On Wed, Feb 17, 2010 at 00:27, Ethan <notet...@gmail.com> wrote:

> On Tue, Feb 16, 2010 at 23:57, Daniel Carosone <d...@geek.com.au> wrote:
>
>> On Tue, Feb 16, 2010 at 11:39:39PM -0500, Ethan wrote:
>> > If slice 2 is the whole disk, why is zpool trying to using slice 8 for
>> all
>> > but one disk?
>>
>> Because it's finding at least part of the labels for the pool member
>> there.
>>
>> Please check the partition tables of all the disks, and use zdb -l on
>> the various partitions, to make sure that you haven't got funny
>> offsets or other problems hiding the data from import.
>>
>> In a default solaris label, s2 and s8 start at cylinder 0 but are
>> vastly different sizes.  You need to arrange for your labels to match
>> however the data you copied got laid out.
>>
>> > Can I explicitly tell zpool to use slice 2 for each device?
>>
>> Not for import, only at creation time.  On import, devices are chosen
>> by inspection of the zfs labels within.  zdb -l will print those for
>> you; when you can see all 4 labels for all devices your import has a
>> much better chance of success.
>>
>> --
>> Dan.
>>
>
> How would I go about arranging labels?
> I only see labels 0 and 1 (and do not see labels 2 and 3) on every device,
> for both slices 8 (which makes sense if 8 is just part of the drive; the zfs
> devices take up the whole drive) and slice 2 (which doesn't seem to make
> sense to me).
>
> Since only two of the four labels are showing up for each of the drives on
> both slice 2 and slice 8, I guess that causes zpool to not have a preference
> between slice 2 and slice 8? So it just picks whichever it sees first, which
> happened to be slice 2 for one of the drives, but 8 for the others? (I am
> really just guessing at this.)
>
> So, on one hand, the fact that it says slice 2 is online for one drive
> makes me think that if I could get it to use slice 2 for the rest maybe it
> would work.
> On the other hand, the fact that I can't see labels 2 and 3 on slice 2 for
> any drive (even the one that says it's online) is worrisome and I want to
> figure out what's up with that.
>
> Labels 2 and 3 _do_ show up (and look right) in zdb -l running in zfs-fuse
> on linux, on the truecrypt volumes.
>
> If it might just be a matter of arranging the labels so that the beginning
> and end of a slice are in the right place, that sounds promising, although I
> have no idea how I go about arranging labels. Could you point me in the
> direction of what utility I might use or some documentation to get me
> started in that direction?
>
> Thanks,
> -Ethan
>

And I just realized - yes, labels 2 and 3 are in the wrong place relative to
the end of the drive; I did not take into account the overhead taken up by
truecrypt when dd'ing the data. The raw drive is 1500301910016 bytes; the
truecrypt volume is 1500301647872 bytes. Off by 262144 bytes - I need a
slice that is sized like the truecrypt volume.
_______________________________________________
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss

Reply via email to