deleting mdadm array?

deleting mdadm array?

[Janek Kozicki]

Hello,

I just created a new array /dev/md1 like this:

mdadm --create --verbose /dev/md1 --chunk=64 --level=raid5 \
   --metadata=1.1  --bitmap=internal \
   --raid-devices=3 /dev/hdc2 /dev/sda2 missing


But later I changed my mind, and I wanted to use chunk 128. Do I need
to delete this array somehow first, or can I just create an array
again (overwriting the current one)?

-- 
Janek Kozicki                                                         |

Re: deleting mdadm array?

[Neil Brown]

On Thursday October 25, janek_listy@wp.pl wrote:
> Hello,
> 
> I just created a new array /dev/md1 like this:
> 
> mdadm --create --verbose /dev/md1 --chunk=64 --level=raid5 \
>    --metadata=1.1  --bitmap=internal \
>    --raid-devices=3 /dev/hdc2 /dev/sda2 missing
> 
> 
> But later I changed my mind, and I wanted to use chunk 128. Do I need
> to delete this array somehow first, or can I just create an array
> again (overwriting the current one)?

Just recreate with new values, overwriting the current one.

NeilBrown

Re: deleting mdadm array?

[David Greaves]

Janek Kozicki wrote:
> Hello,
> 
> I just created a new array /dev/md1 like this:
> 
> mdadm --create --verbose /dev/md1 --chunk=64 --level=raid5 \
>    --metadata=1.1  --bitmap=internal \
>    --raid-devices=3 /dev/hdc2 /dev/sda2 missing
> 
> 
> But later I changed my mind, and I wanted to use chunk 128. Do I need
> to delete this array somehow first, or can I just create an array
> again (overwriting the current one)?

How much later? This will, of course, destroy any data on the array (!) and
you'll need to mkfs again...


To answer the question though: just run mdadm again to create a new array with
new parameters.


I think the only time you need to 'delete' an array before creating a new one is
if you change the superblock version since it quietly writes different
superblocks to different disk locations you may end up with 2 superblocks on the
disk and then you get confusion :)
(I'm not sure if mdadm is clever about this though...)

Also, if you don't mind me asking: why did you choose version 1.1 for the
metadata/superblock version?

David

Re: deleting mdadm array?

[Neil Brown]

On Thursday October 25, david@dgreaves.com wrote:
> I think the only time you need to 'delete' an array before creating a new one is
> if you change the superblock version since it quietly writes different
> superblocks to different disk locations you may end up with 2 superblocks on the
> disk and then you get confusion :)
> (I'm not sure if mdadm is clever about this though...)
> 

Mdadm tries to be clever.

When creating an array, it zeros any superblocks that it finds on the
array in any of the expected locations.
And when guessing the metadata format used, if it find two or more, it
chooses the one with the more recent create timestamp.

NeilBrown

Re: deleting mdadm array?

[Janek Kozicki]

David Greaves said:     (by the date of Thu, 25 Oct 2007 10:55:44 +0100)

> How much later? This will, of course, destroy any data on the array (!) and
> you'll need to mkfs again...

Just after, I didn't even create LVM volume on it (not mentioning
formatting it).

> Also, if you don't mind me asking: why did you choose version 1.1 for the
> metadata/superblock version?

In "time to deprecate old RAID formats" Doug Ledford said, that 1.1
is safest when used with LVM. I wish that this info would get into
the man page. I just hope that grub will be able to boot from LVM 
from '/' partition raid1 (version 1.1), I didn't check this yet.


Doug Ledford said:     (by the date of Fri, 19 Oct 2007 12:15:34 -0400)

> 1.0, 1.1, and 1.2 are the same format, just in different positions on
> the disk.  Of the three, the 1.1 format is the safest to use since it
> won't allow you to accidentally have some sort of metadata between the
> beginning of the disk and the raid superblock (such as an lvm2
> superblock), and hence whenever the raid array isn't up, you won't be
> able to accidentally mount the lvm2 volumes, filesystem, etc.  (In worse
> case situations, I've seen lvm2 find a superblock on one RAID1 array
> member when the RAID1 array was down, the system came up, you used the
> system, the two copies of the raid array were made drastically
> inconsistent, then at the next reboot, the situation that prevented the
> RAID1 from starting was resolved, and it never know it failed to start
> last time, and the two inconsistent members we put back into a clean
> array).  So, deprecating any of these is not really helpful.  And you
> need to keep the old 0.90 format around for back compatibility with
> thousands of existing raid arrays.
> 


-- 
Janek Kozicki                                                         |