Hi David,
Yes, I would certainly think I am in most or all of the mapfiles already.
The main point of my request was to get the JETWEB RunTimeEnvironment
added to a few sites as a flag to indicate that they are willing to run
these jobs.
However, I still don't see UCL (or the gppce CE at RAL) when I run
dg-job-list-match using the Imperial RB. I can still run jobs at UCL using
"dg-job-submit -r" but I can't automatically match jobs to JETWEB-enabled
sites. I also often get some warnings when I run dg-job-list-match. An
example is appended to this mail. Do you know what causes this, and could
it be related?
Cheers,
Ben
Output of dg-job-list-match (see warnings at end):
Connecting to host gm03.hep.ph.ic.ac.uk, port 7771
***************************************************************************
COMPUTING ELEMENT IDs LIST
The following CE(s) matching your job requirements have been found:
- tuber5.phy.bris.ac.uk:2119/jobmanager-pbs-tbq
- tbce01.physics.ox.ac.uk:2119/jobmanager-pbs-workq
- heplnx11.pp.rl.ac.uk:2119/jobmanager-pbs-M
- hepgrid2.ph.liv.ac.uk:2119/jobmanager-pbs-workq
- gw39.hep.ph.ic.ac.uk:2119/jobmanager-pbs-workq
- farm003.hep.phy.cam.ac.uk:2119/jobmanager-pbs-Sq
- heplnx11.pp.rl.ac.uk:2119/jobmanager-pbs-S
- epcf36.ph.bham.ac.uk:2119/jobmanager-pbs-S
- farm003.hep.phy.cam.ac.uk:2119/jobmanager-pbs-Mq
- epcf36.ph.bham.ac.uk:2119/jobmanager-pbs-M
- farm003.hep.phy.cam.ac.uk:2119/jobmanager-pbs-Lq
- heplnx11.pp.rl.ac.uk:2119/jobmanager-pbs-L
- epcf36.ph.bham.ac.uk:2119/jobmanager-pbs-L
***************************************************************************
**** Warning: RB_MATCHMAKING_INFO ****
matchmaking process reported:
- Search on InformationIndex: query excecution failed
- Search on InformationIndex: query excecution failed
- Search on InformationIndex: query excecution failed
On Wed, 26 Mar 2003, Dr D J Colling wrote:
> Hi Ben and John,
>
> I would hope that you would be in the mapfiles for all the UK sites if you
> are in the GridPP VO (although I guess some sites might not have checked
> that they are accepting it). From what I understand about JETWEB (from
> Alex Tapper) this sounds an ideal thing to run over the Grid.
>
> On the subject of non-LHC experiments we generated 400K MICE "events"
> over the Grid yesterday without problems.
>
> All the best,
> david
>
>
> On Tue, 25 Mar 2003, Gordon, JC (John) wrote:
>
> > Not quite Ben, I want to demonstrate that we can run 'across grids' so
> > running on resources for non-LHC experiments that can be reached by the IC
> > RB would meet this. I have already approached BaBar who are about to upgrade
> > to get back into the UK grid. If there are any D0 or CDF resources out there
> > that are on the grid and can be reached from the IC RB then I would be glad
> > to hear if they can try running Ben's JETWEB.
> >
> > John
> >
> > -----Original Message-----
> > From: Ben Waugh [mailto:[log in to unmask]]
> > Sent: 25 March 2003 01:22
> > To: [log in to unmask]
> > Subject: JETWEB jobs: a request
> >
> >
> > John Gordon is also keen to see this work, as evidence that the Grid
> > (GridPP/EDG) can be used not only by large collaborations but
> > by smaller
> > "independent" groups. (Please correct me if I've not got that
> > quite right,
> > John.)
> >
>
--
Dr Ben Waugh Tel. +44 (0)20 7679 3783
Dept of Physics and Astronomy Internal: 33783
University College London
London WC1E 6BT
|