Hi! I'm working in a project fucusing on fault tolerance in Grid systems. We have been using LAM-MPI and BLCR so far, now I want to evaluate OpenMPI.
I read in the mailing lists that the current stable version of OpenMPI lacks many features on checkpointing, making it recommended to use the development version from SVN. All my small test applications are working without any problems. Unfortunately executing the mpi-enabled version of Povray 3.1 failed, which we have used as standard demo application so far: [grid-demo:09575] *** An error occurred in MPI_Recv [grid-demo:09575] *** on communicator MPI_COMM_WORLD [grid-demo:09575] *** MPI_ERR_TRUNCATE: message truncated [grid-demo:09575] *** MPI_ERRORS_ARE_FATAL (goodbye) -------------------------------------------------------------------------- mpirun has exited due to process rank 0 with PID 9575 on node grid-demo exiting without calling "finalize". This may have caused other processes in the application to be terminated by signals sent by mpirun (as reported here). -------------------------------------------------------------------------- I found the following posting about this error: http://www.open-mpi.org/community/lists/devel/2006/11/1191.php We did not have any problems with mpi-povray so far, but maybe the described problem applies to mpi-povray and the problem only did not show up before because other MPI flavors are more flexible. Therefore my question to this list: did anybody of you succeed in executing mpi-povray? Best, Matthias
