#!/bin/bash

Date=`echo $(date +%Y/-%m/-%d/ %H:%M:%S)`HostName=`hostname`ip=`ifconfig eth0 | grep "inet addr" | cut -f 2 -d ":" | cut -f 1 -d " "`ServerInfo=`echo -e "--------$Date--------/n服務器：$HostName IP：$IP"`

#刪除5天前的監控日志LOGPWD=/var/log/monitorLOGDATE=`echo $(date -d -5day +%Y%m%d)`LOGGREP=`ls $LOGPWD | grep -c "$LOGDATE"`if [ $LOGGREP -gt 0 ]then rm -fr $LOGPWD/*$LOGDATE.logfi

echo -e "$ServerInfo/nuptime/n`uptime`/nfree -m/n`free -m`" > $LOGPWD/monitor.log#監控cpu負載PhysicalCpu=`grep 'physical id' /PRoc/cpuinfo | sort -u | wc -l`CoreCpu=`grep 'core id' /proc/cpuinfo | sort -u | wc -l`count_cores=`echo "$PhysicalCpu*$CoreCpu" | bc`count_uptime=`uptime |wc -w`AverageLoad=`uptime | awk '{print $'$count_uptime'}'`AverageInt=`echo $AverageLoad | cut -f 1 -d "."`if [ $AverageInt -gt $count_cores ]then echo -e "$ServerInfo/n15分鐘的負載為$AverageLoad，核心數$count_cores，超過cpu核心數，請處理！" >> $LOGPWD/cpu_status_$(date +%Y%m%d).log echo -e "15分鐘的負載為$AverageLoad，核心數$count_cores，超過cpu核心數，請處理！" >> $LOGPWD/monitor.logelse echo -e "$ServerInfo/n15分鐘的負載為$AverageLoad，核心數$count_cores，負載正常。" >> $LOGPWD/cpu_status_$(date +%Y%m%d).log echo -e "15分鐘的負載為$AverageLoad，核心數$count_cores，負載正常。" >> $LOGPWD/monitor.logfi #監控內存使用率MemTotal=`free -m | grep Mem | awk '{print $2}'`MemFree=`free -m | grep Mem | awk '{print $4}'`MemRate=`echo "100-$MemFree*100/$MemTotal" | bc`if [ $MemRate -gt 80 ]then echo -e "$ServerInfo/n內存使用率$MemRate%，大于80%，請處理。" >> $LOGPWD/mem_status_$(date +%Y%m%d).log echo -e "內存使用率$MemRate%，大于80%，請處理。" >> $LOGPWD/monitor.logelse echo -e "$ServerInfo/n內存使用率$MemRate%，小于等于80%，內存負載正常。" >> $LOGPWD/mem_status_$(date +%Y%m%d).log echo -e "內存使用率$MemRate%，小于等于80%，內存負載正常。" >> $LOGPWD/monitor.logfi

if [ $AverageInt -gt $count_cores ]||[ $MemRate -gt 80 ]then cat $LOGPWD/monitor.log | mail -s "$HostName服務器負載監控報警"xxx@xxx.xxxfi