Linux服务器硬件运行状态及故障邮件提醒的监控脚本分享

#!/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='admin@admin.com' 
 
# 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 

#!/bin/bash 
 
SITES=("http://web01.example.com" "http://web02.example.com") # 要监控的网站 
NOTICE_EMAIL='me@example.com'                 # 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