ba5498cdc6
1. repair of the linear and direct routed modules 2. repair of the ompi/pubsub/orte module to correctly init routes to the ompi-server, and correctly handle failure to correctly parse the provided ompi-server URI 3. modification of orterun to accept both "file" and "FILE" for designating where the ompi-server URI is to be found - purely a convenience feature 4. resolution of a message ordering problem during the connect/accept handshake that allowed the "send-first" proc to attempt to send to the "recv-first" proc before the HNP had actually updated its routes. Let this be a further reminder to all - message ordering is NOT guaranteed in the OOB 5. Repair the ompi/dpm/orte module to correctly init routes during connect/accept. Reminder to all: messages sent to procs in another job family (i.e., started by a different mpirun) are ALWAYS routed through the respective HNPs. As per the comments in orte/routed, this is REQUIRED to maintain connect/accept (where only the root proc on each side is capable of init'ing the routes), allow communication between mpirun's using different routing modules, and to minimize connections on tools such as ompi-server. It is all taken care of "under the covers" by the OOB to ensure that a route back to the sender is maintained, even when the different mpirun's are using different routed modules. 6. corrections in the orte/odls to ensure proper identification of daemons participating in a dynamic launch 7. corrections in build/nidmap to support update of an existing nidmap during dynamic launch 8. corrected implementation of the update_arch function in the ESS, along with consolidation of a number of ESS operations into base functions for easier maintenance. The ability to support info from multiple jobs was added, although we don't currently do so - this will come later to support further fault recovery strategies 9. minor updates to several functions to remove unnecessary and/or no longer used variables and envar's, add some debugging output, etc. 10. addition of a new macro ORTE_PROC_IS_DAEMON that resolves to true if the provided proc is a daemon There is still more cleanup to be done for efficiency, but this at least works. Tested on single-node Mac, multi-node SLURM via odin. Tests included connect/accept, publish/lookup/unpublish, comm_spawn, comm_spawn_multiple, and singleton comm_spawn. Fixes ticket #1256 This commit was SVN r18804.
341 строка
10 KiB
C
341 строка
10 KiB
C
/*
|
|
* Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
|
|
* University Research and Technology
|
|
* Corporation. All rights reserved.
|
|
* Copyright (c) 2004-2005 The University of Tennessee and The University
|
|
* of Tennessee Research Foundation. 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 "orte/constants.h"
|
|
|
|
#include <catamount/cnos_mpi_os.h>
|
|
|
|
#include "orte/util/show_help.h"
|
|
#include "opal/util/argv.h"
|
|
#include "opal/class/opal_pointer_array.h"
|
|
|
|
#include "orte/util/proc_info.h"
|
|
#include "orte/mca/errmgr/base/base.h"
|
|
#include "orte/util/name_fns.h"
|
|
#include "orte/runtime/orte_globals.h"
|
|
|
|
#include "orte/mca/ess/ess.h"
|
|
#include "orte/mca/ess/base/base.h"
|
|
#include "orte/mca/ess/alps/ess_alps.h"
|
|
|
|
static int alps_set_name(void);
|
|
|
|
static int rte_init(char flags);
|
|
static int rte_finalize(void);
|
|
static bool proc_is_local(orte_process_name_t *proc);
|
|
static char* proc_get_hostname(orte_process_name_t *proc);
|
|
static uint32_t proc_get_arch(orte_process_name_t *proc);
|
|
static uint8_t proc_get_local_rank(orte_process_name_t *proc);
|
|
static uint8_t proc_get_node_rank(orte_process_name_t *proc);
|
|
static int update_arch(orte_process_name_t *proc, uint32_t arch);
|
|
|
|
orte_ess_base_module_t orte_ess_alps_module = {
|
|
rte_init,
|
|
rte_finalize,
|
|
orte_ess_base_app_abort,
|
|
proc_is_local,
|
|
proc_get_hostname,
|
|
proc_get_arch,
|
|
proc_get_local_rank,
|
|
proc_get_node_rank,
|
|
update_arch,
|
|
NULL /* ft_event */
|
|
};
|
|
|
|
static opal_pointer_array_t nidmap;
|
|
static opal_pointer_array_t jobmap;
|
|
static orte_vpid_t nprocs;
|
|
|
|
|
|
static int rte_init(char flags)
|
|
{
|
|
int ret;
|
|
char *error = NULL;
|
|
orte_jmap_t *jmap;
|
|
|
|
/* run the prolog */
|
|
if (ORTE_SUCCESS != (ret = orte_ess_base_std_prolog())) {
|
|
error = "orte_ess_base_std_prolog";
|
|
goto error;
|
|
}
|
|
|
|
/* Start by getting a unique name */
|
|
alps_set_name();
|
|
|
|
/* if I am a daemon, complete my setup using the
|
|
* default procedure
|
|
*/
|
|
if (orte_process_info.daemon) {
|
|
if (ORTE_SUCCESS != (ret = orte_ess_base_orted_setup())) {
|
|
ORTE_ERROR_LOG(ret);
|
|
error = "orte_ess_base_orted_setup";
|
|
goto error;
|
|
}
|
|
} else if (orte_process_info.tool) {
|
|
/* otherwise, if I am a tool proc, use that procedure */
|
|
if (ORTE_SUCCESS != (ret = orte_ess_base_tool_setup())) {
|
|
ORTE_ERROR_LOG(ret);
|
|
error = "orte_ess_base_tool_setup";
|
|
goto error;
|
|
}
|
|
} else {
|
|
/* otherwise, I must be an application process - use
|
|
* the default procedure to finish my setup
|
|
*/
|
|
if (ORTE_SUCCESS != (ret = orte_ess_base_app_setup())) {
|
|
ORTE_ERROR_LOG(ret);
|
|
error = "orte_ess_base_app_setup";
|
|
goto error;
|
|
}
|
|
|
|
/* setup the nidmap arrays */
|
|
OBJ_CONSTRUCT(&nidmap, opal_pointer_array_t);
|
|
opal_pointer_array_init(&nidmap, 8, INT32_MAX, 8);
|
|
|
|
/* setup array of jmaps */
|
|
OBJ_CONSTRUCT(&jobmap, opal_pointer_array_t);
|
|
opal_pointer_array_init(&jobmap, 1, INT32_MAX, 1);
|
|
jmap = OBJ_NEW(orte_jmap_t);
|
|
opal_pointer_array_add(&jobmap, jmap);
|
|
|
|
/* if one was provided, build my nidmap */
|
|
if (ORTE_SUCCESS != (ret = orte_ess_base_build_nidmap(orte_process_info.sync_buf,
|
|
&nidmap, &jmap->pmap, &nprocs))) {
|
|
ORTE_ERROR_LOG(ret);
|
|
error = "orte_ess_base_build_nidmap";
|
|
goto error;
|
|
}
|
|
}
|
|
|
|
return ORTE_SUCCESS;
|
|
|
|
error:
|
|
orte_show_help("help-orte-runtime.txt",
|
|
"orte_init:startup:internal-failure",
|
|
true, error, ORTE_ERROR_NAME(ret), ret);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int rte_finalize(void)
|
|
{
|
|
int ret;
|
|
orte_nid_t **nids;
|
|
orte_jmap_t **jmaps;
|
|
int32_t i;
|
|
|
|
/* if I am a daemon, finalize using the default procedure */
|
|
if (orte_process_info.daemon) {
|
|
if (ORTE_SUCCESS != (ret = orte_ess_base_orted_finalize())) {
|
|
ORTE_ERROR_LOG(ret);
|
|
}
|
|
} else if (orte_process_info.tool) {
|
|
/* otherwise, if I am a tool proc, use that procedure */
|
|
if (ORTE_SUCCESS != (ret = orte_ess_base_tool_finalize())) {
|
|
ORTE_ERROR_LOG(ret);
|
|
}
|
|
} else {
|
|
/* otherwise, I must be an application process - deconstruct
|
|
* my nidmap and jobmap arrays
|
|
*/
|
|
nids = (orte_nid_t**)nidmap.addr;
|
|
for (i=0; i < nidmap.size && NULL != nids[i]; i++) {
|
|
OBJ_RELEASE(nids[i]);
|
|
}
|
|
OBJ_DESTRUCT(&nidmap);
|
|
jmaps = (orte_jmap_t**)jobmap.addr;
|
|
for (i=0; i < jobmap.size && NULL != jmaps[i]; i++) {
|
|
OBJ_RELEASE(jmaps[i]);
|
|
}
|
|
OBJ_DESTRUCT(&jobmap);
|
|
|
|
/* use the default procedure to finish */
|
|
if (ORTE_SUCCESS != (ret = orte_ess_base_app_finalize())) {
|
|
ORTE_ERROR_LOG(ret);
|
|
}
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
static bool proc_is_local(orte_process_name_t *proc)
|
|
{
|
|
orte_nid_t *nid;
|
|
|
|
if (NULL == (nid = orte_ess_base_lookup_nid(&nidmap, &jobmap, proc))) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
|
|
return false;
|
|
}
|
|
|
|
if (nid->daemon == ORTE_PROC_MY_DAEMON->vpid) {
|
|
OPAL_OUTPUT_VERBOSE((2, orte_ess_base_output,
|
|
"%s ess:alps: proc %s is LOCAL",
|
|
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
|
|
ORTE_NAME_PRINT(proc)));
|
|
return true;
|
|
}
|
|
|
|
OPAL_OUTPUT_VERBOSE((2, orte_ess_base_output,
|
|
"%s ess:alps: proc %s is REMOTE",
|
|
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
|
|
ORTE_NAME_PRINT(proc)));
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
static char* proc_get_hostname(orte_process_name_t *proc)
|
|
{
|
|
orte_nid_t *nid;
|
|
|
|
if (NULL == (nid = orte_ess_base_lookup_nid(&nidmap, &jobmap, proc))) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
|
|
return NULL;
|
|
}
|
|
|
|
OPAL_OUTPUT_VERBOSE((2, orte_ess_base_output,
|
|
"%s ess:alps: proc %s is on host %s",
|
|
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
|
|
ORTE_NAME_PRINT(proc),
|
|
nid->name));
|
|
|
|
return nid->name;
|
|
}
|
|
|
|
static uint32_t proc_get_arch(orte_process_name_t *proc)
|
|
{
|
|
orte_nid_t *nid;
|
|
|
|
if (NULL == (nid = orte_ess_base_lookup_nid(&nidmap, &jobmap, proc))) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
|
|
return 0;
|
|
}
|
|
|
|
OPAL_OUTPUT_VERBOSE((2, orte_ess_base_output,
|
|
"%s ess:alps: proc %s has arch %0x",
|
|
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
|
|
ORTE_NAME_PRINT(proc),
|
|
nid->arch));
|
|
|
|
return nid->arch;
|
|
}
|
|
|
|
static int update_arch(orte_process_name_t *proc, uint32_t arch)
|
|
{
|
|
orte_nid_t *nid;
|
|
|
|
if (NULL == (nid = orte_ess_base_lookup_nid(&nidmap, &jobmap, proc))) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
|
|
return ORTE_ERR_NOT_FOUND;
|
|
}
|
|
|
|
OPAL_OUTPUT_VERBOSE((2, orte_ess_base_output,
|
|
"%s ess:alps: updating proc %s to arch %0x",
|
|
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
|
|
ORTE_NAME_PRINT(proc),
|
|
arch));
|
|
|
|
nid->arch = arch;
|
|
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
static uint8_t proc_get_local_rank(orte_process_name_t *proc)
|
|
{
|
|
orte_pmap_t *pmap;
|
|
|
|
if (NULL == (pmap = orte_ess_base_lookup_pmap(&jobmap, proc))) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
|
|
return UINT8_MAX;
|
|
}
|
|
|
|
OPAL_OUTPUT_VERBOSE((2, orte_ess_base_output,
|
|
"%s ess:alps: proc %s has local rank %d",
|
|
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
|
|
ORTE_NAME_PRINT(proc),
|
|
(int)pmap->local_rank));
|
|
|
|
return pmap->local_rank;
|
|
}
|
|
|
|
static uint8_t proc_get_node_rank(orte_process_name_t *proc)
|
|
{
|
|
orte_pmap_t *pmap;
|
|
|
|
if (NULL == (pmap = orte_ess_base_lookup_pmap(&jobmap, proc))) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
|
|
return UINT8_MAX;
|
|
}
|
|
|
|
OPAL_OUTPUT_VERBOSE((2, orte_ess_base_output,
|
|
"%s ess:alps: proc %s has node rank %d",
|
|
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
|
|
ORTE_NAME_PRINT(proc),
|
|
(int)pmap->node_rank));
|
|
|
|
return pmap->node_rank;
|
|
}
|
|
|
|
|
|
static int alps_set_name(void)
|
|
{
|
|
int rc;
|
|
int id;
|
|
orte_jobid_t jobid;
|
|
orte_vpid_t starting_vpid;
|
|
char* jobid_string;
|
|
char* vpid_string;
|
|
|
|
OPAL_OUTPUT_VERBOSE((1, orte_ess_base_output,
|
|
"ess:alps setting name"));
|
|
|
|
id = mca_base_param_register_string("orte", "ess", "jobid", NULL, NULL);
|
|
mca_base_param_lookup_string(id, &jobid_string);
|
|
if (NULL == jobid_string) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
|
|
return ORTE_ERR_NOT_FOUND;
|
|
}
|
|
if (ORTE_SUCCESS != (rc = orte_util_convert_string_to_jobid(&jobid, jobid_string))) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return(rc);
|
|
}
|
|
|
|
id = mca_base_param_register_string("orte", "ess", "vpid", NULL, NULL);
|
|
mca_base_param_lookup_string(id, &vpid_string);
|
|
if (NULL == vpid_string) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
|
|
return ORTE_ERR_NOT_FOUND;
|
|
}
|
|
if (ORTE_SUCCESS != (rc = orte_util_convert_string_to_vpid(&starting_vpid, vpid_string))) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return(rc);
|
|
}
|
|
|
|
ORTE_PROC_MY_NAME->jobid = jobid;
|
|
ORTE_PROC_MY_NAME->vpid = (orte_vpid_t) cnos_get_rank() + starting_vpid;
|
|
|
|
OPAL_OUTPUT_VERBOSE((1, orte_ess_base_output,
|
|
"ess:alps set name to %s", ORTE_NAME_PRINT(ORTE_PROC_MY_NAME)));
|
|
|
|
orte_process_info.num_procs = (orte_std_cntr_t) cnos_get_size();
|
|
|
|
return ORTE_SUCCESS;
|
|
}
|