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 www.cineca.it Tel: +39 051 6171722 g.fatigati [AT] cineca.it
