Back out some prior commits. These commits fixed bproc so it would run, but broke several other things (singleton comm_spawn and hostfile operations have been identified so far). Since bproc is the culprit here, let's leave bproc broken for now - I'll work on a fix for that environment that doesn't impact everythig else.

This commit was SVN r12648.

orte/mca/ras/base/ras_base_allocate.c

@@ -27,7 +27,6 @@
 #include "orte/dss/dss.h"
 #include "orte/mca/errmgr/errmgr.h"
 #include "orte/mca/rmgr/rmgr.h"
-#include "orte/mca/gpr/gpr.h"
 
 #include "orte/mca/ras/base/proxy/ras_base_proxy.h"
 #include "orte/mca/ras/base/ras_private.h"
@@ -129,11 +128,23 @@ int orte_ras_base_allocate(orte_jobid_t jobid, opal_list_t *attributes)
      * want to allocate new nodes. Otherwise allocate all the existing nodes to
      * our job */
     OBJ_CONSTRUCT(&nodes, opal_list_t);
+    /* See if there are any nodes already on the registry. Most of the time
+     * these would have been put there by the RDS reading the hostfile. */
+    if (ORTE_SUCCESS != (ret = orte_ras_base_node_query(&nodes))) {
+        OBJ_DESTRUCT(&nodes);
+        return ret;
+    }
+    /* If there are any nodes at all, allocate them all to this job */
+    if (!opal_list_is_empty(&nodes)) {
+        opal_output(orte_ras_base.ras_output,
+                    "orte:ras:base:allocate: reallocating nodes that are already on registry");
+        ret = orte_ras_base_allocate_nodes(jobid, &nodes);
+        OBJ_DESTRUCT(&nodes);
+        return ret;
+    }
 
-    /* Run the RAS components from highest to lowest priority (they are already sorted).
+    /* there were no nodes already on the registry, so get them from the
-     * Stop when the node segment is no longer empty. This ensures we go through the
+     * RAS components */
-     * allocator components at least once
-     */
  
     /* If no components are available, then return an error */
     if (opal_list_is_empty(&orte_ras_base.ras_available)) {

orte/runtime/orte_init_stage1.c

@@ -434,6 +434,7 @@ int orte_init_stage1(bool infrastructure)
             orte_rds_cell_desc_t *rds_item;
             orte_rds_cell_attr_t *new_attr;
             orte_ras_node_t *ras_item;
+            opal_list_t attrs;
             
             OBJ_CONSTRUCT(&single_host, opal_list_t);
             OBJ_CONSTRUCT(&rds_single_host, opal_list_t);
@@ -523,11 +524,21 @@ int orte_init_stage1(bool infrastructure)
                 goto error;;
             }
             
-            if (ORTE_SUCCESS != (ret = orte_ras_base_allocate_nodes(my_jobid, &single_host))) {
+            /* JMS: Same as above -- fix this after 1.0: force a
+                selection so that orte_ras has initialized pointers in
+                case anywhere else tries to use it.  This may end up
+                putting a bunch more nodes on the node segment - e.g.,
+                if you're in a SLURM allocation and you "./a.out",
+                you'll end up with the localhost *and* all the other
+                nodes in your allocation on the node segment -- which
+                is probably fine */
+            OBJ_CONSTRUCT(&attrs, opal_list_t);
+            if (ORTE_SUCCESS != (ret = orte_ras.allocate_job(my_jobid, &attrs))) {
                 ORTE_ERROR_LOG(ret);
                 error = "allocate for a singleton";
                 goto error;
             }
+            OBJ_DESTRUCT(&attrs);
             
             OBJ_DESTRUCT(&single_host);
             OBJ_DESTRUCT(&rds_single_host);