[MITgcm-support] bluesky run

[Ed Hill]

On Wed, 2005-06-08 at 11:24 -0400, Mike Spall wrote:
> Constantinos et al,
> 
> Thanks for the suggestion to remove -qhot, that compiles much
> faster.  Now for the next problem (keeping in mind that I know
> very little of MPI and NCAR machines).  I tried to run the
> following script using llsubmit
> (I am not showing all the file copies, etc):
> #
> #@output=./out
> #@error=err
> #@job_type=parallel
> #@network.MPI=csss,shared,US
> #@node=1
> #@tasks_per_node=4
> #@wall_clock_limit=00:02:00
> #@class=share
> #@queue

Hi Mike & Chris,

Below is a message from Chris that didn't get through our spam filter
because Chris didn't subscribe it.  So I've copied it and added Chris's
new address to an accept filter so that future emails from him will get
through.

Ed

===

Hi Mike,

  Not sure whether the help-desk message is relevant.

  However, Patrick and Constantinos do run on bluesky a lot, I think,
so 
I'm guessing it has more to do with jobs scripts.

  In the  testscript Ed runs at NCAR - see -

http://mitgcm.org/cgi-
bin/viewcvs.cgi/MITgcm_contrib/test_scripts/ncar/bluesky_ll_testreport_all?rev=1.1&content-type=text/vnd.viewcvs-markup

  there is no #@tasks_per_node=4

  Maybe that is the problem?


Chris

-- 
Edward H. Hill III, PhD
office:  MIT Dept. of EAPS;  Rm 54-1424;  77 Massachusetts Ave.
             Cambridge, MA 02139-4307
emails:  eh3 at mit.edu                ed at eh3.com
URLs:    http://web.mit.edu/eh3/    http://eh3.com/
phone:   617-253-0098
fax:     617-253-4464