1
1
openmpi/orte/mca/rmgr/urm/rmgr_urm.c

647 строки
20 KiB
C
Исходник Обычный вид История

/*
* Copyright (c) 2004-2007 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/orte_constants.h"
#ifdef HAVE_SYS_TIME_H
#include <sys/time.h>
#endif /* HAVE_SYS_TIME_H */
#include <errno.h>
#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif /* HAVE_UNISTD_H */
#ifdef HAVE_STRING_H
#include <string.h>
#endif /* HAVE_STRING_H */
#include "opal/class/opal_list.h"
#include "opal/util/trace.h"
#include "opal/util/output.h"
#include "opal/mca/base/mca_base_param.h"
#include "opal/util/opal_environ.h"
#include "opal/threads/condition.h"
#include "orte/mca/errmgr/errmgr.h"
#include "orte/mca/rds/rds.h"
#include "orte/mca/ras/ras.h"
#include "orte/mca/rmaps/rmaps.h"
#include "orte/mca/pls/pls.h"
#include "orte/mca/gpr/gpr.h"
#include "orte/mca/iof/iof.h"
#include "orte/mca/ns/ns.h"
#include "orte/mca/smr/smr.h"
#if OPAL_ENABLE_FT == 1
#include "orte/mca/snapc/snapc.h"
#endif
#include "orte/mca/rmgr/base/rmgr_private.h"
#include "orte/mca/rmgr/base/base.h"
#include "orte/mca/rmgr/urm/rmgr_urm.h"
static int orte_rmgr_urm_setup_job(
orte_app_context_t** app_context,
orte_std_cntr_t num_context,
orte_jobid_t* jobid,
opal_list_t *attrs);
static int orte_rmgr_urm_spawn_job(
orte_app_context_t** app_context,
orte_std_cntr_t num_context,
orte_jobid_t* jobid,
orte_std_cntr_t num_connect,
orte_process_name_t *connect,
orte_rmgr_cb_fn_t cbfn,
orte_proc_state_t cb_conditions,
opal_list_t *attributes);
static int orte_rmgr_urm_module_init(void);
static int orte_rmgr_urm_module_finalize(void);
orte_rmgr_base_module_t orte_rmgr_urm_module = {
orte_rmgr_urm_module_init,
orte_rmgr_urm_setup_job,
orte_rmgr_urm_spawn_job,
orte_rmgr_base_connect,
orte_rmgr_base_disconnect,
orte_rmgr_urm_module_finalize,
/** SUPPORT FUNCTIONS ***/
orte_rmgr_base_find_attribute,
orte_rmgr_base_add_attribute,
orte_rmgr_base_merge_attributes,
orte_rmgr_base_delete_attribute,
orte_rmgr_base_get_app_context,
orte_rmgr_base_put_app_context,
orte_rmgr_base_check_context_cwd,
orte_rmgr_base_check_context_app,
orte_rmgr_base_set_proc_info,
orte_rmgr_base_get_proc_info,
orte_rmgr_base_set_universe_size,
orte_rmgr_base_get_universe_size
};
/*
* Since we were selected, complete the init
* by starting the comm system
*/
static int orte_rmgr_urm_module_init(void)
{
int rc;
if (ORTE_SUCCESS != (rc = orte_rmgr_base_comm_start())) {
ORTE_ERROR_LOG(rc);
}
return rc;
}
/*
* Setup the job
*/
static int orte_rmgr_urm_setup_job(orte_app_context_t** app_context,
orte_std_cntr_t num_context,
orte_jobid_t* jobid,
opal_list_t *attrs)
{
int rc;
orte_std_cntr_t i;
orte_attribute_t *attr;
orte_jobid_t *jptr;
OPAL_TRACE(1);
/* check for given jobid */
if (NULL != (attr = orte_rmgr.find_attribute(attrs, ORTE_RMGR_USE_GIVEN_JOBID))) {
if (ORTE_SUCCESS != (rc = orte_dss.get((void**)&jptr, attr->value, ORTE_JOBID))) {
ORTE_ERROR_LOG(rc);
return rc;
}
*jobid = *jptr;
} else {
/* allocate a jobid */
if (ORTE_SUCCESS != (rc = orte_ns.create_jobid(jobid, attrs))) {
ORTE_ERROR_LOG(rc);
return rc;
}
}
/* for each app_context, we need to purge their environment of HNP
* MCA component selection directives
*/
for (i=0; i < num_context; i++) {
orte_rmgr_base_purge_mca_params(&app_context[i]->env);
}
/* create and initialize job segment */ /* JJH C/N mapping before this */
if (ORTE_SUCCESS !=
(rc = orte_rmgr_base_put_app_context(*jobid, app_context,
num_context))) {
ORTE_ERROR_LOG(rc);
return rc;
}
/* set a default job state of INIT. We need this so that
* orterun doesn't report an error from the registry if
* the spawn fails for some reason. Otherwise, orterun
* will try to get the job state (to see why we exited)
* and will find nothing
*/
if (ORTE_SUCCESS != (rc = orte_smr.set_job_state(*jobid, ORTE_JOB_STATE_INIT))) {
ORTE_ERROR_LOG(rc);
return rc;
Add ability to trap and propagate SIGUSR1/2 to remote processes. There are a number of small changes that hit a bunch of files: 1. Changed the RMGR and PLS APIs to add "signal_job" and "signal_proc" entry points. Only the "signal_job" entries are implemented - none of the components have implementations for "signal_proc" at this time. Thus, you can signal all of the procs in a job, but cannot currently signal only one specific proc. 2. Implemented those new API functions in all components except xgrid (Brian will do so very soon). Only the rsh/ssh and fork modules have been tested, however, and only under OS-X. 3. Added signal traps and callback functions for SIGUSR1/2 to orterun/mpirun that catch those signals and call the appropriate commands to propagate them out to all processes in the job. 4. Added a new test directory under the orte branch to (eventually) hold unit and system level tests for just the run-time. Since our test branch of the repository is under restricted access, people working on the RTE were continually developing their own system-level tests - thus making it hard to help diagnose problems. I have moved the more commonly-used functions here, and added one specifically for testing the SIGUSR1/2 functionality. I will be contacting people directly to seek help with testing the changes on more environments. Other than compile issues, you should see absolutely no change in behavior on any of your systems - this additional functionality is transparent to anyone who does not issue a SIGUSR1/2 to mpirun. Ralph This commit was SVN r10258.
2006-06-08 18:27:17 +00:00
}
return ORTE_SUCCESS;
Add ability to trap and propagate SIGUSR1/2 to remote processes. There are a number of small changes that hit a bunch of files: 1. Changed the RMGR and PLS APIs to add "signal_job" and "signal_proc" entry points. Only the "signal_job" entries are implemented - none of the components have implementations for "signal_proc" at this time. Thus, you can signal all of the procs in a job, but cannot currently signal only one specific proc. 2. Implemented those new API functions in all components except xgrid (Brian will do so very soon). Only the rsh/ssh and fork modules have been tested, however, and only under OS-X. 3. Added signal traps and callback functions for SIGUSR1/2 to orterun/mpirun that catch those signals and call the appropriate commands to propagate them out to all processes in the job. 4. Added a new test directory under the orte branch to (eventually) hold unit and system level tests for just the run-time. Since our test branch of the repository is under restricted access, people working on the RTE were continually developing their own system-level tests - thus making it hard to help diagnose problems. I have moved the more commonly-used functions here, and added one specifically for testing the SIGUSR1/2 functionality. I will be contacting people directly to seek help with testing the changes on more environments. Other than compile issues, you should see absolutely no change in behavior on any of your systems - this additional functionality is transparent to anyone who does not issue a SIGUSR1/2 to mpirun. Ralph This commit was SVN r10258.
2006-06-08 18:27:17 +00:00
}
/* the xconnect functionality in this RMGR component is only utilized
* when a singleton does a dynamic spawn. Hence, the "parent" jobid
* is just my own
*/
static void orte_rmgr_urm_xconnect_callback(orte_gpr_notify_data_t *data, void *cbdata)
{
orte_gpr_value_t **values;
orte_jobid_t child;
int rc;
OPAL_TRACE(1);
/* we made sure in the subscriptions that at least one
* value is always returned
* get the jobid from the segment name in the first value
*/
values = (orte_gpr_value_t**)(data->values)->addr;
if (ORTE_SUCCESS != (rc = orte_schema.extract_jobid_from_segment_name(&child,
values[0]->segment))) {
ORTE_ERROR_LOG(rc);
return;
}
if (ORTE_SUCCESS != (rc = orte_rmgr_base_xconnect(child, ORTE_PROC_MY_NAME->jobid))) {
ORTE_ERROR_LOG(rc);
return;
}
/* signal that the application has completed xconnect */
OPAL_THREAD_LOCK(&mca_rmgr_urm_component.lock);
mca_rmgr_urm_component.xconnect = true;
/* if the launch is also done, then spawn complete */
if (mca_rmgr_urm_component.launched) {
mca_rmgr_urm_component.done = true;
mca_rmgr_urm_component.rc = ORTE_SUCCESS;
opal_condition_signal(&mca_rmgr_urm_component.cond);
}
OPAL_THREAD_UNLOCK(&mca_rmgr_urm_component.lock);
}
static void orte_rmgr_urm_wireup_stdin(orte_jobid_t jobid)
{
int rc;
orte_process_name_t* name;
OPAL_TRACE(1);
if (ORTE_SUCCESS != (rc = orte_ns.create_process_name(&name, 0, jobid, 0))) {
ORTE_ERROR_LOG(rc);
return;
}
if (ORTE_SUCCESS != (rc = orte_iof.iof_push(name, ORTE_NS_CMP_JOBID, ORTE_IOF_STDIN, 0))) {
ORTE_ERROR_LOG(rc);
}
free(name);
}
static void orte_rmgr_urm_callback(orte_gpr_notify_data_t *data, void *cbdata)
{
orte_rmgr_cb_fn_t cbfunc;
union {
orte_rmgr_cb_fn_t func;
void * ptr;
} cbfunc_union;
First phase of the scalable RTE changes: 1. Modify the registry to eliminate redundant data copying for startup messages. 2. Revise the subscription/trigger system to avoid redundant storage of triggers and subscriptions. This dramatically reduces the search time when a registry action occurs - to illustrate the point, there are now only a handful of triggers on the system for each job. Before, there were a handful of triggers for each PROCESS in the job, all of which had to be checked every time something happened on the registry. This is much, much faster now. 3. Update all subscriptions to the new format. There are now "named" subscriptions - this allows you to "name" a subscription that all the processes will be using. The first one to hit the registry actually defines the subscription. From then on, any subsequent "subscribes" to the same name just cause that process to "attach" to the existing subscription. This keeps the number of subscriptions being tracked by the registry to a minimum, while ensuring that each process still gets notified. 4. Do the same for triggers. Also fixed a duplicate subscription problem that was causing people to receive data equal to the number of processes times the data they should have received from a trigger/subscription. Sorry about that... :-( ...but it's all better now! Uncovered a situation where the modex data seems to be getting entered on the registry a second time - the latter time coming after the compound command has been "fired", thereby causing all the subscriptions to fire. Asked Tim and Jeff to look into this. Second phase of the changes will involve modifying the xcast system so that the same message gets sent to all processes. This will further reduce the message traffic, and - once we have a true "broadcast" version of xcast - really speed things up and improve scalability. This commit was SVN r6542.
2005-07-18 18:49:00 +00:00
orte_gpr_value_t **values, *value;
orte_gpr_keyval_t** keyvals;
orte_jobid_t jobid;
orte_std_cntr_t i, j, k;
int rc;
OPAL_TRACE(1);
/* ISO C forbids conversion of object pointer to function
pointer. So we do this, which is the same thing, but without
the warning from GCC */
cbfunc_union.ptr = cbdata;
cbfunc = cbfunc_union.func;
/* we made sure in the subscriptions that at least one
* value is always returned
* get the jobid from the segment name in the first value
*/
First phase of the scalable RTE changes: 1. Modify the registry to eliminate redundant data copying for startup messages. 2. Revise the subscription/trigger system to avoid redundant storage of triggers and subscriptions. This dramatically reduces the search time when a registry action occurs - to illustrate the point, there are now only a handful of triggers on the system for each job. Before, there were a handful of triggers for each PROCESS in the job, all of which had to be checked every time something happened on the registry. This is much, much faster now. 3. Update all subscriptions to the new format. There are now "named" subscriptions - this allows you to "name" a subscription that all the processes will be using. The first one to hit the registry actually defines the subscription. From then on, any subsequent "subscribes" to the same name just cause that process to "attach" to the existing subscription. This keeps the number of subscriptions being tracked by the registry to a minimum, while ensuring that each process still gets notified. 4. Do the same for triggers. Also fixed a duplicate subscription problem that was causing people to receive data equal to the number of processes times the data they should have received from a trigger/subscription. Sorry about that... :-( ...but it's all better now! Uncovered a situation where the modex data seems to be getting entered on the registry a second time - the latter time coming after the compound command has been "fired", thereby causing all the subscriptions to fire. Asked Tim and Jeff to look into this. Second phase of the changes will involve modifying the xcast system so that the same message gets sent to all processes. This will further reduce the message traffic, and - once we have a true "broadcast" version of xcast - really speed things up and improve scalability. This commit was SVN r6542.
2005-07-18 18:49:00 +00:00
values = (orte_gpr_value_t**)(data->values)->addr;
if (ORTE_SUCCESS != (rc =
orte_schema.extract_jobid_from_segment_name(&jobid,
values[0]->segment))) {
ORTE_ERROR_LOG(rc);
return;
}
First phase of the scalable RTE changes: 1. Modify the registry to eliminate redundant data copying for startup messages. 2. Revise the subscription/trigger system to avoid redundant storage of triggers and subscriptions. This dramatically reduces the search time when a registry action occurs - to illustrate the point, there are now only a handful of triggers on the system for each job. Before, there were a handful of triggers for each PROCESS in the job, all of which had to be checked every time something happened on the registry. This is much, much faster now. 3. Update all subscriptions to the new format. There are now "named" subscriptions - this allows you to "name" a subscription that all the processes will be using. The first one to hit the registry actually defines the subscription. From then on, any subsequent "subscribes" to the same name just cause that process to "attach" to the existing subscription. This keeps the number of subscriptions being tracked by the registry to a minimum, while ensuring that each process still gets notified. 4. Do the same for triggers. Also fixed a duplicate subscription problem that was causing people to receive data equal to the number of processes times the data they should have received from a trigger/subscription. Sorry about that... :-( ...but it's all better now! Uncovered a situation where the modex data seems to be getting entered on the registry a second time - the latter time coming after the compound command has been "fired", thereby causing all the subscriptions to fire. Asked Tim and Jeff to look into this. Second phase of the changes will involve modifying the xcast system so that the same message gets sent to all processes. This will further reduce the message traffic, and - once we have a true "broadcast" version of xcast - really speed things up and improve scalability. This commit was SVN r6542.
2005-07-18 18:49:00 +00:00
for(i = 0, k=0; k < data->cnt &&
i < (data->values)->size; i++) {
if (NULL != values[i]) {
k++;
value = values[i];
/* determine the state change */
keyvals = value->keyvals;
for(j=0; j<value->cnt; j++) {
orte_gpr_keyval_t* keyval = keyvals[j];
if(strcmp(keyval->key, ORTE_PROC_NUM_AT_INIT) == 0) {
(*cbfunc)(jobid,ORTE_PROC_STATE_INIT);
continue;
}
if(strcmp(keyval->key, ORTE_PROC_NUM_LAUNCHED) == 0) {
(*cbfunc)(jobid,ORTE_PROC_STATE_LAUNCHED);
continue;
}
if(strcmp(keyval->key, ORTE_PROC_NUM_RUNNING) == 0) {
(*cbfunc)(jobid,ORTE_PROC_STATE_RUNNING);
continue;
}
First phase of the scalable RTE changes: 1. Modify the registry to eliminate redundant data copying for startup messages. 2. Revise the subscription/trigger system to avoid redundant storage of triggers and subscriptions. This dramatically reduces the search time when a registry action occurs - to illustrate the point, there are now only a handful of triggers on the system for each job. Before, there were a handful of triggers for each PROCESS in the job, all of which had to be checked every time something happened on the registry. This is much, much faster now. 3. Update all subscriptions to the new format. There are now "named" subscriptions - this allows you to "name" a subscription that all the processes will be using. The first one to hit the registry actually defines the subscription. From then on, any subsequent "subscribes" to the same name just cause that process to "attach" to the existing subscription. This keeps the number of subscriptions being tracked by the registry to a minimum, while ensuring that each process still gets notified. 4. Do the same for triggers. Also fixed a duplicate subscription problem that was causing people to receive data equal to the number of processes times the data they should have received from a trigger/subscription. Sorry about that... :-( ...but it's all better now! Uncovered a situation where the modex data seems to be getting entered on the registry a second time - the latter time coming after the compound command has been "fired", thereby causing all the subscriptions to fire. Asked Tim and Jeff to look into this. Second phase of the changes will involve modifying the xcast system so that the same message gets sent to all processes. This will further reduce the message traffic, and - once we have a true "broadcast" version of xcast - really speed things up and improve scalability. This commit was SVN r6542.
2005-07-18 18:49:00 +00:00
if(strcmp(keyval->key, ORTE_PROC_NUM_AT_STG1) == 0) {
(*cbfunc)(jobid,ORTE_PROC_STATE_AT_STG1);
continue;
}
if(strcmp(keyval->key, ORTE_PROC_NUM_AT_STG2) == 0) {
(*cbfunc)(jobid,ORTE_PROC_STATE_AT_STG2);
First phase of the scalable RTE changes: 1. Modify the registry to eliminate redundant data copying for startup messages. 2. Revise the subscription/trigger system to avoid redundant storage of triggers and subscriptions. This dramatically reduces the search time when a registry action occurs - to illustrate the point, there are now only a handful of triggers on the system for each job. Before, there were a handful of triggers for each PROCESS in the job, all of which had to be checked every time something happened on the registry. This is much, much faster now. 3. Update all subscriptions to the new format. There are now "named" subscriptions - this allows you to "name" a subscription that all the processes will be using. The first one to hit the registry actually defines the subscription. From then on, any subsequent "subscribes" to the same name just cause that process to "attach" to the existing subscription. This keeps the number of subscriptions being tracked by the registry to a minimum, while ensuring that each process still gets notified. 4. Do the same for triggers. Also fixed a duplicate subscription problem that was causing people to receive data equal to the number of processes times the data they should have received from a trigger/subscription. Sorry about that... :-( ...but it's all better now! Uncovered a situation where the modex data seems to be getting entered on the registry a second time - the latter time coming after the compound command has been "fired", thereby causing all the subscriptions to fire. Asked Tim and Jeff to look into this. Second phase of the changes will involve modifying the xcast system so that the same message gets sent to all processes. This will further reduce the message traffic, and - once we have a true "broadcast" version of xcast - really speed things up and improve scalability. This commit was SVN r6542.
2005-07-18 18:49:00 +00:00
continue;
}
if(strcmp(keyval->key, ORTE_PROC_NUM_AT_STG3) == 0) {
(*cbfunc)(jobid,ORTE_PROC_STATE_AT_STG3);
continue;
}
if(strcmp(keyval->key, ORTE_PROC_NUM_FINALIZED) == 0) {
#if OPAL_ENABLE_FT == 1
/* Stop tracking this job */
if(ORTE_SUCCESS != (rc = orte_snapc.release_job(jobid))) {
ORTE_ERROR_LOG(rc);
}
#endif
First phase of the scalable RTE changes: 1. Modify the registry to eliminate redundant data copying for startup messages. 2. Revise the subscription/trigger system to avoid redundant storage of triggers and subscriptions. This dramatically reduces the search time when a registry action occurs - to illustrate the point, there are now only a handful of triggers on the system for each job. Before, there were a handful of triggers for each PROCESS in the job, all of which had to be checked every time something happened on the registry. This is much, much faster now. 3. Update all subscriptions to the new format. There are now "named" subscriptions - this allows you to "name" a subscription that all the processes will be using. The first one to hit the registry actually defines the subscription. From then on, any subsequent "subscribes" to the same name just cause that process to "attach" to the existing subscription. This keeps the number of subscriptions being tracked by the registry to a minimum, while ensuring that each process still gets notified. 4. Do the same for triggers. Also fixed a duplicate subscription problem that was causing people to receive data equal to the number of processes times the data they should have received from a trigger/subscription. Sorry about that... :-( ...but it's all better now! Uncovered a situation where the modex data seems to be getting entered on the registry a second time - the latter time coming after the compound command has been "fired", thereby causing all the subscriptions to fire. Asked Tim and Jeff to look into this. Second phase of the changes will involve modifying the xcast system so that the same message gets sent to all processes. This will further reduce the message traffic, and - once we have a true "broadcast" version of xcast - really speed things up and improve scalability. This commit was SVN r6542.
2005-07-18 18:49:00 +00:00
(*cbfunc)(jobid,ORTE_PROC_STATE_FINALIZED);
continue;
}
if(strcmp(keyval->key, ORTE_PROC_NUM_TERMINATED) == 0) {
#if OPAL_ENABLE_FT == 1
/* Stop tracking this job */
if(ORTE_SUCCESS != (rc = orte_snapc.release_job(jobid))) {
ORTE_ERROR_LOG(rc);
}
#endif
First phase of the scalable RTE changes: 1. Modify the registry to eliminate redundant data copying for startup messages. 2. Revise the subscription/trigger system to avoid redundant storage of triggers and subscriptions. This dramatically reduces the search time when a registry action occurs - to illustrate the point, there are now only a handful of triggers on the system for each job. Before, there were a handful of triggers for each PROCESS in the job, all of which had to be checked every time something happened on the registry. This is much, much faster now. 3. Update all subscriptions to the new format. There are now "named" subscriptions - this allows you to "name" a subscription that all the processes will be using. The first one to hit the registry actually defines the subscription. From then on, any subsequent "subscribes" to the same name just cause that process to "attach" to the existing subscription. This keeps the number of subscriptions being tracked by the registry to a minimum, while ensuring that each process still gets notified. 4. Do the same for triggers. Also fixed a duplicate subscription problem that was causing people to receive data equal to the number of processes times the data they should have received from a trigger/subscription. Sorry about that... :-( ...but it's all better now! Uncovered a situation where the modex data seems to be getting entered on the registry a second time - the latter time coming after the compound command has been "fired", thereby causing all the subscriptions to fire. Asked Tim and Jeff to look into this. Second phase of the changes will involve modifying the xcast system so that the same message gets sent to all processes. This will further reduce the message traffic, and - once we have a true "broadcast" version of xcast - really speed things up and improve scalability. This commit was SVN r6542.
2005-07-18 18:49:00 +00:00
(*cbfunc)(jobid,ORTE_PROC_STATE_TERMINATED);
continue;
}
}
}
}
}
/**
* define a callback point for completing the wireup of the stdin for io forwarding
*/
static void orte_rmgr_urm_wireup_callback(orte_gpr_notify_data_t *data, void *cbdata)
{
orte_gpr_value_t **values;
orte_jobid_t jobid;
int rc;
OPAL_TRACE(1);
/* we made sure in the subscriptions that at least one
* value is always returned
* get the jobid from the segment name in the first value
*/
values = (orte_gpr_value_t**)(data->values)->addr;
if (ORTE_SUCCESS != (rc = orte_schema.extract_jobid_from_segment_name(&jobid, values[0]->segment))) {
ORTE_ERROR_LOG(rc);
return;
}
opal_output(orte_rmgr_base.rmgr_output, "rmgr_urm:wireup_callback called for job %ld", (long)jobid);
orte_rmgr_urm_wireup_stdin(jobid);
/* signal that we can leave */
OPAL_THREAD_LOCK(&mca_rmgr_urm_component.lock);
mca_rmgr_urm_component.launched = true;
/* if the xconnect is also done, then spawn complete */
if (mca_rmgr_urm_component.xconnect) {
mca_rmgr_urm_component.done = true;
mca_rmgr_urm_component.rc = ORTE_SUCCESS;
opal_condition_signal(&mca_rmgr_urm_component.cond);
}
OPAL_THREAD_UNLOCK(&mca_rmgr_urm_component.lock);
}
/*
* callback that tells us when we can leave the spawn function and return to caller
*/
static void app_terminated(orte_gpr_notify_data_t *data, void *cbdata)
{
/* signal that we can leave */
OPAL_THREAD_LOCK(&mca_rmgr_urm_component.lock);
mca_rmgr_urm_component.done = true;
opal_condition_signal(&mca_rmgr_urm_component.cond);
OPAL_THREAD_UNLOCK(&mca_rmgr_urm_component.lock);
}
/*
* Shortcut for the multiple steps involved in spawning a new job.
*/
static int orte_rmgr_urm_spawn_job(
orte_app_context_t** app_context,
orte_std_cntr_t num_context,
orte_jobid_t* jobid,
orte_std_cntr_t num_connect,
orte_process_name_t *connect,
orte_rmgr_cb_fn_t cbfunc,
orte_proc_state_t cb_conditions,
opal_list_t *attributes)
{
int rc;
orte_process_name_t* name;
struct timeval urmstart, urmstop;
orte_attribute_t *flow, *attr;
uint8_t flags, *fptr;
orte_proc_state_t *gate;
OPAL_TRACE(1);
/* check for timing request - get start time if so */
if (mca_rmgr_urm_component.timing) {
if (0 != gettimeofday(&urmstart, NULL)) {
opal_output(0, "rmgr_urm: could not obtain start time");
urmstart.tv_sec = 0;
urmstart.tv_usec = 0;
}
}
/* mark that the spawn is not done */
OPAL_THREAD_LOCK(&mca_rmgr_urm_component.lock);
mca_rmgr_urm_component.xconnect = false;
mca_rmgr_urm_component.done = false;
mca_rmgr_urm_component.launched = false;
mca_rmgr_urm_component.rc = ORTE_ERR_FAILED_TO_START;
OPAL_THREAD_UNLOCK(&mca_rmgr_urm_component.lock);
/* check for any flow directives to control what we do */
if (NULL != (flow = orte_rmgr.find_attribute(attributes, ORTE_RMGR_SPAWN_FLOW))) {
/* something was specified - get the value */
if (ORTE_SUCCESS != (rc = orte_dss.get((void**)&fptr, flow->value, ORTE_UINT8))) {
ORTE_ERROR_LOG(rc);
return rc;
}
flags = *fptr;
} else {
flags = 0xff;
}
/*
* Initialize job segment and allocate resources
*/ /* JJH Insert C/N mapping stuff here */
/* Only do this step if we have been asked to do it via the
* ORTE_RMGR_SPAWN_FLOW attribute
*/
if (flags & ORTE_RMGR_SETUP) {
if (ORTE_SUCCESS !=
(rc = orte_rmgr_urm_setup_job(app_context, num_context, jobid, attributes))) {
ORTE_ERROR_LOG(rc);
return rc;
}
}
if (flags & ORTE_RMGR_RES_DISC) {
if (ORTE_SUCCESS != (rc = orte_rds.query(*jobid))) {
ORTE_ERROR_LOG(rc);
return rc;
}
}
if (flags & ORTE_RMGR_ALLOC) {
if (ORTE_SUCCESS != (rc = orte_ras.allocate_job(*jobid, attributes))) {
ORTE_ERROR_LOG(rc);
return rc;
}
}
if (flags & ORTE_RMGR_MAP) {
if (ORTE_SUCCESS != (rc = orte_rmaps.map_job(*jobid, attributes))) {
ORTE_ERROR_LOG(rc);
return rc;
}
}
if (flags & ORTE_RMGR_SETUP_TRIGS) {
/*
* setup I/O forwarding
*/
if (ORTE_SUCCESS != (rc = orte_ns.create_process_name(&name, 0, *jobid, 0))) {
ORTE_ERROR_LOG(rc);
return rc;
}
if (ORTE_SUCCESS != (rc = orte_iof.iof_pull(name, ORTE_NS_CMP_JOBID, ORTE_IOF_STDOUT, 1))) {
ORTE_ERROR_LOG(rc);
return rc;
}
if (ORTE_SUCCESS != (rc = orte_iof.iof_pull(name, ORTE_NS_CMP_JOBID, ORTE_IOF_STDERR, 2))) {
ORTE_ERROR_LOG(rc);
return rc;
}
free(name); /* done with this */
#if 0
{
int i = 0;
printf("orte_rmgr_urm_wireup_stdin callback: pid %d\n", getpid());
while (i == 0) sleep(5);
}
#endif
/* setup the launch system's stage gate counters and subscriptions */
if (ORTE_SUCCESS != (rc = orte_rmgr_base_proc_stage_gate_init(*jobid))) {
ORTE_ERROR_LOG(rc);
return rc;
}
/* setup the subscription so we can complete the wireup when all processes reach LAUNCHED. This
* function has the dual purpose of setting the conditioned wait variable so that the RMGR
* can know that the app has indeed launched, and hence return to the caller
*/
rc = orte_smr.job_stage_gate_subscribe(*jobid, orte_rmgr_urm_wireup_callback, NULL, ORTE_PROC_STATE_LAUNCHED);
if(ORTE_SUCCESS != rc) {
ORTE_ERROR_LOG(rc);
return rc;
}
/* see if we need to setup a cross-connect of ORTE information with the new job */
if (NULL != (attr = orte_rmgr.find_attribute(attributes, ORTE_RMGR_XCONNECT_AT_SPAWN))) {
/* cross-connect was requested - get the stage gate name where this is to occur */
if (ORTE_SUCCESS != (rc = orte_dss.get((void**)&gate, attr->value, ORTE_PROC_STATE))) {
ORTE_ERROR_LOG(rc);
return rc;
}
/* setup the xconnect subscription on the new job so we can complete the procedure */
if (ORTE_SUCCESS != (rc = orte_smr.job_stage_gate_subscribe(*jobid,
orte_rmgr_urm_xconnect_callback, NULL, *gate))) {
ORTE_ERROR_LOG(rc);
return rc;
}
} else {
/* indicate that we don't need to wait for xconnect */
OPAL_THREAD_LOCK(&mca_rmgr_urm_component.lock);
mca_rmgr_urm_component.xconnect = true;
OPAL_THREAD_UNLOCK(&mca_rmgr_urm_component.lock);
}
/* setup the subscription so we will know if things fail to launch */
rc = orte_smr.job_stage_gate_subscribe(*jobid, app_terminated, NULL, ORTE_PROC_STATE_TERMINATED);
if(ORTE_SUCCESS != rc) {
ORTE_ERROR_LOG(rc);
return rc;
}
/*
* Define the ERRMGR's callbacks as required
*/
if (ORTE_SUCCESS != (rc = orte_errmgr.register_job(*jobid))) {
ORTE_ERROR_LOG(rc);
return rc;
}
/*
* setup caller's callback
*/
if(NULL != cbfunc) {
union {
orte_rmgr_cb_fn_t func;
void * ptr;
} cbfunc_union;
void *cbdata;
/* ISO C forbids conversion of object pointer to function
pointer. So we do this, which is the same thing, but without
the warning from GCC */
cbfunc_union.func = cbfunc;
cbdata = cbfunc_union.ptr;
rc = orte_smr.job_stage_gate_subscribe(*jobid, orte_rmgr_urm_callback, cbdata, cb_conditions);
if(ORTE_SUCCESS != rc) {
ORTE_ERROR_LOG(rc);
return rc;
}
}
/* check for timing request - get stop time and report elapsed time if so */
if (mca_rmgr_urm_component.timing) {
if (0 != gettimeofday(&urmstop, NULL)) {
opal_output(0, "rmgr_urm: could not obtain stop time");
} else {
opal_output(0, "rmgr_urm: job setup time is %ld usec",
(long int)((urmstop.tv_sec - urmstart.tv_sec)*1000000 +
(urmstop.tv_usec - urmstart.tv_usec)));
}
}
}
/* if we don't want to launch, then just return here */
if (!(flags & ORTE_RMGR_LAUNCH)) {
return ORTE_SUCCESS;
}
#if OPAL_ENABLE_FT == 1
/*
* Wire up the SnapC component to this job
*/
if(ORTE_SUCCESS != (rc = orte_snapc.setup_job(*jobid))) {
ORTE_ERROR_LOG(rc);
return rc;
}
#endif
Bring in the generalized xcast communication system along with the correspondingly revised orted launch. I will send a message out to developers explaining the basic changes. In brief: 1. generalize orte_rml.xcast to become a general broadcast-like messaging system. Messages can now be sent to any tag on the daemons or processes. Note that any message sent via xcast will be delivered to ALL processes in the specified job - you don't get to pick and choose. At a later date, we will introduce an augmented capability that will use the daemons as relays, but will allow you to send to a specified array of process names. 2. extended orte_rml.xcast so it supports more scalable message routing methodologies. At the moment, we support three: (a) direct, which sends the message directly to all recipients; (b) linear, which sends the message to the local daemon on each node, which then relays it to its own local procs; and (b) binomial, which sends the message via a binomial algo across all the daemons, each of which then relays to its own local procs. The crossover points between the algos are adjustable via MCA param, or you can simply demand that a specific algo be used. 3. orteds no longer exhibit two types of behavior: bootproxy or VM. Orteds now always behave like they are part of a virtual machine - they simply launch a job if mpirun tells them to do so. This is another step towards creating an "orteboot" functionality, but also provided a clean system for supporting message relaying. Note one major impact of this commit: multiple daemons on a node cannot be supported any longer! Only a single daemon/node is now allowed. This commit is known to break support for the following environments: POE, Xgrid, Xcpu, Windows. It has been tested on rsh, SLURM, and Bproc. Modifications for TM support have been made but could not be verified due to machine problems at LANL. Modifications for SGE have been made but could not be verified. The developers for the non-verified environments will be separately notified along with suggestions on how to fix the problems. This commit was SVN r15007.
2007-06-12 13:28:54 +00:00
/* setup the orted's stage gate triggers - do this here as, if there are no
* new orteds to launch, the trigger will fire immediately and launch
* the procs
*/
if (ORTE_SUCCESS != (rc = orte_rmgr_base_orted_stage_gate_init(*jobid))) {
ORTE_ERROR_LOG(rc);
return rc;
}
/*
* launch the job
*/
if (ORTE_SUCCESS != (rc = orte_pls.launch_job(*jobid))) {
ORTE_ERROR_LOG(rc);
return rc;
}
/* wait for the application to launch */
OPAL_THREAD_LOCK(&mca_rmgr_urm_component.lock);
while (!mca_rmgr_urm_component.done) {
opal_condition_wait(&mca_rmgr_urm_component.cond,
&mca_rmgr_urm_component.lock);
}
OPAL_THREAD_UNLOCK(&mca_rmgr_urm_component.lock);
/* check for timing request - get start time if so */
if (mca_rmgr_urm_component.timing) {
if (0 != gettimeofday(&urmstart, NULL)) {
opal_output(0, "rmgr_urm: could not obtain launch stop time");
} else {
opal_output(0, "rmgr_urm: launch time is %ld usec",
(long int)((urmstart.tv_sec - urmstop.tv_sec)*1000000 +
(urmstart.tv_usec - urmstop.tv_usec)));
}
}
/* return the status code contained in the component */
return mca_rmgr_urm_component.rc;
}
static int orte_rmgr_urm_module_finalize(void)
{
int rc;
/* Cancel pending receive. */
if (ORTE_SUCCESS != (rc = orte_rmgr_base_comm_stop())) {
ORTE_ERROR_LOG(rc);
}
return rc;
}