Question

I’ve got a very strange bug while using MPI. A successfully created communicator can’t be deleted. A deleting attempt results in FATAL ERROR on all nodes except the ones that are included in communicator group. The minimal working example is below. What do you think about the reason of such strange behaviour?

#include <stdio.h>
#include <mpi.h>

int main(int argc, char* argv[])
{
    MPI_Group group_world;              // group of MPI_COMM_WORLD
    MPI_Group group_new;                // new group
    MPI_Comm  comm_new;                 // new communicator 
    int group_new_ranks[3]={10,20,30};  // new communicator's ranks 

    MPI_Init(&argc, &argv);

    MPI_Comm_group(MPI_COMM_WORLD, &group_world);                 // get group_world - MPI_SUCCESS for all nodes
    MPI_Group_incl(group_world, 3, group_new_ranks, &group_new);  // get new group - MPI_SUCCESS for all nodes
    MPI_Comm_create(MPI_COMM_WORLD, group_new, &comm_new);        // create new communicator - MPI_SUCCESS for all nodes

    MPI_Comm_free(&comm_new);   // FATAL ERROR for all nodes except 10, 20, 30
    MPI_Group_free(&group_new);
    MPI_Group_free(&group_world);

    MPI_Finalize();
    return 0;
}

Answer 1

MPI_Comm_create() returns MPI_COMM_NULL to all processes not within the group. You’re passing MPI_COMM_NULL to MPI_Comm_free(), which is not allowed.