[MITgcm-devel] test on faulks

Ed Hill ed at eh3.com
Wed Jul 12 09:01:13 EDT 2006


On Wed, 2006-07-12 at 08:27 -0400, Patrick Heimbach wrote:
> There's a process (5212) on faulks running 
> taking 99% CPU time. Corresponding user has
> currently 12 hours idle time...
> 
> -p.

> On Wed, 2006-07-12 at 08:17, Jean-Michel Campin wrote:
> > Hello Ed,
> > 
> > I don't see the results of the testing on faulks,
> > that should be done now. Is it normal ?


Hi Jean-Michel, Patrick, and Ivana,

I just killed Ivana's tcsh process (see top output below) that was
taking up 99% cpu and making faulks nearly useless.  This should bring
the testing back.  Ivana, please be careful with faulks and eddy since
they are our daily testing machines and we rely on them for that
purpose.  Model runs or other CPU-intensive work does not belong on
either of them.

Also, I did a related thing on hugo and eddy -- I've scaled back the
number of times per day that the "R2" web pages get built so that they
don't consume so much CPU/IO on those machines.

Ed

=== top output ===

top - 08:50:25 up 49 days, 21:43, 12 users,  load average: 5.97, 5.75,
5.50
Tasks: 142 total,   7 running, 133 sleeping,   1 stopped,   1 zombie
Cpu(s):  0.6% us, 99.4% sy,  0.0% ni,  0.0% id,  0.0% wa,  0.0% hi,
0.0% si
Mem:    515800k total,   495432k used,    20368k free,    28040k buffers
Swap:  1953464k total,   223136k used,  1730328k free,   315036k cached

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND
 5212 ivana     25   0 36276  28m  972 R 99.0  5.6 673:43.95 tcsh
28573 jmc       18   0  5092 1440 1068 R  0.2  0.3   0:04.24 cvs
  446 root      16   0     0    0    0 S  0.1  0.0   0:15.13 kjournald
    1 root      16   0  3256  280  252 S  0.0  0.1   0:04.72 init
    2 root      34  19     0    0    0 S  0.0  0.0   0:46.13 ksoftirqd/0


-- 
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





More information about the MITgcm-devel mailing list