[Hallcsw] Farm resources for the commissioning runs

Brad Sawatzky brads at jlab.org
Mon Dec 4 22:08:54 EST 2017


Hi all,

When you get to the point where you want to run your jobs on the Farm,
you will need to use the following resources.

You should make sure you are in the 'c-comm2017' unix group.
Login to an ifarm machine and run 'groups'.  You should see
'c-comm2017' towards the end of the list of group names.
If not, then email one of the following and request that 
you be added:
  brads at jlab.org, saw at jlab.org, jones at jlab.org

Your Farm jobs should be submitted using the Project name
    c-comm2017

Your analysis ROOT file output should go here:
  /volatile/hallc/comm2017/<your-username>/
  ** Read and understand how /volatile works here: **
    https://scicomp.jlab.org/docs/volatile_disk_pool
  ** It is your responsibility to understand how the JLab **
  ** resources work.  Ignore this and you may lose files  **

Never copy CODA files to /home, /work, or /volatile.  It impacts other
users and will make the IT group grumpy.  Use commands like 'jcache'
to pull files from tape into '/cache/hallc/spring17/raw/', or
use a proper Farm job submission and that will be done for you
efficiently and automatically.

If they have not already done so, the spokespeople of the various
Commissioning experiments should probably request a /work/hallc/eXXXXXX
work directory space for their collaboration.  (Do not use /volatile,
or /home for your analyzer code, etc.  It does not work efficiently
at JLab's present scale and can impact other users.)

Feel free to ask me any questions you may have and I'll do my best to
support you.

All the best,
-- Brad

-- 
Brad Sawatzky, PhD <brads at jlab.org>  -<>-  Jefferson Lab / Hall C / C111
Ph: 757-269-5947  -<>-  Fax: 757-269-5235  -<>- Pager: brads-page at jlab.org
The most exciting phrase to hear in science, the one that heralds new
  discoveries, is not "Eureka!" but "That's funny..."   -- Isaac Asimov


More information about the Hallcsw mailing list