MegaRAID信息查看
#查raid卡信息(生产商、电池信息及所支持的raid级别) /usr/local/sbin/MegaCli -AdpAllInfo -aALL |grep -E "Product Name|BBU|Memory Size|RAID Level Supported" #查看虚拟化(vd)和物理盘(pd)的信息,比如查看物理硬盘数,是否有硬盘offline或者degraded /usr/local/sbin/MegaCli -AdpAllInfo -aALL |grep -E "Device Present" -A9 ## 查看RAID日志 /usr/local/sbin/MegaCli -FwTermLog dsply –aAll #查看硬盘是否online /usr/local/sbin/MegaCli -PDList -aALL |grep "Firmware state" #查看硬盘是否存在物理错误(error不为0,可能会有硬盘故障即将发生) /usr/local/sbin/MegaCli -PDList -aALL |grep -i error #查看电池信息(电池类型、电池状态、充电状态、温度等) /usr/local/sbin/MegaCli -AdpBbuCmd -aAll #raid卡个数 /usr/local/sbin/MegaCli -adpCount #显示所有逻辑磁盘组信息(做了几组raid,raid cache的默认和当前策略,做好raid后的虚拟盘容量) /usr/local/sbin/MegaCli -LDInfo -LALL -aAll #显示所有物理盘(物理磁盘个数、大小、是否存在error) /usr/local/sbin/MegaCli -PDList -aAll #显示所有物理盘物理错误 /usr/local/sbin/MegaCli -PDList -aAll |grep -i error #查看充电状态 /usr/local/sbin/MegaCli -AdpBbuCmd -GetBbuStatus -aALL |grep 'Charger Status' ##查看BBU设置 /usr/local/sbin/MegaClii -AdpBbuCmd -GetBbuProperties -aALL ## 查看当前BBU状态 /usr/local/sbin/MegaClii -AdpBbuCmd -GetBbuStatus -aALL #显示BBU状态信息,比如电池是否,如果issohgood为Yes为正常,No为异常 /usr/local/sbin/MegaCli -AdpBbuCmd -GetBbuStatus -aALL|grep -i issohgood #显示Raid卡型号,cache大小、Raid设置,cache策略、Disk相关信息 /usr/local/sbin/MegaCli -cfgdsply -aALL |egrep "PDs|VDs|Product Name|Memory|BBU:" #磁带状态的变化,从拔盘,到插盘的过程中。 Device |Normal|Damage|Rebuild|Normal Virtual Drive |Optimal|Degraded|Degraded|Optimal Physical Drive |Online|Failed –> Unconfigured|Rebuild|Online #查看磁盘缓存策略(查看vd的) /usr/local/sbin/MegaCli -LDGetProp -Cache -LALL -aALL #或者(查看pd的) #/usr/local/sbin/MegaCli -LDGetProp -DskCache -LALL -aALL #缓存策略解释: WT (Write through WB (Write back) NORA (No read ahead) RA (Read ahead) ADRA (Adaptive read ahead) Cached Direct 例子: #查看物理磁盘重建进度 /usr/local/sbin/MegaCli -PDRbld -ShowProg -PhysDrv [1:5] -a0 或者以动态可视化文字界面显示 /usr/local/sbin/MegaCli -PDRbld -ProgDsply -PhysDrv [1:5] -a0 #磁带状态的变化,从拔盘,到插盘的过程中: Device |Normal|Damage|Rebuild|Normal Virtual Drive |Optimal|Degraded|Degraded|Optimal Physical Drive |Online|Failed –> Unconfigured|Rebuild|Online
HP RAID信息查看
## 查看控制器编号 hpacucli ctrl all show status |egrep 'Smart Array' ## 看出slot=0控制卡的信息 hpacucli ctrl slot=0 show config detail ## 看出slot=0缓存信息 hpacucli ctrl slot=0 show config detail | grep -i 'cache'
MegaRAID修改写缓存
## 强制在BBU损坏时使用Cache /usr/local/sbin/MegaCli -LDSetProp CachedBadBBU -Lall -aALL ## 强制使用WriteBack写策略 /usr/local/sbin/MegaCli -LDSetProp WB -Lall -aALL
HP RAID修改写缓存
## 关闭slot=0上物理磁盘缓存 hpssacli ctrl slot=0 modify drivewritecache=disable ## 开启slot=0上逻辑磁盘缓存 hpssacli ctrl slot=0 logicaldrive 2 modify caching=enable ## 开启slot=0上逻辑磁盘在BBU损坏时缓存 hpssacli ctrl slot=0 modify nobatterywritecache=enable
简易版的RAID检查脚本:
#!/bin/bash ##====================================================## ## 服务器信息 ## server_vendor=`dmidecode -s system-manufacturer|sed '/^#/d'|awk '{print $1}'` server_ip=`ip addr sh|grep -v 'global secondary'|grep inet|grep -v 169.254|grep -v inet6|grep -v '127.0.0.1'|grep -v '172.172.170.11'|grep -v '172.16.0.11'|awk '{print $2}'|awk -F'/' '{print $1}'|head -n 1` docker_flag=`ps -ef|grep "sleep 99999"|grep -v grep|wc -l` os_version=`cat /etc/issue |head -1` if [ "${docker_flag}" == "1" ] then server_vendor="docker" fi raid_product_name='' raid_slot_id='' raid_cache_size='' raid_level='' raid_size='' raid_status='' raid_bbu_count='' raid_bbu_status='' raid_cache_policy='' raid_logic_drive_count='' raid_logic_drive_error='' raid_physical_drive_error='' raid_physical_drive_type='' raid_physical_drive_size='' raid_physical_drive_count='' raid_predictive_failure_count='' log_file='./raid_info.txt' ##====================================================## ## 安装包信息 ## hpacucli_rpm_url="http://xxxx.com/hpacucli-9.40-12.0.x86_64.rpm" hpacucli_rpm_name="hpacucli-9.40-12.0.x86_64.rpm" lib_utils_rpm_url="http://xxxx.com/Lib_Utils-1.00-09.noarch.rpm" lib_utils_rpm_name="Lib_Utils-1.00-09.noarch.rpm" megacli_rpm_url="http://xxxx.com/MegaCli-8.02.21-1.noarch.rpm" megacli_rpm_name="MegaCli-8.02.21-1.noarch.rpm" ##====================================================## ## 高亮输出信息 ## function echo_info() { message=$1 echo -e " 33[;37;32m ${message} 33[0m" } function echo_error() { message=$1 echo -e " 33[;37;31m ${message} 33[0m" } ##====================================================## ## 获取服务器ILO信息 ## imm_idrac_mac="" imm_idrac_ip="" function get_imm_info() { if [[ "${server_vendor}" == "docker" ]] then echo_info "server is docker" elif [[ "${server_vendor}" == "HP" ]] then imm_idrac_mac=`timeout 3s ipmitool -I open lan print 2|grep "MAC Address" |awk '{print $4}'` imm_idrac_ip=`timeout 3s ipmitool -I open lan print 2 |grep -w "IP Address " |awk -F : '{print $2}'|sed 's/^ *//'` elif [[ "${server_vendor}" == "LENOVO" ]] then imm_idrac_mac=`timeout 3s ipmitool -I open lan print 1|grep "MAC Address" |awk '{print $4}'` imm_idrac_ip=`timeout 3s ipmitool -I open lan print 1 |grep -w "IP Address " |awk -F : '{print $2}'|sed 's/^ *//'` elif [[ "${server_vendor}" == "INSPUR" ]] then imm_idrac_mac=`timeout 3s ipmitool -I open lan print 8|grep "MAC Address" |awk '{print $4}'` imm_idrac_ip=`timeout 3s ipmitool -I open lan print 8 |grep -w "IP Address " |awk -F : '{print $2}'|sed 's/^ *//'` else imm_idrac_mac=`timeout 3s ipmitool -I open lan print 1|grep "MAC Address" |awk '{print $4}'` imm_idrac_ip=`timeout 3s ipmitool -I open lan print 1 |grep -w "IP Address " |awk -F : '{print $2}'|sed 's/^ *//' ` fi } get_imm_info echo_info "ILO_MAC:${imm_idrac_mac}" echo_info "ILO_IP:${imm_idrac_ip}" ##====================================================## ## 安装HP服务器使用的hpssacli ## function install_hpssacli() { rpm_count=`rpm -qa |grep -i 'hpacucli' |wc -l` if [ ${rpm_count} -gt 0 ] then echo_info 'hpacucli has been installed' else echo_info 'start to install hpacucli' /bin/rm -f "/tmp/${hpacucli_rpm_name}" wget -O "/tmp/${hpacucli_rpm_name}" "${hpacucli_rpm_url}" rpm -ivh "/tmp/${hpacucli_rpm_name}" >/dev/null echo_info 'end to install hpacucli' fi } ##====================================================## ## 安装服务器使用的MegaCli ## function install_MegaCli() { rpm_count=`rpm -qa |grep 'Lib_Utils-' |wc -l` if [ ${rpm_count} -gt 0 ] then echo_info 'Lib_Utils has been installed' else echo_info 'start to install Lib_Utils' /bin/rm -f "/tmp/${lib_utils_rpm_name}" wget -O "/tmp/${lib_utils_rpm_name}" "${lib_utils_rpm_url}" rpm -ivh "/tmp/${lib_utils_rpm_name}" echo_info 'end to install Lib_Utils' fi rpm_count=`rpm -qa |grep 'MegaCli-' |wc -l` if [ ${rpm_count} -gt 0 ] then echo_info 'MegaCli has been installed' else echo_info 'start to install Lib_Utils' /bin/rm -f "/tmp/${megacli_rpm_name}" wget -O "/tmp/${megacli_rpm_name}" "${megacli_rpm_url}" rpm -ivh "/tmp/${megacli_rpm_name}" echo_info 'end to install Lib_Utils' fi } ##====================================================## ## 安装服务器RAID使用的包 ## function install_raid_rpm() { if [[ "${server_vendor}" == "docker" ]] then echo_info "server is docker" elif [[ "${server_vendor}" == "HP" ]] then install_hpssacli else install_MegaCli fi } ##====================================================## ## 安装服务器RAID使用的包 ## function get_hp_raid_info() { raid_product_name='HP' raid_slot_id=`hpacucli ctrl all show status | grep 'Smart Array'|tail -n 1|awk '{ print $6 }'` raid_cache_size=`hpacucli ctrl all show config detail |grep 'Total Cache Size'|awk -F ':' '{print $2}'` raid_level=`hpacucli ctrl slot=${raid_slot_id} ld all show|grep -i 'raid' |awk -F ',' '{print $2}'` raid_size=`hpacucli ctrl slot=${raid_slot_id} ld all show|grep -i 'raid' |awk -F '(' '{print $2}'|awk -F ',' '{print $1}'` raid_status=`hpacucli ctrl all show config detail|grep 'Controller Status'|awk -F ':' '{print $2}'` raid_bbu_count=`hpacucli ctrl all show config detail|grep 'Capacitor Count'|awk -F ':' '{print $2}'` raid_bbu_status=`hpacucli ctrl all show config detail|grep 'Capacitor Status'|awk -F ':' '{print $2}'` raid_cache_radio=`hpacucli ctrl all show config detail|grep 'Cache Ratio'| sed 's/:/ is/g'` raid_cache_write_policy=`hpacucli ctrl all show config detail|grep 'No-Battery Write Cache' | sed 's/:/ is/g'` raid_cache_policy="${raid_cache_radio},${raid_cache_write_policy}" raid_logic_drive_count=`hpacucli ctrl all show status | grep 'Smart Array'|wc -l` raid_logic_drive_error=`hpacucli ctrl slot=${raid_slot_id} ld all show| grep 'logicaldrive' |grep -v 'OK' |wc -l` raid_physical_drive_error=`hpacucli ctrl slot=${raid_slot_id} physicaldrive all show| grep 'physicaldrive' |grep -v 'OK' |wc -l` raid_physical_drive_type=`hpacucli ctrl slot=${raid_slot_id} physicaldrive all show| grep 'physicaldrive' |tail -n 1|awk -F ',' '{print $2}'` raid_physical_drive_size=`hpacucli ctrl slot=${raid_slot_id} physicaldrive all show| grep 'physicaldrive' |tail -n 1|awk -F ',' '{print $3}'` raid_physical_drive_count=`hpacucli ctrl slot=${raid_slot_id} physicaldrive all show| grep 'physicaldrive' |wc -l` raid_predictive_failure_count=0 raid_error_count=0 if [[ "${raid_physical_drive_error}" != '0' ]] then raid_error_count=${raid_physical_drive_error} fi raid_warning_count=0 } function get_normal_raid_info() { raid_product_name=`/opt/MegaRAID/MegaCli/MegaCli64 -cfgdsply -aALL |egrep "Product Name" |awk -F ':' '{print $2}'` raid_cache_size=`/opt/MegaRAID/MegaCli/MegaCli64 -cfgdsply -aALL |egrep "Memory" | awk -F ':' '{print $2}'` raid_level=`/opt/MegaRAID/MegaCli/MegaCli64 -LDInfo -Lall -aALL |grep 'RAID Level' |awk -F ':' '{print $2}'` raid_size=`/opt/MegaRAID/MegaCli/MegaCli64 -LDInfo -Lall -aALL |egrep '^Size'|tail -n 1 |awk -F ':' '{print $2}'` raid_status='' raid_bbu_count=`/opt/MegaRAID/MegaCli/MegaCli64 -cfgdsply -aALL |egrep '^BBU'|wc -l` raid_bbu_status=`/opt/MegaRAID/MegaCli/MegaCli64 -cfgdsply -aALL |egrep '^BBU'|awk -F ':' '{print $2}'` raid_cache_policy=`/opt/MegaRAID/MegaCli/MegaCli64 -LDInfo -Lall -aALL |grep 'Current Cache Policy' |tail -n 1 |awk -F ':' '{print $2}'` raid_logic_drive_count=`/opt/MegaRAID/MegaCli/MegaCli64 -LDInfo -Lall -aALL |grep 'Target Id'|wc -l` raid_logic_drive_error=0 raid_physical_drive_error=`/opt/MegaRAID/MegaCli/MegaCli64 -PDList -aALL |grep -i 'error' | grep -v '0' |wc -l` raid_physical_drive_type=`/opt/MegaRAID/MegaCli/MegaCli64 -PDList -aALL |grep 'Media Type' |tail -n 1 |awk -F ':' '{print $2}' |awk -F '[' '{print $1 }'` raid_physical_drive_size=`/opt/MegaRAID/MegaCli/MegaCli64 -PDList -aALL |grep 'Raw Size' |tail -n 1 |awk -F ':' '{print $2}' |awk -F '[' '{print $1 }'` raid_physical_drive_count=`/opt/MegaRAID/MegaCli/MegaCli64 -PDList -aALL |grep 'Raw Size' |wc -l` raid_span_depth=`/opt/MegaRAID/MegaCli/MegaCli64 -LDInfo -Lall -aALL |egrep '^Span Depth'|tail -n 1 |awk -F ':' '{print $2}'|sed s/[[:space:]]//g` match_result=$(echo ${raid_level} |grep "Primary-1") raid_error_count=`/opt/MegaRAID/MegaCli/MegaCli64 -PDList -aALL |grep -i 'Firmware state' | grep 'Unconfigured(bad)' |wc -l` raid_warning_count=`/opt/MegaRAID/MegaCli/MegaCli64 -PDList -aALL |grep -i 'S.M.A.R.T alert' | grep -v ': No' |wc -l` raid_predictive_failure_count=`/opt/MegaRAID/MegaCli/MegaCli64 -PDList -aALL |grep -i 'Predictive Failure Count' | grep -v ': 0' |wc -l` if [[ "${match_result}" != "" ]] then echo_info 'Primary-1' if [[ "${raid_span_depth}" == "1" ]] then raid_level='RAID 1' else raid_level='RAID 10' fi fi match_result=$(echo ${raid_level} |grep "Primary-5") if [[ "${match_result}" != "" ]] then echo_info 'Primary-5' if [[ "${raid_span_depth}" == "1" ]] then raid_level='RAID 5' else raid_level='RAID 50' fi fi } function get_raid_info() { if [[ "${server_vendor}" == "docker" ]] then echo_info "server is docker" elif [[ "${server_vendor}" == "HP" ]] then get_hp_raid_info else get_normal_raid_info fi } function write_raid_info() { echo "server_vendor:${server_vendor}" > "${log_file}" echo "server_ip:${server_ip}" >> "${log_file}" echo "os_version:${os_version}" >> "${log_file}" echo "imm_idrac_mac:${imm_idrac_mac}" >> "${log_file}" echo "imm_idrac_ip:${imm_idrac_ip}" >> "${log_file}" echo "raid_product_name:${raid_product_name}" >> "${log_file}" echo "raid_cache_size:${raid_cache_size}" >> "${log_file}" echo "raid_level:${raid_level}" >> "${log_file}" echo "raid_size:${raid_size}" >> "${log_file}" echo "raid_status:${raid_status}" >> "${log_file}" echo "raid_bbu_count:${raid_bbu_count}" >> "${log_file}" echo "raid_bbu_status:${raid_bbu_status}" >> "${log_file}" echo "raid_cache_policy:${raid_cache_policy}" >> "${log_file}" echo "raid_logic_drive_count:${raid_logic_drive_count}" >> "${log_file}" echo "raid_logic_drive_error:${raid_logic_drive_error}" >> "${log_file}" echo "raid_physical_drive_error:${raid_physical_drive_error}" >> "${log_file}" echo "raid_physical_drive_type:${raid_physical_drive_type}" >> "${log_file}" echo "raid_physical_drive_size:${raid_physical_drive_size}" >> "${log_file}" echo "raid_physical_drive_count:${raid_physical_drive_count}" >> "${log_file}" echo "raid_error_count:${raid_error_count}" >> "${log_file}" echo "raid_warning_count:${raid_warning_count}" >> "${log_file}" echo "raid_predictive_failure_count:${raid_predictive_failure_count}" >> "${log_file}" } echo_info "get imm rpm" get_imm_info echo_info "install rpm" install_raid_rpm echo_info "get raid info" get_raid_info echo_info "write raid info to log" write_raid_info echo_info "#======================Server Info=======================##" cat "${log_file}" echo_info "#========================================================##"