On Fri, 5 Jun 2009, Burke, S (Stephen) wrote:
> Testbed Support for GridPP member institutes
>> [mailto:[log in to unmask]] On Behalf Of Gordon, JC (John)
> said:
>> I guess this is before your time Chris but it does raise the question
>> of what user requirements you were planning for when you bought this.
>
> I don't think there's any problem with this per se, it's looking like
> cluster file systems may well be the future (or at least a future) of
> disk storage, but since we haven't had SEs supporting "file" access
> since the EDG days it may take a while for everything to catch up.
> Actually the experiment requirements back in EDG all insisted that
> direct posix access was absolutely vital, it's just that in practice
> no-one complained when we took it away!
IIRC one of the worries back then was that if the SE storage was directly
mounted (e.g. NFS) then users could modify the datafiles without the SE
noticing, thus completely messing up replica management.
Do current invocations of "file" access get round this somehow?
Thanks
Henry
--
Dr. Henry Nebrensky [log in to unmask]
http://people.brunel.ac.uk/~eesrjjn
"The opossum is a very sophisticated animal.
It doesn't even get up until 5 or 6 p.m."
|