fix for hideous instability on some systems where MPI_Gather in a shared...

fix for hideous instability on some systems where MPI_Gather in a shared memory communicator can sometimes return permaturely before all data has safely arrived

src/mpi_utils/shared_mem_handler.cc

@@ -87,6 +87,9 @@ void shmem::shared_memory_handler(void)
           prepare_offset_table(NULL, tree_info[handle].SphP_offsets);
           prepare_offset_table(NULL, tree_info[handle].Foreign_Nodes_offsets);
           prepare_offset_table(NULL, tree_info[handle].Foreign_Points_offsets);
+
+          MPI_Barrier(SharedMemComm);  // this barrier is in principle superfluous, but on some systems,
+                                       // the MPI_Gather in prepare_offset_table() can return prematurely before all data has arrived
         }
       else if(tag == TAG_HEADER)  // signals that we are freeing addresses we stored for tree access
         {

src/tree/tree.cc

@@ -957,6 +957,10 @@ void tree<node, partset, point_data, foreign_point_data>::prepare_shared_memory_
       Shmem.inform_offset_table(Foreign_Nodes);
       Shmem.inform_offset_table(Foreign_Points);
 
+      MPI_Barrier(Shmem.SharedMemComm);  // this barrier is in principle superfluous, but on some systems,
+                                         // the MPI_Gather in prepare_offset_table() can return prematurely
+                                         // on the target rank before all data has arrived
+
       /* the following is needed to make sure that the shared memory handler on different nodes is already properly initialized */
       MPI_Barrier(D->Communicator);
     }