Hi Gabriele

What the message is saying is that you specified a host that isn't in your allocation. I'm not sure how you are telling mpirun what hosts are allocated for your use, or which ones you want it to use. Could you include your command line and/or any hostfile you might be using?

We don't have a component in the 1.2 series for automatically reading LSF allocations, so you would have to tell the system which hosts are available to you. Since this used to work for you, my guess is that there is some of the hosts you specified to use aren't in your hostfile.

Ralph


On Jan 8, 2009, at 6:00 AM, Gabriele Fatigati wrote:

More precisely:

/cineca/sysprod/lsf/7.0/linux2.6-glibc2.3-x86_64/bin/TaskStarter
The requested hosts were:
  node0911

Verify that you have mapped the allocated resources properly using the
--host specification.
--------------------------------------------------------------------------
[node0862:29190] [0,0,0] ORTE_ERROR_LOG: Out of resource in file
base/rmaps_base_support_fns.c at line 225
[node0862:29190] [0,0,0] ORTE_ERROR_LOG: Out of resource in file
rmaps_rr.c at line 478
[node0862:29190] [0,0,0] ORTE_ERROR_LOG: Out of resource in file
base/rmaps_base_map_job.c at line 210
[node0862:29190] [0,0,0] ORTE_ERROR_LOG: Out of resource in file
rmgr_urm.c at line 372
[node0862:29190] mpirun: spawn failed with errno=-2

2009/1/8 Gabriele Fatigati <g.fatig...@cineca.it>:
Dear OpenMPI Developers,
i'm running my jobs under OpenMPI 1.2.5 Intel compiled. Our cluster
has Infiniband net and LSF scheduler. Since yesterday, I have a
strange problem over some nodes:

[node0862:29190] [0,0,0] ORTE_ERROR_LOG: Out of resource in file
base/rmaps_base_support_fns.c at line 225
[node0862:29190] [0,0,0] ORTE_ERROR_LOG: Out of resource in file
rmaps_rr.c at line 478
[node0862:29190] [0,0,0] ORTE_ERROR_LOG: Out of resource in file
base/rmaps_base_map_job.c at line 210
[node0862:29190] [0,0,0] ORTE_ERROR_LOG: Out of resource in file
rmgr_urm.c at line 372
[node0862:29190] mpirun: spawn failed with errno=-2

I don't understand if the problem depends by OpenMPI, Infiniband or
other. Any idea?

--
Ing. Gabriele Fatigati

Parallel programmer

CINECA Systems & Tecnologies Department

Supercomputing Group

Via Magnanelli 6/3, Casalecchio di Reno (BO) Italy

www.cineca.it                    Tel:   +39 051 6171722

g.fatigati [AT] cineca.it




--
Ing. Gabriele Fatigati

Parallel programmer

CINECA Systems & Tecnologies Department

Supercomputing Group

Via Magnanelli 6/3, Casalecchio di Reno (BO) Italy

www.cineca.it                    Tel:   +39 051 6171722

g.fatigati [AT] cineca.it
_______________________________________________
users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users

Reply via email to