[glue-wg] Updated thoughts...
Maarten Litmaath
Maarten.Litmaath at cern.ch
Fri Apr 11 13:39:46 CDT 2008
Paul Millar wrote:
>>I argued that GLUE probably should allow for the RP being multi-valued,
>>and probably the AccessLatency as well. In WLCG/EGEE we would have a
>>single value for each normally, so that the Storage Class is clear.
>
>
> I'm not sure what AccessLatency as a multivalue means: I'd push this attribute
> down to the hardware layer (StorageDatastore/StorageMedia/StorageStorage)
>
> It's possible that we've been talking slightly at cross-purposes. It seems to
> me that what WLCG means by "access latency" is really the minimum (ie,
> fastest) guaranteed access latency (MGAL):
> D0T1 this is nearline
> D1T0 this is online
> D1T1 this is online
Yes, in WLCG we want it like that, but I wondered whether it is necessary
to insist there be exactly 1 access latency.
It does seem to make sense with the current ordered set of values:
Online < Nearline < Offline
But what about an SRM v1 or a Classic SE that has unspecified subsets of
its name space going to tape (current practice): one might want to list
both Online and Nearline as potential guaranteed latencies - some files
have Online, other files have Nearline as their _guaranteed_ latency.
A single value Nearline might suggest that everything goes to tape.
Probably devil's advocate, but in GLUE we should be careful with
insisting that a particular property shall _always_ hold...
Thanks,
Maarten
More information about the glue-wg
mailing list