aec5cd08bd
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.
93 строки
2.4 KiB
C
93 строки
2.4 KiB
C
/*
|
|
* Copyright (c) 2011 Cisco Systems, Inc. All rights reserved.
|
|
* Copyright (c) 2011-2013 Los Alamos National Security, LLC. All
|
|
* rights reserved.
|
|
* 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"
|
|
#include "opal/mca/pmix/pmix.h"
|
|
|
|
#include "orte/util/proc_info.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 = {
|
|
{
|
|
ORTE_ESS_BASE_VERSION_3_0_0,
|
|
|
|
/* Component name and version */
|
|
"pmi",
|
|
ORTE_MAJOR_VERSION,
|
|
ORTE_MINOR_VERSION,
|
|
ORTE_RELEASE_VERSION,
|
|
|
|
/* Component open and close functions */
|
|
pmi_component_open,
|
|
pmi_component_close,
|
|
pmi_component_query
|
|
},
|
|
{
|
|
/* 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)
|
|
{
|
|
/* we are available anywhere PMI is available, but not for HNP itself */
|
|
if (!ORTE_PROC_IS_HNP && NULL != opal_pmix.init &&
|
|
OPAL_SUCCESS == opal_pmix.init()) {
|
|
/* if PMI is available, use it */
|
|
*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)
|
|
{
|
|
if (NULL != opal_pmix.finalize) {
|
|
opal_pmix.finalize(); // balances query
|
|
}
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|