ompi/mpi_init: fix barrier

Relax CPU usage pressure from the application processes when doing
modex and barrier in ompi_mpi_init.

We see significant latencies in SLURM/pmix plugin barrier progress
because app processes are aggressively call opal_progress pushing
away daemon process doing collective progress.

Author: artpol84

ompi/runtime/ompi_mpi_init.c

@@ -658,7 +658,7 @@ int ompi_mpi_init(int argc, char **argv, int requested, int *provided)
         if (NULL != opal_pmix.fence_nb) {
             opal_pmix.fence_nb(NULL, opal_pmix_collect_all_data,
                                fence_release, (void*)&active);
-            OMPI_WAIT_FOR_COMPLETION(active);
+            OMPI_LAZY_WAIT_FOR_COMPLETION(active);
         } else {
             opal_pmix.fence(NULL, opal_pmix_collect_all_data);
         }
@@ -835,7 +835,7 @@ int ompi_mpi_init(int argc, char **argv, int requested, int *provided)
         if (NULL != opal_pmix.fence_nb) {
             opal_pmix.fence_nb(NULL, opal_pmix_collect_all_data,
                                fence_release, (void*)&active);
-            OMPI_WAIT_FOR_COMPLETION(active);
+            OMPI_LAZY_WAIT_FOR_COMPLETION(active);
         } else {
             opal_pmix.fence(NULL, opal_pmix_collect_all_data);
         }