nagios CPU温度检测插件
http://hi.baidu.com/icanwen/item/e6ed673c3f79e7302f20c403最近公司的机房空调经常的自动关闭！使机房温度过热引起设备故障！因而想到用nagios检测CPU温度！当温度达到一定上限时！自动发送SMS到手机。在dell R200测试通过。参照了网上 很多高手的资料在此谢过！
nagios 主程序服务服务定制设置如下：
define service{
use generic-service ; Name of service template to use
host_name fileserver
service_description cpu temperature
check_command check_nrpe!check_cpu_temp
}
被监控主机服务定制如下：
vi /usr/local/nagios/etc/nrpe.cfg
#解释：用sensors检测cpu的温度当cpu温度到达35度时报警，到达40度时处于紧急状态
command=/usr/local/nagios/libexec/check_cputemp.sh -m sensors -w 35 -c 40
不可以上传附件 插件代码直接贴到这里了：）
#!/bin/sh
######################check_cputemp#######################
#version: 1.0
#Author : xiaoyong wen
#date : May 2011
#Licence GPLv2
#INSTALLATION
#the script need to install lm_sensors
#sensors's output need like below format
#########################################
#coretemp-isa-0000 #
#Adapter: ISA adapter #
#Core 0: +27°C(high = +85°C) #
#
#coretemp-isa-0001 #
#Adapter: ISA adapter #
#Core 1: +25°C(high = +85°C) #
#########################################
#you can use NRPE to define service in nagios
#check_nrpe!check_cputemp.sh
######my taobao shop http://ujjj.taobao.com######just a AD :)####
# Plugin return statements
STATE_OK=0
STATE_WARNING=1
STATE_CRITICAL=2
STATE_UNKNOWN=3
print_help_msg(){
$Echo "Usage: $0 -h to get help."
}
print_full_help_msg(){
$Echo "Usage:"
$Echo "$0 [ -v ] -m sensors -w cpuT -c cpuT"
$Echo "Sepicify the method to use the temperature data sensors."
$Echo "And the corresponding Critical value must greater than Warning value."
$Echo "Example:"
$Echo "${0} -m sensors -w 50 -c 55"
}
print_err_msg(){
$Echo "Error."
print_full_help_msg
}
to_debug(){
if [ "$Debug" = "true" ]; then
$Echo "$*" >> /var/log/check_sys_temperature.log.$$ 2>&1
fi
}
unset LANG
Echo="echo -e"
if [ $# -lt 1 ]; then
print_help_msg
exit 3
else
while getopts :vhm:w:c: OPTION
do
case $OPTION
in
v)
#$Echo "Verbose mode."
Debug=true
;;
m)
method=$OPTARG
;;
w)
WARNING=$OPTARG
;;
c)
CRITICAL=$OPTARG ;;
h)
print_full_help_msg
exit 3
;;
?)
$Echo "Error: Illegal Option."
print_help_msg
exit 3
;;
esac
done
if [ "$method" = "sensors" ]; then
use_sensors="true"
to_debug use_sensors
else
$Echo "Error. Must to sepcify the method to use sensors."
print_full_help_msg
exit 3
fi
to_debug All Valuesare \" Warning: "$WARNING" and Critical: "$CRITICAL" \".
fi
#########lm_sensors##################
if [ "$use_sensors" = "true" ]; then
sensorsCheckOut=`which sensors 2>&1`
if [ $? -ne 0 ];then
echo $sensorsCheckOut
echo Maybe you need to check your sensors.
exit 3
fi
to_debug Use $sensorsCheckOut to check system temperature
TEMP1=`sensors | head -3 | tail -1 | gawk '{print $3}' | grep -o `
TEMP2=`sensors | head -7 | tail -1 | gawk '{print $3}' | grep -o `
SUM=$(( $TEMP1 + $TEMP2 ))
TEMP=$(($SUM/2))
if [ -z "$TEMP" ] ; then
$Echo "No Data been get here. Please confirm your ARGS and re-check it with Verbose mode, then to check the log."
exit 3
fi
to_debug temperature data is $TEMP
else
$Echo "Error. Must to sepcify the method to use sensors"
print_full_help_msg
exit 3
fi
######### Comparaison with the warnings and criticals thresholds given by user############
CPU_TEMP=$TEMP
#if [ "$WARNING" != "0" ] || [ "$CRITICAL" != "0" ]; then
if [ "$CPU_TEMP" -gt "$CRITICAL" ]&& [ "$CRITICAL" != "0" ]; then
STATE="$STATE_CRITICAL"
STATE_MESSAGE="CRITICAL"
to_debug $STATE , Message is $STATE_MESSAGE
elif [ "$CPU_TEMP" -gt "$WARNING" ] && [ "$WARNING" != "0" ]; then
STATE="$STATE_WARNING"
STATE_MESSAGE="WARNING"
to_debug $STATE , Message is $STATE_MESSAGE
else
STATE="$STATE_OK"
STATE_MESSAGE="OK"
to_debug $STATE , Message is $STATE_MESSAGE
fi
echo "The TEMPERATURE "$STATE_MESSAGE" "-" The CPU's Temperature is "$CPU_TEMP" degree"
exit $STATE
页:
[1]