1
1
openmpi/orte/mca/ess/pmi/ess_pmi_component.c

116 строки
3.4 KiB
C
Исходник Обычный вид История

/* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
/*
* Copyright (c) 2011 Cisco Systems, Inc. All rights reserved.
* Copyright (c) 2011-2015 Los Alamos National Security, LLC. All
* rights reserved.
Per the PMIx RFC: WHAT: Merge the PMIx branch into the devel repo, creating a new OPAL “lmix” framework to abstract PMI support for all RTEs. Replace the ORTE daemon-level collectives with a new PMIx server and update the ORTE grpcomm framework to support server-to-server collectives WHY: We’ve had problems dealing with variations in PMI implementations, and need to extend the existing PMI definitions to meet exascale requirements. WHEN: Mon, Aug 25 WHERE: https://github.com/rhc54/ompi-svn-mirror.git Several community members have been working on a refactoring of the current PMI support within OMPI. Although the APIs are common, Slurm and Cray implement a different range of capabilities, and package them differently. For example, Cray provides an integrated PMI-1/2 library, while Slurm separates the two and requires the user to specify the one to be used at runtime. In addition, several bugs in the Slurm implementations have caused problems requiring extra coding. All this has led to a slew of #if’s in the PMI code and bugs when the corner-case logic for one implementation accidentally traps the other. Extending this support to other implementations would have increased this complexity to an unacceptable level. Accordingly, we have: * created a new OPAL “pmix” framework to abstract the PMI support, with separate components for Cray, Slurm PMI-1, and Slurm PMI-2 implementations. * Replaced the current ORTE grpcomm daemon-based collective operation with an integrated PMIx server, and updated the grpcomm APIs to provide more flexible, multi-algorithm support for collective operations. At this time, only the xcast and allgather operations are supported. * Replaced the current global collective id with a signature based on the names of the participating procs. The allows an unlimited number of collectives to be executed by any group of processes, subject to the requirement that only one collective can be active at a time for a unique combination of procs. Note that a proc can be involved in any number of simultaneous collectives - it is the specific combination of procs that is subject to the constraint * removed the prior OMPI/OPAL modex code * added new macros for executing modex send/recv to simplify use of the new APIs. The send macros allow the caller to specify whether or not the BTL supports async modex operations - if so, then the non-blocking “fence” operation is used, if the active PMIx component supports it. Otherwise, the default is a full blocking modex exchange as we currently perform. * retained the current flag that directs us to use a blocking fence operation, but only to retrieve data upon demand This commit was SVN r32570.
2014-08-21 18:56:47 +00:00
* Copyright (c) 2014 Intel, Inc. All rights reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*
* These symbols are in a file by themselves to provide nice linker
* semantics. Since linkers generally pull in symbols by object
* files, keeping these symbols as the only symbols in this file
* prevents utility programs such as "ompi_info" from having to import
* entire components just to query their version and parameters.
*/
#include "orte_config.h"
#include "orte/constants.h"
#include "opal/runtime/opal_params.h"
Per the PMIx RFC: WHAT: Merge the PMIx branch into the devel repo, creating a new OPAL “lmix” framework to abstract PMI support for all RTEs. Replace the ORTE daemon-level collectives with a new PMIx server and update the ORTE grpcomm framework to support server-to-server collectives WHY: We’ve had problems dealing with variations in PMI implementations, and need to extend the existing PMI definitions to meet exascale requirements. WHEN: Mon, Aug 25 WHERE: https://github.com/rhc54/ompi-svn-mirror.git Several community members have been working on a refactoring of the current PMI support within OMPI. Although the APIs are common, Slurm and Cray implement a different range of capabilities, and package them differently. For example, Cray provides an integrated PMI-1/2 library, while Slurm separates the two and requires the user to specify the one to be used at runtime. In addition, several bugs in the Slurm implementations have caused problems requiring extra coding. All this has led to a slew of #if’s in the PMI code and bugs when the corner-case logic for one implementation accidentally traps the other. Extending this support to other implementations would have increased this complexity to an unacceptable level. Accordingly, we have: * created a new OPAL “pmix” framework to abstract the PMI support, with separate components for Cray, Slurm PMI-1, and Slurm PMI-2 implementations. * Replaced the current ORTE grpcomm daemon-based collective operation with an integrated PMIx server, and updated the grpcomm APIs to provide more flexible, multi-algorithm support for collective operations. At this time, only the xcast and allgather operations are supported. * Replaced the current global collective id with a signature based on the names of the participating procs. The allows an unlimited number of collectives to be executed by any group of processes, subject to the requirement that only one collective can be active at a time for a unique combination of procs. Note that a proc can be involved in any number of simultaneous collectives - it is the specific combination of procs that is subject to the constraint * removed the prior OMPI/OPAL modex code * added new macros for executing modex send/recv to simplify use of the new APIs. The send macros allow the caller to specify whether or not the BTL supports async modex operations - if so, then the non-blocking “fence” operation is used, if the active PMIx component supports it. Otherwise, the default is a full blocking modex exchange as we currently perform. * retained the current flag that directs us to use a blocking fence operation, but only to retrieve data upon demand This commit was SVN r32570.
2014-08-21 18:56:47 +00:00
#include "opal/mca/pmix/pmix.h"
#include "opal/mca/pmix/base/base.h"
Per the meeting on moving the BTLs to OPAL, move the ORTE database "db" framework to OPAL so the relocated BTLs can access it. Because the data is indexed by process, this requires that we define a new "opal_identifier_t" that corresponds to the orte_process_name_t struct. In order to support multiple run-times, this is defined in opal/mca/db/db_types.h as a uint64_t without identifying the meaning of any part of that data. A few changes were required to support this move: 1. the PMI component used to identify rte-related data (e.g., host name, bind level) and package them as a unit to reduce the number of PMI keys. This code was moved up to the ORTE layer as the OPAL layer has no understanding of these concepts. In addition, the component locally stored data based on process jobid/vpid - this could no longer be supported (see below for the solution). 2. the hash component was updated to use the new opal_identifier_t instead of orte_process_name_t as its index for storing data in the hash tables. Previously, we did a hash on the vpid and stored the data in a 32-bit hash table. In the revised system, we don't see a separate "vpid" field - we only have a 64-bit opaque value. The orte_process_name_t hash turned out to do nothing useful, so we now store the data in a 64-bit hash table. Preliminary tests didn't show any identifiable change in behavior or performance, but we'll have to see if a move back to the 32-bit table is required at some later time. 3. the db framework was a "select one" system. However, since the PMI component could no longer use its internal storage system, the framework has now been changed to a "select many" mode of operation. This allows the hash component to handle all internal storage, while the PMI component only handles pushing/pulling things from the PMI system. This was something we had planned for some time - when fetching data, we first check internal storage to see if we already have it, and then automatically go to the global system to look for it if we don't. Accordingly, the framework was provided with a custom query function used during "select" that lets you seperately specify the "store" and "fetch" ordering. 4. the ORTE grpcomm and ess/pmi components, and the nidmap code, were updated to work with the new db framework and to specify internal/global storage options. No changes were made to the MPI layer, except for modifying the ORTE component of the OMPI/rte framework to support the new db framework. This commit was SVN r28112.
2013-02-26 17:50:04 +00:00
#include "orte/util/proc_info.h"
#include "orte/mca/errmgr/errmgr.h"
#include "orte/mca/ess/ess.h"
#include "orte/mca/ess/pmi/ess_pmi.h"
extern orte_ess_base_module_t orte_ess_pmi_module;
static int pmi_component_open(void);
static int pmi_component_close(void);
static int pmi_component_query(mca_base_module_t **module, int *priority);
/*
* Instantiate the public struct with all of our public information
* and pointers to our public functions in it
*/
orte_ess_base_component_t mca_ess_pmi_component = {
.base_version = {
ORTE_ESS_BASE_VERSION_3_0_0,
/* Component name and version */
.mca_component_name = "pmi",
MCA_BASE_MAKE_VERSION(component, ORTE_MAJOR_VERSION, ORTE_MINOR_VERSION,
ORTE_RELEASE_VERSION),
/* Component open and close functions */
.mca_open_component = pmi_component_open,
.mca_close_component = pmi_component_close,
.mca_query_component = pmi_component_query,
},
.base_data = {
/* The component is checkpoint ready */
MCA_BASE_METADATA_PARAM_CHECKPOINT
},
};
static int pmi_component_open(void)
{
return ORTE_SUCCESS;
}
static int pmi_component_query(mca_base_module_t **module, int *priority)
{
int ret;
/* all APPS must use pmix */
if (ORTE_PROC_IS_APP) {
/* open and setup pmix */
if (NULL == opal_pmix.initialized) {
if (OPAL_SUCCESS != (ret = mca_base_framework_open(&opal_pmix_base_framework, 0))) {
ORTE_ERROR_LOG(ret);
*priority = -1;
*module = NULL;
return ret;
}
if (OPAL_SUCCESS != (ret = opal_pmix_base_select())) {
/* don't error log this as it might not be an error at all */
*priority = -1;
*module = NULL;
(void) mca_base_framework_close(&opal_pmix_base_framework);
return ret;
}
}
if (!opal_pmix.initialized()) {
/* we may have everything setup, but we are not
* in a PMIx environment and so we need to disqualify
* ourselves - we are likely a singleton and will
* pick things up from there */
*priority = -1;
*module = NULL;
return ORTE_ERROR;
}
*priority = 35;
*module = (mca_base_module_t *)&orte_ess_pmi_module;
return ORTE_SUCCESS;
}
/* we can't run */
*priority = -1;
*module = NULL;
return ORTE_ERROR;
}
static int pmi_component_close(void)
{
return ORTE_SUCCESS;
}