process will not die.

Jason Barnes jbarnes at c3po.barnesos.net
Thu Sep 30 16:13:46 PDT 2004


	While running an mpirun job on my dual-processor SMP system
(FreeBSD 4-STABLE from August 28), my program (initiated with the command
line 'mpirun -np 2 ../sphagr') periodically dies, leaving a process that I
can't kill -9.  Here's the top:

  216 root       2   0   166M   113M select 1  27:44  3.22%  3.22% XFree86
  327 jbarnes    2   0 72364K 58056K poll   1   6:53  0.00%  0.00% kdeinit
  549 jbarnes   28   0   400M 90744K CPU0   0   3:02  0.00%  0.00% sphagr
  267 jbarnes    2   0 23388K 10932K poll   1   0:42  0.00%  0.00% kdeinit

	here's ps -auxw | grep sph:

jbarnes   549  0.0  8.7 410076 90744  p2  R     3:39PM   3:01.97 sphagr -p4pg /usr/home/
jbarnes   550  0.0  0.0     0    0  p2  Z     3:39PM   0:00.00  (sphagr)

	The 550 process I kill -9ed, but its still there, and now when I
try to kill it it says 'no such process'.
	Has anyone else had any experience with mpi processes being
unkillable?  Supposedly 5.3 has better SMP support -- might it solve this
problem?  Thanks for your ideas,

				- Jason Barnes


More information about the freebsd-questions mailing list