Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |  

This web mail archive is frozen.

This page is part of a frozen web archive of this mailing list.

You can still navigate around this archive, but know that no new mails have been added to it since July of 2016.

Click here to be taken to the new web archives of this list; it includes all the mails that are in this frozen archive plus all new mails that have been sent to the list since it was migrated to the new archives.

Subject: [OMPI users] Possibile OpenMPI bug
From: Gabriele Fatigati (g.fatigati_at_[hidden])
Date: 2009-07-17 05:32:53

Dear OpenMPi developers,
i'm writing you about a possibile bug in OpenMPi 1.3.2 I'm running
under LSF and Infiniband net. When i launch a job, sometimes i have
the follow error:

Jul 17 10:10:54 2009 10653 4 7.02 handleTSRegisterStart: unwanted task
registration. PAM expected 3 tasks on host<node0724>. This is task 4
on this host. Total number of expected tasks for this job is 255. This
is task 161 in total. Shutting down ...
Jul 17 10:10:55 2009 10653 3 7.02 handleTSRegisterTerm: cannot find
pid 16029 on host node0724 in node table
mpirun has exited due to process rank 1 with PID 25266 on
node node0724 exiting without calling "finalize". This may
have caused other processes in the application to be
terminated by signals sent by mpirun (as reported here).

It sounds like a different procs number read by LSF and OpenMPI. I
have launched 255 procs and there are 161 task.. very very strange.
Any idea?
Thanks in advance.

Ing. Gabriele Fatigati
Parallel programmer
CINECA Systems & Tecnologies Department
Supercomputing Group
Via Magnanelli 6/3, Casalecchio di Reno (BO) Italy                    Tel:   +39 051 6171722
g.fatigati [AT]