0629cdc2d7
command: svn merge -r 7567:7663 https://svn.open-mpi.org/svn/ompi/tmp/jjhursey-rmaps . (where "." is a trunk checkout) The logs from this branch are much more descriptive than I will put here (including a *really* long description from last night). Here's the short version: - fixed some broken implementations in ras and rmaps - "orterun --host ..." now works and has clearly defined semantics (this was the impetus for the branch and all these fixes -- LANL had a requirement for --host to work for 1.0) - there is still a little bit of cleanup left to do post-1.0 (we got correct functionality for 1.0 -- we did not fix bad implementations that still "work") - rds/hostfile and ras/hostfile handshaking - singleton node segment assignments in stage1 - remove the default hostfile (no need for it anymore with the localhost ras component) - clean up pls components to avoid duplicate ras mapping queries - [possible] -bynode/-byslot being specific to a single app context This commit was SVN r7664.
137 строки
3.6 KiB
C
137 строки
3.6 KiB
C
/*
|
|
* Copyright (c) 2004-2005 The Trustees of Indiana University.
|
|
* All rights reserved.
|
|
* Copyright (c) 2004-2005 The Trustees of the University of Tennessee.
|
|
* All rights reserved.
|
|
* Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
|
|
* University of Stuttgart. All rights reserved.
|
|
* Copyright (c) 2004-2005 The Regents of the University of California.
|
|
* All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
|
|
#include "orte_config.h"
|
|
|
|
#include "opal/class/opal_list.h"
|
|
#include "opal/util/output.h"
|
|
#include "orte/include/orte_constants.h"
|
|
#include "orte/include/orte_types.h"
|
|
#include "orte/mca/ras/base/base.h"
|
|
#include "orte/mca/ras/base/ras_base_node.h"
|
|
#include "orte/mca/rmgr/base/base.h"
|
|
#include "orte/mca/ras/base/ras_base_node.h"
|
|
#include "orte/mca/errmgr/errmgr.h"
|
|
|
|
#include "orte/mca/ras/localhost/ras_localhost.h"
|
|
|
|
|
|
/*
|
|
* Local functions
|
|
*/
|
|
static int orte_ras_localhost_allocate(orte_jobid_t jobid);
|
|
static int orte_ras_localhost_deallocate(orte_jobid_t jobid);
|
|
static int orte_ras_localhost_finalize(void);
|
|
|
|
|
|
/*
|
|
* Local variables
|
|
*/
|
|
orte_ras_base_module_t orte_ras_localhost_module = {
|
|
orte_ras_localhost_allocate,
|
|
orte_ras_base_node_insert,
|
|
orte_ras_base_node_query,
|
|
orte_ras_localhost_deallocate,
|
|
orte_ras_localhost_finalize
|
|
};
|
|
|
|
|
|
orte_ras_base_module_t *orte_ras_localhost_init(int* priority)
|
|
{
|
|
*priority = mca_ras_localhost_component.priority;
|
|
return &orte_ras_localhost_module;
|
|
}
|
|
|
|
|
|
static int orte_ras_localhost_allocate(orte_jobid_t jobid)
|
|
{
|
|
bool empty;
|
|
int ret;
|
|
opal_list_t nodes;
|
|
orte_ras_node_t *node;
|
|
opal_list_item_t *item;
|
|
|
|
/* If the node segment is not empty, do nothing */
|
|
|
|
if (ORTE_SUCCESS != (ret = orte_ras_base_node_segment_empty(&empty))) {
|
|
ORTE_ERROR_LOG(ret);
|
|
return ret;
|
|
}
|
|
if (!empty) {
|
|
opal_output(orte_ras_base.ras_output,
|
|
"orte:ras:localhost: node segment not empty; not doing anything");
|
|
return ORTE_SUCCESS;
|
|
}
|
|
opal_output(orte_ras_base.ras_output,
|
|
"orte:ras:localhost: node segment empty; adding \"localhost\"");
|
|
|
|
/* Ok, the node segment is empty -- so add a localhost node */
|
|
|
|
node = OBJ_NEW(orte_ras_node_t);
|
|
if (NULL == node) {
|
|
return ORTE_ERR_OUT_OF_RESOURCE;
|
|
}
|
|
node->node_name = strdup("localhost");
|
|
node->node_arch = NULL;
|
|
node->node_state = ORTE_NODE_STATE_UP;
|
|
/* JMS: this should not be hard-wired to 0, but there's no
|
|
other value to put it to [yet]... */
|
|
node->node_cellid = 0;
|
|
node->node_slots_inuse = 0;
|
|
node->node_slots_max = 0;
|
|
node->node_slots = 1;
|
|
OBJ_CONSTRUCT(&nodes, opal_list_t);
|
|
opal_list_append(&nodes, &node->super);
|
|
|
|
/* Put it on the segment and allocate it */
|
|
|
|
if (ORTE_SUCCESS !=
|
|
(ret = orte_ras_base_node_insert(&nodes)) ||
|
|
ORTE_SUCCESS !=
|
|
(ret = orte_ras_base_allocate_nodes(jobid, &nodes))) {
|
|
goto cleanup;
|
|
}
|
|
|
|
cleanup:
|
|
item = opal_list_remove_first(&nodes);
|
|
OBJ_RELEASE(item);
|
|
OBJ_DESTRUCT(&nodes);
|
|
|
|
/* All done */
|
|
|
|
return ret;
|
|
}
|
|
|
|
|
|
static int orte_ras_localhost_deallocate(orte_jobid_t jobid)
|
|
{
|
|
/* Nothing to do */
|
|
|
|
opal_output(orte_ras_base.ras_output,
|
|
"ras:localhost:deallocate: success (nothing to do)");
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
|
|
static int orte_ras_localhost_finalize(void)
|
|
{
|
|
/* Nothing to do */
|
|
|
|
opal_output(orte_ras_base.ras_output,
|
|
"ras:localhost:finalize: success (nothing to do)");
|
|
return ORTE_SUCCESS;
|
|
}
|