RAID6 mdadm --grow bug?

RAID6 mdadm --grow bug?

[David Miller]

Problem:

The mdadm --grow command fails when trying to add disk to a RAID6.

The man page says it can do this.

"GROW MODE
        The GROW mode is used for changing the size or shape of an  
active array.  For this to  work,
        the  kernel must support the necessary change.  Various types  
of growth are being added dur-
        ing 2.6 development, including restructuring a raid5 array to  
have more active devices.

        Currently the only support available is to

        ·   change the "size" attribute for RAID1, RAID5 and RAID6.

        ·   increase the "raid-disks" attribute of RAID1, RAID5, and  
RAID6.

        ·   add a write-intent bitmap to any array which supports  
these bitmaps, or remove a  write-
            intent bitmap from such an array.
"

So far I have replicated this problem on RHEL5 and Ubuntu 7.04  
running the latest official updates and patches. I have even tried it  
with the most latest version of mdadm 2.6.3 under RHEL5. RHEL5 uses  
version 2.5.4.

How to replicate the problem:

You can either use real physical disks or use the loopback device to  
create fake disks.

Here are the steps using the loopback method as root.

cd /tmp
dd if=/dev/zero of=rd1 bs=10240 count=10240
cp rd1 rd2;cp rd1 rd3;cp rd1 rd4;cp rd1 rd5
losetup /dev/loop1 rd1;losetup /dev/loop2 rd2;losetup /dev/loop3  
rd3;losetup /dev/loop4 rd4;losetup /dev/loop5 rd5
mdadm --create --verbose /dev/md0 --level=6 --raid-devices=4 /dev/ 
loop1 /dev/loop2 /dev/loop3 /dev/loop4

At this point wait a minute while the raid is being built.

mdadm --add /dev/md0 /dev/loop5
mdadm --grow /dev/md0 --raid-devices=5

You should get the following error

mdadm: Need to backup 384K of critical section..
mdadm: Cannot set device size/shape for /dev/md0: Invalid argument

How to clean up

mdadm --stop /dev/md0
mdadm --remove /dev/md0
losetup -d /dev/loop1;losetup -d /dev/loop2;losetup -d /dev/ 
loop3;losetup -d /dev/loop4;losetup -d /dev/loop5
rm rd1 rd2 rd3 rd4 rd5

David.
-
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: RAID6 mdadm --grow bug?

[Neil Brown]

On Wednesday September 12, millerdc@fusion.gat.com wrote:
> 
> 
> Problem:
> 
> The mdadm --grow command fails when trying to add disk to a RAID6.
> 
..
> 
> So far I have replicated this problem on RHEL5 and Ubuntu 7.04  
> running the latest official updates and patches. I have even tried it  
> with the most latest version of mdadm 2.6.3 under RHEL5. RHEL5 uses  
> version 2.5.4.

You don't say what kernel version you are using (as I don't use RHEL5
or Ubunutu, I don't know what 'latest' means).

If it is 2.6.23-rcX, then it is a known problem that should be fixed
in the next -rc.  If it is something else... I need details.

Also, any kernel message (run 'dmesg') might be helpful.

NeilBrown

Re: RAID6 mdadm --grow bug?

[David Miller]

Neil,

On RHEL5 the kernel is 2.6.18-8.1.8. On Ubuntu 7.04 the kernel is  
2.6.20-16. Someone on the Arstechnica forums wrote they see the same  
thing in Debian etch running kernel 2.6.18. Below is a messages log  
from the RHEL5 system. I have only included the section for creating  
the RAID6, adding a spare and trying to grow it. There is a one line  
error when I do the "mdadm --grow" command. It is "md: couldn't  
update array info. -22."

md: bind<loop1>
md: bind<loop2>
md: bind<loop3>
md: bind<loop4>
md: md0: raid array is not clean -- starting background reconstruction
raid5: device loop4 operational as raid disk 3
raid5: device loop3 operational as raid disk 2
raid5: device loop2 operational as raid disk 1
raid5: device loop1 operational as raid disk 0
raid5: allocated 4204kB for md0
raid5: raid level 6 set md0 active with 4 out of 4 devices, algorithm 2
RAID5 conf printout:
  --- rd:4 wd:4 fd:0
  disk 0, o:1, dev:loop1
  disk 1, o:1, dev:loop2
  disk 2, o:1, dev:loop3
  disk 3, o:1, dev:loop4
md: syncing RAID array md0
md: minimum _guaranteed_ reconstruction speed: 1000 KB/sec/disc.
md: using maximum available idle IO bandwidth (but not more than  
200000 KB/sec) for reconstruction.
md: using 128k window, over a total of 102336 blocks.
md: md0: sync done.
RAID5 conf printout:
  --- rd:4 wd:4 fd:0
  disk 0, o:1, dev:loop1
  disk 1, o:1, dev:loop2
  disk 2, o:1, dev:loop3
  disk 3, o:1, dev:loop4
md: bind<loop5>
md: couldn't update array info. -22

David.



On Sep 13, 2007, at 3:52 AM, Neil Brown wrote:

> On Wednesday September 12, millerdc@fusion.gat.com wrote:
>>
>>
>> Problem:
>>
>> The mdadm --grow command fails when trying to add disk to a RAID6.
>>
> ..
>>
>> So far I have replicated this problem on RHEL5 and Ubuntu 7.04
>> running the latest official updates and patches. I have even tried it
>> with the most latest version of mdadm 2.6.3 under RHEL5. RHEL5 uses
>> version 2.5.4.
>
> You don't say what kernel version you are using (as I don't use RHEL5
> or Ubunutu, I don't know what 'latest' means).
>
> If it is 2.6.23-rcX, then it is a known problem that should be fixed
> in the next -rc.  If it is something else... I need details.
>
> Also, any kernel message (run 'dmesg') might be helpful.
>
> NeilBrown

Re: RAID6 mdadm --grow bug?

[Neil Brown]

On Thursday September 13, millerdc@fusion.gat.com wrote:
> Neil,
> 
> On RHEL5 the kernel is 2.6.18-8.1.8. On Ubuntu 7.04 the kernel is  
> 2.6.20-16. Someone on the Arstechnica forums wrote they see the same  
> thing in Debian etch running kernel 2.6.18. Below is a messages log  
> from the RHEL5 system. I have only included the section for creating  
> the RAID6, adding a spare and trying to grow it. There is a one line  
> error when I do the "mdadm --grow" command. It is "md: couldn't  
> update array info. -22."

reshaping raid6 arrays was not supported until 2.6.21.  So you'll need
a newer kernel.

NeilBrown