!/bin/ksh
# # 首先载入配置文件,如果配置文件不存在,则报错退出 # SOURCE=$HOME/config/config check_source() { if [ -r $SOURCE ]; then . $SOURCE else echo "$(basename $0): Cannot locate the default setting file." exit 1 fi } # # 定义报表头 # report_header() { HOSTIP=$(ifconfig -a | sed -n '2p' |awk '{print $2}') HOSTNAME=$(hostname) USER=`who am i | cut -d " " -f1` cat<<! Hostname: $HOSTNAME Server: $HOSTIP User: $USER Time: $(date +%Y'-'%m'-'%d' '%H':'%M':'%S) SYSTEM CHECK REPORT
=================== ! } #
# 定义日志文件存放的目录和日志文件名,将当前用户目录设置为LOG_PATH # LOG_PATH=$(echo $HOME) LOG_FILE=$LOG_PATH/log`date +%Y%m%d%H%M%S` #
# 备份历史文件 # cd $LOG_PATH test -f log2007* if [ "$?" -eq 0 ];then mv $LOG_PATH/log2007* $LOG_PATH/niyl/ >/dev/null 2>&1 else : fi #define temp directory ,if not exist,create temp directory first.
TEMP_PATH=$LOG_PATH/temp if [ -d $TEMP_PATH ];then : else mkdir $TEMP_PATH fi #
# 载入环境设置 # check_source #
# 输出报表头信息 # report_header >>$LOG_FILE # 检查 CPU的使用情况,这里使用vmstat命令 echo "***************************************** Check CPU *****************************************">>$LOG_FILE vmstat 1 10 | awk '{print $0;if($1 ~ /^[0-9].*/) (totalcpu+=$16);(avecpu=100-totalcpu/10)}; END {print "The average usage of cpu is :"avecpu}' >$TEMP_PATH/cpu_info cat $TEMP_PATH/cpu_info >>$LOG_FILE
cpu_used_pct=`cat $TEMP_PATH/cpu_info | grep "The average usage of cpu is" |awk -F ":" '{print $2}' `
if [ "$cpu_used_pct" -gt "$CPU_VALUE" ] ; then echo "LOG-Warnning:`date +%Y'-'%m'-'%d' '%H':'%M':'%S`, CPU负载超过阀值设置,请检查系统!!">>$LOG_FILE else echo "\t\t\t\t CPU负载正常!!">>$LOG_FILE fi #
# 内存使用监控,包括交换区的使用情况监控 # echo >>$LOG_FILE echo >>$LOG_FILE echo "***************************************** check memory useage *****************************************">>$LOG_FILE cat $TEMP_PATH/cpu_info | awk '{print $0;if($1 ~ /^[0-9].*/) (totalpi+=$6)(totalpo+=$7)};\ END {if(totalpi<10 && totalpo<10) print "\t\t\t\tMemory负载正常!!"; if(totalpi>10 || totalpo>10) print "Memory负载异常,请检查系统!!"} '>>$LOG_FILE # # 检查磁盘空间 # echo >>$LOG_FILE echo >>$LOG_FILE echo "***************************************** check disk space *****************************************">>$LOG_FILE df -k >>$LOG_FILE df -k |grep -v proc |grep -v Filesystem |awk '{x=1*$4}{print $1","$2","$3","$4","$5","$6","$7}'>$TEMP_PATH/disk_info cat $TEMP_PATH/disk_info | grep -v '^#' | while read line
do item1=$(echo $line | awk -F ',' '{print $1}') item2=$(echo $line | awk -F ',' '{print $2}') item3=$(echo $line | awk -F ',' '{print $3}') item4=$(echo $line | awk -F ',' '{print $4}' |awk -F '%' '{print $1}') item5=$(echo $line | awk -F ',' '{print $5}') item6=$(echo $line | awk -F ',' '{print $6}') item7=$(echo $line | awk -F ',' '{print $7}') if [ "$item4" -gt "$DISK_VALUE" ]; then echo "LOG-Warnning: `date +%Y'-'%m'-'%d' '%H':'%M':'%S`, 磁盘$item7\t剩余空间不足,请处理!!" >>$LOG_FILE else echo "\t\t\t\t 磁盘空间$item7\t\t使用正常!!" >>$LOG_FILE fi done #
# 检查磁盘的io进行监控,iostat # echo >>$LOG_FILE echo >>$LOG_FILE echo "***************************************** check iostat *****************************************">>$LOG_FILE iostat 1 3 >>$LOG_FILE #
# 对网络流量进行监控,在这里可以作一个主机列表,对每个主机ping检查网络是否连通。 # echo >>$LOG_FILE echo >>$LOG_FILE echo "***************************************** check netstat *****************************************">>$LOG_FILE netstat -i >>$LOG_FILE #
# 检查主机的告警日志 # echo >>$LOG_FILE echo >>$LOG_FILE echo "***************************************** check system err *****************************************">>$LOG_FILE errpt | head -10 >>$LOG_FILE day=`date +%D |awk -F "/" '{print $1$2}'` errpt | awk '{print $2}' | grep ^$day if [ $? -eq 0 ] ; then echo "LOG-Warnning: `date +%Y'-'%m'-'%d' '%H':'%M':'%S`,The system has found a error today.Please check the error report." >>$LOG_FILE else echo >>$LOG_FILE echo "\t\t\t\t There is no system error report today.System is OK!!" >>$LOG_FILE fi #
# 检查HA的运行是否正常 # echo >>$LOG_FILE echo >>$LOG_FILE echo "***************************************** check HACMP status *****************************************">>$LOG_FILE /usr/es/sbin/cluster/clstat -o > $TEMP_PATH/ha_info lssrc -g cluster >> $TEMP_PATH/ha_info cat $TEMP_PATH/ha_info >>$LOG_FILE echo >>$LOG_FILE cat $TEMP_PATH/ha_info| grep "Node:" |awk -F ':' '{print $2,$3}' | awk '{print $1,$3}' | while read line do node=$(echo $line | awk '{print $1}')"'s" echo $line |grep UP$ >/dev/null if [ "$?" -eq 0 ]; then echo "\t\t\t\t The node $node is OK!!" >>$LOG_FILE else echo "`date +%Y'-'%m'-'%d' '%H':'%M':'%S`,LOG-Warnning: The node $node status is DOWN ,it was terminated ." >>$LOG_FILE fi done |
|