cf6137b530
Bring Slurm PMI-1 component online Bring the s2 component online Little cleanup - let the various PMIx modules set the process name during init, and then just raise it up to the ORTE level. Required as the different PMI environments all pass the jobid in different ways. Bring the OMPI pubsub/pmi component online Get comm_spawn working again Ensure we always provide a cpuset, even if it is NULL pmix/cray: adjust cray pmix component for pmix Make changes so cray pmix can work within the integrated ompi/pmix framework. Bring singletons back online. Implement the comm_spawn operation using pmix - not tested yet Cleanup comm_spawn - procs now starting, error in connect_accept Complete integration
320 строки
12 KiB
C
320 строки
12 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 (c) 2007 Cisco Systems, Inc. All rights reserved.
|
|
* Copyright (c) 2011-2012 Los Alamos National Security, LLC.
|
|
* All rights reserved.
|
|
* Copyright (c) 2013-2015 Intel, Inc. All rights reserved.
|
|
* Copyright (c) 2015 Research Organization for Information Science
|
|
* and Technology (RIST). All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*
|
|
*/
|
|
|
|
#include "orte_config.h"
|
|
#include "orte/constants.h"
|
|
|
|
#include "opal/dss/dss.h"
|
|
#include "opal/util/path.h"
|
|
#include "opal/mca/installdirs/installdirs.h"
|
|
#include "opal/mca/pmix/base/base.h"
|
|
#include "opal/util/argv.h"
|
|
|
|
#include "orte/util/name_fns.h"
|
|
#include "orte/util/show_help.h"
|
|
#include "orte/mca/errmgr/errmgr.h"
|
|
#include "orte/mca/oob/base/base.h"
|
|
#include "orte/mca/rml/rml.h"
|
|
#include "orte/mca/rml/rml_types.h"
|
|
#include "orte/mca/rml/base/rml_contact.h"
|
|
#include "orte/mca/routed/routed.h"
|
|
#include "orte/mca/state/state.h"
|
|
#include "orte/orted/pmix/pmix_server.h"
|
|
#include "orte/runtime/orte_globals.h"
|
|
#include "orte/runtime/orte_wait.h"
|
|
|
|
#include "orte/mca/plm/base/base.h"
|
|
#include "orte/mca/plm/base/plm_private.h"
|
|
|
|
#define ORTE_URI_MSG_LGTH 256
|
|
|
|
static void set_handler_default(int sig)
|
|
{
|
|
struct sigaction act;
|
|
|
|
act.sa_handler = SIG_DFL;
|
|
act.sa_flags = 0;
|
|
sigemptyset(&act.sa_mask);
|
|
|
|
sigaction(sig, &act, (struct sigaction *)0);
|
|
}
|
|
|
|
int orte_plm_base_fork_hnp(void)
|
|
{
|
|
int p[2], death_pipe[2];
|
|
char *cmd;
|
|
char **argv = NULL;
|
|
int argc;
|
|
char *param, *cptr, *pmix_uri;
|
|
sigset_t sigs;
|
|
int buffer_length, num_chars_read, chunk;
|
|
char *orted_uri;
|
|
int rc;
|
|
orte_jobid_t jobid;
|
|
|
|
/* if we don't have any active OOB modules, then abort */
|
|
if (0 == opal_list_get_size(&orte_oob_base.actives)) {
|
|
orte_show_help("help-plm-base.txt", "no-oob", true);
|
|
ORTE_FORCED_TERMINATE(ORTE_ERR_SILENT);
|
|
return ORTE_ERR_SILENT;
|
|
}
|
|
|
|
/* A pipe is used to communicate between the parent and child to
|
|
indicate whether the exec ultimately succeeded or failed. The
|
|
child sets the pipe to be close-on-exec; the child only ever
|
|
writes anything to the pipe if there is an error (e.g.,
|
|
executable not found, exec() fails, etc.). The parent does a
|
|
blocking read on the pipe; if the pipe closed with no data,
|
|
then the exec() succeeded. If the parent reads something from
|
|
the pipe, then the child was letting us know that it failed.
|
|
*/
|
|
if (pipe(p) < 0) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_SYS_LIMITS_PIPES);
|
|
return ORTE_ERR_SYS_LIMITS_PIPES;
|
|
}
|
|
|
|
/* we also have to give the HNP a pipe it can watch to know when
|
|
* we terminated. Since the HNP is going to be a child of us, it
|
|
* can't just use waitpid to see when we leave - so it will watch
|
|
* the pipe instead
|
|
*/
|
|
if (pipe(death_pipe) < 0) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_SYS_LIMITS_PIPES);
|
|
return ORTE_ERR_SYS_LIMITS_PIPES;
|
|
}
|
|
|
|
/* find the orted binary using the install_dirs support - this also
|
|
* checks to ensure that we can see this executable and it *is* executable by us
|
|
*/
|
|
cmd = opal_path_access("orted", opal_install_dirs.bindir, X_OK);
|
|
if (NULL == cmd) {
|
|
/* guess we couldn't do it - best to abort */
|
|
ORTE_ERROR_LOG(ORTE_ERR_FILE_NOT_EXECUTABLE);
|
|
close(p[0]);
|
|
close(p[1]);
|
|
return ORTE_ERR_FILE_NOT_EXECUTABLE;
|
|
}
|
|
|
|
/* okay, setup an appropriate argv */
|
|
opal_argv_append(&argc, &argv, "orted");
|
|
|
|
/* tell the daemon it is to be the HNP */
|
|
opal_argv_append(&argc, &argv, "--hnp");
|
|
|
|
/* tell the daemon to get out of our process group */
|
|
opal_argv_append(&argc, &argv, "--set-sid");
|
|
|
|
/* tell the daemon to report back its uri so we can connect to it */
|
|
opal_argv_append(&argc, &argv, "--report-uri");
|
|
asprintf(¶m, "%d", p[1]);
|
|
opal_argv_append(&argc, &argv, param);
|
|
free(param);
|
|
|
|
/* give the daemon a pipe it can watch to tell when we have died */
|
|
opal_argv_append(&argc, &argv, "--singleton-died-pipe");
|
|
asprintf(¶m, "%d", death_pipe[0]);
|
|
opal_argv_append(&argc, &argv, param);
|
|
free(param);
|
|
|
|
/* add any debug flags */
|
|
if (orte_debug_flag) {
|
|
opal_argv_append(&argc, &argv, "--debug");
|
|
}
|
|
|
|
if (orte_debug_daemons_flag) {
|
|
opal_argv_append(&argc, &argv, "--debug-daemons");
|
|
}
|
|
|
|
if (orte_debug_daemons_file_flag) {
|
|
if (!orte_debug_daemons_flag) {
|
|
opal_argv_append(&argc, &argv, "--debug-daemons");
|
|
}
|
|
opal_argv_append(&argc, &argv, "--debug-daemons-file");
|
|
}
|
|
|
|
/* indicate that it must use the novm state machine */
|
|
opal_argv_append(&argc, &argv, "-"OPAL_MCA_CMD_LINE_ID);
|
|
opal_argv_append(&argc, &argv, "state_novm_select");
|
|
opal_argv_append(&argc, &argv, "1");
|
|
|
|
/* pass it a jobid to match my job family */
|
|
opal_argv_append(&argc, &argv, "-"OPAL_MCA_CMD_LINE_ID);
|
|
opal_argv_append(&argc, &argv, "ess_base_jobid");
|
|
jobid = ORTE_DAEMON_JOBID(ORTE_PROC_MY_NAME->jobid);
|
|
if (ORTE_SUCCESS != (rc = orte_util_convert_jobid_to_string(¶m, jobid))) {
|
|
ORTE_ERROR_LOG(rc);
|
|
free(cmd);
|
|
return rc;
|
|
}
|
|
opal_argv_append(&argc, &argv, param);
|
|
free(param);
|
|
|
|
/* Fork off the child */
|
|
orte_process_info.hnp_pid = fork();
|
|
if(orte_process_info.hnp_pid < 0) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_SYS_LIMITS_CHILDREN);
|
|
close(p[0]);
|
|
close(p[1]);
|
|
close(death_pipe[0]);
|
|
close(death_pipe[1]);
|
|
free(cmd);
|
|
opal_argv_free(argv);
|
|
return ORTE_ERR_SYS_LIMITS_CHILDREN;
|
|
}
|
|
|
|
if (orte_process_info.hnp_pid == 0) {
|
|
close(p[0]);
|
|
close(death_pipe[1]);
|
|
/* I am the child - exec me */
|
|
|
|
/* Set signal handlers back to the default. Do this close
|
|
to the execve() because the event library may (and likely
|
|
will) reset them. If we don't do this, the event
|
|
library may have left some set that, at least on some
|
|
OS's, don't get reset via fork() or exec(). Hence, the
|
|
orted could be unkillable (for example). */
|
|
set_handler_default(SIGTERM);
|
|
set_handler_default(SIGINT);
|
|
set_handler_default(SIGHUP);
|
|
set_handler_default(SIGPIPE);
|
|
set_handler_default(SIGCHLD);
|
|
|
|
/* Unblock all signals, for many of the same reasons that
|
|
we set the default handlers, above. This is noticable
|
|
on Linux where the event library blocks SIGTERM, but we
|
|
don't want that blocked by the orted (or, more
|
|
specifically, we don't want it to be blocked by the
|
|
orted and then inherited by the ORTE processes that it
|
|
forks, making them unkillable by SIGTERM). */
|
|
sigprocmask(0, 0, &sigs);
|
|
sigprocmask(SIG_UNBLOCK, &sigs, 0);
|
|
|
|
execv(cmd, argv);
|
|
|
|
/* if I get here, the execv failed! */
|
|
orte_show_help("help-ess-base.txt", "ess-base:execv-error",
|
|
true, cmd, strerror(errno));
|
|
exit(1);
|
|
|
|
} else {
|
|
free(cmd);
|
|
/* I am the parent - wait to hear something back and
|
|
* report results
|
|
*/
|
|
close(p[1]); /* parent closes the write - orted will write its contact info to it*/
|
|
close(death_pipe[0]); /* parent closes the death_pipe's read */
|
|
opal_argv_free(argv);
|
|
|
|
/* setup the buffer to read the HNP's uri */
|
|
buffer_length = ORTE_URI_MSG_LGTH;
|
|
chunk = ORTE_URI_MSG_LGTH-1;
|
|
num_chars_read = 0;
|
|
orted_uri = (char*)malloc(buffer_length);
|
|
|
|
while (chunk == (rc = read(p[0], &orted_uri[num_chars_read], chunk))) {
|
|
/* we read an entire buffer - better get more */
|
|
num_chars_read += chunk;
|
|
buffer_length += ORTE_URI_MSG_LGTH;
|
|
orted_uri = realloc((void*)orted_uri, buffer_length);
|
|
}
|
|
num_chars_read += rc;
|
|
|
|
if (num_chars_read <= 0) {
|
|
/* we didn't get anything back - this is bad */
|
|
ORTE_ERROR_LOG(ORTE_ERR_HNP_COULD_NOT_START);
|
|
free(orted_uri);
|
|
return ORTE_ERR_HNP_COULD_NOT_START;
|
|
}
|
|
|
|
/* parse the sysinfo from the returned info - must
|
|
* start from the end of the string as the uri itself
|
|
* can contain brackets */
|
|
if (NULL == (param = strrchr(orted_uri, '['))) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_COMM_FAILURE);
|
|
free(orted_uri);
|
|
return ORTE_ERR_COMM_FAILURE;
|
|
}
|
|
*param = '\0'; /* terminate the uri string */
|
|
++param; /* point to the start of the sysinfo */
|
|
|
|
/* find the end of the sysinfo */
|
|
if (NULL == (cptr = strchr(param, ']'))) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_COMM_FAILURE);
|
|
free(orted_uri);
|
|
return ORTE_ERR_COMM_FAILURE;
|
|
}
|
|
*cptr = '\0'; /* terminate the sysinfo string */
|
|
++cptr; /* point to the start of the pmix uri */
|
|
|
|
/* convert the sysinfo string */
|
|
if (ORTE_SUCCESS != (rc = orte_util_convert_string_to_sysinfo(&orte_local_cpu_type,
|
|
&orte_local_cpu_model, param))) {
|
|
ORTE_ERROR_LOG(rc);
|
|
free(orted_uri);
|
|
return rc;
|
|
}
|
|
|
|
/* save the daemon uri - we will process it later */
|
|
orte_process_info.my_daemon_uri = strdup(orted_uri);
|
|
/* Set the contact info in the RML - this won't actually establish
|
|
* the connection, but just tells the RML how to reach the daemon
|
|
* if/when we attempt to send to it
|
|
*/
|
|
orte_rml.set_contact_info(orte_process_info.my_daemon_uri);
|
|
if (ORTE_SUCCESS != (rc = orte_rml_base_parse_uris(orte_process_info.my_daemon_uri,
|
|
ORTE_PROC_MY_DAEMON, NULL))) {
|
|
ORTE_ERROR_LOG(rc);
|
|
free(orted_uri);
|
|
return rc;
|
|
}
|
|
|
|
/* likewise, since this is also the HNP, set that uri too */
|
|
orte_process_info.my_hnp_uri = orted_uri;
|
|
orte_rml.set_contact_info(orte_process_info.my_hnp_uri);
|
|
if (ORTE_SUCCESS != (rc = orte_rml_base_parse_uris(orte_process_info.my_hnp_uri,
|
|
ORTE_PROC_MY_HNP, NULL))) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
|
|
/* push the pmix_uri into our environment - need to protect it */
|
|
(void)asprintf(&pmix_uri, "PMIX_SERVER_URI=%s", cptr);
|
|
putenv(pmix_uri);
|
|
/* now re-init the pmix framework so we can connect when required */
|
|
if (OPAL_SUCCESS != (rc = opal_pmix.init())) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
/* now call fence to push our own modex data into the
|
|
* newly-launched HNP in case someone else needs it */
|
|
if (OPAL_SUCCESS != (rc = opal_pmix.fence(NULL, 0))) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
/* all done - report success */
|
|
return ORTE_SUCCESS;
|
|
}
|
|
}
|