Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Open MPI User's mailing list

Subject: Re: [OMPI users] Problems with Open MPI/BLCR checkpoint/restart routine.
From: pat.o'bryant_at_[hidden]
Date: 2009-06-11 07:24:24


Gleb,
    I am trying to use BLCR as well. What levels of OpenMPI, OFED, and BLCR
are you using? I can get a serial checkpoint/restart to work but not the
parallel case. I built my system using OFED 1.3.1, OpenMPI 1.3.1, and BLCR
0.8.1-1. I also used your same BLCR configuration options for OpenMPI.
             Thanks,
              Pat

J.W. (Pat) O'Bryant,Jr.
Business Line Infrastructure
Technical Systems, HPC

                                                                           
             "Gleb \"Crazy
             Sage\"
             Igumnov" To
             <crazy.sage_at_gm Gleb Igumnov <crazy.sage_at_[hidden]>
             ail.com> cc
             Sent by: users_at_[hidden]
             users-bounces@ Subject
             open-mpi.org Re: [OMPI users] Problems with Open
                                      MPI/BLCR checkpoint/restart
                                      routine.
             06/10/09 12:06
             PM
                                                                           
                                                                           
             Please respond
                   to
             "Gleb \"Crazy
                 Sage\"
                Igumnov"
             <crazy.sage_at_gm
               ail.com>;
             Please respond
                   to
             Open MPI Users
             <users_at_open-mp
                 i.org>
                                                                           
                                                                           
                                                                           
                                                                           

Fixed this, not all paths were in variables. Sorry.

> Hello. I've got following problem. I've run MPI programm and successful
> checkpointed it with BLCR.
> But now, when I'm trying to restart it using ompi-restart -v
> ompi_global_snapshot_7190.ckpt I'm getting following message:

> [umu2:07572] Checking for the existence of
> (/root/ompi_global_snapshot_7190.ckpt)
> [umu2:07572] Restarting from file (ompi_global_snapshot_7190.ckpt)
> [umu2:07572] Exec in self
>
--------------------------------------------------------------------------
> Error: Unable to obtain the proper restart command to restart from the
> checkpoint file (ompi_global_snapshot_7190.ckpt). Returned -1.

>
--------------------------------------------------------------------------

> Both Open-MPI and BLCR are installed into shared NFS directory, blcr
> directories are included into PATH and LD_LIBRARY_PATH variables on
> restart node.
> Open MPI initially configured with keys
> ??with?ft=cr ??enable?ft?thread ??enable?mpi?thread
> ??with?blcr=/path/to/blcr

> Program was run with -am ft-enable-cr.
> What can cause such problem?
> --------------------------------------------
> With best regards
> Gleb "Crazy Sage" Igumnov
> mailto:crazy.sage_at_[hidden]

--
With best regards,
 Gleb "Crazy Sage" Igumnov
mailto:crazy.sage_at_[hidden]
_______________________________________________
users mailing list
users_at_[hidden]
http://www.open-mpi.org/mailman/listinfo.cgi/users