1. Centos7配置软RAID 1
准备两块新硬盘，最好是同容量同转速的，新加硬盘必需重新启动系统才能读取：
- 列出所有磁盘： [root@linux-node1 ~]# fdisk -l
- [root@linux-node1 ~]# fdisk /dev/sdb
- 新建分区/dev/sdb1，并更改ID为fd（Linux raid autodetect类型），按w退出并保存
- [root@linux-node1 ~]# fdisk /dev/sdc
- 新建分区/dev/sdc1，并更改ID为fdLinux raid autodetect类型），按w退出并保存
- 使用partprobe /dev/sdb,partprobe /dev/sdc命令让linux内核重新读取硬盘参数
- 使用mdadm -C /dev/md0 -l 1 -a yes -n 2 /dev/sdb1 /dev/sdc1命令新建一个md0 软RAID
- mkfs -t ext4 /dev/md0格式化RAID分区
- mkdir /raid && mount /dev/md0 /raid 新建目录并挂载分区
- vim /etc/fstab 增加开机启动设备
- /dev/md0 /raid ext4 defaults 0 0
- mount -a 检查开机启动设备文件是否无误
2. ubuntu 18.04.5
2.1 小插曲
- 在制作软RAID之前，安装ubuntu18.04.5安装了两次，第一次安装在500G的 /dev/sda机械硬盘{安装一半中止安装}
- 第二次安装在240G的 /dev/sdb固态硬盘，最终以固态硬盘为系统盘启动
- 在系统中查看到根目录下挂载了LV，但是通过lvdisplay查看到有两块盘都挂载在/目录下，但有一个是活动，一个未活动，想删除未活动的，没有命令，最后重启后生效，以下是过程
root@ubuntu-18:/etc/apt# pvdisplay
--- Physical volume ---
PV Name /dev/sdb5
VG Name ubuntu-18-vg
PV Size <222.62 GiB / not usable 2.00 MiB
Allocatable yes (but full)
PE Size 4.00 MiB
Total PE 56989
Free PE 0
Allocated PE 56989
PV UUID idWKzJ-wlWM-W1TV-4dqs-dbac-5K2v-C2kbSW
--- Physical volume ---
PV Name /dev/sda5
VG Name ubuntu-18-vg
PV Size <464.81 GiB / not usable 0
Allocatable yes (but full)
PE Size 4.00 MiB
Total PE 118990
Free PE 0
Allocated PE 118990
PV UUID r0apGr-033N-9Eo2-r6he-rlIy-fepN-hmXdBF
root@ubuntu-18:/etc/apt# vgdisplay
--- Volume group ---
VG Name ubuntu-18-vg
System ID
Format lvm2
Metadata Areas 1
Metadata Sequence No 2
VG Access read/write
VG Status resizable
MAX LV 0
Cur LV 1
Open LV 1
Max PV 0
Cur PV 1
Act PV 1
VG Size 222.61 GiB
PE Size 4.00 MiB
Total PE 56989
Alloc PE / Size 56989 / 222.61 GiB
Free PE / Size 0 / 0
VG UUID jC6Pgy-fjgQ-yP8m-ZSGI-XGrb-VN7W-JF1CHR
--- Volume group ---
VG Name ubuntu-18-vg
System ID
Format lvm2
Metadata Areas 1
Metadata Sequence No 2
VG Access read/write
VG Status resizable
MAX LV 0
Cur LV 1
Open LV 0
Max PV 0
Cur PV 1
Act PV 1
VG Size 464.80 GiB
PE Size 4.00 MiB
Total PE 118990
Alloc PE / Size 118990 / 464.80 GiB
Free PE / Size 0 / 0
VG UUID A9eqdH-5erA-oSje-eg4I-PJu0-Y6XP-SJhfSj
root@ubuntu-18:/etc/apt# lvdisplay
--- Logical volume ---
LV Path /dev/ubuntu-18-vg/root
LV Name root
VG Name ubuntu-18-vg
LV UUID hQdPeT-9evX-ncOs-xoId-w1Az-XMsA-JXAbWE
LV Write Access read/write
LV Creation host, time ubuntu-18, 2022-11-24 21:58:25 +0800
LV Status available
# open 1
LV Size 222.61 GiB
Current LE 56989
Segments 1
Allocation inherit
Read ahead sectors auto
- currently set to 256
Block device 253:0
--- Logical volume ---
LV Path /dev/ubuntu-18-vg/root
LV Name root
VG Name ubuntu-18-vg
LV UUID ifOmAN-zW2N-KrIp-zZDH-R5ST-7RIQ-HTn97u
LV Write Access read/write
LV Creation host, time ubuntu-18, 2022-11-24 21:50:11 +0800
LV Status NOT available #未活动，想删除掉
LV Size 464.80 GiB
Current LE 118990
Segments 1
Allocation inherit
Read ahead sectors auto
root@ubuntu-18:/etc/apt# df -TH
Filesystem Type Size Used Avail Use% Mounted on
udev devtmpfs 4.2G 0 4.2G 0% /dev
tmpfs tmpfs 827M 914k 826M 1% /run
/dev/mapper/ubuntu--18--vg-root xfs 239G 4.3G 235G 2% / #实际只挂载了ssd硬盘
tmpfs tmpfs 4.2G 0 4.2G 0% /dev/shm
tmpfs tmpfs 5.3M 0 5.3M 0% /run/lock
tmpfs tmpfs 4.2G 0 4.2G 0% /sys/fs/cgroup
/dev/sdb1 ext4 991M 64M 859M 7% /boot
tmpfs tmpfs 827M 0 827M 0% /run/user/0
root@ubuntu-18:/etc/apt# mkfs --type xfs -f /dev/sda #格式化sda硬盘
root@ubuntu-18:/etc/apt# mkfs --type xfs -f /dev/sdc #格式化sda硬盘
root@ubuntu-18:/etc/apt# lvdisplay
--- Logical volume ---
LV Path /dev/ubuntu-18-vg/root
LV Name root
VG Name ubuntu-18-vg
LV UUID hQdPeT-9evX-ncOs-xoId-w1Az-XMsA-JXAbWE
LV Write Access read/write
LV Creation host, time ubuntu-18, 2022-11-24 21:58:25 +0800
LV Status available
# open 1
LV Size 222.61 GiB
Current LE 56989
Segments 1
Allocation inherit
Read ahead sectors auto
- currently set to 256
Block device 253:0
WARNING: Device for PV r0apGr-033N-9Eo2-r6he-rlIy-fepN-hmXdBF not found or rejected by a filter. #提示/dev/sda这个PV是没有用的
--- Logical volume ---
LV Path /dev/ubuntu-18-vg/root
LV Name root
VG Name ubuntu-18-vg
LV UUID ifOmAN-zW2N-KrIp-zZDH-R5ST-7RIQ-HTn97u
LV Write Access read/write
LV Creation host, time ubuntu-18, 2022-11-24 21:50:11 +0800
LV Status NOT available
LV Size 464.80 GiB
Current LE 118990
Segments 1
Allocation inherit
Read ahead sectors auto
注：最后重启后生效，系统自动会清除没有用的lv,vg,pv
2.2 制作软RAID 1
# 安装软raid工具
root@office:~# apt install -y mdadm
# 列出所有块设备
root@office:~# lsblk
NAME MAJ:MIN RM SIZE RO TYPE MOUNTPOINT
sda 8:0 0 465.8G 0 disk
sdb 8:16 0 223.6G 0 disk
|-sdb1 8:17 0 976M 0 part /boot
|-sdb2 8:18 0 1K 0 part
`-sdb5 8:21 0 222.6G 0 part
`-ubuntu--18--vg-root 253:0 0 222.6G 0 lvm /
sdc 8:32 0 465.8G 0 disk
# sudo mdadm --create --verbose /dev/md1 --level=1 --raid-devices=2 /dev/sda /dev/sdc #software raid 1
# sudo mdadm --create --verbose /dev/md5 --level=5 --raid-devices=3 /dev/sda /dev/sdc /dev/sdd #software raid 5
# sudo mdadm --create --verbose /dev/md6 --level=6 --raid-devices=4 /dev/sda /dev/sdc /dev/sdd /dev/sde #software raid 6
# 创建软raid1
root@office:~# sudo mdadm --create --verbose /dev/md0 --level=1 --raid-devices=2 /dev/sda /dev/sdc
mdadm: Note: this array has metadata at the start and
may not be suitable as a boot device. If you plan to
store '/boot' on this device please ensure that
your boot-loader understands md/v1.x metadata, or use
--metadata=0.90
mdadm: size set to 488254464K
mdadm: automatically enabling write-intent bitmap on large array
Continue creating array? y
mdadm: Defaulting to version 1.2 metadata
mdadm: array /dev/md0 started.
# 查看软raid信息
root@office:~# cat /proc/mdstat
Personalities : [raid1]
md0 : active raid1 sdc[1] sda[0]
488254464 blocks super 1.2 [2/2] [UU]
[>....................] resync = 0.1% (653120/488254464) finish=62.2min speed=130624K/sec #同步0.1%
bitmap: 4/4 pages [16KB], 65536KB chunk
unused devices: <none>
root@office:~# cat /proc/mdstat
Personalities : [raid1]
md0 : active raid1 sdc[1] sda[0]
488254464 blocks super 1.2 [2/2] [UU]
[>....................] resync = 3.0% (15125888/488254464) finish=59.5min speed=132494K/sec #同步3%
bitmap: 4/4 pages [16KB], 65536KB chunk
unused devices: <none>
# 查看所有块设备信息
root@office:~# fdisk -l
Disk /dev/sda: 465.8 GiB, 500107862016 bytes, 976773168 sectors
Units: sectors of 1 * 512 = 512 bytes
Sector size (logical/physical): 512 bytes / 512 bytes
I/O size (minimum/optimal): 512 bytes / 512 bytes
Disk /dev/sdb: 223.6 GiB, 240057409536 bytes, 468862128 sectors
Units: sectors of 1 * 512 = 512 bytes
Sector size (logical/physical): 512 bytes / 512 bytes
I/O size (minimum/optimal): 512 bytes / 512 bytes
Disklabel type: dos
Disk identifier: 0xcb1878ad
Device Boot Start End Sectors Size Id Type
/dev/sdb1 * 2048 2000895 1998848 976M 83 Linux
/dev/sdb2 2002942 468860927 466857986 222.6G 5 Extended
/dev/sdb5 2002944 468860927 466857984 222.6G 8e Linux LVM
Disk /dev/sdc: 465.8 GiB, 500107862016 bytes, 976773168 sectors
Units: sectors of 1 * 512 = 512 bytes
Sector size (logical/physical): 512 bytes / 512 bytes
I/O size (minimum/optimal): 512 bytes / 512 bytes
Disk /dev/mapper/ubuntu--18--vg-root: 222.6 GiB, 239029190656 bytes, 466853888 sectors
Units: sectors of 1 * 512 = 512 bytes
Sector size (logical/physical): 512 bytes / 512 bytes
I/O size (minimum/optimal): 512 bytes / 512 bytes
Disk /dev/md0: 465.7 GiB, 499972571136 bytes, 976508928 sectors
Units: sectors of 1 * 512 = 512 bytes
Sector size (logical/physical): 512 bytes / 512 bytes
I/O size (minimum/optimal): 512 bytes / 512 bytes
---
# 格式化块设备为xfs文件系统
root@office:~# mkfs --type xfs -f /dev/md0
meta-data=/dev/md0 isize=512 agcount=4, agsize=30515904 blks
= sectsz=512 attr=2, projid32bit=1
= crc=1 finobt=1, sparse=0, rmapbt=0, reflink=0
data = bsize=4096 blocks=122063616, imaxpct=25
= sunit=0 swidth=0 blks
naming =version 2 bsize=4096 ascii-ci=0 ftype=1
log =internal log bsize=4096 blocks=59601, version=2
= sectsz=512 sunit=0 blks, lazy-count=1
realtime =none extsz=4096 blocks=0, rtextents=0
# 挂载存储目录
root@office:~# mkdir -p /data
root@office:~# mount /dev/md0 /data/
root@office:~# df -TH
Filesystem Type Size Used Avail Use% Mounted on
udev devtmpfs 4.2G 0 4.2G 0% /dev
tmpfs tmpfs 827M 898k 826M 1% /run
/dev/mapper/ubuntu--18--vg-root xfs 239G 4.3G 235G 2% /
tmpfs tmpfs 4.2G 0 4.2G 0% /dev/shm
tmpfs tmpfs 5.3M 0 5.3M 0% /run/lock
tmpfs tmpfs 4.2G 0 4.2G 0% /sys/fs/cgroup
/dev/sdb1 ext4 991M 65M 859M 7% /boot
tmpfs tmpfs 827M 0 827M 0% /run/user/0
/dev/md0 xfs 500G 532M 500G 1% /data
# 保存数组布局
为了确保在引导时自动重新组装阵列，我们将不得不调整/etc/mdadm/mdadm.conf文件。您可以通过键入以下内容自动扫描活动数组并附加文件：
root@office:~# sudo mdadm --detail --scan | sudo tee -a /etc/mdadm/mdadm.conf
ARRAY /dev/md0 metadata=1.2 name=office.hs.com:0 UUID=8c669a34:60d603ea:2ac3604a:2b191b74
root@office:~# cat /etc/mdadm/mdadm.conf
HOMEHOST <system>
MAILADDR root
ARRAY /dev/md0 metadata=1.2 name=office.hs.com:0 UUID=8c669a34:60d603ea:2ac3604a:2b191b74
# 更新initramfs或初始RAM文件系统，以便在早期启动过程中阵列可用：
root@office:~# sudo update-initramfs -u
update-initramfs: Generating /boot/initrd.img-4.15.0-112-generic
----------
# 如果启动系统后，原来的名称/dev/md1变成/dev/md127了，可如下操作：
mdadm --assemble /dev/md1 --name=1 --update-name /dev/sda1 /dev/sdb1
# 如果原来的名称/dev/md2变成/dev/md127了，可如下操作：
mdadm --assemble /dev/md2 --name=2 --update-name /dev/sda1 /dev/sdb1
# 最后运行
sudo update-initramfs -u
----------
# 将新的文件系统挂载选项添加到/etc/fstab文件中以便在引导时自动挂载：
root@office:~# echo '/dev/md0 /data xfs defaults 0 0' | sudo tee -a /etc/fstab
/dev/md0 /data xfs defaults 0 0
# 测试是否自动开机挂载
root@office:~# umount /data
root@office:~# mount -a
root@office:~# df -TH
Filesystem Type Size Used Avail Use% Mounted on
udev devtmpfs 4.2G 0 4.2G 0% /dev
tmpfs tmpfs 827M 898k 826M 1% /run
/dev/mapper/ubuntu--18--vg-root xfs 239G 4.3G 235G 2% /
tmpfs tmpfs 4.2G 0 4.2G 0% /dev/shm
tmpfs tmpfs 5.3M 0 5.3M 0% /run/lock
tmpfs tmpfs 4.2G 0 4.2G 0% /sys/fs/cgroup
/dev/sdb1 ext4 991M 65M 859M 7% /boot
tmpfs tmpfs 827M 0 827M 0% /run/user/0
/dev/md0 xfs 500G 532M 500G 1% /data
# 重启查看是否正常
root@office:~# cat /proc/mdstat
Personalities : [raid1]
md0 : active raid1 sdc[1] sda[0]
488254464 blocks super 1.2 [2/2] [UU]
[======>..............] resync = 31.3% (152994432/488254464) finish=48.2min speed=115736K/sec
bitmap: 3/4 pages [12KB], 65536KB chunk
unused devices: <none>
root@office:~# reboot
# 重启后状态，如预期正常
root@office:~# df -TH
Filesystem Type Size Used Avail Use% Mounted on
udev devtmpfs 4.2G 0 4.2G 0% /dev
tmpfs tmpfs 827M 914k 826M 1% /run
/dev/mapper/ubuntu--18--vg-root xfs 239G 4.3G 235G 2% /
tmpfs tmpfs 4.2G 0 4.2G 0% /dev/shm
tmpfs tmpfs 5.3M 0 5.3M 0% /run/lock
tmpfs tmpfs 4.2G 0 4.2G 0% /sys/fs/cgroup
/dev/sdb1 ext4 991M 65M 859M 7% /boot
/dev/md0 xfs 500G 532M 500G 1% /data
tmpfs tmpfs 827M 0 827M 0% /run/user/0
root@office:~# cat /proc/mdstat
Personalities : [raid1] [linear] [multipath] [raid0] [raid6] [raid5] [raid4] [raid10]
md0 : active raid1 sda[0] sdc[1]
488254464 blocks super 1.2 [2/2] [UU]
[======>..............] resync = 32.0% (156609536/488254464) finish=47.3min speed=116771K/sec
bitmap: 3/4 pages [12KB], 65536KB chunk
unused devices: <none>
---
# 同步完成状态
root@office:~# cat /proc/mdstat
Personalities : [raid1] [linear] [multipath] [raid0] [raid6] [raid5] [raid4] [raid10]
md0 : active raid1 sda[0] sdc[1]
488254464 blocks super 1.2 [2/2] [UU]
bitmap: 0/4 pages [0KB], 65536KB chunk
unused devices: <none>
2.3 创建LVM on 软RAID
# 在软RAID之上创建LVM分区
root@office:~# fdisk -l /dev/md0
Disk /dev/md0: 465.7 GiB, 499972571136 bytes, 976508928 sectors
Units: sectors of 1 * 512 = 512 bytes
Sector size (logical/physical): 512 bytes / 512 bytes
I/O size (minimum/optimal): 512 bytes / 512 bytes
Disklabel type: dos
Disk identifier: 0x3637f591
Device Boot Start End Sectors Size Id Type
/dev/md0p1 2048 976508927 976506880 465.7G 8e Linux LVM
# 创建PV
root@office:~# pvcreate /dev/md0p1
Physical volume "/dev/md0p1" successfully created.
root@office:~# pvdisplay
--- Physical volume ---
PV Name /dev/md0p1
VG Name data
PV Size 465.63 GiB / not usable 2.00 MiB
Allocatable yes
PE Size 4.00 MiB
Total PE 119202
Free PE 119202
Allocated PE 0
PV UUID bN1emA-z0g0-uwoR-gm4X-Hj3h-jIEY-siJeL4
--- Physical volume ---
PV Name /dev/sdb5
VG Name ubuntu-18-vg
PV Size <222.62 GiB / not usable 2.00 MiB
Allocatable yes (but full)
PE Size 4.00 MiB
Total PE 56989
Free PE 0
Allocated PE 56989
PV UUID idWKzJ-wlWM-W1TV-4dqs-dbac-5K2v-C2kbSW
# 创建VG
root@office:~# vgcreate data /dev/md0p1
Volume group "data" successfully created
root@office:~# vgdisplay
--- Volume group ---
VG Name data
System ID
Format lvm2
Metadata Areas 1
Metadata Sequence No 1
VG Access read/write
VG Status resizable
MAX LV 0
Cur LV 0
Open LV 0
Max PV 0
Cur PV 1
Act PV 1
VG Size 465.63 GiB
PE Size 4.00 MiB
Total PE 119202
Alloc PE / Size 0 / 0
Free PE / Size 119202 / 465.63 GiB
VG UUID 53eZFT-NBTs-n7ZE-YqPH-P9r5-vFZU-A0pX66
--- Volume group ---
VG Name ubuntu-18-vg
System ID
Format lvm2
Metadata Areas 1
Metadata Sequence No 2
VG Access read/write
VG Status resizable
MAX LV 0
Cur LV 1
Open LV 1
Max PV 0
Cur PV 1
Act PV 1
VG Size 222.61 GiB
PE Size 4.00 MiB
Total PE 56989
Alloc PE / Size 56989 / 222.61 GiB
Free PE / Size 0 / 0
VG UUID jC6Pgy-fjgQ-yP8m-ZSGI-XGrb-VN7W-JF1CHR
# 创建LV
root@office:~# lvcreate -l 100%FREE -n data-lv data
Logical volume "data-lv" created.
root@office:~# lvdisplay
--- Logical volume ---
LV Path /dev/data/data-lv
LV Name data-lv
VG Name data
LV UUID 8sWufC-pYOZ-URbg-pZyb-07O4-BBGc-GMgdB8
LV Write Access read/write
LV Creation host, time office.hs.com, 2022-11-24 17:28:01 +0800
LV Status available
# open 0
LV Size 465.63 GiB
Current LE 119202
Segments 1
Allocation inherit
Read ahead sectors auto
- currently set to 256
Block device 253:1
--- Logical volume ---
LV Path /dev/ubuntu-18-vg/root
LV Name root
VG Name ubuntu-18-vg
LV UUID hQdPeT-9evX-ncOs-xoId-w1Az-XMsA-JXAbWE
LV Write Access read/write
LV Creation host, time ubuntu-18, 2022-11-24 21:58:25 +0800
LV Status available
# open 1
LV Size 222.61 GiB
Current LE 56989
Segments 1
Allocation inherit
Read ahead sectors auto
- currently set to 256
Block device 253:0
注：如果扩展大小，需要执行：xfs_growfs /dev/vg1/lv1增加文件系统的容量
# 格式化LV为xfs文件系统
root@office:~# mkfs -t xfs /dev/data/data-lv
meta-data=/dev/data/data-lv isize=512 agcount=4, agsize=30515712 blks
= sectsz=512 attr=2, projid32bit=1
= crc=1 finobt=1, sparse=0, rmapbt=0, reflink=0
data = bsize=4096 blocks=122062848, imaxpct=25
= sunit=0 swidth=0 blks
naming =version 2 bsize=4096 ascii-ci=0 ftype=1
log =internal log bsize=4096 blocks=59601, version=2
= sectsz=512 sunit=0 blks, lazy-count=1
realtime =none extsz=4096 blocks=0, rtextents=0
root@office:~# fdisk -l /dev/data/data-lv
Disk /dev/data/data-lv: 465.6 GiB, 499969425408 bytes, 976502784 sectors
Units: sectors of 1 * 512 = 512 bytes
Sector size (logical/physical): 512 bytes / 512 bytes
I/O size (minimum/optimal): 512 bytes / 512 bytes
# 挂载存储目录
root@office:~# mount /dev/data/data-lv /data/
root@office:~# cat /etc/fstab
# <file system> <mount point> <type> <options> <dump> <pass>
/dev/mapper/ubuntu--18--vg-root / xfs defaults 0 0
# /boot was on /dev/sda1 during installation
UUID=d9974eb6-44d5-4ba2-a1d6-e0ae846aea5c /boot ext4 defaults 0 2
/swapfile none swap sw 0 0
/dev/data/data-lv /data xfs defaults 0 0
---
root@office:~# df -TH
Filesystem Type Size Used Avail Use% Mounted on
udev devtmpfs 4.2G 0 4.2G 0% /dev
tmpfs tmpfs 827M 926k 826M 1% /run
/dev/mapper/ubuntu--18--vg-root xfs 239G 4.3G 235G 2% /
tmpfs tmpfs 4.2G 0 4.2G 0% /dev/shm
tmpfs tmpfs 5.3M 0 5.3M 0% /run/lock
tmpfs tmpfs 4.2G 0 4.2G 0% /sys/fs/cgroup
/dev/sdb1 ext4 991M 65M 859M 7% /boot
tmpfs tmpfs 827M 0 827M 0% /run/user/0
/dev/mapper/data-data--lv xfs 500G 532M 500G 1% /data
root@office:~# umount /data
root@office:~# mount -a
droot@office:~# df -TH
Filesystem Type Size Used Avail Use% Mounted on
udev devtmpfs 4.2G 0 4.2G 0% /dev
tmpfs tmpfs 827M 926k 826M 1% /run
/dev/mapper/ubuntu--18--vg-root xfs 239G 4.3G 235G 2% /
tmpfs tmpfs 4.2G 0 4.2G 0% /dev/shm
tmpfs tmpfs 5.3M 0 5.3M 0% /run/lock
tmpfs tmpfs 4.2G 0 4.2G 0% /sys/fs/cgroup
/dev/sdb1 ext4 991M 65M 859M 7% /boot
tmpfs tmpfs 827M 0 827M 0% /run/user/0
/dev/mapper/data-data--lv xfs 500G 532M 500G 1% /data
3. 软RAID
datetime: 20240508 OS: CentOS7
3.1 创建软RAID1
# 创建分区/dev/sda1, /dev/sdb1
[root@testhoteles ~]# lsblk
NAME MAJ:MIN RM SIZE RO TYPE MOUNTPOINT
sda 8:0 0 465.8G 0 disk
└─sda1 8:1 0 465.8G 0 part
sdb 8:16 0 465.8G 0 disk
└─sdb1 8:17 0 465.8G 0 part
sdc 8:32 0 223.6G 0 disk
├─sdc1 8:33 0 500M 0 part /boot
└─sdc2 8:34 0 223.1G 0 part
├─centos-root 253:0 0 50G 0 lvm /
├─centos-swap 253:1 0 7.8G 0 lvm [SWAP]
└─centos-home 253:2 0 165.2G 0 lvm /home
# 创建软RAID1
[root@testhoteles ~]# yum install mdadm -y
[root@testhoteles ~]# mdadm --create --verbose /dev/md1 --level=1 --raid-devices=2 /dev/sda1 /dev/sdb1
mdadm: partition table exists on /dev/sda1
mdadm: partition table exists on /dev/sda1 but will be lost or
meaningless after creating array
mdadm: Note: this array has metadata at the start and
may not be suitable as a boot device. If you plan to
store '/boot' on this device please ensure that
your boot-loader understands md/v1.x metadata, or use
--metadata=0.90
mdadm: partition table exists on /dev/sdb1
mdadm: partition table exists on /dev/sdb1 but will be lost or
meaningless after creating array
mdadm: size set to 488253440K
mdadm: automatically enabling write-intent bitmap on large array
Continue creating array? y # 确认
mdadm: Defaulting to version 1.2 metadata
mdadm: array /dev/md1 started.
# 查看软RAID详细信息
[root@testhoteles ~]# mdadm -D /dev/md1
/dev/md1:
Version : 1.2
Creation Time : Wed May 8 06:11:58 2024
Raid Level : raid1
Array Size : 488253440 (465.63 GiB 499.97 GB)
Used Dev Size : 488253440 (465.63 GiB 499.97 GB)
Raid Devices : 2
Total Devices : 2
Persistence : Superblock is persistent
Intent Bitmap : Internal
Update Time : Wed May 8 06:12:43 2024
State : clean, resyncing
Active Devices : 2
Working Devices : 2
Failed Devices : 0
Spare Devices : 0
Consistency Policy : bitmap
Resync Status : 1% complete
Name : testhoteles.hs.com:1 (local to host testhoteles.hs.com)
UUID : 611ac412:b50551be:6cf89141:7d2d4580
Events : 9
Number Major Minor RaidDevice State
0 8 1 0 active sync /dev/sda1
1 8 17 1 active sync /dev/sdb1
# 查看已经组装（激活）的阵列状态
[root@testhoteles ~]# cat /proc/mdstat
Personalities : [raid1]
md1 : active raid1 sdb1[1] sda1[0]
488253440 blocks super 1.2 [2/2] [UU]
[>....................] resync = 1.8% (9164160/488253440) finish=66.3min speed=120344K/sec
bitmap: 4/4 pages [16KB], 65536KB chunk
unused devices: <none>
# 查看陈列配置
[root@testhoteles ~]# mdadm -Q /dev/md1
/dev/md1: 465.63GiB raid1 2 devices, 0 spares. Use mdadm --detail for more detail.
[root@testhoteles ~]# lsblk
NAME MAJ:MIN RM SIZE RO TYPE MOUNTPOINT
sda 8:0 0 465.8G 0 disk
└─sda1 8:1 0 465.8G 0 part
└─md1 9:1 0 465.7G 0 raid1
sdb 8:16 0 465.8G 0 disk
└─sdb1 8:17 0 465.8G 0 part
└─md1 9:1 0 465.7G 0 raid1
sdc 8:32 0 223.6G 0 disk
├─sdc1 8:33 0 500M 0 part /boot
└─sdc2 8:34 0 223.1G 0 part
├─centos-root 253:0 0 50G 0 lvm /
├─centos-swap 253:1 0 7.8G 0 lvm [SWAP]
└─centos-home 253:2 0 165.2G 0 lvm /home
# 查看阵列构成配置(转储超级块内容)
[root@testhoteles ~]# mdadm --query --examine /dev/sda1
/dev/sda1:
Magic : a92b4efc
Version : 1.2
Feature Map : 0x1
Array UUID : 611ac412:b50551be:6cf89141:7d2d4580
Name : testhoteles.hs.com:1 (local to host testhoteles.hs.com)
Creation Time : Wed May 8 06:11:58 2024
Raid Level : raid1
Raid Devices : 2
Avail Dev Size : 976506928 sectors (465.63 GiB 499.97 GB)
Array Size : 488253440 KiB (465.63 GiB 499.97 GB)
Used Dev Size : 976506880 sectors (465.63 GiB 499.97 GB)
Data Offset : 264192 sectors
Super Offset : 8 sectors
Unused Space : before=264112 sectors, after=48 sectors
State : active
Device UUID : 88720bbd:f63659bd:f432717e:8440d35c
Internal Bitmap : 8 sectors from superblock
Update Time : Wed May 8 06:33:01 2024
Bad Block Log : 512 entries available at offset 16 sectors
Checksum : 7c6f3018 - correct
Events : 225
Device Role : Active device 0
Array State : AA ('A' == active, '.' == missing, 'R' == replacing)
# 同步完成状态
[root@testhoteles ~]# mdadm -D /dev/md1
/dev/md1:
Version : 1.2
Creation Time : Wed May 8 06:11:58 2024
Raid Level : raid1
Array Size : 488253440 (465.63 GiB 499.97 GB)
Used Dev Size : 488253440 (465.63 GiB 499.97 GB)
Raid Devices : 2
Total Devices : 2
Persistence : Superblock is persistent
Intent Bitmap : Internal
Update Time : Wed May 8 15:35:00 2024
State : clean # 这里没有resyncing状态了，表示干净状态
Active Devices : 2
Working Devices : 2
Failed Devices : 0
Spare Devices : 0
Consistency Policy : bitmap
Name : testhoteles.hs.com:1 (local to host testhoteles.hs.com)
UUID : 611ac412:b50551be:6cf89141:7d2d4580
Events : 1127
Number Major Minor RaidDevice State
0 8 1 0 active sync /dev/sda1
1 8 17 1 active sync /dev/sdb1
3.2 raid停止和重组装
[root@testhoteles ~]# lsblk
NAME MAJ:MIN RM SIZE RO TYPE MOUNTPOINT
sda 8:0 0 465.8G 0 disk
└─sda1 8:1 0 465.8G 0 part
└─md1 9:1 0 465.7G 0 raid1
sdb 8:16 0 465.8G 0 disk
└─sdb1 8:17 0 465.8G 0 part
└─md1 9:1 0 465.7G 0 raid1
sdc 8:32 0 223.6G 0 disk
├─sdc1 8:33 0 500M 0 part /boot
└─sdc2 8:34 0 223.1G 0 part
├─centos-root 253:0 0 50G 0 lvm /
├─centos-swap 253:1 0 7.8G 0 lvm [SWAP]
└─centos-home 253:2 0 165.2G 0 lvm /home
# 停止软RAID
[root@testhoteles ~]# mdadm --stop /dev/md1
mdadm: stopped /dev/md1
# 查看块
[root@testhoteles ~]# lsblk
NAME MAJ:MIN RM SIZE RO TYPE MOUNTPOINT
sda 8:0 0 465.8G 0 disk
└─sda1 8:1 0 465.8G 0 part
sdb 8:16 0 465.8G 0 disk
└─sdb1 8:17 0 465.8G 0 part
sdc 8:32 0 223.6G 0 disk
├─sdc1 8:33 0 500M 0 part /boot
└─sdc2 8:34 0 223.1G 0 part
├─centos-root 253:0 0 50G 0 lvm /
├─centos-swap 253:1 0 7.8G 0 lvm [SWAP]
└─centos-home 253:2 0 165.2G 0 lvm /home
# 重新装载陈列
# mdadm --assemble --scan # 自动组装所有阵列
[root@testhoteles ~]# mdadm --assemble /dev/md1 /dev/sda1 /dev/sdb1 --force
mdadm: /dev/md1 has been started with 2 drives.
[root@testhoteles ~]#
mdadm: /dev/md/1 has been started with 2 drives.
[root@testhoteles ~]# mdadm -D /dev/md1
/dev/md1:
Version : 1.2
Creation Time : Wed May 8 06:11:58 2024
Raid Level : raid1
Array Size : 488253440 (465.63 GiB 499.97 GB)
Used Dev Size : 488253440 (465.63 GiB 499.97 GB)
Raid Devices : 2
Total Devices : 2
Persistence : Superblock is persistent
Intent Bitmap : Internal
Update Time : Wed May 8 06:28:39 2024
State : clean, resyncing
Active Devices : 2
Working Devices : 2
Failed Devices : 0
Spare Devices : 0
Consistency Policy : bitmap
Resync Status : 20% complete
Name : testhoteles.hs.com:1 (local to host testhoteles.hs.com)
UUID : 611ac412:b50551be:6cf89141:7d2d4580
Events : 172
Number Major Minor RaidDevice State
0 8 1 0 active sync /dev/sda1
1 8 17 1 active sync /dev/sdb1
3.3 保存已有的陈列配置
[root@testhoteles ~]# mdadm --detail --scan > /etc/mdadm.conf
[root@testhoteles ~]# cat /etc/mdadm.conf
ARRAY /dev/md1 metadata=1.2 name=testhoteles.hs.com:1 UUID=611ac412:b50551be:6cf89141:7d2d4580
3.4 挂载并开机启动
[root@testhoteles ~]# mkfs -t xfs /dev/md1
[root@testhoteles ~]# mkdir /data
[root@testhoteles ~]# cat /etc/fstab | grep /data
/dev/md1 /data xfs defaults 0 0
[root@testhoteles ~]# mount -a
[root@testhoteles ~]# df -TH | grep /data
/dev/md1 xfs 500G 34M 500G 1% /data
# CentOS7更新initramfs，避免raid名称变成md127，在对raid有更新的情况下，都需要更新一下initramfs的，以保证在启动时能正确的找到raid信息
[root@testhoteles ~]# dracut --mdadmconf --fstab --add="mdraid" --filesystems "xfs ext4 ext3" --add-drivers="raid1" --force /boot/initramfs-$(uname -r).img $(uname -r) -M
# 检查是否配置生效
[root@syslog ~]# ls /boot/initramfs-$(uname -r).img
/boot/initramfs-3.10.0-1160.119.1.el7.x86_64.img
# 查看/boot/initramfs-3.10.0-1160.119.1.el7.x86_64.img镜像中所有文件，通过过滤条件进行查看
[root@syslog ~]# lsinitrd /boot/initramfs-$(uname -r).img | grep -E 'mdraid|raid1|xfs|ext4|ext3'
Arguments: --mdadmconf --fstab --add 'mdraid' --filesystems 'xfs ext4 ext3' --add-drivers 'raid1' --force -M
mdraid
-rwxr-xr-x 1 root root 265 Sep 12 2013 usr/lib/dracut/hooks/cleanup/99-mdraid-needshutdown.sh
-rwxr-xr-x 1 root root 910 Sep 12 2013 usr/lib/dracut/hooks/pre-mount/10-mdraid-waitclean.sh
-rw-r--r-- 1 root root 22232 Jun 4 2024 usr/lib/modules/3.10.0-1160.119.1.el7.x86_64/kernel/drivers/md/raid1.ko.xz
drwxr-xr-x 2 root root 0 Apr 9 13:57 usr/lib/modules/3.10.0-1160.119.1.el7.x86_64/kernel/fs/ext4
-rw-r--r-- 1 root root 224256 Jun 4 2024 usr/lib/modules/3.10.0-1160.119.1.el7.x86_64/kernel/fs/ext4/ext4.ko.xz
drwxr-xr-x 2 root root 0 Apr 9 13:57 usr/lib/modules/3.10.0-1160.119.1.el7.x86_64/kernel/fs/xfs
-rw-r--r-- 1 root root 348176 Jun 4 2024 usr/lib/modules/3.10.0-1160.119.1.el7.x86_64/kernel/fs/xfs/xfs.ko.xz
-rwxr-xr-x 3 root root 0 Apr 9 13:57 usr/sbin/fsck.ext3
-rwxr-xr-x 3 root root 256560 Apr 9 13:57 usr/sbin/fsck.ext4
-rwxr-xr-x 1 root root 433 Oct 1 2020 usr/sbin/fsck.xfs
-rwxr-xr-x 1 root root 708 Sep 12 2013 usr/sbin/mdraid-cleanup
-rwxr-xr-x 1 root root 1951 Sep 30 2020 usr/sbin/mdraid_start
-rwxr-xr-x 1 root root 590208 Apr 9 13:57 usr/sbin/xfs_db
-rwxr-xr-x 1 root root 747 Oct 1 2020 usr/sbin/xfs_metadump
-rwxr-xr-x 1 root root 576720 Apr 9 13:57 usr/sbin/xfs_repair
## 查看/boot/initramfs-3.10.0-1160.119.1.el7.x86_64.img镜像中的文件etc/mdadm.conf的内容
[root@syslog ~]# lsinitrd /boot/initramfs-$(uname -r).img -f etc/mdadm.conf
ARRAY /dev/md1 metadata=1.2 name=syslog:1 UUID=2b810998:9c4d6da4:cfac8aa3:2c176956
CentOS7更新initramfs可不做，因为后续测试重启服务器，也能成功挂载到/data目录下
3.5 模拟软RAID故障和修复
# 手动停掉一个设备(当设备显示磨损迹象时，例如通过SMART)
[root@testhoteles ~]# mdadm --manage /dev/md1 --fail /dev/sda1
mdadm: set /dev/sda1 faulty in /dev/md1
[root@testhoteles ~]# mdadm -D /dev/md1
/dev/md1:
Version : 1.2
Creation Time : Wed May 8 06:11:58 2024
Raid Level : raid1
Array Size : 488253440 (465.63 GiB 499.97 GB)
Used Dev Size : 488253440 (465.63 GiB 499.97 GB)
Raid Devices : 2
Total Devices : 2
Persistence : Superblock is persistent
Intent Bitmap : Internal
Update Time : Wed May 8 15:39:18 2024
State : clean, degraded
Active Devices : 1
Working Devices : 1
Failed Devices : 1
Spare Devices : 0
Consistency Policy : bitmap
Name : testhoteles.hs.com:1 (local to host testhoteles.hs.com)
UUID : 611ac412:b50551be:6cf89141:7d2d4580
Events : 1129
Number Major Minor RaidDevice State
- 0 0 0 removed
1 8 17 1 active sync /dev/sdb1
0 8 1 - faulty /dev/sda1# 此时/dev/sda1是故障的，不影响使用
[root@testhoteles ~]# df -TH | grep /data
/dev/md1 xfs 500G 35M 500G 1% /data
# 移除一个错误的组员设备(在设备故障后，应提前更换设备)
[root@testhoteles ~]# mdadm --manage /dev/md1 --remove /dev/sda1
mdadm: hot removed /dev/sda1 from /dev/md1
[root@testhoteles ~]# mdadm -D /dev/md1
/dev/md1:
Version : 1.2
Creation Time : Wed May 8 06:11:58 2024
Raid Level : raid1
Array Size : 488253440 (465.63 GiB 499.97 GB)
Used Dev Size : 488253440 (465.63 GiB 499.97 GB)
Raid Devices : 2
Total Devices : 1
Persistence : Superblock is persistent
Intent Bitmap : Internal
Update Time : Wed May 8 15:41:10 2024
State : clean, degraded
Active Devices : 1
Working Devices : 1
Failed Devices : 0
Spare Devices : 0
Consistency Policy : bitmap
Name : testhoteles.hs.com:1 (local to host testhoteles.hs.com)
UUID : 611ac412:b50551be:6cf89141:7d2d4580
Events : 1134
Number Major Minor RaidDevice State
- 0 0 0 removed # 已经移除
1 8 17 1 active sync /dev/sdb1
# 添加一个成员到现有阵列，这将开始重建修复，因为硬盘超级块信息未清除，而且是/dev/md1原来的成员磁盘，所以加入进来后不需要同步 或者 及少数同步就可使用
[root@testhoteles ~]# mdadm /dev/md1 --add /dev/sda1
mdadm: re-added /dev/sda1
[root@testhoteles ~]# mdadm -D /dev/md1
/dev/md1:
Version : 1.2
Creation Time : Wed May 8 06:11:58 2024
Raid Level : raid1
Array Size : 488253440 (465.63 GiB 499.97 GB)
Used Dev Size : 488253440 (465.63 GiB 499.97 GB)
Raid Devices : 2
Total Devices : 2
Persistence : Superblock is persistent
Intent Bitmap : Internal
Update Time : Wed May 8 15:42:06 2024
State : clean # 状态是健康的
Active Devices : 2
Working Devices : 2
Failed Devices : 0
Spare Devices : 0
Consistency Policy : bitmap
Name : testhoteles.hs.com:1 (local to host testhoteles.hs.com)
UUID : 611ac412:b50551be:6cf89141:7d2d4580
Events : 1158
Number Major Minor RaidDevice State
0 8 1 0 active sync /dev/sda1
1 8 17 1 active sync /dev/sdb1
# 当有数据写入时，状态为active
[root@testhoteles ~]# mdadm -D /dev/md1
/dev/md1:
Version : 1.2
Creation Time : Wed May 8 06:11:58 2024
Raid Level : raid1
Array Size : 488253440 (465.63 GiB 499.97 GB)
Used Dev Size : 488253440 (465.63 GiB 499.97 GB)
Raid Devices : 2
Total Devices : 2
Persistence : Superblock is persistent
Intent Bitmap : Internal
Update Time : Wed May 8 12:25:06 2024
State : active
Active Devices : 2
Working Devices : 2
Failed Devices : 0
Spare Devices : 0
Consistency Policy : bitmap
Name : testhoteles.hs.com:1 (local to host testhoteles.hs.com)
UUID : 611ac412:b50551be:6cf89141:7d2d4580
Events : 2291
Number Major Minor RaidDevice State
2 8 1 0 active sync /dev/sda1
1 8 17 1 active sync /dev/sdb1
3.6 扩容软RAID，RAID0和RAID5可以
mdadm /dev/md5 -a /dev/sde1
mdadm --grow /dev/md5 --raid-devices=4
xfs_growfs -d /mnt
3.7 清除软RAID超级块信息
将软RAID其中一个分区独立出来时，用于其他目的之前必须清除软RAID超级块信息，因为只有清除了此数据后，该分区才干净可用于挂载、或者当做其它软RAID成员使用。
# 清除硬盘超级块信息
[root@testhoteles ~]# mdadm --zero-superblock /dev/sda1
[root@testhoteles ~]# mdadm -D /dev/md1
/dev/md1:
Version : 1.2
Creation Time : Wed May 8 06:11:58 2024
Raid Level : raid1
Array Size : 488253440 (465.63 GiB 499.97 GB)
Used Dev Size : 488253440 (465.63 GiB 499.97 GB)
Raid Devices : 2
Total Devices : 1
Persistence : Superblock is persistent
Intent Bitmap : Internal
Update Time : Wed May 8 15:43:16 2024
State : clean, degraded
Active Devices : 1
Working Devices : 1
Failed Devices : 0
Spare Devices : 0
Consistency Policy : bitmap
Name : testhoteles.hs.com:1 (local to host testhoteles.hs.com)
UUID : 611ac412:b50551be:6cf89141:7d2d4580
Events : 1163
Number Major Minor RaidDevice State
- 0 0 0 removed
1 8 17 1 active sync /dev/sdb1
# 加入清除硬盘超级块信息后的磁盘，将会使此块磁盘从新同步另一块磁盘，从0开始
[root@testhoteles ~]# mdadm /dev/md1 --add /dev/sda1
mdadm: added /dev/sda1
[root@testhoteles ~]# mdadm -D /dev/md1
/dev/md1:
Version : 1.2
Creation Time : Wed May 8 06:11:58 2024
Raid Level : raid1
Array Size : 488253440 (465.63 GiB 499.97 GB)
Used Dev Size : 488253440 (465.63 GiB 499.97 GB)
Raid Devices : 2
Total Devices : 2
Persistence : Superblock is persistent
Intent Bitmap : Internal
Update Time : Wed May 8 15:43:47 2024
State : clean, degraded, recovering
Active Devices : 1
Working Devices : 2
Failed Devices : 0
Spare Devices : 1
Consistency Policy : bitmap
Rebuild Status : 0% complete
Name : testhoteles.hs.com:1 (local to host testhoteles.hs.com)
UUID : 611ac412:b50551be:6cf89141:7d2d4580
Events : 1167
Number Major Minor RaidDevice State
2 8 1 0 spare rebuilding /dev/sda1
1 8 17 1 active sync /dev/sdb1
3.8 软RAID故障告警
$ yum install -y mailx
$ vim /etc/mail.rc
set from=name@test.com
set smtp=smtp.qiye.163.com
set smtp-auth=login
set smtp-auth-user=name@test.com
set smtp-auth-password=password
set ssl-verify=ignore
$ cat /shell/send_mail.sh
#!/bin/bash
HOST=`/sbin/ip a s eth0 | /bin/grep -oP '(?<=inet\s)\d+(\.\d+){3}'`
echo "testhoteles($HOST) soft raid status is change, can fail!" | mail -s "softraid alert" name@test.com
$ vim /etc/rc.d/rc.local
# monitor mdadm
mdadm --monitor --daemonise --delay=60 --scan --program=/shell/send_mail.sh
3.9 软RAID相关故障
**事情起由：**公司停电，服务器未先关闭，所以服务器是突然关闭的，来电后，服务器起来不了
centos7 启动报错描述：
dracut-initqueue: Warning: dracut-initqueue timeout - starting timeout scripts;
dracut-initqueue: Warning: dracut-initqueue timeout - starting timeout scripts;
.....
dracut-initqueue: Warning: /dev/centos/root does not exist
dracut-initqueue: Warning: /dev/centos/swap does not exist
dracut-initqueue: Warning: /dev/mapper/centos-root does not exist
1. 通过LiveCD挂载系统盘操作–未采用此方式
# 挂载/
sudo mount /dev/mapper/centos-root /mnt
# 挂载/boot
sudo mount /dev/sda1 /mnt/boot
# 挂载当前LiveCD的目录 /dev /proc 到 /mnt之中，
sudo mount -o bind /dev /mnt/dev
sudo mount -t proc /proc /mnt/proc
# 更改/
sudo chroot /mnt
# 更改/后，只能进去修改和备份配置文件，对于修复/boot里面的操作会失败，例如执行以下命令会提示/proc里面的一些文件未找到，所以未成功，而故障原因正是在这里，因为在做RAID的时候为了让RAID的名称不变开机自动挂载，从而更改了initramfs-3.10.0-1160.119.1.el7.x86_64.img里面的参数，突然断电导致里面参数和软RAID不兼容了
dracut -f /boot/initramfs-3.10.0-1160.119.1.el7.x86_64.img 3.10.0-1160.119.1.el7.x86_64
# 不能修复，所以退出/
exit
# 在LiveCD系统上操作，对源系统分区文件系统进行修复
# 对`/`进行修复，命令执行成功
sudo xfs_repair -v /dev/mapper/centos-root
# 对`/boot`进行修复，命令执行失败
sudo fsck /dev/sda1 # 提示使用xfs-repair命令，应该不是ext文件系统
sudo xfs_repair -v /dev/sda1 # 提示文件系统发生了元数据变化，需要使用`sudo xfs_repair -vL /dev/sda1`命令，但是`-L`参数可能会导致文件系统损坏，有风险所以没有执行，实在没有办法可执行此命令试试
通过liveCD操作，得出结论：
- 在chroot中，无法对
/boot分区执行dracut等涉及内核的变更操作- 在chroot中，可以备份旧硬盘中的数据到备份位置中
- 在LiveCD命令行中，对
/boot分区执行修复报错，说明此分区有问题，需要加-L参数，但是-L参数可能会导致文件系统损坏，有风险所以没有执行，实在没有办法可执行此命令试试，其实哪个分区报错，往往说明这个分区有问题- 在LiveCD命令行中，对
/分区执行修复成功，说明无问题。
2.通过系统自带的救援模式操作–采用此方式
centos启动菜单描述：
CentOS Linux(3.10.8-1160.119.1.e17.x86 64)7 (Core)是默认启动的菜单，内核为1160，是系统更新后的内核版本CentOS Linux(3.10.8-327.e17.x86 64)7(Core)是旧的启动的菜单，内核为327，是系统更新前的内核版本Cent0S linux(-rescue-d4c338676e204e23a84637cd863cae7d)7(Core)是救援模式菜单，内核其实也为327，但是跟CentOS Linux(3.10.8-327.e17.x86 64)7(Core)有点不同，我们需要使用此模式来修复/boot分区
进入救援模式，执行命令对/boot分区进行修复
# 选择默认启动系统菜单对应的img，从/boor/grub2/grub.cfg中可以看出
[root@syslog ~]# dracut -f /boot/initramfs-3.10.0-1160.119.1.el7.x86_64.img 3.10.0-1160.119.1.el7.x86_64
[root@syslog ~]# lsinitrd /boot/initramfs-3.10.0-1160.119.1.el7.x86_64.img | grep -E 'mdraid|raid1|xfs|ext4|ext3'
drwxr-xr-x 2 root root 0 Sep 17 2013 usr/lib/modules/3.10.0-1160.119.1.el7.x86_64/kernel/fs/xfs
-rw-r--r-- 1 root root 348176 Jun 4 2024 usr/lib/modules/3.10.0-1160.119.1.el7.x86_64/kernel/fs/xfs/xfs.ko.xz
-rwxr-xr-x 1 root root 433 Oct 1 2020 usr/sbin/fsck.xfs
-rwxr-xr-x 1 root root 590208 Sep 17 2013 usr/sbin/xfs_db
-rwxr-xr-x 1 root root 747 Oct 1 2020 usr/sbin/xfs_metadump
-rwxr-xr-x 1 root root 576720 Sep 17 2013 usr/sbin/xfs_repair
修复完成后重新启动系统，从CentOS Linux(3.10.8-1160.119.1.e17.x86 64)7 (Core)菜单进入
# 此时正常进入系统，再次查看img没有了之前写入相关md1的配置
[root@syslog ~]# lsinitrd /boot/initramfs-$(uname -r).img | grep -E 'mdraid|raid1|xfs|ext4|ext3'
drwxr-xr-x 2 root root 0 Sep 17 2013 usr/lib/modules/3.10.0-1160.119.1.el7.x86_64/kernel/fs/xfs
-rw-r--r-- 1 root root 348176 Jun 4 2024 usr/lib/modules/3.10.0-1160.119.1.el7.x86_64/kernel/fs/xfs/xfs.ko.xz
-rwxr-xr-x 1 root root 433 Oct 1 2020 usr/sbin/fsck.xfs
-rwxr-xr-x 1 root root 590208 Sep 17 2013 usr/sbin/xfs_db
-rwxr-xr-x 1 root root 747 Oct 1 2020 usr/sbin/xfs_metadump
-rwxr-xr-x 1 root root 576720 Sep 17 2013 usr/sbin/xfs_repair
此时已无之前配置的mdraid相关参数，如下为之前配置的数据信息
[root@syslog ~]# lsinitrd /boot/initramfs-$(uname -r).img | grep -E 'mdraid|raid1|xfs|ext4|ext3' Arguments: --mdadmconf --fstab --add 'mdraid' --filesystems 'xfs ext4 ext3' --add-drivers 'raid1' --force -M mdraid -rwxr-xr-x 1 root root 265 Sep 12 2013 usr/lib/dracut/hooks/cleanup/99-mdraid-needshutdown.sh -rwxr-xr-x 1 root root 910 Sep 12 2013 usr/lib/dracut/hooks/pre-mount/10-mdraid-waitclean.sh -rw-r--r-- 1 root root 22232 Jun 4 2024 usr/lib/modules/3.10.0-1160.119.1.el7.x86_64/kernel/drivers/md/raid1.ko.xz drwxr-xr-x 2 root root 0 Apr 9 13:57 usr/lib/modules/3.10.0-1160.119.1.el7.x86_64/kernel/fs/ext4 -rw-r--r-- 1 root root 224256 Jun 4 2024 usr/lib/modules/3.10.0-1160.119.1.el7.x86_64/kernel/fs/ext4/ext4.ko.xz drwxr-xr-x 2 root root 0 Apr 9 13:57 usr/lib/modules/3.10.0-1160.119.1.el7.x86_64/kernel/fs/xfs -rw-r--r-- 1 root root 348176 Jun 4 2024 usr/lib/modules/3.10.0-1160.119.1.el7.x86_64/kernel/fs/xfs/xfs.ko.xz -rwxr-xr-x 3 root root 0 Apr 9 13:57 usr/sbin/fsck.ext3 -rwxr-xr-x 3 root root 256560 Apr 9 13:57 usr/sbin/fsck.ext4 -rwxr-xr-x 1 root root 433 Oct 1 2020 usr/sbin/fsck.xfs -rwxr-xr-x 1 root root 708 Sep 12 2013 usr/sbin/mdraid-cleanup -rwxr-xr-x 1 root root 1951 Sep 30 2020 usr/sbin/mdraid_start -rwxr-xr-x 1 root root 590208 Apr 9 13:57 usr/sbin/xfs_db -rwxr-xr-x 1 root root 747 Oct 1 2020 usr/sbin/xfs_metadump -rwxr-xr-x 1 root root 576720 Apr 9 13:57 usr/sbin/xfs_repair
查看软RAID挂载配置
[root@syslog ~]# cat /etc/fstab | grep md1
/dev/md1 /data xfs defaults 0 0
[root@syslog ~]# cat /etc/mdadm.conf
ARRAY /dev/md1 metadata=1.2 name=syslog:1 UUID=2b810998:9c4d6da4:cfac8aa3:2c176956
经过多次重启测试，每次都可以自动挂载
/dev/md1到/data目录下，并无挂载失效问题，所以前面的CentOS7更新initramfs命令可不执行，只确定/etc/fatab和/etc/mdadm.conf的配置正常即可
3. 软RAID故障处理
确定硬盘是否故障
# 查看软raid状态
[root@testhoteles ~]# mdadm -D /dev/md1
/dev/md1:
Version : 1.2
Creation Time : Wed May 8 06:11:58 2024
Raid Level : raid1
Array Size : 488253440 (465.63 GiB 499.97 GB)
Used Dev Size : 488253440 (465.63 GiB 499.97 GB)
Raid Devices : 2
Total Devices : 2
Persistence : Superblock is persistent
Intent Bitmap : Internal
Update Time : Tue Jun 17 13:30:50 2025
State : active, degraded
Active Devices : 1
Working Devices : 1
Failed Devices : 1
Spare Devices : 0
Consistency Policy : bitmap
Name : testhoteles.hs.com:1 (local to host testhoteles.hs.com)
UUID : 611ac412:b50551be:6cf89141:7d2d4580
Events : 2033547
Number Major Minor RaidDevice State
- 0 0 0 removed
1 8 17 1 active sync /dev/sdb1
2 8 1 - faulty /dev/sda1
# 对故障的硬盘进行查看，由此可见已经可能故障
[root@testhoteles ~]# smartctl -a /dev/sda
smartctl 7.0 2018-12-30 r4883 [x86_64-linux-3.10.0-1160.118.1.el7.x86_64] (local build)
Copyright (C) 2002-18, Bruce Allen, Christian Franke, www.smartmontools.org
Short INQUIRY response, skip product id
A mandatory SMART command failed: exiting. To continue, add one or more '-T permissive' options.
# 对正常的硬盘进行查看
[root@testhoteles ~]# smartctl -a /dev/sda
smartctl 7.0 2018-12-30 r4883 [x86_64-linux-3.10.0-1160.118.1.el7.x86_64] (local build)
Copyright (C) 2002-18, Bruce Allen, Christian Franke, www.smartmontools.org
Short INQUIRY response, skip product id
A mandatory SMART command failed: exiting. To continue, add one or more '-T permissive' options.
[root@testhoteles ~]# smartctl -a /dev/sdb
smartctl 7.0 2018-12-30 r4883 [x86_64-linux-3.10.0-1160.118.1.el7.x86_64] (local build)
Copyright (C) 2002-18, Bruce Allen, Christian Franke, www.smartmontools.org
=== START OF INFORMATION SECTION ===
Model Family: Seagate Barracuda 7200.14 (AF)
Device Model: ST500DM002-1BD142
Serial Number: Z3TQ7THR
LU WWN Device Id: 5 000c50 064a40353
Firmware Version: KC47
User Capacity: 500,107,862,016 bytes [500 GB]
Sector Sizes: 512 bytes logical, 4096 bytes physical
Rotation Rate: 7200 rpm
Device is: In smartctl database [for details use: -P show]
ATA Version is: ATA8-ACS T13/1699-D revision 4
SATA Version is: SATA 3.0, 6.0 Gb/s (current: 6.0 Gb/s)
Local Time is: Tue Jun 17 13:31:17 2025 CST
SMART support is: Available - device has SMART capability.
SMART support is: Enabled
=== START OF READ SMART DATA SECTION ===
SMART overall-health self-assessment test result: PASSED
General SMART Values:
Offline data collection status: (0x82) Offline data collection activity
was completed without error.
Auto Offline Data Collection: Enabled.
Self-test execution status: ( 0) The previous self-test routine completed
without error or no self-test has ever
been run.
Total time to complete Offline
data collection: ( 600) seconds.
Offline data collection
capabilities: (0x7b) SMART execute Offline immediate.
Auto Offline data collection on/off support.
Suspend Offline collection upon new
command.
Offline surface scan supported.
Self-test supported.
Conveyance Self-test supported.
Selective Self-test supported.
SMART capabilities: (0x0003) Saves SMART data before entering
power-saving mode.
Supports SMART auto save timer.
Error logging capability: (0x01) Error logging supported.
General Purpose Logging supported.
Short self-test routine
recommended polling time: ( 1) minutes.
Extended self-test routine
recommended polling time: ( 78) minutes.
Conveyance self-test routine
recommended polling time: ( 2) minutes.
SCT capabilities: (0x303f) SCT Status supported.
SCT Error Recovery Control supported.
SCT Feature Control supported.
SCT Data Table supported.
SMART Attributes Data Structure revision number: 10
Vendor Specific SMART Attributes with Thresholds:
ID# ATTRIBUTE_NAME FLAG VALUE WORST THRESH TYPE UPDATED WHEN_FAILED RAW_VALUE
1 Raw_Read_Error_Rate 0x000f 102 099 006 Pre-fail Always - 23328
3 Spin_Up_Time 0x0003 100 097 000 Pre-fail Always - 0
4 Start_Stop_Count 0x0032 093 093 020 Old_age Always - 8147
5 Reallocated_Sector_Ct 0x0033 100 100 036 Pre-fail Always - 0
7 Seek_Error_Rate 0x000f 081 060 030 Pre-fail Always - 147092174
9 Power_On_Hours 0x0032 058 058 000 Old_age Always - 37450
10 Spin_Retry_Count 0x0013 100 100 097 Pre-fail Always - 0
12 Power_Cycle_Count 0x0032 099 099 020 Old_age Always - 1693
183 Runtime_Bad_Block 0x0032 100 100 000 Old_age Always - 0
184 End-to-End_Error 0x0032 100 100 099 Old_age Always - 0
187 Reported_Uncorrect 0x0032 099 099 000 Old_age Always - 1
188 Command_Timeout 0x0032 100 098 000 Old_age Always - 5 5 5
189 High_Fly_Writes 0x003a 100 100 000 Old_age Always - 0
190 Airflow_Temperature_Cel 0x0022 055 048 045 Old_age Always - 45 (Min/Max 21/49)
194 Temperature_Celsius 0x0022 045 052 000 Old_age Always - 45 (0 4 0 0 0)
195 Hardware_ECC_Recovered 0x001a 048 023 000 Old_age Always - 23328
197 Current_Pending_Sector 0x0012 100 100 000 Old_age Always - 0
198 Offline_Uncorrectable 0x0010 100 100 000 Old_age Offline - 0
199 UDMA_CRC_Error_Count 0x003e 200 200 000 Old_age Always - 0
240 Head_Flying_Hours 0x0000 100 253 000 Old_age Offline - 35085h+52m+51.078s
241 Total_LBAs_Written 0x0000 100 253 000 Old_age Offline - 686882885
242 Total_LBAs_Read 0x0000 100 253 000 Old_age Offline - 1844199465
SMART Error Log Version: 1
No Errors Logged
SMART Self-test log structure revision number 1
Num Test_Description Status Remaining LifeTime(hours) LBA_of_first_error
# 1 Short offline Completed without error 00% 0 -
SMART Selective self-test log data structure revision number 1
SPAN MIN_LBA MAX_LBA CURRENT_TEST_STATUS
1 0 0 Not_testing
2 0 0 Not_testing
3 0 0 Not_testing
4 0 0 Not_testing
5 0 0 Not_testing
Selective self-test flags (0x0):
After scanning selected spans, do NOT read-scan remainder of disk.
If Selective self-test is pending on power-up, resume after 0 minute delay.
# 查看日志截图sda磁盘是否有故障
[root@testhoteles ~]# dmesg | grep -i sda | tail -n 20
[30422350.262969] sd 0:0:0:0: [sda] tag#1 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
[30422350.262977] sd 0:0:0:0: [sda] tag#1 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
[30422350.263274] sd 0:0:0:0: [sda] tag#2 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
[30422350.263281] sd 0:0:0:0: [sda] tag#2 CDB: ATA command pass through(16) 85 06 2c 00 da 00 00 00 00 00 4f 00 c2 00 b0 00
[30424149.433114] sd 0:0:0:0: [sda] tag#5 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
[30424149.433121] sd 0:0:0:0: [sda] tag#5 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
[30425949.742854] sd 0:0:0:0: [sda] tag#7 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
[30425949.742862] sd 0:0:0:0: [sda] tag#7 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
[30427750.047628] sd 0:0:0:0: [sda] tag#9 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
[30427750.047637] sd 0:0:0:0: [sda] tag#9 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
[30429550.214047] sd 0:0:0:0: [sda] tag#11 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
[30429550.214055] sd 0:0:0:0: [sda] tag#11 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
[30431350.386420] sd 0:0:0:0: [sda] tag#13 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
[30431350.386429] sd 0:0:0:0: [sda] tag#13 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
[30433149.616538] sd 0:0:0:0: [sda] tag#15 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
[30433149.616543] sd 0:0:0:0: [sda] tag#15 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
[30434949.845775] sd 0:0:0:0: [sda] tag#17 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
[30434949.845783] sd 0:0:0:0: [sda] tag#17 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
[30436750.032715] sd 0:0:0:0: [sda] tag#3 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
[30436750.032722] sd 0:0:0:0: [sda] tag#3 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
[root@testhoteles ~]# journalctl -k | grep -i sda | tail -n 20
6月 17 09:27:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#1 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
6月 17 09:27:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#1 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
6月 17 09:27:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#2 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
6月 17 09:27:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#2 CDB: ATA command pass through(16) 85 06 2c 00 da 00 00 00 00 00 4f 00 c2 00 b0 00
6月 17 09:57:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#5 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
6月 17 09:57:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#5 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
6月 17 10:27:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#7 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
6月 17 10:27:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#7 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
6月 17 10:57:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#9 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
6月 17 10:57:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#9 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
6月 17 11:27:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#11 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
6月 17 11:27:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#11 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
6月 17 11:57:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#13 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
6月 17 11:57:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#13 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
6月 17 12:27:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#15 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
6月 17 12:27:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#15 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
6月 17 12:57:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#17 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
6月 17 12:57:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#17 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
6月 17 13:27:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#3 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK cmd_age=0s
6月 17 13:27:54 testhoteles.hs.com kernel: sd 0:0:0:0: [sda] tag#3 CDB: ATA command pass through(16) 85 06 2c 00 00 00 00 00 00 00 00 00 00 00 e5 00
# 查看/dev/sda磁盘是否有响应，直接从硬盘获取详细/当前信息
[root@testhoteles ~]# hdparm -I /dev/sda
/dev/sda:
HDIO_DRIVE_CMD(identify) failed: Input/output error
# 查看/dev/sdb磁盘是否有响应，直接从硬盘获取详细/当前信息
[root@testhoteles ~]# hdparm -I /dev/sdb
/dev/sdb:
ATA device, with non-removable media
Model Number: ST500DM002-1BD142
Serial Number: Z3TQ7THR
Firmware Revision: KC47
Transport: Serial, SATA Rev 3.0
Standards:
Used: unknown (minor revision code 0x0029)
Supported: 8 7 6 5
Likely used: 8
Configuration:
Logical max current
cylinders 16383 16383
heads 16 16
sectors/track 63 63
--
CHS current addressable sectors: 16514064
LBA user addressable sectors: 268435455
LBA48 user addressable sectors: 976773168
Logical Sector size: 512 bytes
Physical Sector size: 4096 bytes
Logical Sector-0 offset: 0 bytes
device size with M = 1024*1024: 476940 MBytes
device size with M = 1000*1000: 500107 MBytes (500 GB)
cache/buffer size = 16384 KBytes
Nominal Media Rotation Rate: 7200
Capabilities:
LBA, IORDY(can be disabled)
Queue depth: 32
Standby timer values: spec'd by Standard, no device specific minimum
R/W multiple sector transfer: Max = 16 Current = 16
Recommended acoustic management value: 208, current value: 208
DMA: mdma0 mdma1 mdma2 udma0 udma1 udma2 udma3 udma4 udma5 *udma6
Cycle time: min=120ns recommended=120ns
PIO: pio0 pio1 pio2 pio3 pio4
Cycle time: no flow control=120ns IORDY flow control=120ns
Commands/features:
Enabled Supported:
* SMART feature set
Security Mode feature set
* Power Management feature set
* Write cache
* Look-ahead
* Host Protected Area feature set
* WRITE_BUFFER command
* READ_BUFFER command
* DOWNLOAD_MICROCODE
Power-Up In Standby feature set
* SET_FEATURES required to spinup after power up
SET_MAX security extension
* Automatic Acoustic Management feature set
* 48-bit Address feature set
* Device Configuration Overlay feature set
* Mandatory FLUSH_CACHE
* FLUSH_CACHE_EXT
* SMART error logging
* SMART self-test
* General Purpose Logging feature set
* WRITE_{DMA|MULTIPLE}_FUA_EXT
* 64-bit World wide name
Write-Read-Verify feature set
* WRITE_UNCORRECTABLE_EXT command
* {READ,WRITE}_DMA_EXT_GPL commands
* Segmented DOWNLOAD_MICROCODE
* Gen1 signaling speed (1.5Gb/s)
* Gen2 signaling speed (3.0Gb/s)
* Gen3 signaling speed (6.0Gb/s)
* Native Command Queueing (NCQ)
* Phy event counters
* unknown 76[15]
Device-initiated interface power management
* Software settings preservation
* SMART Command Transport (SCT) feature set
* SCT Read/Write Long (AC1), obsolete
* SCT Write Same (AC2)
* SCT Error Recovery Control (AC3)
* SCT Features Control (AC4)
* SCT Data Tables (AC5)
unknown 206[12] (vendor specific)
unknown 206[13] (vendor specific)
Security:
Master password revision code = 65534
supported
not enabled
not locked
frozen
not expired: security count
supported: enhanced erase
76min for SECURITY ERASE UNIT. 76min for ENHANCED SECURITY ERASE UNIT.
Logical Unit WWN Device Identifier: 5000c50064a40353
NAA : 5
IEEE OUI : 000c50
Unique ID : 064a40353
Checksum: correct
可通过好的硬盘编号来反向推断坏的硬盘，以下编号的硬盘是好的，也就是除开以下编号的硬盘是坏的
Serial Number: Z3TQ7THR LU WWN Device Id: 5 000c50 064a40353
更改换好新硬盘后，添加新硬盘到软raid组中
# 添加新硬盘
[root@testhoteles ~]# mdadm /dev/md1 --add /dev/sda1
mdadm: added /dev/sda1
# 查看状态，此时正在重建中
[root@testhoteles ~]# mdadm -D /dev/md1
/dev/md1:
Version : 1.2
Creation Time : Wed May 8 06:11:58 2024
Raid Level : raid1
Array Size : 488253440 (465.63 GiB 499.97 GB)
Used Dev Size : 488253440 (465.63 GiB 499.97 GB)
Raid Devices : 2
Total Devices : 2
Persistence : Superblock is persistent
Intent Bitmap : Internal
Update Time : Tue Jun 17 13:46:13 2025
State : active, degraded, recovering
Active Devices : 1
Working Devices : 2
Failed Devices : 0
Spare Devices : 1
Consistency Policy : bitmap
Rebuild Status : 0% complete
Name : testhoteles.hs.com:1 (local to host testhoteles.hs.com)
UUID : 611ac412:b50551be:6cf89141:7d2d4580
Events : 2033885
Number Major Minor RaidDevice State
2 8 1 0 spare rebuilding /dev/sda1
1 8 17 1 active sync /dev/sdb1
# 正在重建中
[root@testhoteles ~]# cat /proc/mdstat
Personalities : [raid1]
md1 : active raid1 sda1[2] sdb1[1]
488253440 blocks super 1.2 [2/1] [_U]
[>....................] recovery = 0.0% (38016/488253440) finish=7794.8min speed=1043K/sec
bitmap: 3/4 pages [12KB], 65536KB chunk
unused devices: <none>
4. LVM VG同名冲突问题
新机器：安装CentOS 7操作系统，有/dev/centos/root和/dev/centos/swap LV，VG名称为centos
旧机器：也是CentOS 7操作系统有/dev/centos/root和/dev/centos/swap LV，VG名称为centos
因为旧机器有坏道，elasticsearch7服务读取索引报错，无法继续使用，所以需要重新更换新磁盘，将此旧磁盘数据迁移到新硬盘之上
问题：新机器和旧机器都有VG名称为centos，该如何迁移数据
4.1 当前LVM信息
PV信息
[root@syslog ~]# pvdisplay
--- Physical volume ---
PV Name /dev/sda2
VG Name centos
PV Size 223.08 GiB / not usable 3.00 MiB
Allocatable yes (but full)
PE Size 4.00 MiB
Total PE 57108
Free PE 0
Allocated PE 57108
PV UUID pUfIZ0-Fmwd-Y3IT-E794-ZNZa-RfkU-wtFeTE
--- Physical volume ---
PV Name /dev/sdd2
VG Name centos
PV Size <1.82 TiB / not usable 4.00 MiB
Allocatable yes (but full)
PE Size 4.00 MiB
Total PE 476806
Free PE 0
Allocated PE 476806
PV UUID ZAsYXD-fdeV-AGoV-oP0P-BmiK-yZ7p-dgPTp2
VG信息
[root@syslog ~]# vgdisplay
--- Volume group ---
VG Name centos
System ID
Format lvm2
Metadata Areas 1
Metadata Sequence No 7
VG Access read/write
VG Status resizable
MAX LV 0
Cur LV 2
Open LV 2
Max PV 0
Cur PV 1
Act PV 1
VG Size <223.08 GiB
PE Size 4.00 MiB
Total PE 57108
Alloc PE / Size 57108 / <223.08 GiB
Free PE / Size 0 / 0
VG UUID 0kZqzY-CU3x-WO5g-Yhsu-WPsV-34O8-beg0Fc
--- Volume group ---
VG Name centos
System ID
Format lvm2
Metadata Areas 1
Metadata Sequence No 7
VG Access read/write
VG Status resizable
MAX LV 0
Cur LV 2
Open LV 0
Max PV 0
Cur PV 1
Act PV 1
VG Size <1.82 TiB
PE Size 4.00 MiB
Total PE 476806
Alloc PE / Size 476806 / <1.82 TiB
Free PE / Size 0 / 0
VG UUID b8uQE2-lSBQ-pszt-jYwa-XX9n-KS0z-wLGdqS
LV信息
[root@syslog ~]# lvdisplay
--- Logical volume ---
LV Path /dev/centos/swap
LV Name swap
VG Name centos
LV UUID n0pO4Z-Htyg-O0Tt-Fb0P-ccnN-QnOB-9Y1Vl5
LV Write Access read/write
LV Creation host, time localhost.localdomain, 2025-04-07 17:23:21 +0800
LV Status available
# open 2
LV Size 7.81 GiB
Current LE 2000
Segments 1
Allocation inherit
Read ahead sectors auto
- currently set to 256
Block device 253:1
--- Logical volume ---
LV Path /dev/centos/root
LV Name root
VG Name centos
LV UUID ofjacO-gWSX-2Yif-05ic-0bcy-fAVg-S2eSLn
LV Write Access read/write
LV Creation host, time localhost.localdomain, 2025-04-07 17:23:22 +0800
LV Status available
# open 1
LV Size <215.27 GiB
Current LE 55108
Segments 2
Allocation inherit
Read ahead sectors auto
- currently set to 256
Block device 253:0
--- Logical volume ---
LV Path /dev/centos/swap
LV Name swap
VG Name centos
LV UUID WJ7f1U-BCz1-LOZg-djAZ-GvIR-t06P-3F4KKD
LV Write Access read/write
LV Creation host, time syslog, 2024-09-23 14:38:28 +0800
LV Status NOT available
LV Size 7.81 GiB
Current LE 2000
Segments 1
Allocation inherit
Read ahead sectors auto
--- Logical volume ---
LV Path /dev/centos/root
LV Name root
VG Name centos
LV UUID waqOcy-ettH-58z1-WogT-GgDY-v97j-fTij7p
LV Write Access read/write
LV Creation host, time syslog, 2024-09-23 14:38:32 +0800
LV Status NOT available
LV Size 1.81 TiB
Current LE 474806
Segments 2
Allocation inherit
Read ahead sectors auto
4.2 识别冲突的VG信息
[root@syslog ~]# pvs
PV VG Fmt Attr PSize PFree
/dev/sda2 centos lvm2 a-- <223.08g 0
/dev/sdd2 centos lvm2 a-- <1.82t 0
[root@syslog ~]# vgs -v
Cache: Duplicate VG name centos: Prefer existing 0kZqzY-CU3x-WO5g-Yhsu-WPsV-34O8-beg0Fc vs new b8uQE2-lSBQ-pszt-jYwa-XX9n-KS0z-wLGdqS
Cache: Duplicate VG name centos: Prefer existing b8uQE2-lSBQ-pszt-jYwa-XX9n-KS0z-wLGdqS vs new 0kZqzY-CU3x-WO5g-Yhsu-WPsV-34O8-beg0Fc
Archiving volume group "centos" metadata (seqno 7).
Archiving volume group "centos" metadata (seqno 7).
Creating volume group backup "/etc/lvm/backup/centos" (seqno 7).
Cache: Duplicate VG name centos: Prefer existing 0kZqzY-CU3x-WO5g-Yhsu-WPsV-34O8-beg0Fc vs new b8uQE2-lSBQ-pszt-jYwa-XX9n-KS0z-wLGdqS
Archiving volume group "centos" metadata (seqno 7).
Archiving volume group "centos" metadata (seqno 7).
Creating volume group backup "/etc/lvm/backup/centos" (seqno 7).
VG Attr Ext #PV #LV #SN VSize VFree VG UUID VProfile
centos wz--n- 4.00m 1 2 0 <223.08g 0 0kZqzY-CU3x-WO5g-Yhsu-WPsV-34O8-beg0Fc
centos wz--n- 4.00m 1 2 0 <1.82t 0 b8uQE2-lSBQ-pszt-jYwa-XX9n-KS0z-wLGdqS
4.3 根据UUID重命名VG（例如将原VG名centos改为centos_old）
[root@syslog ~]# vgrename b8uQE2-lSBQ-pszt-jYwa-XX9n-KS0z-wLGdqS centos_old
Processing VG centos because of matching UUID b8uQE2-lSBQ-pszt-jYwa-XX9n-KS0z-wLGdqS
Volume group "b8uQE2-lSBQ-pszt-jYwa-XX9n-KS0z-wLGdqS" successfully renamed to "centos_old"
[root@syslog ~]# vgs -v
Archiving volume group "centos" metadata (seqno 7).
Creating volume group backup "/etc/lvm/backup/centos" (seqno 7).
VG Attr Ext #PV #LV #SN VSize VFree VG UUID VProfile
centos wz--n- 4.00m 1 2 0 <223.08g 0 0kZqzY-CU3x-WO5g-Yhsu-WPsV-34O8-beg0Fc
centos_old wz--n- 4.00m 1 2 0 <1.82t 0 b8uQE2-lSBQ-pszt-jYwa-XX9n-KS0z-wLGdqS
4.4 激活并验证新VG
[root@syslog ~]# vgchange -ay centos_old
2 logical volume(s) in volume group "centos_old" now active
[root@syslog ~]# lvscan
ACTIVE '/dev/centos/swap' [7.81 GiB] inherit
ACTIVE '/dev/centos/root' [<215.27 GiB] inherit
ACTIVE '/dev/centos_old/swap' [7.81 GiB] inherit
ACTIVE '/dev/centos_old/root' [1.81 TiB] inherit
4.5 挂载外部硬盘到本机目录
[root@syslog ~]# mount /dev/centos_old/root /mnt/
[root@syslog ~]# ls /mnt
bin boot data dev download etc home lib lib64 media mnt opt proc root run sbin shell srv sys tmp usr var windows
### elasticsearch和docker数据在此目录
[root@syslog ~]# ls /mnt/data/
docker rsyslog
然后使用
rsync -avrPz SOURCE/* DEST/或者cp -ar命令进行数据迁移-a: archive -v: verbose -r: recursive -P: progress -z: compress SOURCE/*: 同步源目录下所有数据 DEST/：到目标目录之下
如果磁盘有坏道，可以使用dd命令
dd if=/dev/sda of=/dev/sdb bs=64k conv=noerror,sync status=progressconv=noerror,sync： 该参数组合是处理坏道的关键。noerror允许dd在读取错误时继续执行而非终止，sync则用零填充无法读取的块，确保目标设备与源设备的块对齐。