Merge pull request #6321 from hppritcha/topic/fix_6236_for_v4.x
Topic/fix 6236 for v4.x
Этот коммит содержится в:
Howard Pritchard
GitHub
Коммит
4dfb9384cb
@ -123,7 +123,8 @@ ORTE_DECLSPEC int orte_rmaps_base_filter_nodes(orte_app_context_t *app,
|
||||
opal_list_t *nodes,
|
||||
bool remove);
|
||||
|
||||
ORTE_DECLSPEC int orte_rmaps_base_set_mapping_policy(orte_mapping_policy_t *policy,
|
||||
ORTE_DECLSPEC int orte_rmaps_base_set_mapping_policy(orte_job_t *jdata,
|
||||
orte_mapping_policy_t *policy,
|
||||
char **device, char *spec);
|
||||
ORTE_DECLSPEC int orte_rmaps_base_set_ranking_policy(orte_ranking_policy_t *policy,
|
||||
orte_mapping_policy_t mapping,
|
||||
|
||||
@ -12,7 +12,7 @@
|
||||
* Copyright (c) 2006-2015 Cisco Systems, Inc. All rights reserved.
|
||||
* Copyright (c) 2011-2013 Los Alamos National Security, LLC.
|
||||
* All rights reserved.
|
||||
* Copyright (c) 2014-2018 Intel, Inc. All rights reserved.
|
||||
* Copyright (c) 2014-2019 Intel, Inc. All rights reserved.
|
||||
* Copyright (c) 2014-2015 Research Organization for Information Science
|
||||
* and Technology (RIST). All rights reserved.
|
||||
* $COPYRIGHT$
|
||||
@ -296,7 +296,7 @@ static int orte_rmaps_base_open(mca_base_open_flag_t flags)
|
||||
"rmaps_base_cpus_per_proc", "rmaps_base_mapping_policy=<obj>:PE=N, default <obj>=NUMA");
|
||||
}
|
||||
|
||||
if (ORTE_SUCCESS != (rc = orte_rmaps_base_set_mapping_policy(&orte_rmaps_base.mapping,
|
||||
if (ORTE_SUCCESS != (rc = orte_rmaps_base_set_mapping_policy(NULL, &orte_rmaps_base.mapping,
|
||||
&orte_rmaps_base.device,
|
||||
rmaps_base_mapping_policy))) {
|
||||
return rc;
|
||||
@ -593,7 +593,8 @@ static int check_modifiers(char *ck, orte_mapping_policy_t *tmp)
|
||||
return ORTE_ERR_TAKE_NEXT_OPTION;
|
||||
}
|
||||
|
||||
int orte_rmaps_base_set_mapping_policy(orte_mapping_policy_t *policy,
|
||||
int orte_rmaps_base_set_mapping_policy(orte_job_t *jdata,
|
||||
orte_mapping_policy_t *policy,
|
||||
char **device, char *inspec)
|
||||
{
|
||||
char *ck;
|
||||
@ -618,136 +619,144 @@ int orte_rmaps_base_set_mapping_policy(orte_mapping_policy_t *policy,
|
||||
|
||||
if (NULL == inspec) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYSOCKET);
|
||||
} else {
|
||||
spec = strdup(inspec); // protect the input string
|
||||
/* see if a colon was included - if so, then we have a policy + modifier */
|
||||
ck = strchr(spec, ':');
|
||||
if (NULL != ck) {
|
||||
/* if the colon is the first character of the string, then we
|
||||
* just have modifiers on the default mapping policy */
|
||||
if (ck == spec) {
|
||||
ck++;
|
||||
opal_output_verbose(5, orte_rmaps_base_framework.framework_output,
|
||||
"%s rmaps:base only modifiers %s provided - assuming bysocket mapping",
|
||||
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME), ck);
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYSOCKET);
|
||||
if (ORTE_ERR_SILENT == (rc = check_modifiers(ck, &tmp)) &&
|
||||
goto setpolicy;
|
||||
}
|
||||
|
||||
spec = strdup(inspec); // protect the input string
|
||||
/* see if a colon was included - if so, then we have a policy + modifier */
|
||||
ck = strchr(spec, ':');
|
||||
if (NULL != ck) {
|
||||
/* if the colon is the first character of the string, then we
|
||||
* just have modifiers on the default mapping policy */
|
||||
if (ck == spec) {
|
||||
ck++; // step over the colon
|
||||
opal_output_verbose(5, orte_rmaps_base_framework.framework_output,
|
||||
"%s rmaps:base only modifiers %s provided - assuming bysocket mapping",
|
||||
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME), ck);
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYSOCKET);
|
||||
if (ORTE_ERR_SILENT == (rc = check_modifiers(ck, &tmp)) &&
|
||||
ORTE_ERR_BAD_PARAM != rc) {
|
||||
free(spec);
|
||||
return ORTE_ERR_SILENT;
|
||||
}
|
||||
free(spec);
|
||||
goto setpolicy;
|
||||
}
|
||||
*ck = '\0'; // terminate spec where the colon was
|
||||
ck++; // step past the colon
|
||||
opal_output_verbose(5, orte_rmaps_base_framework.framework_output,
|
||||
"%s rmaps:base policy %s modifiers %s provided",
|
||||
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME), spec, ck);
|
||||
|
||||
if (0 == strncasecmp(spec, "ppr", strlen(spec))) {
|
||||
/* at this point, ck points to a string that contains at least
|
||||
* two fields (specifying the #procs/obj and the object we are
|
||||
* to map by). we have to allow additional modifiers here - e.g.,
|
||||
* specifying #pe's/proc or oversubscribe - so check for modifiers. if
|
||||
* they are present, ck will look like "N:obj:mod1,mod2,mod3"
|
||||
*/
|
||||
if (NULL == (ptr = strchr(ck, ':'))) {
|
||||
/* this is an error - there had to be at least one
|
||||
* colon to delimit the number from the object type
|
||||
*/
|
||||
orte_show_help("help-orte-rmaps-base.txt", "invalid-pattern", true, inspec);
|
||||
free(spec);
|
||||
return ORTE_ERR_SILENT;
|
||||
}
|
||||
ptr++; // move past the colon
|
||||
/* at this point, ptr is pointing to the beginning of the string that describes
|
||||
* the object plus any modifiers (i.e., "obj:mod1,mod2". We first check to see if there
|
||||
* is another colon indicating that there are modifiers to the request */
|
||||
if (NULL != (cptr = strchr(ptr, ':'))) {
|
||||
/* there are modifiers, so we terminate the object string
|
||||
* at the location of the colon */
|
||||
*cptr = '\0';
|
||||
/* step over that colon */
|
||||
cptr++;
|
||||
/* now check for modifiers - may be none, so
|
||||
* don't emit an error message if the modifier
|
||||
* isn't recognized */
|
||||
if (ORTE_ERR_SILENT == (rc = check_modifiers(cptr, &tmp)) &&
|
||||
ORTE_ERR_BAD_PARAM != rc) {
|
||||
free(spec);
|
||||
return ORTE_ERR_SILENT;
|
||||
}
|
||||
free(spec);
|
||||
goto setpolicy;
|
||||
}
|
||||
/* split the string */
|
||||
*ck = '\0';
|
||||
ck++;
|
||||
opal_output_verbose(5, orte_rmaps_base_framework.framework_output,
|
||||
"%s rmaps:base policy %s modifiers %s provided",
|
||||
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME), spec, ck);
|
||||
/* if the policy is "dist", then we set the policy to that value
|
||||
* and save the second argument as the device
|
||||
*/
|
||||
if (0 == strncasecmp(spec, "ppr", strlen(spec))) {
|
||||
/* we have to allow additional modifiers here - e.g., specifying
|
||||
* #pe's/proc or oversubscribe - so check for modifiers
|
||||
*/
|
||||
if (NULL == (ptr = strrchr(ck, ':'))) {
|
||||
/* this is an error - there had to be at least one
|
||||
* colon to delimit the number from the object type
|
||||
*/
|
||||
orte_show_help("help-orte-rmaps-base.txt", "invalid-pattern", true, inspec);
|
||||
free(spec);
|
||||
return ORTE_ERR_SILENT;
|
||||
}
|
||||
ptr++; // move past the colon
|
||||
/* at this point, ck is pointing to the number of procs/object
|
||||
* and ptr is pointing to the beginning of the string that describes
|
||||
* the object plus any modifiers. We first check to see if there
|
||||
* is a comma indicating that there are modifiers to the request */
|
||||
if (NULL != (cptr = strchr(ptr, ','))) {
|
||||
/* there are modifiers, so we terminate the object string
|
||||
* at the location of the first comma */
|
||||
*cptr = '\0';
|
||||
/* step over that comma */
|
||||
cptr++;
|
||||
/* now check for modifiers - may be none, so
|
||||
* don't emit an error message if the modifier
|
||||
* isn't recognized */
|
||||
if (ORTE_ERR_SILENT == (rc = check_modifiers(cptr, &tmp)) &&
|
||||
ORTE_ERR_BAD_PARAM != rc) {
|
||||
free(spec);
|
||||
return ORTE_ERR_SILENT;
|
||||
}
|
||||
}
|
||||
/* now save the pattern */
|
||||
/* now save the pattern */
|
||||
if (NULL == jdata || NULL == jdata->map) {
|
||||
orte_rmaps_base.ppr = strdup(ck);
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_PPR);
|
||||
ORTE_SET_MAPPING_DIRECTIVE(tmp, ORTE_MAPPING_GIVEN);
|
||||
free(spec);
|
||||
goto setpolicy;
|
||||
}
|
||||
if (ORTE_SUCCESS != (rc = check_modifiers(ck, &tmp)) &&
|
||||
ORTE_ERR_TAKE_NEXT_OPTION != rc) {
|
||||
if (ORTE_ERR_BAD_PARAM == rc) {
|
||||
orte_show_help("help-orte-rmaps-base.txt", "unrecognized-modifier", true, inspec);
|
||||
}
|
||||
free(spec);
|
||||
return rc;
|
||||
}
|
||||
}
|
||||
len = strlen(spec);
|
||||
if (0 == strncasecmp(spec, "slot", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYSLOT);
|
||||
} else if (0 == strncasecmp(spec, "node", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYNODE);
|
||||
} else if (0 == strncasecmp(spec, "seq", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_SEQ);
|
||||
} else if (0 == strncasecmp(spec, "core", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYCORE);
|
||||
} else if (0 == strncasecmp(spec, "l1cache", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYL1CACHE);
|
||||
} else if (0 == strncasecmp(spec, "l2cache", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYL2CACHE);
|
||||
} else if (0 == strncasecmp(spec, "l3cache", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYL3CACHE);
|
||||
} else if (0 == strncasecmp(spec, "socket", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYSOCKET);
|
||||
} else if (0 == strncasecmp(spec, "numa", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYNUMA);
|
||||
} else if (0 == strncasecmp(spec, "board", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYBOARD);
|
||||
} else if (0 == strncasecmp(spec, "hwthread", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYHWTHREAD);
|
||||
/* if we are mapping processes to individual hwthreads, then
|
||||
* we need to treat those hwthreads as separate cpus
|
||||
*/
|
||||
opal_hwloc_use_hwthreads_as_cpus = true;
|
||||
} else if (0 == strncasecmp(spec, "dist", len)) {
|
||||
if (NULL != rmaps_dist_device) {
|
||||
if (NULL != (pch = strchr(rmaps_dist_device, ':'))) {
|
||||
*pch = '\0';
|
||||
}
|
||||
if (NULL != device) {
|
||||
*device = strdup(rmaps_dist_device);
|
||||
}
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYDIST);
|
||||
} else {
|
||||
orte_show_help("help-orte-rmaps-base.txt", "device-not-specified", true);
|
||||
free(spec);
|
||||
return ORTE_ERR_SILENT;
|
||||
jdata->map->ppr = strdup(ck);
|
||||
}
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_PPR);
|
||||
ORTE_SET_MAPPING_DIRECTIVE(tmp, ORTE_MAPPING_GIVEN);
|
||||
free(spec);
|
||||
goto setpolicy;
|
||||
}
|
||||
if (ORTE_SUCCESS != (rc = check_modifiers(ck, &tmp)) &&
|
||||
ORTE_ERR_TAKE_NEXT_OPTION != rc) {
|
||||
if (ORTE_ERR_BAD_PARAM == rc) {
|
||||
orte_show_help("help-orte-rmaps-base.txt", "unrecognized-modifier", true, inspec);
|
||||
}
|
||||
free(spec);
|
||||
return rc;
|
||||
}
|
||||
}
|
||||
len = strlen(spec);
|
||||
if (0 == strncasecmp(spec, "slot", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYSLOT);
|
||||
} else if (0 == strncasecmp(spec, "node", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYNODE);
|
||||
} else if (0 == strncasecmp(spec, "seq", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_SEQ);
|
||||
} else if (0 == strncasecmp(spec, "core", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYCORE);
|
||||
} else if (0 == strncasecmp(spec, "l1cache", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYL1CACHE);
|
||||
} else if (0 == strncasecmp(spec, "l2cache", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYL2CACHE);
|
||||
} else if (0 == strncasecmp(spec, "l3cache", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYL3CACHE);
|
||||
} else if (0 == strncasecmp(spec, "socket", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYSOCKET);
|
||||
} else if (0 == strncasecmp(spec, "numa", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYNUMA);
|
||||
} else if (0 == strncasecmp(spec, "board", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYBOARD);
|
||||
} else if (0 == strncasecmp(spec, "hwthread", len)) {
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYHWTHREAD);
|
||||
/* if we are mapping processes to individual hwthreads, then
|
||||
* we need to treat those hwthreads as separate cpus
|
||||
*/
|
||||
opal_hwloc_use_hwthreads_as_cpus = true;
|
||||
} else if (0 == strncasecmp(spec, "dist", len)) {
|
||||
if (NULL != rmaps_dist_device) {
|
||||
if (NULL != (pch = strchr(rmaps_dist_device, ':'))) {
|
||||
*pch = '\0';
|
||||
}
|
||||
if (NULL != device) {
|
||||
*device = strdup(rmaps_dist_device);
|
||||
}
|
||||
ORTE_SET_MAPPING_POLICY(tmp, ORTE_MAPPING_BYDIST);
|
||||
} else {
|
||||
orte_show_help("help-orte-rmaps-base.txt", "unrecognized-policy", true, "mapping", spec);
|
||||
orte_show_help("help-orte-rmaps-base.txt", "device-not-specified", true);
|
||||
free(spec);
|
||||
return ORTE_ERR_SILENT;
|
||||
}
|
||||
} else {
|
||||
orte_show_help("help-orte-rmaps-base.txt", "unrecognized-policy", true, "mapping", spec);
|
||||
free(spec);
|
||||
ORTE_SET_MAPPING_DIRECTIVE(tmp, ORTE_MAPPING_GIVEN);
|
||||
return ORTE_ERR_SILENT;
|
||||
}
|
||||
free(spec);
|
||||
ORTE_SET_MAPPING_DIRECTIVE(tmp, ORTE_MAPPING_GIVEN);
|
||||
|
||||
setpolicy:
|
||||
*policy = tmp;
|
||||
if (NULL == jdata || NULL == jdata->map) {
|
||||
*policy = tmp;
|
||||
} else {
|
||||
jdata->map->mapping = tmp;
|
||||
}
|
||||
|
||||
return ORTE_SUCCESS;
|
||||
}
|
||||
|
||||
@ -876,7 +876,7 @@ int orte_submit_job(char *argv[], int *index,
|
||||
jdata->map = OBJ_NEW(orte_job_map_t);
|
||||
|
||||
if (NULL != orte_cmd_options.mapping_policy) {
|
||||
if (ORTE_SUCCESS != (rc = orte_rmaps_base_set_mapping_policy(&jdata->map->mapping, NULL, orte_cmd_options.mapping_policy))) {
|
||||
if (ORTE_SUCCESS != (rc = orte_rmaps_base_set_mapping_policy(jdata, &jdata->map->mapping, NULL, orte_cmd_options.mapping_policy))) {
|
||||
ORTE_ERROR_LOG(rc);
|
||||
return rc;
|
||||
}
|
||||
|
||||
@ -308,7 +308,7 @@ int pmix_server_spawn_fn(opal_process_name_t *requestor,
|
||||
orte_rmaps_base_print_mapping(orte_rmaps_base.mapping));
|
||||
return ORTE_ERR_BAD_PARAM;
|
||||
}
|
||||
rc = orte_rmaps_base_set_mapping_policy(&jdata->map->mapping,
|
||||
rc = orte_rmaps_base_set_mapping_policy(jdata, &jdata->map->mapping,
|
||||
NULL, info->data.string);
|
||||
if (ORTE_SUCCESS != rc) {
|
||||
return rc;
|
||||
|
||||
@ -489,7 +489,7 @@ static void _query(int sd, short args, void *cbdata)
|
||||
orte_job_t *jdata;
|
||||
orte_proc_t *proct;
|
||||
orte_app_context_t *app;
|
||||
int rc, i, k, num_replies;
|
||||
int rc = ORTE_SUCCESS, i, k, num_replies;
|
||||
opal_list_t *results, targets, *array;
|
||||
size_t n;
|
||||
uint32_t key;
|
||||
@ -716,7 +716,7 @@ static void _query(int sd, short args, void *cbdata)
|
||||
}
|
||||
}
|
||||
if (ORTE_JOBID_INVALID == jobid) {
|
||||
rc = ORTE_ERR_BAD_PARAM;
|
||||
rc = ORTE_ERR_NOT_FOUND;
|
||||
goto done;
|
||||
}
|
||||
/* construct a list of values with opal_proc_info_t
|
||||
@ -810,12 +810,12 @@ static void _query(int sd, short args, void *cbdata)
|
||||
}
|
||||
|
||||
done:
|
||||
if (0 == opal_list_get_size(results)) {
|
||||
rc = ORTE_ERR_NOT_FOUND;
|
||||
} else if (opal_list_get_size(results) < opal_list_get_size(cd->info)) {
|
||||
rc = ORTE_ERR_PARTIAL_SUCCESS;
|
||||
} else {
|
||||
rc = ORTE_SUCCESS;
|
||||
if (ORTE_SUCCESS == rc) {
|
||||
if (0 == opal_list_get_size(results)) {
|
||||
rc = ORTE_ERR_NOT_FOUND;
|
||||
} else if (opal_list_get_size(results) < opal_list_get_size(cd->info)) {
|
||||
rc = ORTE_ERR_PARTIAL_SUCCESS;
|
||||
}
|
||||
}
|
||||
cd->infocbfunc(rc, results, cd->cbdata, qrel, results);
|
||||
}
|
||||
|
||||
Загрузка…
x
Ссылка в новой задаче
Block a user