Ensure the process knows it local cpuset early enough to perform the locality computation

This commit was SVN r28221.

orte/mca/ess/base/ess_base_fns.c

@@ -51,6 +51,7 @@ int orte_ess_base_proc_binding(void)
     char *map;
     int ret;
     char *error;
+    hwloc_cpuset_t mycpus;
 
     /* Determine if we were pre-bound or not */
     if (NULL != getenv("OMPI_MCA_orte_bound_at_launch")) {
@@ -253,25 +254,37 @@ int orte_ess_base_proc_binding(void)
      * times, so it's more efficient to keep a global copy
      */
     opal_hwloc_base_get_local_cpuset();
-    /* report bindings, if requested */
-    if (opal_hwloc_report_bindings) {
-        char tmp1[1024], tmp2[1024];
-        hwloc_cpuset_t mycpus;
+
     /* get the cpus we are bound to */
     mycpus = hwloc_bitmap_alloc();
     if (hwloc_get_cpubind(opal_hwloc_topology, 
                           mycpus, 
                           HWLOC_CPUBIND_PROCESS) < 0) {
+        if (NULL != orte_process_info.cpuset) {
+            free(orte_process_info.cpuset);
+            orte_process_info.cpuset = NULL;
+        }
+        if (opal_hwloc_report_bindings) {
             opal_output(0, "MCW rank %d is not bound",
                         ORTE_PROC_MY_NAME->vpid);
+        }
     } else {
+        /* store/update the string representation of our local binding */
+        if (NULL != orte_process_info.cpuset) {
+            free(orte_process_info.cpuset);
+            orte_process_info.cpuset = NULL;
+        }
+        hwloc_bitmap_list_asprintf(&orte_process_info.cpuset, mycpus);
+        /* report the binding, if requested */
+        if (opal_hwloc_report_bindings) {
+            char tmp1[1024], tmp2[1024];
             opal_hwloc_base_cset2str(tmp1, sizeof(tmp1), mycpus);
             opal_hwloc_base_cset2mapstr(tmp2, sizeof(tmp2), mycpus);
             opal_output(0, "MCW rank %d bound to %s: %s",
                         ORTE_PROC_MY_NAME->vpid, tmp1, tmp2);
         }
-        hwloc_bitmap_free(mycpus);
     }
+    hwloc_bitmap_free(mycpus);
 
     return ORTE_SUCCESS;
 

orte/util/nidmap.c

@@ -662,7 +662,6 @@ int orte_util_encode_pidmap(opal_byte_object_t *boptr, bool update)
             ORTE_ERROR_LOG(rc);
             goto cleanup_and_return;
         }
-
         /* cycle thru the job's procs, including only those that have
          * been updated so we minimize the amount of info being sent
          */
@@ -843,6 +842,11 @@ int orte_util_decode_pidmap(opal_byte_object_t *bo)
                 /* set mine */
                 orte_process_info.my_local_rank = local_rank;
                 orte_process_info.my_node_rank = node_rank;
+#if OPAL_HAVE_HWLOC
+                if (NULL != cpu_bitmap) {
+                    orte_process_info.cpuset = strdup(cpu_bitmap);
+                }
+#endif
             }
             /* apps don't need the rest of the data in the buffer for this proc,
              * but we have to unpack it anyway to stay in sync
@@ -881,6 +885,9 @@ int orte_util_decode_pidmap(opal_byte_object_t *bo)
                 ORTE_ERROR_LOG(rc);
                 goto cleanup;
             }
+            if (NULL != cpu_bitmap) {
+                free(cpu_bitmap);
+            }
 #endif
             /* we don't need to store the rest of the values
              * for ourself in the database
@@ -1032,7 +1039,6 @@ int orte_util_decode_daemon_pidmap(opal_byte_object_t *bo)
     orte_local_rank_t local_rank;
     orte_node_rank_t node_rank;
 #if OPAL_HAVE_HWLOC
-    opal_hwloc_level_t bind_level = OPAL_HWLOC_NODE_LEVEL;
     char *cpu_bitmap;
 #endif
     orte_std_cntr_t n;