Hi Wei, I think it would be a more productive discussion if I can get the people who will run these jobs involved -- John Chapman plus whoever will do the actually submission. Otherwise, we will simply rehash the options without knowing constraints on their side. Cheers. Charlie -- Charles C. Young M.S. 43, Stanford Linear Accelerator Center P.O. Box 20450 Stanford, CA 94309 [log in to unmask] voice (650) 926 2669 fax (650) 926 2923 CERN GSM +41 76 487 2069 > -----Original Message----- > From: Wei Yang via RT [mailto:[log in to unmask]] > Sent: Thursday, March 12, 2009 12:44 PM > To: Young, Charles C. > Cc: atlas-sccs-planning-l; Moss, Leonard J. > Subject: Re: [SLAC #163429] Request to use few memfs machines > for ATLAS testing > > > Hi Charlie, > > I forgot atlint01 is running a 32bit OS. It is not useful to John. > > At SCCS site, I think we also need Neal or Randy so that we > know the status of batch queue. I don't think we need Panda > team until we decide to use Panda. I hope we don't have to > because Kaushik is saying that Panda team is extremely busy > migrating Panda DB from BNL to CERN. The drawback of not > using Panda is that user will have to bookkeeping. > > If we don't use Panda, people can submit to batch locally or > via globus tools to submit to the grid, or even better > Condor-G. Do you want to setup a short meeting soon? Are all > the parties at SLAC? > > Regards, > Wei Yang | [log in to unmask] | 650-926-3338(O) > > > > This is very useful information. We should not look at it as "what > > production wants" but "how do we get these jobs done". For > example, if > > not using pilots is best, that is what we should do. If setting up > > another "site" is best, that is what we should do. Who do > we need to > > make an informed decision with all affected parties in the > discussion? My first guess: > > > > SCCS: Wei + anyone? > > John > > Production: Borat K. > > Panda: ? > > > >