ports/openmpi
ports/openmpi
1
1
Форкнуть 0
Код Релизы Активность
c7939aeebc
openmpi/opal/mca/pmix/pmix4x/pmix4x.h

352 строки
15 KiB
C
Исходник Обычный вид История

pmix/pmix2x: fix errors in event abstration Parts of the pmix2x component called the event_* functions directly instead of the opal_event_* wrappers. This is fine as long as we are using libevent but becomes a problem with other event libraries. Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2017-02-03 02:13:41 +03:00
/* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
/*
Update the PMIx 3.x component Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-01-25 19:34:44 +03:00
* Copyright (c) 2014-2018 Intel, Inc. All rights reserved.
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
* Copyright (c) 2014-2015 Mellanox Technologies, Inc.
* All rights reserved.
* Copyright (c) 2016 Research Organization for Information Science
* and Technology (RIST). All rights reserved.
pmix/pmix2x: fix errors in event abstration Parts of the pmix2x component called the event_* functions directly instead of the opal_event_* wrappers. This is fine as long as we are using libevent but becomes a problem with other event libraries. Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2017-02-03 02:13:41 +03:00
* Copyright (c) 2017 Los Alamos National Security, LLC. All rights
* reserved.
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
#ifndef MCA_PMIX_PMIX2X_H
#define MCA_PMIX_PMIX2X_H
#include "opal_config.h"
#ifdef HAVE_SYS_SOCKET_H
#include <sys/socket.h>
#endif
#ifdef HAVE_SYS_UN_H
#include <sys/un.h>
#endif
#include "opal/class/opal_list.h"
#include "opal/mca/mca.h"
#include "opal/mca/event/event.h"
#include "opal/util/proc.h"
Update to latest PMIx master - equivalent to 2.0rc2. Update the thread support in the opal/pmix framework to protect the framework-level structures. This now passes the loop test, and so we believe it resolves the random hangs in finalize. Changes in PMIx master that are included here: * Fixed a bug in the PMIx_Get logic * Fixed self-notification procedure * Made pmix_output functions thread safe * Fixed a number of thread safety issues * Updated configury to use 'uname -n' when hostname is unavailable Work on cleaning up the event handler thread safety problem Rarely used functions, but protect them anyway Fix the last part of the intercomm problem Ensure we don't cover any PMIx calls with the framework-level lock. Protect against NULL argv comm_spawn Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-06-13 02:54:35 +03:00
#include "opal/mca/pmix/base/base.h"
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
#include "pmix_server.h"
Update to latest PMIx toolext branch Fix indentations Update the ext20 component to match latest PMIx master. Cleanup name conflicts and uninit vars
2016-08-11 07:03:00 +03:00
#include "pmix_common.h"
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
BEGIN_C_DECLS
typedef struct {
Update to PMIx v3.0 PR for cleanup registration If available, have apps use registration capability to cleanup their session directories. Setup capability for vader to register its shared memory file location - let someone familiar with that code do so. Final cleanup to track uid/gid, update the opal/pmix API to pass flags for ignore and leave top directory alone Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-12-12 00:50:24 +03:00
opal_pmix_base_component_t super;
pmix_proc_t myproc;
opal_list_t jobids;
bool native_launch;
size_t evindex;
opal_list_t events;
int cache_size;
opal_list_t cache;
opal_list_t dmdx;
bool silence_warning;
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
} mca_pmix_pmix4x_component_t;
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_DECLSPEC extern mca_pmix_pmix4x_component_t mca_pmix_pmix4x_component;
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_DECLSPEC extern const opal_pmix_base_module_t opal_pmix_pmix4x_module;
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
/**** INTERNAL OBJECTS ****/
typedef struct {
opal_list_item_t super;
opal_jobid_t jobid;
char nspace[PMIX_MAX_NSLEN + 1];
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
} opal_pmix4x_jobid_trkr_t;
OBJ_CLASS_DECLARATION(opal_pmix4x_jobid_trkr_t);
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
typedef struct {
opal_list_item_t super;
Update to latest PMIx master - equivalent to 2.0rc2. Update the thread support in the opal/pmix framework to protect the framework-level structures. This now passes the loop test, and so we believe it resolves the random hangs in finalize. Changes in PMIx master that are included here: * Fixed a bug in the PMIx_Get logic * Fixed self-notification procedure * Made pmix_output functions thread safe * Fixed a number of thread safety issues * Updated configury to use 'uname -n' when hostname is unavailable Work on cleaning up the event handler thread safety problem Rarely used functions, but protect them anyway Fix the last part of the intercomm problem Ensure we don't cover any PMIx calls with the framework-level lock. Protect against NULL argv comm_spawn Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-06-13 02:54:35 +03:00
opal_pmix_lock_t lock;
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
size_t index;
opal_pmix_notification_fn_t handler;
Remove stale global variables Revamp the event notification integration to rely on the PMIx event chaining and remove the duplicate chaining in OPAL. This ensures we get system-level events that target non-default handlers. Restore the hostname entries for MPI-level error messages, but provide an MCA param (orte_hostname_cutoff) to remove them for large clusters where the memory footprint is problematic. Set the default at 1000 nodes in the job (not the allocation). Begin first cut at memory profiler Some minor cleanups of memprobe Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2016-12-31 18:37:24 +03:00
void *cbdata;
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
} opal_pmix4x_event_t;
OBJ_CLASS_DECLARATION(opal_pmix4x_event_t);
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
Implement a background fence that collects all data during modex operation The direct modex operation is slow, especially at scale for even modestly-connected applications. Likewise, blocking in MPI_Init while we wait for a full modex to complete takes too long. However, as George pointed out, there is a middle ground here. We could kickoff the modex operation in the background, and then trap any modex_recv's until the modex completes and the data is delivered. For most non-benchmark apps, this may prove to be the best of the available options as they are likely to perform other (non-communicating) setup operations after MPI_Init, and so there is a reasonable chance that the modex will actually be done before the first modex_recv gets called. Once we get instant-on-enabled hardware, this won't be necessary. Clearly, zero time will always out-perform the time spent doing a modex. However, this provides a decent compromise in the interim. This PR changes the default settings of a few relevant params to make "background modex" the default behavior: * pmix_base_async_modex -> defaults to true * pmix_base_collect_data -> continues to default to true (no change) * async_mpi_init - defaults to true. Note that the prior code attempted to base the default setting of this value on the setting of pmix_base_async_modex. Unfortunately, the pmix value isn't set prior to setting async_mpi_init, and so that attempt failed to accomplish anything. The logic in MPI_Init is: * if async_modex AND collect_data are set, AND we have a non-blocking fence available, then we execute the background modex operation * if async_modex is set, but collect_data is false, then we simply skip the modex entirely - no fence is performed * if async_modex is not set, then we block until the fence completes (regardless of collecting data or not) * if we do NOT have a non-blocking fence (e.g., we are not using PMIx), then we always perform the full blocking modex operation. * if we do perform the background modex, and the user requested the barrier be performed at the end of MPI_Init, then we check to see if the modex has completed when we reach that point. If it has, then we execute the barrier. However, if the modex has NOT completed, then we block until the modex does complete and skip the extra barrier. So we never perform two barriers in that case. HTH Ralph Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-04-21 20:29:23 +03:00
typedef struct {
opal_list_item_t super;
char *nspace;
pmix_modex_cbfunc_t cbfunc;
void *cbdata;
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
} opal_pmix4x_dmx_trkr_t;
OBJ_CLASS_DECLARATION(opal_pmix4x_dmx_trkr_t);
Implement a background fence that collects all data during modex operation The direct modex operation is slow, especially at scale for even modestly-connected applications. Likewise, blocking in MPI_Init while we wait for a full modex to complete takes too long. However, as George pointed out, there is a middle ground here. We could kickoff the modex operation in the background, and then trap any modex_recv's until the modex completes and the data is delivered. For most non-benchmark apps, this may prove to be the best of the available options as they are likely to perform other (non-communicating) setup operations after MPI_Init, and so there is a reasonable chance that the modex will actually be done before the first modex_recv gets called. Once we get instant-on-enabled hardware, this won't be necessary. Clearly, zero time will always out-perform the time spent doing a modex. However, this provides a decent compromise in the interim. This PR changes the default settings of a few relevant params to make "background modex" the default behavior: * pmix_base_async_modex -> defaults to true * pmix_base_collect_data -> continues to default to true (no change) * async_mpi_init - defaults to true. Note that the prior code attempted to base the default setting of this value on the setting of pmix_base_async_modex. Unfortunately, the pmix value isn't set prior to setting async_mpi_init, and so that attempt failed to accomplish anything. The logic in MPI_Init is: * if async_modex AND collect_data are set, AND we have a non-blocking fence available, then we execute the background modex operation * if async_modex is set, but collect_data is false, then we simply skip the modex entirely - no fence is performed * if async_modex is not set, then we block until the fence completes (regardless of collecting data or not) * if we do NOT have a non-blocking fence (e.g., we are not using PMIx), then we always perform the full blocking modex operation. * if we do perform the background modex, and the user requested the barrier be performed at the end of MPI_Init, then we check to see if the modex has completed when we reach that point. If it has, then we execute the barrier. However, if the modex has NOT completed, then we block until the modex does complete and skip the extra barrier. So we never perform two barriers in that case. HTH Ralph Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-04-21 20:29:23 +03:00
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
typedef struct {
opal_object_t super;
Update to latest PMIx master - equivalent to 2.0rc2. Update the thread support in the opal/pmix framework to protect the framework-level structures. This now passes the loop test, and so we believe it resolves the random hangs in finalize. Changes in PMIx master that are included here: * Fixed a bug in the PMIx_Get logic * Fixed self-notification procedure * Made pmix_output functions thread safe * Fixed a number of thread safety issues * Updated configury to use 'uname -n' when hostname is unavailable Work on cleaning up the event handler thread safety problem Rarely used functions, but protect them anyway Fix the last part of the intercomm problem Ensure we don't cover any PMIx calls with the framework-level lock. Protect against NULL argv comm_spawn Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-06-13 02:54:35 +03:00
opal_event_t ev;
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
pmix_status_t status;
Update to latest PMIx master - equivalent to 2.0rc2. Update the thread support in the opal/pmix framework to protect the framework-level structures. This now passes the loop test, and so we believe it resolves the random hangs in finalize. Changes in PMIx master that are included here: * Fixed a bug in the PMIx_Get logic * Fixed self-notification procedure * Made pmix_output functions thread safe * Fixed a number of thread safety issues * Updated configury to use 'uname -n' when hostname is unavailable Work on cleaning up the event handler thread safety problem Rarely used functions, but protect them anyway Fix the last part of the intercomm problem Ensure we don't cover any PMIx calls with the framework-level lock. Protect against NULL argv comm_spawn Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-06-13 02:54:35 +03:00
char *nspace;
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
pmix_proc_t p;
pmix_proc_t *procs;
size_t nprocs;
Update to latest PMIx master - equivalent to 2.0rc2. Update the thread support in the opal/pmix framework to protect the framework-level structures. This now passes the loop test, and so we believe it resolves the random hangs in finalize. Changes in PMIx master that are included here: * Fixed a bug in the PMIx_Get logic * Fixed self-notification procedure * Made pmix_output functions thread safe * Fixed a number of thread safety issues * Updated configury to use 'uname -n' when hostname is unavailable Work on cleaning up the event handler thread safety problem Rarely used functions, but protect them anyway Fix the last part of the intercomm problem Ensure we don't cover any PMIx calls with the framework-level lock. Protect against NULL argv comm_spawn Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-06-13 02:54:35 +03:00
pmix_pdata_t *pdata;
size_t npdata;
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
pmix_proc_t *error_procs;
size_t nerror_procs;
pmix_info_t *info;
size_t ninfo;
pmix_app_t *apps;
size_t sz;
Update to latest PMIx master - equivalent to 2.0rc2. Update the thread support in the opal/pmix framework to protect the framework-level structures. This now passes the loop test, and so we believe it resolves the random hangs in finalize. Changes in PMIx master that are included here: * Fixed a bug in the PMIx_Get logic * Fixed self-notification procedure * Made pmix_output functions thread safe * Fixed a number of thread safety issues * Updated configury to use 'uname -n' when hostname is unavailable Work on cleaning up the event handler thread safety problem Rarely used functions, but protect them anyway Fix the last part of the intercomm problem Ensure we don't cover any PMIx calls with the framework-level lock. Protect against NULL argv comm_spawn Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-06-13 02:54:35 +03:00
opal_pmix_lock_t lock;
Remove stale global variables Revamp the event notification integration to rely on the PMIx event chaining and remove the duplicate chaining in OPAL. This ensures we get system-level events that target non-default handlers. Restore the hostname entries for MPI-level error messages, but provide an MCA param (orte_hostname_cutoff) to remove them for large clusters where the memory footprint is problematic. Set the default at 1000 nodes in the job (not the allocation). Begin first cut at memory profiler Some minor cleanups of memprobe Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2016-12-31 18:37:24 +03:00
opal_list_t *codes;
pmix_status_t *pcodes;
size_t ncodes;
Complete the memprobe support. This provides a new scaling tool called "mpi_memprobe" that samples the memory footprint of the local daemon and the client procs, and then reports the results. The output contains the footprint of the daemon on each node, plus the average footprint of the client procs on that node. Samples are taken after MPI_Init, and then again after MPI_Barrier. This allows the user to see memory consumption caused by add_procs, as well as any modex contribution from forming connections if pmix_base_async_modex is given. Using the probe simply involves executing it via mpirun, with however many copies you want per node. Example: $ mpirun -npernode 2 ./mpi_memprobe Sampling memory usage after MPI_Init Data for node rhc001 Daemon: 12.483398 Client: 6.514648 Data for node rhc002 Daemon: 11.865234 Client: 4.643555 Sampling memory usage after MPI_Barrier Data for node rhc001 Daemon: 12.520508 Client: 6.576660 Data for node rhc002 Daemon: 11.879883 Client: 4.703125 Note that the client value on node rhc001 is larger - this is where rank=0 is housed, and apparently it gets a larger footprint for some reason. Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-01-05 20:46:05 +03:00
pmix_query_t *queries;
size_t nqueries;
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
opal_pmix4x_event_t *event;
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_pmix_op_cbfunc_t opcbfunc;
opal_pmix_modex_cbfunc_t mdxcbfunc;
opal_pmix_value_cbfunc_t valcbfunc;
opal_pmix_lookup_cbfunc_t lkcbfunc;
opal_pmix_spawn_cbfunc_t spcbfunc;
Remove stale global variables Revamp the event notification integration to rely on the PMIx event chaining and remove the duplicate chaining in OPAL. This ensures we get system-level events that target non-default handlers. Restore the hostname entries for MPI-level error messages, but provide an MCA param (orte_hostname_cutoff) to remove them for large clusters where the memory footprint is problematic. Set the default at 1000 nodes in the job (not the allocation). Begin first cut at memory profiler Some minor cleanups of memprobe Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2016-12-31 18:37:24 +03:00
opal_pmix_evhandler_reg_cbfunc_t evregcbfunc;
Complete the memprobe support. This provides a new scaling tool called "mpi_memprobe" that samples the memory footprint of the local daemon and the client procs, and then reports the results. The output contains the footprint of the daemon on each node, plus the average footprint of the client procs on that node. Samples are taken after MPI_Init, and then again after MPI_Barrier. This allows the user to see memory consumption caused by add_procs, as well as any modex contribution from forming connections if pmix_base_async_modex is given. Using the probe simply involves executing it via mpirun, with however many copies you want per node. Example: $ mpirun -npernode 2 ./mpi_memprobe Sampling memory usage after MPI_Init Data for node rhc001 Daemon: 12.483398 Client: 6.514648 Data for node rhc002 Daemon: 11.865234 Client: 4.643555 Sampling memory usage after MPI_Barrier Data for node rhc001 Daemon: 12.520508 Client: 6.576660 Data for node rhc002 Daemon: 11.879883 Client: 4.703125 Note that the client value on node rhc001 is larger - this is where rank=0 is housed, and apparently it gets a larger footprint for some reason. Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-01-05 20:46:05 +03:00
opal_pmix_info_cbfunc_t qcbfunc;
Update ORTE to support PMIx v3 This is a point-in-time update that includes support for several new PMIx features, mostly focused on debuggers and "instant on": * initial prototype support for PMIx-based debuggers. For the moment, this is restricted to using the DVM. Supports direct launch of apps under debugger control, and indirect launch using prun as the intermediate launcher. Includes ability for debuggers to control the environment of both the launcher and the spawned app procs. Work continues on completing support for indirect launch * IO forwarding for tools. Output of apps launched under tool control is directed to the tool and output there - includes support for XML formatting and output to files. Stdin can be forwarded from the tool to apps, but this hasn't been implemented in ORTE yet. * Fabric integration for "instant on". Enable collection of network "blobs" to be delivered to network libraries on compute nodes prior to local proc spawn. Infrastructure is in place - implementation will come later. * Harvesting and forwarding of envars. Enable network plugins to harvest envars and include them in the launch msg for setting the environment prior to local proc spawn. Currently, only OmniPath is supported. PMIx MCA params control which envars are included, and also allows envars to be excluded. Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-02-23 20:57:19 +03:00
opal_pmix_setup_application_cbfunc_t setupcbfunc;
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
void *cbdata;
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
} pmix4x_opcaddy_t;
OBJ_CLASS_DECLARATION(pmix4x_opcaddy_t);
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
typedef struct {
opal_object_t super;
opal_list_t procs;
opal_list_t info;
opal_list_t apps;
pmix_op_cbfunc_t opcbfunc;
pmix_dmodex_response_fn_t dmdxfunc;
pmix_modex_cbfunc_t mdxcbfunc;
pmix_lookup_cbfunc_t lkupcbfunc;
pmix_spawn_cbfunc_t spwncbfunc;
Add support for PMIx tool connections and queries. Initially only support a request to list all known namespaces (jobids) from ORTE, but other folks will extend that support to include additional information Update to match PMIx RFC Fix configury to point to correct libevent and hwloc locations
2016-06-18 01:15:13 +03:00
pmix_info_cbfunc_t infocbfunc;
pmix_tool_connection_cbfunc_t toolcbfunc;
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
void *cbdata;
opal_pmix_release_cbfunc_t odmdxfunc;
void *ocbdata;
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
} pmix4x_opalcaddy_t;
OBJ_CLASS_DECLARATION(pmix4x_opalcaddy_t);
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
typedef struct {
opal_object_t super;
opal_event_t ev;
Update to latest PMIx master - equivalent to 2.0rc2. Update the thread support in the opal/pmix framework to protect the framework-level structures. This now passes the loop test, and so we believe it resolves the random hangs in finalize. Changes in PMIx master that are included here: * Fixed a bug in the PMIx_Get logic * Fixed self-notification procedure * Made pmix_output functions thread safe * Fixed a number of thread safety issues * Updated configury to use 'uname -n' when hostname is unavailable Work on cleaning up the event handler thread safety problem Rarely used functions, but protect them anyway Fix the last part of the intercomm problem Ensure we don't cover any PMIx calls with the framework-level lock. Protect against NULL argv comm_spawn Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-06-13 02:54:35 +03:00
opal_pmix_lock_t lock;
const char *msg;
char *strings;
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
size_t id;
int status;
opal_process_name_t pname;
opal_jobid_t jobid;
const opal_process_name_t *source;
opal_pmix_data_range_t range;
bool nondefault;
size_t handler;
Update to latest PMIx master - equivalent to 2.0rc2. Update the thread support in the opal/pmix framework to protect the framework-level structures. This now passes the loop test, and so we believe it resolves the random hangs in finalize. Changes in PMIx master that are included here: * Fixed a bug in the PMIx_Get logic * Fixed self-notification procedure * Made pmix_output functions thread safe * Fixed a number of thread safety issues * Updated configury to use 'uname -n' when hostname is unavailable Work on cleaning up the event handler thread safety problem Rarely used functions, but protect them anyway Fix the last part of the intercomm problem Ensure we don't cover any PMIx calls with the framework-level lock. Protect against NULL argv comm_spawn Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-06-13 02:54:35 +03:00
opal_value_t *val;
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_list_t *event_codes;
opal_list_t *info;
Remove stale global variables Revamp the event notification integration to rely on the PMIx event chaining and remove the duplicate chaining in OPAL. This ensures we get system-level events that target non-default handlers. Restore the hostname entries for MPI-level error messages, but provide an MCA param (orte_hostname_cutoff) to remove them for large clusters where the memory footprint is problematic. Set the default at 1000 nodes in the job (not the allocation). Begin first cut at memory profiler Some minor cleanups of memprobe Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2016-12-31 18:37:24 +03:00
opal_list_t results;
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_pmix_notification_fn_t evhandler;
opal_pmix_evhandler_reg_cbfunc_t cbfunc;
opal_pmix_op_cbfunc_t opcbfunc;
Remove stale global variables Revamp the event notification integration to rely on the PMIx event chaining and remove the duplicate chaining in OPAL. This ensures we get system-level events that target non-default handlers. Restore the hostname entries for MPI-level error messages, but provide an MCA param (orte_hostname_cutoff) to remove them for large clusters where the memory footprint is problematic. Set the default at 1000 nodes in the job (not the allocation). Begin first cut at memory profiler Some minor cleanups of memprobe Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2016-12-31 18:37:24 +03:00
pmix_event_notification_cbfunc_fn_t pmixcbfunc;
Update to latest PMIx master - equivalent to 2.0rc2. Update the thread support in the opal/pmix framework to protect the framework-level structures. This now passes the loop test, and so we believe it resolves the random hangs in finalize. Changes in PMIx master that are included here: * Fixed a bug in the PMIx_Get logic * Fixed self-notification procedure * Made pmix_output functions thread safe * Fixed a number of thread safety issues * Updated configury to use 'uname -n' when hostname is unavailable Work on cleaning up the event handler thread safety problem Rarely used functions, but protect them anyway Fix the last part of the intercomm problem Ensure we don't cover any PMIx calls with the framework-level lock. Protect against NULL argv comm_spawn Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-06-13 02:54:35 +03:00
opal_pmix_value_cbfunc_t valcbfunc;
opal_pmix_lookup_cbfunc_t lkcbfunc;
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
void *cbdata;
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
} pmix4x_threadshift_t;
OBJ_CLASS_DECLARATION(pmix4x_threadshift_t);
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
#define OPAL_PMIX_OP_THREADSHIFT(e, fn, cb, cd) \
do { \
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
pmix4x_threadshift_t *_cd; \
_cd = OBJ_NEW(pmix4x_threadshift_t); \
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
_cd->handler = (e); \
_cd->opcbfunc = (cb); \
_cd->cbdata = (cd); \
pmix/pmix2x: fix errors in event abstration Parts of the pmix2x component called the event_* functions directly instead of the opal_event_* wrappers. This is fine as long as we are using libevent but becomes a problem with other event libraries. Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2017-02-03 02:13:41 +03:00
opal_event_assign(&((_cd)->ev), opal_pmix_base.evbase, \
-1, EV_WRITE, (fn), (_cd)); \
Update OPAL and ORTE for thread safety (I swear, if I look this over one more time, I'll puke) Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-06-06 01:22:28 +03:00
OPAL_POST_OBJECT(_cd); \
pmix/pmix2x: fix errors in event abstration Parts of the pmix2x component called the event_* functions directly instead of the opal_event_* wrappers. This is fine as long as we are using libevent but becomes a problem with other event libraries. Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2017-02-03 02:13:41 +03:00
opal_event_active(&((_cd)->ev), EV_WRITE, 1); \
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
} while(0)
#define OPAL_PMIX_THREADSHIFT(e, i, eh, fn, cb, cd) \
do { \
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
pmix4x_threadshift_t *_cd; \
_cd = OBJ_NEW(pmix4x_threadshift_t); \
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
_cd->event_codes = (e); \
_cd->info = (i); \
_cd->evhandler = (eh); \
_cd->cbfunc = (cb); \
_cd->cbdata = (cd); \
pmix/pmix2x: fix errors in event abstration Parts of the pmix2x component called the event_* functions directly instead of the opal_event_* wrappers. This is fine as long as we are using libevent but becomes a problem with other event libraries. Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2017-02-03 02:13:41 +03:00
opal_event_assign(&((_cd)->ev), opal_pmix_base.evbase, \
-1, EV_WRITE, (fn), (_cd)); \
Update OPAL and ORTE for thread safety (I swear, if I look this over one more time, I'll puke) Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-06-06 01:22:28 +03:00
OPAL_POST_OBJECT(_cd); \
pmix/pmix2x: fix errors in event abstration Parts of the pmix2x component called the event_* functions directly instead of the opal_event_* wrappers. This is fine as long as we are using libevent but becomes a problem with other event libraries. Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2017-02-03 02:13:41 +03:00
opal_event_active(&((_cd)->ev), EV_WRITE, 1); \
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
} while(0)
#define OPAL_PMIX_NOTIFY_THREADSHIFT(s, sr, r, i, fn, cb, cd) \
do { \
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
pmix4x_threadshift_t *_cd; \
_cd = OBJ_NEW(pmix4x_threadshift_t); \
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
_cd->status = (s); \
_cd->source = (sr); \
_cd->range = (r); \
_cd->info = (i); \
_cd->opcbfunc = (cb); \
_cd->cbdata = (cd); \
pmix/pmix2x: fix errors in event abstration Parts of the pmix2x component called the event_* functions directly instead of the opal_event_* wrappers. This is fine as long as we are using libevent but becomes a problem with other event libraries. Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2017-02-03 02:13:41 +03:00
opal_event_assign(&((_cd)->ev), opal_pmix_base.evbase, \
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
-1, EV_WRITE, (fn), (_cd)); \
Update OPAL and ORTE for thread safety (I swear, if I look this over one more time, I'll puke) Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-06-06 01:22:28 +03:00
OPAL_POST_OBJECT(_cd); \
pmix/pmix2x: fix errors in event abstration Parts of the pmix2x component called the event_* functions directly instead of the opal_event_* wrappers. This is fine as long as we are using libevent but becomes a problem with other event libraries. Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2017-02-03 02:13:41 +03:00
opal_event_active(&((_cd)->ev), EV_WRITE, 1); \
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
} while(0)
Update to latest PMIx master - equivalent to 2.0rc2. Update the thread support in the opal/pmix framework to protect the framework-level structures. This now passes the loop test, and so we believe it resolves the random hangs in finalize. Changes in PMIx master that are included here: * Fixed a bug in the PMIx_Get logic * Fixed self-notification procedure * Made pmix_output functions thread safe * Fixed a number of thread safety issues * Updated configury to use 'uname -n' when hostname is unavailable Work on cleaning up the event handler thread safety problem Rarely used functions, but protect them anyway Fix the last part of the intercomm problem Ensure we don't cover any PMIx calls with the framework-level lock. Protect against NULL argv comm_spawn Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-06-13 02:54:35 +03:00
#define OPAL_PMIX2X_THREADSHIFT(p, cb) \
do { \
opal_event_assign(&((p)->ev), opal_pmix_base.evbase, \
-1, EV_WRITE, (cb), (p)); \
OPAL_POST_OBJECT(p); \
opal_event_active(&((p)->ev), EV_WRITE, 1); \
} while(0)
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
/**** CLIENT FUNCTIONS ****/
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_client_init(opal_list_t *ilist);
OPAL_MODULE_DECLSPEC int pmix4x_client_finalize(void);
OPAL_MODULE_DECLSPEC int pmix4x_initialized(void);
OPAL_MODULE_DECLSPEC int pmix4x_abort(int flag, const char *msg,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_list_t *procs);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_commit(void);
OPAL_MODULE_DECLSPEC int pmix4x_fence(opal_list_t *procs, int collect_data);
OPAL_MODULE_DECLSPEC int pmix4x_fencenb(opal_list_t *procs, int collect_data,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_pmix_op_cbfunc_t cbfunc, void *cbdata);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_put(opal_pmix_scope_t scope,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_value_t *val);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_get(const opal_process_name_t *proc, const char *key,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_list_t *info, opal_value_t **val);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_getnb(const opal_process_name_t *proc, const char *key,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_list_t *info,
opal_pmix_value_cbfunc_t cbfunc, void *cbdata);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_publish(opal_list_t *info);
OPAL_MODULE_DECLSPEC int pmix4x_publishnb(opal_list_t *info,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_pmix_op_cbfunc_t cbfunc, void *cbdata);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_lookup(opal_list_t *data, opal_list_t *info);
OPAL_MODULE_DECLSPEC int pmix4x_lookupnb(char **keys, opal_list_t *info,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_pmix_lookup_cbfunc_t cbfunc, void *cbdata);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_unpublish(char **keys, opal_list_t *info);
OPAL_MODULE_DECLSPEC int pmix4x_unpublishnb(char **keys, opal_list_t *info,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_pmix_op_cbfunc_t cbfunc, void *cbdata);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_spawn(opal_list_t *job_info, opal_list_t *apps, opal_jobid_t *jobid);
OPAL_MODULE_DECLSPEC int pmix4x_spawnnb(opal_list_t *job_info, opal_list_t *apps,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_pmix_spawn_cbfunc_t cbfunc, void *cbdata);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_connect(opal_list_t *procs);
OPAL_MODULE_DECLSPEC int pmix4x_connectnb(opal_list_t *procs,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_pmix_op_cbfunc_t cbfunc,
void *cbdata);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_disconnect(opal_list_t *procs);
OPAL_MODULE_DECLSPEC int pmix4x_disconnectnb(opal_list_t *procs,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_pmix_op_cbfunc_t cbfunc,
void *cbdata);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_resolve_peers(const char *nodename, opal_jobid_t jobid,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_list_t *procs);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_resolve_nodes(opal_jobid_t jobid, char **nodelist);
OPAL_MODULE_DECLSPEC int pmix4x_allocate(opal_pmix_alloc_directive_t directive,
Add a new launcher "prun" for starting applications against the ORTE DVM. Unlike "orterun", "prun" is a PMIx-only program that discovers the DVM connection instead of requiring that we explicitly provide it. Only build "prun" if PMIx v2.x is available. This gets the DVM working again, but still is showing problems for multiple executions. I'll detail those in a separate issue. Thus, the DVM should still be considered "broken". Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-09-13 07:40:41 +03:00
opal_list_t *info,
opal_pmix_info_cbfunc_t cbfunc, void *cbdata);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_job_control(opal_list_t *targets,
Add a new launcher "prun" for starting applications against the ORTE DVM. Unlike "orterun", "prun" is a PMIx-only program that discovers the DVM connection instead of requiring that we explicitly provide it. Only build "prun" if PMIx v2.x is available. This gets the DVM working again, but still is showing problems for multiple executions. I'll detail those in a separate issue. Thus, the DVM should still be considered "broken". Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-09-13 07:40:41 +03:00
opal_list_t *directives,
opal_pmix_info_cbfunc_t cbfunc, void *cbdata);
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
Update the tools support so it allows tools to access PMIx Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-07-25 21:19:29 +03:00
/**** TOOL FUNCTIONS ****/
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_tool_init(opal_list_t *info);
OPAL_MODULE_DECLSPEC int pmix4x_tool_fini(void);
Update the tools support so it allows tools to access PMIx Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-07-25 21:19:29 +03:00
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
/**** COMMON FUNCTIONS ****/
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_store_local(const opal_process_name_t *proc,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_value_t *val);
/**** SERVER SOUTHBOUND FUNCTIONS ****/
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_server_init(opal_pmix_server_module_t *module,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_list_t *info);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_server_finalize(void);
OPAL_MODULE_DECLSPEC int pmix4x_server_gen_regex(const char *input, char **regex);
OPAL_MODULE_DECLSPEC int pmix4x_server_gen_ppn(const char *input, char **ppn);
OPAL_MODULE_DECLSPEC int pmix4x_server_register_nspace(opal_jobid_t jobid,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
int nlocalprocs,
opal_list_t *info,
opal_pmix_op_cbfunc_t cbfunc,
void *cbdata);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC void pmix4x_server_deregister_nspace(opal_jobid_t jobid,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_pmix_op_cbfunc_t cbfunc,
void *cbdata);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_server_register_client(const opal_process_name_t *proc,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
uid_t uid, gid_t gid,
void *server_object,
opal_pmix_op_cbfunc_t cbfunc,
void *cbdata);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC void pmix4x_server_deregister_client(const opal_process_name_t *proc,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_pmix_op_cbfunc_t cbfunc,
void *cbdata);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_server_setup_fork(const opal_process_name_t *proc, char ***env);
OPAL_MODULE_DECLSPEC int pmix4x_server_dmodex(const opal_process_name_t *proc,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
opal_pmix_modex_cbfunc_t cbfunc, void *cbdata);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_server_notify_event(int status,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
const opal_process_name_t *source,
opal_list_t *info,
opal_pmix_op_cbfunc_t cbfunc, void *cbdata);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_server_iof_push(const opal_process_name_t *source,
Update the PMIx 3.x component Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-01-25 19:34:44 +03:00
opal_pmix_iof_channel_t channel,
unsigned char *data, size_t nbytes);
Update ORTE to support PMIx v3 This is a point-in-time update that includes support for several new PMIx features, mostly focused on debuggers and "instant on": * initial prototype support for PMIx-based debuggers. For the moment, this is restricted to using the DVM. Supports direct launch of apps under debugger control, and indirect launch using prun as the intermediate launcher. Includes ability for debuggers to control the environment of both the launcher and the spawned app procs. Work continues on completing support for indirect launch * IO forwarding for tools. Output of apps launched under tool control is directed to the tool and output there - includes support for XML formatting and output to files. Stdin can be forwarded from the tool to apps, but this hasn't been implemented in ORTE yet. * Fabric integration for "instant on". Enable collection of network "blobs" to be delivered to network libraries on compute nodes prior to local proc spawn. Infrastructure is in place - implementation will come later. * Harvesting and forwarding of envars. Enable network plugins to harvest envars and include them in the launch msg for setting the environment prior to local proc spawn. Currently, only OmniPath is supported. PMIx MCA params control which envars are included, and also allows envars to be excluded. Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-02-23 20:57:19 +03:00
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_server_setup_application(opal_jobid_t jobid,
Update ORTE to support PMIx v3 This is a point-in-time update that includes support for several new PMIx features, mostly focused on debuggers and "instant on": * initial prototype support for PMIx-based debuggers. For the moment, this is restricted to using the DVM. Supports direct launch of apps under debugger control, and indirect launch using prun as the intermediate launcher. Includes ability for debuggers to control the environment of both the launcher and the spawned app procs. Work continues on completing support for indirect launch * IO forwarding for tools. Output of apps launched under tool control is directed to the tool and output there - includes support for XML formatting and output to files. Stdin can be forwarded from the tool to apps, but this hasn't been implemented in ORTE yet. * Fabric integration for "instant on". Enable collection of network "blobs" to be delivered to network libraries on compute nodes prior to local proc spawn. Infrastructure is in place - implementation will come later. * Harvesting and forwarding of envars. Enable network plugins to harvest envars and include them in the launch msg for setting the environment prior to local proc spawn. Currently, only OmniPath is supported. PMIx MCA params control which envars are included, and also allows envars to be excluded. Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-02-23 20:57:19 +03:00
opal_list_t *info,
opal_pmix_setup_application_cbfunc_t cbfunc, void *cbdata);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_server_setup_local_support(opal_jobid_t jobid,
Update ORTE to support PMIx v3 This is a point-in-time update that includes support for several new PMIx features, mostly focused on debuggers and "instant on": * initial prototype support for PMIx-based debuggers. For the moment, this is restricted to using the DVM. Supports direct launch of apps under debugger control, and indirect launch using prun as the intermediate launcher. Includes ability for debuggers to control the environment of both the launcher and the spawned app procs. Work continues on completing support for indirect launch * IO forwarding for tools. Output of apps launched under tool control is directed to the tool and output there - includes support for XML formatting and output to files. Stdin can be forwarded from the tool to apps, but this hasn't been implemented in ORTE yet. * Fabric integration for "instant on". Enable collection of network "blobs" to be delivered to network libraries on compute nodes prior to local proc spawn. Infrastructure is in place - implementation will come later. * Harvesting and forwarding of envars. Enable network plugins to harvest envars and include them in the launch msg for setting the environment prior to local proc spawn. Currently, only OmniPath is supported. PMIx MCA params control which envars are included, and also allows envars to be excluded. Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-02-23 20:57:19 +03:00
opal_list_t *info,
opal_pmix_op_cbfunc_t cbfunc, void *cbdata);
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
/**** COMPONENT UTILITY FUNCTIONS ****/
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int opal_pmix_pmix4x_check_evars(void);
Per discussion on the PMIx side, do a better job of detecting mismatches between location directives for OPAL and PMIx. Provide a more helpful error message and error out if we find a mismatch. If any OPAL values are set and the PMIx equivalent is not, then transfer it. Do not clear PMIX_INSTALL_PREFIX from the daemon's launch environment Fixes #3980 Closes #4007 Refs #3985 Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-08-03 04:46:38 +03:00
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC void pmix4x_event_hdlr(size_t evhdlr_registration_id,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
pmix_status_t status, const pmix_proc_t *source,
pmix_info_t info[], size_t ninfo,
pmix_info_t results[], size_t nresults,
pmix_event_notification_cbfunc_fn_t cbfunc,
void *cbdata);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC pmix_status_t pmix4x_convert_opalrc(int rc);
OPAL_MODULE_DECLSPEC int pmix4x_convert_rc(pmix_status_t rc);
Update to include extended tool support, new datatypes
2016-08-08 06:41:54 +03:00
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC opal_vpid_t pmix4x_convert_rank(pmix_rank_t rank);
OPAL_MODULE_DECLSPEC pmix_rank_t pmix4x_convert_opalrank(opal_vpid_t vpid);
Update to include extended tool support, new datatypes
2016-08-08 06:41:54 +03:00
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC opal_pmix_scope_t pmix4x_convert_scope(pmix_scope_t scope);
OPAL_MODULE_DECLSPEC pmix_scope_t pmix4x_convert_opalscope(opal_pmix_scope_t scope);
Update to include extended tool support, new datatypes
2016-08-08 06:41:54 +03:00
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC pmix_data_range_t pmix4x_convert_opalrange(opal_pmix_data_range_t range);
OPAL_MODULE_DECLSPEC opal_pmix_data_range_t pmix4x_convert_range(pmix_data_range_t range);
Update to include extended tool support, new datatypes
2016-08-08 06:41:54 +03:00
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC opal_pmix_persistence_t pmix4x_convert_persist(pmix_persistence_t scope);
OPAL_MODULE_DECLSPEC pmix_persistence_t pmix4x_convert_opalpersist(opal_pmix_persistence_t scope);
Update to include extended tool support, new datatypes
2016-08-08 06:41:54 +03:00
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC void pmix4x_value_load(pmix_value_t *v,
Add support for PMIx tool connections and queries. Initially only support a request to list all known namespaces (jobids) from ORTE, but other folks will extend that support to include additional information Update to match PMIx RFC Fix configury to point to correct libevent and hwloc locations
2016-06-18 01:15:13 +03:00
opal_value_t *kv);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_value_unload(opal_value_t *kv,
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
const pmix_value_t *v);
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC opal_pmix_alloc_directive_t pmix4x_convert_allocdir(pmix_alloc_directive_t dir);
Update to include the PMIx 2.0 APIs for monitoring and job control. Include required integration, but leave the monitors off for now. Move the sensor framework out of ORTE as it is being absorbed into PMIx Fix typo and silence warnings Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-03-15 07:44:05 +03:00
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC char* pmix4x_convert_jobid(opal_jobid_t jobid);
Update to latest PMIx master - equivalent to 2.0rc2. Update the thread support in the opal/pmix framework to protect the framework-level structures. This now passes the loop test, and so we believe it resolves the random hangs in finalize. Changes in PMIx master that are included here: * Fixed a bug in the PMIx_Get logic * Fixed self-notification procedure * Made pmix_output functions thread safe * Fixed a number of thread safety issues * Updated configury to use 'uname -n' when hostname is unavailable Work on cleaning up the event handler thread safety problem Rarely used functions, but protect them anyway Fix the last part of the intercomm problem Ensure we don't cover any PMIx calls with the framework-level lock. Protect against NULL argv comm_spawn Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2017-06-13 02:54:35 +03:00
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC int pmix4x_convert_state(pmix_proc_state_t state);
Implement support for proctable queries Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-02-28 18:52:11 +03:00
Update master to PMIx v4 Retain ext3x for PMIx 3 compatibility Get the blasted permissions correct on config files Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-09-13 05:20:24 +03:00
OPAL_MODULE_DECLSPEC pmix_proc_state_t pmix4x_convert_opalstate(int state);
Implement support for proctable queries Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2018-02-28 18:52:11 +03:00
Enable the PMIx event notification capability and use that for all error notifications, including debugger release. This capability requires use of PMIx 2.0 or above as the features are not available with earlier PMIx releases. When OMPI master is built against an earlier external version, it will fallback to the prior behavior - i.e., debugger will be released via RML and all notifications will go strictly to the default error handler. Add PMIx 2.0 Remove PMIx 1.1.4 Cleanup copying of component Add missing file Touchup a typo in the Makefile.am Update the pmix ext114 component Minor cleanups and resync to master Update to latest PMIx 2.x Update to the PMIx event notification branch latest changes
2016-06-02 02:34:03 +03:00
END_C_DECLS
#endif /* MCA_PMIX_EXTERNAL_H */
Копировать постоянную ссылку