Linux伺服器硬體運行狀態及故障寄件提醒的監控指令碼分享_linux shell

監控硬體健全狀態

shell 監控cpu，memory，load average，記錄到log，當負載壓力時，發電郵通知管理員。
原理：
1.擷取cpu，memory，load average的數值
2.判斷數值是否超過自訂的範圍，例如（CPU>90%，Memory<10%，load average>2）
3.如數值超過範圍，發送電郵通知管理員。發送有時間間隔，每小時只會發送一次。
4.將數值寫入log。
5.設定crontab 每30秒運行一次。

ServerMonitor.sh

#!/bin/bash  # 系統監控,記錄cpu、memory、load average,當超過規定數值時發電郵通知管理員  # *** config start ***  # 目前的目錄路徑 ROOT=$(cd "$(dirname "$0")"; pwd)  # 當前伺服器名 HOST=$(hostname)  # log 檔案路徑 CPU_LOG="${ROOT}/logs/cpu.log" MEM_LOG="${ROOT}/logs/mem.log" LOAD_LOG="${ROOT}/logs/load.log"  # 通知電郵列表 NOTICE_EMAIL='admin@admin.com'  # cpu,memory,load average 記錄上一次發送通知電郵時間 CPU_REMARK='/tmp/servermonitor_cpu.remark' MEM_REMARK='/tmp/servermonitor_mem.remark' LOAD_REMARK='/tmp/servermonitor_loadaverage.remark'  # 發通知電郵間隔時間 REMARK_EXPIRE=3600 NOW=$(date +%s)  # *** config end ***   # *** function start ***  # 擷取CPU佔用 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 ${CPU_REMARK})    # 檢查CPU佔用是否超過90%   if [ "$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)" > "$CPU_REMARK"   fi }  # 擷取記憶體使用量情況 function GetMem() {   mem=$(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 ${MEM_REMARK})    # 檢查記憶體佔用是否超過90%   if [ "$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)" > "$MEM_REMARK"   fi }  # 擷取load average function GetLoad() {   load=$(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 ${LOAD_REMARK})    # 檢查是否負載是否有壓力   if [ "$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 }  # 擷取上一次發送電郵時間 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 

監控網站是否異常
shell 監控網站是否異常的指令碼，如有異常自動發電郵通知管理員。
流程：
1.檢查網站返回的http_code是否等於200，如不是200視為異常。
2.檢查網站的訪問時間，超過MAXLOADTIME（10秒）視為異常。
3.發送通知電郵後，在/tmp/monitor_load.remark記錄發送時間，在一小時內不重複發送，如一小時後則清空/tmp/monitor_load.remark。

#!/bin/bash  SITES=("http://web01.example.com" "http://web02.example.com") # 要監控的網站 NOTICE_EMAIL='me@example.com'                 # 管理員電郵 MAXLOADTIME=10                        # 訪問逾時時間設定 REMARKFILE='/tmp/monitor_load.remark'             # 記錄時否發送過通知電郵，如發送過則一小時內不再發送 ISSEND=0                           # 是否有發送電郵 EXPIRE=3600                          # 每次發送電郵的間隔秒數 NOW=$(date +%s)  if [ -f "$REMARKFILE" ] && [ -s "$REMARKFILE" ]; then   REMARK=$(cat $REMARKFILE)      # 刪除到期的電郵發送時間記錄檔案   if [ $(( $NOW - $REMARK )) -gt "$EXPIRE" ]; then     rm -f ${REMARKFILE}     REMARK=""   fi else   REMARK="" fi  # 迴圈判斷每個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 ${NOTICE_EMAIL}         ISSEND=1       fi     fi   fi  done  # 發送電郵後記錄發送時間 if [ "$ISSEND" = "1" ]; then   echo "$(date +%s)" > $REMARKFILE fi  exit 0