[pnfs] 19 questions

[J. Bruce Fields]

On Wed, Feb 06, 2008 at 11:27:05AM -0800, Dean Hildebrand wrote:
> Hmmm, the problem I see is that there could be multiple exported file 
> systems supporting the same layout type.  So matching the exported 
> layout type to the getdeviceinfo layout type isn't sufficient.  You 
> would have to call export_op->getdeviceinfo on each exported file system 
> that matches the layout type until you find one that recognizes the 
> deviceid.  ugh.
> 
> So I think that we still need to somehow encapsulate which export we are 
> referring to in the deviceid.  But if fsid's can be up to 24 bytes long, 
> we have a problem.

Ignorant question from someone who hasn't looked at the protocol in a
while, but: do deviceid's have to remain the same after reboot of the
metadata server, or can they be constructed in memory and then forgotten
on reboot?

--b.