On Fri, Sep 16, 2005 at 04:54:47PM +0100 or thereabouts, Burke, S (Stephen) wrote:
> Testbed Support for GridPP member institutes
> > [mailto:[log in to unmask]] On Behalf Of Simon George said:
> > I do not see the absolute need for one at each
> > Tier2. As long
> > as the network is up, could it not equally be cited centrally for each
> > Tier2 or even at the nearest Tier1?
>
> That seems to be one of the key questions. The discussion we had this
> week (summarised in Steve's slides) seemed to be saying that we wouldn't
> accept anything intrusive, i.e. no backdoor access to job submission,
> storage etc. However, in that case it's a bit hard to see why it needs
> to be local - you may have some argument for wanting fast network
> connections, but these days that could well be available off-site.
> Actually I suspect that at least some people in the experiments *do*
> want back-door access, so if we don't agree to that it will need to be
> made very clear.
To this point they have required backdoor access to the already existing
software area. But this in itself is not to different to what they have. Just
gsissh access rather than globus-job-run access. It is very much less than
asking for qstat access which is where we probably don't want to go.
Steve
>
> > I'm willing to be convinced but I am perplexed that no one
> > seems to want
> > to do that. I realise that such people may not read
> > tb-support, but could
> > it be arranged for some of them to talk to us before we try
> > to decide our position on this?
>
> The place to debate it looks like being the LCG workshop at Culham - you
> don't seem to be registered but you still have a bit of time! I don't
> know how many experiment people will be there but I doubt there will be
> any other general forum, unless it becomes so controversial that we get
> a dedicated meeting just on this topic.
>
> http://egee.in2p3.fr/events/UKI/
>
> Stephen
--
Steve Traylen
[log in to unmask]
http://www.gridpp.ac.uk/
|