[mpich-discuss] mpiexec: ignore exit codes

[Yauheni Zelenko]

Hi, Silvan!

I had similar problem. 

As workaround you need to change next line in src/pm/hydra/pm/pmiserv/pmiserv_cb.c from

if (!WIFEXITED(proxy->exit_status[i]) || WEXITSTATUS(proxy->exit_status[i])) {
 
to

if (!WIFEXITED(proxy->exit_status[i]) /* || WEXITSTATUS(proxy->exit_status[i]) */) {

I already suggested to introduce Hydra command line option which will allow to ignore non-zero exit codes.

Eugene.
________________________________________
From: discuss-bounces at mpich.org [discuss-bounces at mpich.org] On Behalf Of Silvan Brändli [silvan.braendli at tuhh.de]
Sent: Friday, February 22, 2013 5:46 AM
To: discuss at mpich.org
Subject: [mpich-discuss] mpiexec: ignore exit codes

Dear all,

one of my spawned processes returns Exit Code 1 when finishing, causing
mpiexec to abort (see below). Despite that I would like to continue
running my programs. Is there a way to make mpiexec ignore the exit codes?

Best regards
Silvan Brändli

===================================================================================
=   BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
=   EXIT CODE: 1
=   CLEANING UP REMAINING PROCESSES
=   YOU CAN IGNORE THE BELOW CLEANUP MESSAGES
===================================================================================
[proxy:0:0 at leibniz] HYD_pmcd_pmip_control_cmd_cb
(./pm/pmiserv/pmip_cb.c:883): assert (!closed) failed
[proxy:0:0 at leibniz] HYDT_dmxu_poll_wait_for_event
(./tools/demux/demux_poll.c:77): callback returned error status
[proxy:0:0 at leibniz] main (./pm/pmiserv/pmip.c:210): demux engine error
waiting for event
[proxy:2:0 at leibniz] HYD_pmcd_pmip_control_cmd_cb
(./pm/pmiserv/pmip_cb.c:883): assert (!closed) failed
[proxy:2:0 at leibniz] HYDT_dmxu_poll_wait_for_event
(./tools/demux/demux_poll.c:77): callback returned error status
[proxy:2:0 at leibniz] main (./pm/pmiserv/pmip.c:210): demux engine error
waiting for event
[mpiexec at leibniz] HYDT_bscu_wait_for_completion
(./tools/bootstrap/utils/bscu_wait.c:76): one of the processes
terminated badly; aborting
[mpiexec at leibniz] HYDT_bsci_wait_for_completion
(./tools/bootstrap/src/bsci_wait.c:23): launcher returned error waiting
for completion
[mpiexec at leibniz] HYD_pmci_wait_for_completion
(./pm/pmiserv/pmiserv_pmci.c:216): launcher returned error waiting for
completion
[mpiexec at leibniz] main (./ui/mpich/mpiexec.c:325): process manager error
waiting for completion

--
Dipl.-Ing. Silvan Brändli
Numerische Strukturanalyse mit Anwendungen in der Schiffstechnik (M-10)

Technische Universität Hamburg-Harburg
Schwarzenbergstraße 95c
21073 Hamburg

Tel.  : +49 (0)40 42878 - 6187
Fax.  : +49 (0)40 42878 - 6090
e-mail: silvan.braendli at tuhh.de
www   : http://www.tuhh.de/skf

5th GACM Colloquium on Computational Mechanics
http://www.tu-harburg.de/gacm2013
_______________________________________________
discuss mailing list     discuss at mpich.org
To manage subscription options or unsubscribe:
https://lists.mpich.org/mailman/listinfo/discuss