My suspects were confirmed. After a orte_iof_base_setup_child/parent the
problem does not occur.
Leonardo
Leonardo Fialho escribió:
Hi All,
I´m trying to restart a process from a previous checkpoint. My
(modified) orted is trying to do this. Its uses the opal-restart
command, but after cr_restart is called by CRS (crs:blcr:
blcr_restart: SELF: exec :(cr_restart, cr_restart
/tmp/radic//1/ompi_blcr_context.6507)) the SO freezes (kernel panic).
The error generated at this moment is:
"Restart failed: No such device or address"
I think that it can be generated because the stdin/stdout/stderr from
the checkpointed file points to undefined descriptor os something like
this...
Anybody can help about this? How can I close these descriptor before
the checkpoint? The opal-restart open these descriptor too? What can I
make to it works?
Thanks,
--
Leonardo Fialho
Computer Architecture and Operating Systems Department - CAOS
Universidad Autonoma de Barcelona - UAB
ETSE, Edifcio Q, QC/3088
http://www.caos.uab.es
Phone: +34-93-581-2888
Fax: +34-93-581-2478
