shell 監控cpu,memory,load average

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.獲取cpu，memory，load average的數值

2.判斷數值是否超過自定義的範圍，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.設置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 ***

# 當前目錄路徑
ROOT=$(cd "$(dirname "$0")"; pwd)

# 當前服務器名
HOST=$(hostname)

# log 文件路徑
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 ***

# 獲取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
}

# 獲取內存使用狀況
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})

    # 檢查內存佔用是否超過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
}

# 獲取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
}

# 獲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

crontab

* * * * * /home/xxxx/ServerMonitor.sh
* * * * * sleep 30; /home/xxxx/ServerMonitor.sh