Open MPI logo

Open MPI Development Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Development mailing list

Subject: [OMPI devel] Error while restarting a checkpoint
From: Leonardo Fialho (lfialho_at_[hidden])
Date: 2008-10-30 15:32:20


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