Linux下服务器做了硬件raid之后，磁盘的状态比较难定位，windows则可以通过MegaRAID来检测，此脚本通过MegaCli来达到定位raid下哪块磁盘是坏块的功能，在nagios上面可以实现通过定期通过检测以邮箱或者短信等形式，来达到预警的功能，脚本在几台物理机上面测试过，是没问题的，分享给各位，也希望大家能相互讨论，学习。
会宁ssl适用于网站、小程序/APP、API接口等需要进行数据传输应用场景，ssl证书未来市场广阔！成为成都创新互联公司的ssl证书销售渠道，可以享受市场价格4-6折优惠！如果有意向欢迎电话联系或者加微信：13518219792（备注：SSL证书合作）期待与您的合作！
一、安装Megacli:
rpm-ivh megacli-8.00.46-2.x86_64.rpm
二、添加脚本到nagios监控：
执行visudo,然后在文件中root ALL=(ALL) ALL下面加入如下一行:
nagios ALL=(ALL)NOPASSWD:/usr/local/nagios/libexec/check_raid.sh
并注释以下一行
#Defaults requiretty
把脚本放在/usr/local/nagios/libexec目录下,chmod +x check_raid.sh,赋予x权限,并编辑/usr/local/nagios/etc/nrpe.cfg加入
command[check_raid]=/usr/bin/sudo/usr/local/nagios/libexec/check_raid.sh
重启nrpe(根据安装方式的不同，可能有差异)
#pkill nrpe #/usr/local/nagios/bin/nrpe -c/usr/local/nagios/etc/nrpe.cfg -d
三、监控脚本说明：
#!/bin/sh
#Program:
# for monitor raid disk state
#history:
#------ First release
#检测是否是LSI卡
rcexist=`dmesg| grep RAID | grep LSI`
if [ ! -n"$rcexist" ]; then
echo "not LSI or no raid"
exit 2
fi
OUTPUT=''
#判断raid类型
R1=`/usr/sbin/MegaCli-cfgdsply -aALL | grep "RAID Level" |awk -F: '{print $2}' | sed -e"s/^[ ]*//" | grep -c "Primary-1, Secondary-0, RAID LevelQualifier-0"`
R0=`/usr/sbin/MegaCli-cfgdsply -aALL | grep "RAID Level" |awk -F: '{print $2}' | sed -e"s/^[ ]*//" | grep -c "Primary-0, Secondary-0, RAID LevelQualifier-0"`
R5=`/usr/sbin/MegaCli-cfgdsply -aALL | grep "RAID Level" |awk -F: '{print $2}' | sed -e"s/^[ ]*//" | grep -c "Primary-5, Secondary-0, RAID LevelQualifier-3"`
R10=`/usr/sbin/MegaCli-cfgdsply -aALL | grep "RAID Level" |awk -F: '{print $2}' | sed -e"s/^[ ]*//" | grep -c "Primary-1, Secondary-3, RAID LevelQualifier-0"`
if [ $R1-ge 2 ];then
OUTPUT+="RAID10 "
elif [ $R1-eq 1 ];then
OUTPUT+="RAID1 "
fi
if [ $R0-ne 0 ];then
OUTPUT+="RAID0 "
fi
if [ $R5-ne 0 ];then
OUTPUT+="RAID5 "
fi
if [ $R10-ne 0 ];then
OUTPUT+="RAID10 "
fi
#以上的if是根据资料和实际情况做了微调
#raid下面总的磁盘数
DiskNum=`/usr/sbin/MegaCli-cfgdsply -aALL | grep -c "Non Coerced Size"`
OUTPUT+="TotalDisk:$DiskNum"
#处于raid中的正常的盘数
OnlineDisk=`/usr/sbin/MegaCli-cfgdsply -aALL | grep "Online" | wc -l`
OUTPUT+="online: $OnlineDisk"
if [$DiskNum -ne $OnlineDisk ];then
echo "CRITICAL:$OUTPUT"
exit 2
fi
#是否有坏的盘
FailDisk=`/usr/sbin/MegaCli-AdpAllInfo -aALL | grep "Failed Disks" | awk '{print $4}'`
if [$FailDisk -eq 0 ];then
OUTPUT+=" failed disk:0 "
else
OUTPUT+=" failed disk:$FailDisk"
echo "CRITICAL: $OUTPUT"
exit 2
fi
#预警的盘以及位置
CriticalDisk=`/usr/sbin/MegaCli-AdpAllInfo -aALL | grep "Critical Disks" | awk '{print $4}'`
if [$CriticalDisk -eq 0 ];then
OUTPUT+="critiDisk is 0"
else
CriDisk=`/usr/sbin/MegaCli -cfgdsply -aALL| grep -E 'Predictive|Slot' | awk \
'{if(NR%3){printf$0":"}else{print $0}}'|awk -F':' '{if($4!=0){print $2+1}}'`
OUTPUT+=" critidisk in $CriDiskslot"
echo "WARNING: $OUTPUT"
exit 1
fi
#MediaErrcount检测坏块和哪块盘
MediaErrcount=`/usr/sbin/MegaCli-pdlist -aALL | grep -E "Media Error" |awk -F’:’ -v errcount=0 \
'{errcount+=$2}END{printerrcount}'`
OtherErrcount=`/usr/sbin/MegaCli-pdlist -aALL | grep -E "Other Error" |awk -F’:’ -v errcount=0 \
'{errcount+=$2}END{printerrcount}'`
#坏盘的位置
if [ $MediaErrcount-ne 0 -o $OtherErrcount -ne 0 ];then
mDoD=`/usr/sbin/MegaCli -pdlist -aALL |grep -E "Media Error|Other Error|Slot" | awk \
'{if(NR%3){printf$0":"}else{print $0}}' | awk -F':' '{if($4!=0||$6!=0){print $2+1}}'`
OUTPUT+=" bad block in $mDoD"
echo "CRITICAL: $OUTPUT"
exit 2
else
OUTPUT+=" mediaerr:0 othererr:0"
fi
#raid状态是否正常
raidstate=`/usr/sbin/MegaCli-LDInfo -Lall -aAll | grep 'State' |awk -F':' '{print $2}' | \
sort |uniq | sed -e "s/^[ ]*//" | awk '{if($0 != "Optimal"){print"bad"}}'`
if ["$raidstate" != "bad" ];then
OUTPUT+=" raidstate:ok"
else
OUTPUT+=" raidstate:bad"
echo "CRITICAL: $OUTPUT"
exit 2
fi
rm -rf./MegaSAS.log
echo$OUTPUT检测结果如下：
RAID5 Total Disk: 4 online: 4 failed disk:0 critidisk is 0 mediaerr:0 othererr:0 raidstate:ok
