Search code examples
debuggingmpilldbxterm

xterm's are being closed while debugging an MPI application

I have a problem debugging MPI application with lldb. Essentially, i attach it to every process via

mpirun_lldb() {
mpirun --mca orte_base_help_aggregate 0 --mca mpi_abort_print_stack 1 -np $1 xterm -hold -e lldb -f $2 -- "${@:3}"
}

but at some point MPI_Abort happens and all xterm windows are being closed immediately and I can't even read the stack, leave alone debugging and inspecting variables:

MPI_ABORT was invoked on rank 2 in communicator MPI_COMM_WORLD
with errorcode 255.

NOTE: invoking MPI_ABORT causes Open MPI to kill all MPI processes.
You may or may not see output from other processes, depending on
exactly when Open MPI kills them.

I tried using -hold for xterm but this does not help.

p.s. I don't have access to licensed debuggers like TotalView. It's a first time i have a problem with a simple method described above.

Solution

  • sorry for noise, adding a breakpoint b MPI_Abort solved the issue.