On 17/12/12 11:48, Christopher J. Walker wrote:
>
> I shall start ticketing sites soon - though clearly sites should make
> their own judgement of the risks of making changes this close to Christmas.
>
Rather than ticketing sites, here's the status for the ngs.ac.uk VO.
WMS:
The following claim to support ngs.ac.uk
walker@heppc300:~$ lcg-infosites --vo ngs.ac.uk wms
https://lcgwms02.gridpp.rl.ac.uk:7443/glite_wms_wmproxy_server
https://lcgwms03.gridpp.rl.ac.uk:7443/glite_wms_wmproxy_server
https://svr022.gla.scotgrid.ac.uk:7443/glite_wms_wmproxy_server
https://svr023.gla.scotgrid.ac.uk:7443/glite_wms_wmproxy_server
https://wms01.grid.hep.ph.ic.ac.uk:7443/glite_wms_wmproxy_server
https://wms02.grid.hep.ph.ic.ac.uk:7443/glite_wms_wmproxy_server
Only the first two at RAL actually work with certificates from the
gridPP voms server. Imperial and Glasgow need to fix theirs.
Working:
ce07.esc.qmul.ac.uk:8443/cream-sge-lcg_long
lcgce01.gridpp.rl.ac.uk:8443/cream-pbs-grid2000M
lcgce01.gridpp.rl.ac.uk:8443/cream-pbs-grid500M
lcgce01.gridpp.rl.ac.uk:8443/cream-pbs-grid700M
lcgce01.gridpp.rl.ac.uk:8443/cream-pbs-gridS
Failed:
abaddon.hec.lancs.ac.uk:8443/cream-lsf-hex
ce01.tier2.hep.manchester.ac.uk:8443/cream-pbs-long
ceprod05.grid.hep.ph.ic.ac.uk:8443/cream-sge-grid.q
ceprod06.grid.hep.ph.ic.ac.uk:8443/cream-sge-grid.q
ceprod07.grid.hep.ph.ic.ac.uk:8443/cream-sge-grid.q
ceprod08.grid.hep.ph.ic.ac.uk:8443/cream-sge-grid.q
cream02.dur.scotgrid.ac.uk:8443/cream-pbs-q7d
dc2-grid-66.brunel.ac.uk:8443/cream-pbs-ngs.ac.uk
dc2-grid-68.brunel.ac.uk:8443/cream-pbs-ngs.ac.uk
dc2-grid-70.brunel.ac.uk:8443/cream-pbs-ngs.ac.uk
dgc-grid-43.brunel.ac.uk:8443/cream-pbs-ngs.ac.uk
epgr02.ph.bham.ac.uk:8443/cream-pbs-long
hepgrid6.ph.liv.ac.uk:8443/cream-pbs-long
lcgce03.phy.bris.ac.uk:8443/cream-pbs-long
lcgce04.phy.bris.ac.uk:8443/cream-pbs-express
svr009.gla.scotgrid.ac.uk:8443/cream-pbs-q1d
t2ce02.physics.ox.ac.uk:8443/cream-pbs-longfive
t2ce06.physics.ox.ac.uk:8443/cream-pbs-mediumfive
I've missed some queues out, but QMUL and RAL are working, the other
sites need to update.
Looking at the EGI accounting stats, we see that for 2012 the usage in
ksi2k is:
http://accounting.egi.eu/egi.php?query=normcpu&startYear=2012&startMonth=1&endYear=2012&endMonth=12&yRange=VO&xRange=DATE&voGroup=all&chart=GRBAR&scale=LIN&localJobs=onlygridjobs
Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
ngs 198 916 0 319 0 0 0 0 0 0 0 0
Neiss 783 2644 0 0 172 0 0 317 30 352 318 0
So ngs.ac.uk doesn't seem to have used any CPU at sites publishing into
APEL (and all GridPP sites should do) in the last 8 months.
I suspect therefore that this is a problem for the new year.
Chris
|