Institution
  
Item
Fermilab

​When you submit jobs and use the --memory option you can give units in both MB and GB. jobsub_submit interprets 1 GB as 1024 MB, not 1000 MB. So --memory=2GB is equivalent to --memory=2048MB, not 2000MB.

Fermilab

​We have a 16-core build node, dunebuild01

Fermilab

​Remember : DUNE resources are for DUNE work and not other experiments.

Fermilab

​You are more likely to get a grid slot for your job if you request the lifetime you actually need. This will be enforced in early summer 2016.

Fermilab

​The LBNE Dropbox is dead!! Long live the DUNE Dropbox!! (used for uploading files to enstore and registering with SAM)

Fermilab

​Are priority numbers comparable across experiments?

  • If two different exps have same priority (a tie) – there is a tie-breaking mechanism. Otherwise are the same.
Fermilab

​How are resources determined between experiments? Jobs running at a given moment – tune priority factors, and relaxation factor)

  • Priority factor of accounting group: per user
    • How many jobs are running, how many running recently (past 1.5 days approx.)
    • Only changed when user asks.  Default to start with is same for all.
  • Relaxation factor : is global
Fermilab

​How do priorities affect grid job startup?

  • Lower priority numbers are better.  Assuming resource matching. Lowest priority wins. Exponential relaxation time.
Fermilab

​Jobs that run past their resource limits get held, not killed (do jobsub_q to see reason why). Understand why, kill jobs and resubmit.

Fermilab

​DELETE your files before you leave DUNE/no longer have access to these areas

Fermilab

​Use the grid file systems as follows –

  • /dune/app : mounted on the gpgrid nodes, but not on OSG, code development and installation – WILL BE IMPLEMENTING 100 GB/user QUOTA END of MAY 2016
  • /dune/data/users : interactive data files (not mounted on grid worker nodes : use ifdh cp on worker nodes to copy files to here)
  • /dune/data2/users : interactive data files (not mounted on grid worker nodes : use ifdh cp on worker nodes to copy files to here)
  • /pnfs/dune/scratch/users : dCache data files
  • /pnfs/dune/persistent/users : dCache data files
Fermilab

Distributed Computing Access with Federated Identities (DCAFI) DUNE transition will be June 27 – July 11 : job submission without using Kerberos