Linux服务器硬件运行状态及故障邮件提醒的监控脚本分享

监控硬件运行状况

shell 监控cpu，memory，load average，记录到log，当负载压力时，发电邮通知管理员。
原理：
1.获取cpu，memory，load average的数值
2.判断数值是否超过自定义的范围，例如（cpu>90%，memory<10%，load average>2）
3.如数值超过范围，发送电邮通知管理员。发送有时间间隔，每小时只会发送一次。
4.将数值写入log。
5.设置crontab 每30秒运行一次。

servermonitor.sh

#!/bin/bash 
 
# 系统监控,记录cpu、memory、load average,当超过规定数值时发电邮通知管理员 
 
# *** config start *** 
 
# 当前目录路径 
root=$(cd "$(dirname "$0")"; pwd) 
 
# 当前服务器名 
host=$(hostname) 
 
# log 文件路径 
cpu_log="${root}/logs/cpu.log" 
mem_log="${root}/logs/mem.log" 
load_log="${root}/logs/load.log" 
 
# 通知电邮列表 
notice_email='[e-mail]' 
 
# cpu,memory,load average 记录上一次发送通知电邮时间 
cpu_remark='/tmp/servermonitor_cpu.remark' 
mem_remark='/tmp/servermonitor_mem.remark' 
load_remark='/tmp/servermonitor_loadaverage.remark' 
 
# 发通知电邮间隔时间 
remark_expire=3600 
now=$(date +%s) 
 
# *** config end *** 
 
 
# *** function start *** 
 
# 获取cpu占用 
function getcpu() { 
  cpufree=$(vmstat 1 5 |sed -n '3,$p' |awk '{x = x + $15} end {print x/5}' |awk -f. '{print $1}') 
  cpuused=$((100 - $cpufree)) 
  echo $cpuused 
 
  local remark 
  remark=$(getremark ${cpu_remark}) 
 
  # 检查cpu占用是否超过90% 
  if [ "$remark" = "" ] && [ "$cpuused" -gt 90 ]; then 
    echo "subject: ${host} cpu uses more than 90% $(date +%y-%m-%d' '%h:%m:%s)" | sendmail ${notice_email} 
    echo "$(date +%s)" > "$cpu_remark" 
  fi 
} 
 
# 获取内存使用情况 
function getmem() { 
  mem=$(free -m | sed -n '3,3p') 
  used=$(echo $mem | awk -f ' ' '{print $3}') 
  free=$(echo $mem | awk -f ' ' '{print $4}') 
  total=$(($used + $free)) 
  limit=$(($total/10)) 
  echo "${total} ${used} ${free}" 
 
  local remark 
  remark=$(getremark ${mem_remark}) 
 
  # 检查内存占用是否超过90% 
  if [ "$remark" = "" ] && [ "$limit" -gt "$free" ]; then 
    echo "subject: ${host} memory uses more than 90% $(date +%y-%m-%d' '%h:%m:%s)" | sendmail ${notice_email} 
    echo "$(date +%s)" > "$mem_remark" 
  fi 
} 
 
# 获取load average 
function getload() { 
  load=$(uptime | awk -f 'load average: ' '{print $2}') 
  m1=$(echo $load | awk -f ', ' '{print $1}') 
  m5=$(echo $load | awk -f ', ' '{print $2}') 
  m15=$(echo $load | awk -f ', ' '{print $3}') 
  echo "${m1} ${m5} ${m15}" 
 
  m1u=$(echo $m1 | awk -f '.' '{print $1}') 
 
  local remark 
  remark=$(getremark ${load_remark}) 
 
  # 检查是否负载是否有压力 
  if [ "$remark" = "" ] && [ "$m1u" -gt "2" ]; then 
    echo "subject: ${host} load average more than 2 $(date +%y-%m-%d' '%h:%m:%s)" | sendmail ${notice_email} 
    echo "$(date +%s)" > "$load_remark" 
  fi 
} 
 
# 获取上一次发送电邮时间 
function getremark() { 
  local remark 
 
  if [ -f "$1" ] && [ -s "$1" ]; then 
    remark=$(cat $1) 
 
    if [ $(( $now - $remark )) -gt "$remark_expire" ]; then 
      rm -f $1 
      remark="" 
    fi 
  else 
    remark="" 
  fi 
 
  echo $remark 
} 
 
 
# *** function end *** 
 
cpuinfo=$(getcpu) 
meminfo=$(getmem) 
loadinfo=$(getload) 
 
echo "cpu: ${cpuinfo}" >> "${cpu_log}" 
echo "mem: ${meminfo}" >> "${mem_log}" 
echo "load: ${loadinfo}" >> "${load_log}" 
 
exit 0 

监控网站是否异常
shell 监控网站是否异常的脚本，如有异常自动发电邮通知管理员。
流程：
1.检查网站返回的http_code是否等于200，如不是200视为异常。
2.检查网站的访问时间，超过maxloadtime（10秒）视为异常。
3.发送通知电邮后，在/tmp/monitor_load.remark记录发送时间，在一小时内不重复发送，如一小时后则清空/tmp/monitor_load.remark。

#!/bin/bash 
 
sites=("http://web01.example.com" "http://web02.example.com") # 要监控的网站 
notice_email='[e-mail]'                 # 管理员电邮 
maxloadtime=10                        # 访问超时时间设置 
remarkfile='/tmp/monitor_load.remark'             # 记录时否发送过通知电邮，如发送过则一小时内不再发送 
issend=0                           # 是否有发送电邮 
expire=3600                          # 每次发送电邮的间隔秒数 
now=$(date +%s) 
 
if [ -f "$remarkfile" ] && [ -s "$remarkfile" ]; then 
  remark=$(cat $remarkfile) 
   
  # 删除过期的电邮发送时间记录文件 
  if [ $(( $now - $remark )) -gt "$expire" ]; then 
    rm -f ${remarkfile} 
    remark="" 
  fi 
else 
  remark="" 
fi 
 
# 循环判断每个site 
for site in ${sites[*]}; do 
 
  printf "start to load ${site}\n" 
  site_load_time=$(curl -o /dev/null -s -w "time_connect: %{time_connect}\ntime_starttransfer: %{time_starttransfer}\ntime_total: %{time_total}" "${site}") 
  site_access=$(curl -o /dev/null -s -w %{http_code} "${site}") 
  time_total=${site_load_time##*:} 
 
  printf "$(date '+%y-%m-%d %h:%m:%s')\n" 
  printf "site load time\n${site_load_time}\n" 
  printf "site access:${site_access}\n\n" 
 
  # not send 
  if [ "$remark" = "" ]; then 
    # check access 
    if [ "$time_total" = "0.000" ] || [ "$site_access" != "200" ]; then 
      echo "subject: ${site} can access $(date +%y-%m-%d' '%h:%m:%s)" | sendmail ${notice_email} 
      issend=1 
    else 
      # check load time 
      if [ "${time_total%%.*}" -ge ${maxloadtime} ]; then 
        echo "subject: ${site} load time total:${time_total} $(date +%y-%m-%d' '%h:%m:%s)" | sendmail ${notice_email} 
        issend=1 
      fi 
    fi 
  fi 
 
done 
 
# 发送电邮后记录发送时间 
if [ "$issend" = "1" ]; then 
  echo "$(date +%s)" > $remarkfile 
fi 
 
exit 0