 |
 |
On Fri, 14 Jan 2005, Burke, S (Stephen) wrote: > LHC Computer Grid - Rollout >> [mailto:[log in to unmask]] On Behalf Of Oxana Smirnova said: > >> Seriously, I would suggest to change the entire LCG SE model - and the >> information system schema. > > Nothing major then :) I seem to remember when I first joined EDG I started > by trying to understand what an SE was supposed to be; I'm not sure I've > ever managed it ... part of the problem is that sites just think "we're > supposed to have an SE", so they put one in even if it's just a normal > machine with a 100 Gb disk. As you say, given good networking there's no > strong reason for that, sites can easily point their close SE somewhere else > - as NIKHEF have apparently done, although Sara isn't entirely a different > site. Ah, but this should be documented then. Because the documentation says "A site that can provide resources will add a computing element (CE), that acts as a gateway to the computing resources and a storage element (SE), that acts as a gateway to the local storage." From this it is quite easy to get the impression that you have to have a local SE, instead of a documentation talking about what is expected from an SE when it comes to data permanence etc. Also, is it a failure state in LCG2 to have the close SE[s] (as defined by IS) full and not accepting new files? Will this impact running jobs on CPU resources, or will they just chose to put output files somewhere else? >> The disk space local to the site and necessary for its >> proper functioning should be renamed and treated as "cache" >> and must not be used for long-term data storage. > > A local SE is never *necessary*, it's just a network bandwidth issue. Then a clearer difference between the CE and SE functionality in the Site Setup documentation would probably be helpful. Perhaps even to the point of talking about Storage Sites and Computing Sites, that might coincide at the same location. /Mattias Wadenstein