Although this didn't solve the earlier termination problem, the code will be required once we get connection terminations properly detected. If a daemon (or HNP) is trying to terminate, then we need to check for termination conditions whenever a route is lost - when all child connections are gone, then we are free to finalize.

This commit was SVN r25248.

orte/mca/routed/binomial/routed_binomial.c

@@ -32,6 +32,7 @@
 #include "orte/util/nidmap.h"
 #include "orte/runtime/orte_globals.h"
 #include "orte/runtime/orte_wait.h"
+#include "orte/runtime/orte_quit.h"
 #include "orte/runtime/runtime.h"
 #include "orte/runtime/data_type_support/orte_dt_support.h"
 
@@ -830,11 +831,22 @@ static int route_lost(const orte_process_name_t *route)
              item = opal_list_get_next(item)) {
             child = (orte_routed_tree_t*)item;
             if (child->vpid == route->vpid) {
+                OPAL_OUTPUT_VERBOSE((4, orte_routed_base_output,
+                                     "%s routed_binomial: removing route to child daemon %s",
+                                     ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
+                                     ORTE_NAME_PRINT(route)));
                 opal_list_remove_item(&my_children, item);
                 OBJ_RELEASE(item);
                 return ORTE_SUCCESS;
             }
         }
+        /* if we are the HNP or daemon, AND we are terminating,
+         * then we want to finalize if all our child daemons
+         * have left
+         */
+        if (orte_terminating && 0 == opal_list_get_size(&my_children)) {
+            orte_quit();
+        }
     }
 
     /* we don't care about this one, so return success */

orte/orted/orted_comm.c

@@ -743,6 +743,8 @@ int orte_daemon_process_commands(orte_process_name_t* sender,
             opal_output(0, "%s orted_cmd: received exit cmd",
                         ORTE_NAME_PRINT(ORTE_PROC_MY_NAME));
         }
+        /* flag that we are terminating */
+        orte_terminating = true;
         /* kill the local procs */
         orte_odls.kill_local_procs(NULL);
         /* trigger our appropriate exit procedure

orte/runtime/orte_init.c

@@ -52,6 +52,7 @@
  */
 bool orte_initialized = false;
 bool orte_finalizing = false;
+bool orte_terminating = false;
 bool orte_debug_flag = false;
 int orte_debug_verbosity;
 char *orte_prohibited_session_dirs = NULL;

orte/runtime/orte_quit.c

@@ -143,6 +143,9 @@ void orte_quit(void)
         return;
     }
 
+    /* flag that we are finalizing */
+    orte_finalizing = true;
+
     /* whack any lingering session directory files from our jobs */
     orte_session_dir_cleanup(ORTE_JOBID_WILDCARD);
 

orte/runtime/runtime.h

@@ -43,6 +43,7 @@ ORTE_DECLSPEC extern const char orte_version_string[];
  */
 ORTE_DECLSPEC extern bool orte_initialized;
 ORTE_DECLSPEC extern bool orte_finalizing;
+ORTE_DECLSPEC extern bool orte_terminating;
 ORTE_DECLSPEC extern int orte_debug_output;
 ORTE_DECLSPEC extern bool orte_debug_flag;