对软raid（mdadm）方式进行各个场景失效测试。
内核版本：
root@omv30:~# uname -a linux omv30 4.18.0-0.bpo.1-amd64 #1 smp debian 4.18.6-1~bpo9+1 (2018-09-13) x86_64 gnu/linux
使用omv创建raid1之后，查询sdb的信息，此时sdb对应的是8ac693c5的uuid，device号为1：
root@omv30:~# mdadm --query /dev/sdb /dev/sdb: is not an md array /dev/sdb: device 1 in 2 device undetected raid1 /dev/md0. use mdadm --examine for more detail.
我要评论root@omv30:~# mdadm --examine /dev/sdb
/dev/sdb:
magic : a92b4efc
version : 1.2
feature map : 0x0
array uuid : 921a8946:b273e00e:3fa4b99d:040a4437
name : omv30:raid1 (local to host omv30)
creation time : sun sep 30 22:31:39 2018
raid level : raid1
raid devices : 2
avail dev size : 2095104 (1023.00 mib 1072.69 mb)
array size : 1047552 (1023.00 mib 1072.69 mb)
data offset : 2048 sectors
super offset : 8 sectors
unused space : before=1960 sectors, after=0 sectors
state : clean
device uuid : 64a58fb5:c7e76b1a:29453878:8ac693c5
update time : mon oct 1 13:20:56 2018
bad block log : 512 entries available at offset 72 sectors
checksum : 2e1fb65b - correct
events : 21
device role : active device 1
array state : aa ('a' == active, '.' == missing, 'r' == replacing)
root@omv30:~# mdadm -d /dev/md0
/dev/md0:
version : 1.2
creation time : sun sep 30 22:31:39 2018
raid level : raid1
array size : 1047552 (1023.00 mib 1072.69 mb)
used dev size : 1047552 (1023.00 mib 1072.69 mb)
raid devices : 2
total devices : 2
persistence : superblock is persistent
update time : mon oct 1 19:46:42 2018
state : clean
active devices : 2
working devices : 2
failed devices : 0
spare devices : 0
name : omv30:raid1 (local to host omv30)
uuid : 921a8946:b273e00e:3fa4b99d:040a4437
events : 25
number major minor raiddevice state
0 8 32 0 active sync /dev/sdc
1 8 16 1 active sync /dev/sdb
配置文件信息：
root@omv30:~# cat /etc/mdadm/mdadm.conf # mdadm.conf # # please refer to mdadm.conf(5) for information about this file. # # by default, scan all partitions (/proc/partitions) for md superblocks. # alternatively, specify devices to scan, using wildcards if desired. # note, if no device line is present, then "device partitions" is assumed. # to avoid the auto-assembly of raid devices a pattern that can't match is # used if no raid devices are configured. device partitions # auto-create devices with debian standard permissions create owner=root group=disk mode=0660 auto=yes # automatically tag new arrays as belonging to the local system homehost <system> # definitions of existing md arrays array /dev/md0 metadata=1.2 name=omv30:raid1 uuid=921a8946:b273e00e:3fa4b99d:040a4437
在virtualbox的存储-sata下，分别选中两块硬盘，在右边的属性将sata端口调换位置，即可交换盘符。
root@omv30:~# mdadm -d /dev/md0
/dev/md0:
version : 1.2
creation time : sun sep 30 22:31:39 2018
raid level : raid1
array size : 1047552 (1023.00 mib 1072.69 mb)
used dev size : 1047552 (1023.00 mib 1072.69 mb)
raid devices : 2
total devices : 2
persistence : superblock is persistent
update time : mon oct 1 19:52:46 2018
state : clean
active devices : 2
working devices : 2
failed devices : 0
spare devices : 0
name : omv30:raid1 (local to host omv30)
uuid : 921a8946:b273e00e:3fa4b99d:040a4437
events : 29
number major minor raiddevice state
0 8 16 0 active sync /dev/sdb
1 8 32 1 active sync /dev/sdc
可以看到盘符已经换了。
root@omv30:~# mdadm --examine /dev/sdb
/dev/sdb:
magic : a92b4efc
version : 1.2
feature map : 0x0
array uuid : 921a8946:b273e00e:3fa4b99d:040a4437
name : omv30:raid1 (local to host omv30)
creation time : sun sep 30 22:31:39 2018
raid level : raid1
raid devices : 2
avail dev size : 2095104 (1023.00 mib 1072.69 mb)
array size : 1047552 (1023.00 mib 1072.69 mb)
data offset : 2048 sectors
super offset : 8 sectors
unused space : before=1960 sectors, after=0 sectors
state : clean
device uuid : 6e545465:3dcf10df:1d5bb938:fe840307
update time : mon oct 1 19:52:46 2018
bad block log : 512 entries available at offset 72 sectors
checksum : a47a7d1f - correct
events : 29
device role : active device 0
array state : aa ('a' == active, '.' == missing, 'r' == replacing)
root@omv30:~# cat /proc/mdstat
personalities : [raid1] [linear] [multipath] [raid0] [raid6] [raid5] [raid4] [raid10]
md0 : active (auto-read-only) raid1 sdb[0] sdc[1]
1047552 blocks super 1.2 [2/2] [uu]
unused devices: <none>
root@omv30:~# fdisk -l
...（省略）
disk /dev/md0: 1023 mib, 1072693248 bytes, 2095104 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
mount后访问正常。
关机，新增一块硬盘，占用原来sdc的位置，启动：
root@omv30:~# mdadm -d /dev/md0
/dev/md0:
version : 1.2
creation time : sun sep 30 22:31:39 2018
raid level : raid1
array size : 1047552 (1023.00 mib 1072.69 mb)
used dev size : 1047552 (1023.00 mib 1072.69 mb)
raid devices : 2
total devices : 2
persistence : superblock is persistent
update time : mon oct 1 19:52:46 2018
state : clean
active devices : 2
working devices : 2
failed devices : 0
spare devices : 0
name : omv30:raid1 (local to host omv30)
uuid : 921a8946:b273e00e:3fa4b99d:040a4437
events : 29
number major minor raiddevice state
0 8 16 0 active sync /dev/sdb
1 8 48 1 active sync /dev/sdd
root@omv30:~# cat /proc/mdstat
personalities : [raid1] [linear] [multipath] [raid0] [raid6] [raid5] [raid4] [raid10]
md0 : active (auto-read-only) raid1 sdb[0] sdd[1]
1047552 blocks super 1.2 [2/2] [uu]
unused devices: <none>
原来的sdc变成了sdc，raid1还完好保存，不受影响。
关机，然后移除一块硬盘，启动：
root@omv30:~# mdadm -d /dev/md0
/dev/md0:
version : 1.2
raid level : raid0
total devices : 1
persistence : superblock is persistent
state : inactive
name : omv30:raid1 (local to host omv30)
uuid : 921a8946:b273e00e:3fa4b99d:040a4437
events : 29
number major minor raiddevice
- 8 16 - /dev/sdb
root@omv30:~# mdadm --query /dev/sdb /dev/sdb: is not an md array /dev/sdb: device 0 in 2 device undetected raid1 /dev/md0. use mdadm --examine for more detail.
root@omv30:~# mdadm --examine /dev/sdb
/dev/sdb:
magic : a92b4efc
version : 1.2
feature map : 0x0
array uuid : 921a8946:b273e00e:3fa4b99d:040a4437
name : omv30:raid1 (local to host omv30)
creation time : sun sep 30 22:31:39 2018
raid level : raid1
raid devices : 2
avail dev size : 2095104 (1023.00 mib 1072.69 mb)
array size : 1047552 (1023.00 mib 1072.69 mb)
data offset : 2048 sectors
super offset : 8 sectors
unused space : before=1960 sectors, after=0 sectors
state : clean
device uuid : 6e545465:3dcf10df:1d5bb938:fe840307
update time : mon oct 1 19:52:46 2018
bad block log : 512 entries available at offset 72 sectors
checksum : a47a7d1f - correct
events : 29
device role : active device 0
array state : aa ('a' == active, '.' == missing, 'r' == replacing)
root@omv30:~# cat /proc/mdstat
personalities : [linear] [multipath] [raid0] [raid1] [raid6] [raid5] [raid4] [raid10]
md0 : inactive sdb[0](s)
1047552 blocks super 1.2
unused devices: <none>
root@omv30:~# fdisk -l disk /dev/sda: 8 gib, 8589934592 bytes, 16777216 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: 0x8c9b0fb9 device boot start end sectors size id type /dev/sda1 * 2048 12582911 12580864 6g 83 linux /dev/sda2 12584958 16775167 4190210 2g 5 extended /dev/sda5 12584960 16775167 4190208 2g 82 linux swap / solaris disk /dev/sdb: 1 gib, 1073741824 bytes, 2097152 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
raid1变成了inactive，但raid信息本身是保存在磁盘中，不会丢失。
场景：正常运行的raid1，突然一块盘失效，进行重建恢复。
方法：可以用模拟fail的方式，也可以用virtualbox热插拔硬盘的功能。
初始信息如下：
root@omv30:~# mdadm -d /dev/md0
/dev/md0:
version : 1.2
creation time : sun sep 30 22:31:39 2018
raid level : raid1
array size : 1047552 (1023.00 mib 1072.69 mb)
used dev size : 1047552 (1023.00 mib 1072.69 mb)
raid devices : 2
total devices : 2
persistence : superblock is persistent
update time : mon oct 1 20:29:44 2018
state : clean
active devices : 2
working devices : 2
failed devices : 0
spare devices : 0
name : omv30:raid1 (local to host omv30)
uuid : 921a8946:b273e00e:3fa4b99d:040a4437
events : 31
number major minor raiddevice state
0 8 16 0 active sync /dev/sdb
1 8 48 1 active sync /dev/sdd
(1)手工fail掉sdd：
root@omv30:~# mdadm /dev/md0 --fail /dev/sdd mdadm: set /dev/sdd faulty in /dev/md0
root@omv30:~# mdadm -d /dev/md0
/dev/md0:
version : 1.2
creation time : sun sep 30 22:31:39 2018
raid level : raid1
array size : 1047552 (1023.00 mib 1072.69 mb)
used dev size : 1047552 (1023.00 mib 1072.69 mb)
raid devices : 2
total devices : 2
persistence : superblock is persistent
update time : mon oct 1 20:29:59 2018
state : clean, degraded
active devices : 1
working devices : 1
failed devices : 1
spare devices : 0
name : omv30:raid1 (local to host omv30)
uuid : 921a8946:b273e00e:3fa4b99d:040a4437
events : 33
number major minor raiddevice state
0 8 16 0 active sync /dev/sdb
- 0 0 1 removed
1 8 48 - faulty /dev/sdd
如果未移除，要先移除损坏的硬盘：
root@omv30:~# mdadm /dev/md0 -r /dev/sdd mdadm: hot remove failed for /dev/sdd: no such device or address
(2)增加新盘：
root@omv30:~# mdadm /dev/md0 --add /dev/sdc （新加的盘是2g的，经实测不影响raid1重建）
mdadm: added /dev/sdc
root@omv30:~# mdadm -d /dev/md0
/dev/md0:
version : 1.2
creation time : sun sep 30 22:31:39 2018
raid level : raid1
array size : 1047552 (1023.00 mib 1072.69 mb)
used dev size : 1047552 (1023.00 mib 1072.69 mb)
raid devices : 2
total devices : 2
persistence : superblock is persistent
update time : mon oct 1 20:36:22 2018
state : clean, degraded, recovering
active devices : 1
working devices : 2
failed devices : 0
spare devices : 1
rebuild status : 76% complete
name : omv30:raid1 (local to host omv30)
uuid : 921a8946:b273e00e:3fa4b99d:040a4437
events : 48
number major minor raiddevice state
0 8 16 0 active sync /dev/sdb
2 8 32 1 spare rebuilding /dev/sdc
可以看到正在重建。
过一会儿再执行：
root@omv30:~# mdadm -d /dev/md0
/dev/md0:
version : 1.2
creation time : sun sep 30 22:31:39 2018
raid level : raid1
array size : 1047552 (1023.00 mib 1072.69 mb)
used dev size : 1047552 (1023.00 mib 1072.69 mb)
raid devices : 2
total devices : 2
persistence : superblock is persistent
update time : mon oct 1 20:36:24 2018
state : clean
active devices : 2
working devices : 2
failed devices : 0
spare devices : 0
name : omv30:raid1 (local to host omv30)
uuid : 921a8946:b273e00e:3fa4b99d:040a4437
events : 53
number major minor raiddevice state
0 8 16 0 active sync /dev/sdb
2 8 32 1 active sync /dev/sdc
root@omv30:~# cat /proc/mdstat
personalities : [raid1] [linear] [multipath] [raid0] [raid6] [raid5] [raid4] [raid10]
md0 : active raid1 sdc[2] sdb[0]
1047552 blocks super 1.2 [2/2] [uu]
unused devices: <none>
已经重建成功。
在virtualbox的存储中，勾选sdb的热插拔，然后启动。
系统在运行时，到virtualbox的存储中移除sdb硬盘，然后查看状态：
root@omv30:~# mdadm -d /dev/md0
/dev/md0:
version : 1.2
creation time : sun sep 30 22:31:39 2018
raid level : raid1
array size : 1047552 (1023.00 mib 1072.69 mb)
used dev size : 1047552 (1023.00 mib 1072.69 mb)
raid devices : 2
total devices : 1
persistence : superblock is persistent
update time : mon oct 1 21:13:45 2018
state : clean, degraded
active devices : 1
working devices : 1
failed devices : 0
spare devices : 0
name : omv30:raid1 (local to host omv30)
uuid : 921a8946:b273e00e:3fa4b99d:040a4437
events : 56
number major minor raiddevice state
- 0 0 0 removed
2 8 32 1 active sync /dev/sdc
查看系统日志，发现有硬盘离线，并且raid1降级（有日志跟踪是软raid的一个优势）：
root@omv30:/var/log# dmesg | tail -20
[ 340.551533] md: recovery of raid array md0
[ 345.881625] md: md0: recovery done.
[ 657.932091] ext4-fs (md0): mounted filesystem with ordered data mode. opts: (null)
[ 2571.324851] ata2: sata link down (sstatus 0 scontrol 300)
[ 2576.667851] ata2: sata link down (sstatus 0 scontrol 300)
[ 2582.044796] ata2: sata link down (sstatus 0 scontrol 300)
[ 2582.044864] ata2.00: disabled
[ 2582.045573] ata2.00: detaching (scsi 3:0:0:0)
[ 2582.058467] sd 3:0:0:0: [sdb] synchronizing scsi cache
[ 2582.058528] sd 3:0:0:0: [sdb] synchronize cache(10) failed: result: hostbyte=did_bad_target driverbyte=driver_ok
[ 2582.058536] sd 3:0:0:0: [sdb] stopping disk
[ 2582.058552] sd 3:0:0:0: [sdb] start/stop unit failed: result: hostbyte=did_bad_target driverbyte=driver_ok
[ 2586.709149] md/raid1:md0: disk failure on sdb, disabling device.
md/raid1:md0: operation continuing on 1 devices.
加入新硬盘。新加的硬盘不能比现有的小，可以比现在的大。
root@omv30:~# mdadm /dev/md0 --add /dev/sdc
开始重建：
root@omv30:~# mdadm -d /dev/md0
/dev/md0:
version : 1.2
creation time : sun sep 30 22:31:39 2018
raid level : raid1
array size : 1047552 (1023.00 mib 1072.69 mb)
used dev size : 1047552 (1023.00 mib 1072.69 mb)
raid devices : 2
total devices : 2
persistence : superblock is persistent
update time : mon oct 1 21:38:36 2018
state : clean, degraded, recovering
active devices : 1
working devices : 2
failed devices : 0
spare devices : 1
rebuild status : 56% complete
name : omv30:raid1 (local to host omv30)
uuid : 921a8946:b273e00e:3fa4b99d:040a4437
events : 69
number major minor raiddevice state
3 8 32 0 spare rebuilding /dev/sdc
2 8 16 1 active sync /dev/sdb
root@omv30:~# cat /proc/mdstat
personalities : [raid1] [linear] [multipath] [raid0] [raid6] [raid5] [raid4] [raid10]
md0 : active raid1 sdc[3] sdb[2]
1047552 blocks super 1.2 [2/1] [_u]
[===================>.] recovery = 95.0% (996288/1047552) finish=0.0min speed=249072k/sec
unused devices: <none>
重建完成：
root@omv30:~# mdadm -d /dev/md0
/dev/md0:
version : 1.2
creation time : sun sep 30 22:31:39 2018
raid level : raid1
array size : 1047552 (1023.00 mib 1072.69 mb)
used dev size : 1047552 (1023.00 mib 1072.69 mb)
raid devices : 2
total devices : 2
persistence : superblock is persistent
update time : mon oct 1 21:38:39 2018
state : clean
active devices : 2
working devices : 2
failed devices : 0
spare devices : 0
name : omv30:raid1 (local to host omv30)
uuid : 921a8946:b273e00e:3fa4b99d:040a4437
events : 78
number major minor raiddevice state
3 8 32 0 active sync /dev/sdc
2 8 16 1 active sync /dev/sdb
root@omv30:~# cat /proc/mdstat
personalities : [raid1] [linear] [multipath] [raid0] [raid6] [raid5] [raid4] [raid10]
md0 : active raid1 sdc[3] sdb[2]
1047552 blocks super 1.2 [2/2] [uu]
unused devices: <none>
将两块硬盘挂到一个新装的ubuntu中，启动。
root@ub13:/home/op# fdisk -l ...（省略） disk /dev/md127：1023 mib，1072693248 字节，2095104 个扇区 单元：扇区 / 1 * 512 = 512 字节 扇区大小(逻辑/物理)：512 字节 / 512 字节 i/o 大小(最小/最佳)：512 字节 / 512 字节
root@ub13:/home/op# cat /proc/mdstat
personalities : [raid1] [linear] [multipath] [raid0] [raid6] [raid5] [raid4] [raid10]
md127 : active raid1 sdd[1] sdc[0]
1047552 blocks super 1.2 [2/2] [uu]
unused devices: <none>
可以看到，自动识别出来/dev/md127。
root@ub13:/mnt/md# mdadm -d /dev/md127
/dev/md127:
version : 1.2
creation time : sun sep 30 22:31:39 2018
raid level : raid1
array size : 1047552 (1023.00 mib 1072.69 mb)
used dev size : 1047552 (1023.00 mib 1072.69 mb)
raid devices : 2
total devices : 2
persistence : superblock is persistent
update time : mon oct 1 19:31:08 2018
state : clean
active devices : 2
working devices : 2
failed devices : 0
spare devices : 0
consistency policy : resync
name : omv30:raid1
uuid : 921a8946:b273e00e:3fa4b99d:040a4437
events : 25
number major minor raiddevice state
0 8 32 0 active sync /dev/sdc
1 8 48 1 active sync /dev/sdd
系统自动识别并恢复了raid1，不用执行mdadm --assemble --scan。
查看/etc/mdadm/mdadm.conf，也是自动加入了md信息。
mount后访问正常。
至于如何将md127修改成md0，详见下一节。
只有一块硬盘可用，需要在新系统上重建raid1。
root@op:/home/op# fdisk -l （未发现新的md设备，略去详细输出）
root@op:/home/op# mdadm --examine /dev/sdb
/dev/sdb:
magic : a92b4efc
version : 1.2
feature map : 0x0
array uuid : 921a8946:b273e00e:3fa4b99d:040a4437
name : omv30:raid1
creation time : sun sep 30 22:31:39 2018
raid level : raid1
raid devices : 2
avail dev size : 4192256 (2047.00 mib 2146.44 mb)
array size : 1047552 (1023.00 mib 1072.69 mb)
used dev size : 2095104 (1023.00 mib 1072.69 mb)
data offset : 2048 sectors
super offset : 8 sectors
unused space : before=1960 sectors, after=2097152 sectors
state : clean
device uuid : 6e2fc709:35a8f6fb:d4c0e242:6905437d
update time : mon oct 1 21:40:25 2018
bad block log : 512 entries available at offset 72 sectors
checksum : e65b30a8 - correct
events : 78
device role : active device 1
array state : aa ('a' == active, '.' == missing, 'r' == replacing)
root@op:/home/op# cat /proc/mdstat personalities : unused devices: <none>
说明新挂载的盘raid1信息犹在，只需要重新识别：
root@op:/home/op# mdadm --assemble --scan mdadm: /dev/md/raid1 has been started with 1 drive (out of 2).
root@op:/home/op# fdisk -l ...（省略） disk /dev/md127：1023 mib，1072693248 字节，2095104 个扇区 单元：扇区 / 1 * 512 = 512 字节 扇区大小(逻辑/物理)：512 字节 / 512 字节 i/o 大小(最小/最佳)：512 字节 / 512 字节
root@op:/home/op# mdadm -d /dev/md127
/dev/md127:
version : 1.2
creation time : sun sep 30 22:31:39 2018
raid level : raid1
array size : 1047552 (1023.00 mib 1072.69 mb)
used dev size : 1047552 (1023.00 mib 1072.69 mb)
raid devices : 2
total devices : 1
persistence : superblock is persistent
update time : mon oct 1 21:40:25 2018
state : clean, degraded
active devices : 1
working devices : 1
failed devices : 0
spare devices : 0
consistency policy : resync
name : omv30:raid1
uuid : 921a8946:b273e00e:3fa4b99d:040a4437
events : 78
number major minor raiddevice state
- 0 0 0 removed
2 8 16 1 active sync /dev/sdb
如果这个时间重启系统，会发现fdisk -l中没有md127了。并且mdadm -d发现raid1处于inactive。
root@op:/home/op# mdadm -d /dev/md127
/dev/md127:
version : 1.2
raid level : raid0
total devices : 1
persistence : superblock is persistent
state : inactive
working devices : 1
name : omv30:raid1
uuid : 921a8946:b273e00e:3fa4b99d:040a4437
events : 78
number major minor raiddevice
- 8 16 - /dev/sdb
这时需要先mdadm -s /dev/md127删除旧的md127，
再重新mdadm --assemble --scan。
再add硬盘，完成重建即可。
root@omv30:~# mdadm /dev/md0 --add /dev/sdc
这时再重启也不会有影响，唯一的变化就是在之前主机是md0，现在变成了md127了。
解决方法：
修改/etc/mdadm/mdadm.conf，
把第二列：/dev/md/raid1
修改成：/dev/md0
再执行：
update-initramfs -u
重启，搞定。
查看状态
mdadm -d /dev/md0 cat /proc/mdstat mdadm --examine /dev/sdb
删除md
mdadm -s /dev/md0
激活md
mdadm -a /dev/md0
在新os上重新导入raid
mdadm --assemble --scan
重建
mdadm /dev/md0 --add /dev/sdc
如对本文有疑问， 点击进行留言回复！！
linux下文本编辑器vim的使用方法(复制、粘贴、替换、行号、撤销、多文件操作)
网友评论