command监控哪些服务。在nagios libexec下有很多监控插件，如果不够用可以自定义插件，这个以后介绍。
现在开启nrpe进程就可以利用nrpe来收集服务信息了。nrpe可以加入xinetd启动也可以写脚本启动。下面是一个nrpe启动脚本是网友提供的直接拿来用了。
[root@localhost nagios]# cat /etc/init.d/nrpe
#!/bin/sh
#
# Source function library
if [ -f /etc/rc.d/init.d/functions ]; then
. /etc/rc.d/init.d/functions
elif [ -f /etc/init.d/functions ]; then
. /etc/init.d/functions
elif [ -f /etc/rc.d/functions ]; then
. /etc/rc.d/functions
fi

# Source networking configuration.
. /etc/sysconfig/network

# Check that networking is up.
[ ${NETWORKING} = "no" ] && exit 0

NrpeBin=/usr/local/nagios/bin/nrpe
NrpeCfg=/usr/local/nagios/etc/nrpe.cfg
LockFile=/var/lock/subsys/nrpe

# See how we were called.
case "$1" in
  start)
 # Start daemons.
 echo -n "Starting nrpe: "
 daemon $NrpeBin -c $NrpeCfg -d
 echo
 touch $LockFile
 ;;
  stop)
 # Stop daemons.
 echo -n "Shutting down nrpe: "
 killproc nrpe
 echo
 rm -f $LockFile
 ;;
  restart)
 $0 stop
 $0 start
 ;;
  status)
 status nrpe
 ;;
  *)
 echo "Usage: nrpe {start|stop|restart|status}"
 exit 1
esac
exit 0
好不容易进入正题，上批量添加脚本吧
[root@localhost scripts]# cat nag_host_serv.sh
#!/bin/bash
#Author: Andy
#Time: 20140307
NAGIOS_OBJ=/usr/local/nagios/etc/objects
NAGIOS_CONF=/usr/local/nagios/etc
function add_host_serv()
{
while read groups ip services
do
    #monitor linux host,etnet-host must be defined in templates.cfg
    #添加主机
    cat >>${NAGIOS_OBJ}/${groups}.cfg<     #monitor host ${ip}
    define host{
      use  etnet-host
      host_name ${groups}-${ip}
      alias     ${ip}
      address   ${ip}
    }
    EOF
#添加服务
    #monitor  services,etnet-service must be defined in templates.cfg
    for ser in `echo ${services}`;do
        #monitor linux  services
        cat >>${NAGIOS_OBJ}/${groups}.cfg<         #monitor service ${ser}
        define service{
          use    etnet-service
          host_name  ${groups}-${ip}
          service_description check_${ser}
          check_command  check_nrpe!check_${ser}
        }
        EOF
    done
done< nag_host_serv.txt
}
#在nagios.cfg中添加监控文件
function config_edit()
{
#append cfg files to nagios.cfg
for group in `cat nag_host_serv.txt|cut -d " " -f 1|uniq`;do
    resul=`cat ${NAGIOS_CONF}/nagios.cfg|grep -Ew "${group}.cfg"`
    if [ -z "${resul}" ];then
        sed -i "/templates.cfg/a cfg_file=${NAGIOS_OBJ}/${group}.cfg" ${NAGIOS_CONF}/nagios.cfg
      fi
done
}
#==============================
add_host_serv
config_edit

来自 “ ITPUB博客 ” ，链接：http://blog.itpub.net/27181165/viewspace-1107510/，如需转载，请注明出处，否则将追究法律责任。

转载于:http://blog.itpub.net/27181165/viewspace-1107510/