[MITgcm-devel] ACES test

[Ed Hill]

On Sat, 2006-07-29 at 13:34 -0400, Jean-Michel Campin wrote:
> 
> The renaming and cleaning of the optfiles for the ACES cluster 
> test worked well last night. 

Hi Jean-Michel,

Yes, I'm glad it mostly worked.


> However, there are 2 exp. (the 2 last of the list) that did not
> finish, and I guess it could be related to a disk space Pb.
> 
> ao{edhill}% pwd
> /net/ds-01/scratch-5/edhill
> ao{edhill}% df .
> Filesystem           1K-blocks      Used Available Use% Mounted on
> ds-01:/scratch-5     251575872 238796512        64 100% /net/ds-01/scratch-5
> 
> Should we ask people to make some space on this disk ?

My vote would be to implement the official ACES storage policy as posted
at:

  http://acesgrid.org/storage.html

and I know for a fact that the relevant part:

 "Data stored in short term storage is automatically deleted when 
  disk capacity exceeds 80% on the main "ds-xx" NFS servers and 
  50% (with a 24-hour grace period) on the compute nodes."

is not currently being enforced.  Its pretty easy to write a script that
does the above so we should either write it ourselves or have Greg do
it.

Ed

-- 
Edward H. Hill III, PhD
office:  MIT Dept. of EAPS 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