Here's the patch: I've set it up to go into 1.5, but not 1.4 as that series is
being closed out. Please let me know if this solves the problem for you.
Modified: orte/mca/ras/gridengine/ras_gridengine_module.c
==============================================================================
--- orte/mca/ras/gridengine/ras_gridengine_module.c (original)
+++ orte/mca/ras/gridengine/ras_gridengine_module.c 2012-03-15 13:45:50 EDT
(Thu, 15 Mar 2012)
@@ -64,6 +64,8 @@
int rc;
FILE *fp;
orte_node_t *node;
+ opal_list_item_t *item;
+ bool found;
/* show the Grid Engine's JOB_ID */
if (mca_ras_gridengine_component.show_jobid ||
@@ -92,22 +94,36 @@
queue = strtok_r(NULL, " \n", &tok);
arch = strtok_r(NULL, " \n", &tok);
- /* create a new node entry */
- node = OBJ_NEW(orte_node_t);
- if (NULL == node) {
- fclose(fp);
- return ORTE_ERR_OUT_OF_RESOURCE;
+ /* see if we already have this node */
+ found = false;
+ for (item = opal_list_get_first(nodelist);
+ item != opal_list_get_end(nodelist);
+ item = opal_list_get_next(item)) {
+ node = (orte_node_t*)item;
+ if (0 == strcmp(ptr, node->name)) {
+ /* just add the slots */
+ node->slots += (int)strtol(num, (char **)NULL, 10);
+ found = true;
+ break;
+ }
+ }
+ if (!found) {
+ /* create a new node entry */
+ node = OBJ_NEW(orte_node_t);
+ if (NULL == node) {
+ fclose(fp);
+ return ORTE_ERR_OUT_OF_RESOURCE;
+ }
+ node->name = strdup(ptr);
+ node->state = ORTE_NODE_STATE_UP;
+ node->slots_inuse = 0;
+ node->slots_max = 0;
+ node->slots = (int)strtol(num, (char **)NULL, 10);
+ opal_output(mca_ras_gridengine_component.verbose,
+ "ras:gridengine: %s: PE_HOSTFILE shows slots=%d",
+ node->name, node->slots);
+ opal_list_append(nodelist, &node->super);
}
- node->name = strdup(ptr);
- node->state = ORTE_NODE_STATE_UP;
- node->slots_inuse = 0;
- node->slots_max = 0;
- node->slots = (int)strtol(num, (char **)NULL, 10);
- opal_output(mca_ras_gridengine_component.verbose,
- "ras:gridengine: %s: PE_HOSTFILE shows slots=%d",
- node->name, node->slots);
- opal_list_append(nodelist, &node->super);
-
} /* finished reading the $PE_HOSTFILE */
cleanup:
On Mar 15, 2012, at 11:41 AM, Joshua Baker-LePain wrote:
> On Thu, 15 Mar 2012 at 11:38am, Ralph Castain wrote
>
>> No, I'll fix the parser as we should be able to run anyway. Just can't
>> guarantee which queue the job will end up in, but at least it -will- run.
>
> Makes sense to me. Thanks!
>
> --
> Joshua Baker-LePain
> QB3 Shared Cluster Sysadmin
> UCSF
> _______________________________________________
> users mailing list
> us...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/users
