Yes Stephen you are right
in my ce01.lip.pt /etc/globus.cconf
[gatekeeper/torque]
type=lcgpbs
some weeks ago when the job submission was not working
properly I thought "those" lines could be the problem
but they were not
this the way it is in fact
cheers
Mario
Quoting "Burke, S (Stephen)" <[log in to unmask]>:
> LHC Computer Grid - Rollout
> > [mailto:[log in to unmask]] On Behalf Of Maarten
> > Litmaath, CERN said:
> > Cannot plan: JobAdapterHelper: invalid value torque for
> > > attribute lrms_type (expecting lsf or pbs)
>
> [...]
>
> > You have set up the "lcgpbs" job manager, which does *not* support MPI
> > (it is on the to-do list, non-trivial).
>
> Actually it looks to me as though they, and some others, have set up a
> "torque" jobmanager:
>
> edg-job-list-match hw0.jdl | grep torque
> ce.ui.savba.sk:2119/jobmanager-torque-atlas
> ce01.isabella.grnet.gr:2119/jobmanager-torque-atlas
> ce01.isabella.grnet.gr:2119/jobmanager-torque-short
> ce01.lip.pt:2119/jobmanager-torque-atlas
> grid.uibk.ac.at:2119/jobmanager-torque-atlas
> grid10.lal.in2p3.fr:2119/jobmanager-torque-atlas
> heplnx201.pp.rl.ac.uk:2119/jobmanager-torque-atlas
> heplnx201.pp.rl.ac.uk:2119/jobmanager-torque-short
> i101.hpc2n.umu.se:2119/jobmanager-torque-atlas
> ingvar.nsc.liu.se:2119/jobmanager-torque-atlas
> pcncp04.ncp.edu.pk:2119/jobmanager-torque-atlas
> zeus02.cyf-kr.edu.pl:2119/jobmanager-torque-atlas
>
> Am I right in thinking that it should still be jobmanager-lcgpbs for
> torque?
>
> Stephen
>
|