服务器健康状态监控，包括监控内存、硬盘、cpu、进程等，从而形成状态报告。
#!/bin/bash
#
#内存最大使用比率
mem_quota=80
#硬盘最大使用比率
hd_quota=80
#cpu最大使用比率
cpu_quota=80
#获取cpu状态的时间间隔
time_gap=60
#每10分钟形成报告
runtime_gap=600
#内存监控函数
watch_memory()
{
mem_total=`cat /proc/meminfo | grep MemTotal | awk '{print $2}'`
mem_free=`cat /proc/meminfo | grep MemFree | awk '{print $2}'`
mem_usage=$((100-mem_free*100/mem_total))
if [ $mem_usage -gt $mem_quota ];then
mem_message="the memory usage is $mem_usage%!!!"
return 1
else
return 0
fi
}
#硬盘监控函数
watch_hd()
{
hd_usage=`df | grep /dev/sda2 | awk '{print $5}' | sed 's/%//g'`
if [ $hd_usage -gt $hd_quota ];then
hd_message="the hard disk usage is $hd_usage%!!!"
return 1
else
return 0
fi
}
#函数读取/proc/stat文件，做数据准备工作，从而获得cpu从启动到现在的忙碌时间
get_cpu_info()
{
cat /proc/stat | grep -i "^cpu[0-9]\+" | awk '{used+=$2+$3+$4; unused+=$5+$6+$7+$8} END{print used,unused}'
}
#cpu监控函数
watch_cpu()
{
time_point_1=`get_cpu_info`
sleep $time_gap
time_point_2=`get_cpu_info`
cpu_usage=`return $time_point_1 $time_point_2 | awk '{used=$3-$1;total+=$3+$4-$1-$2;print used*100/total}'`
if [ $cpu_usage > $cpu_quota ];then
cpu_message="the cpu usage is over $cpu_usage!!!"
echo $cpu_usage
return 1
else
echo $cpu_usage
return 0
fi
}
#获得最近忙碌的进程
proc_cpu_top10()
{
proc_busiest=`ps aux | sort -nk 3r | head -10`
}
while true;
do
report="" #报告内容
if [ `watch_memory` -eq 1 ];then #内存监控
report=$report'\n'$mem_message
fi
if [ `watch_hd` -eq 1 ];then #硬盘监控
report=$report'\n'$hd_message
fi
if [ `watch_cpu` -eq 1 ];then
report=$report'\n'$cpu_message
proc_cpu_top10
report=$report'\n'$proc_busiest
fi
if [ -n $report ];then
echo sendmessage phonenumber report
fi
sleep $`runtime_gap-time_gap`
done
