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.
134 строки
4.3 KiB
C
134 строки
4.3 KiB
C
/* -*- C -*-
|
|
*
|
|
* Copyright (c) 2004-2008 The Trustees of Indiana University and Indiana
|
|
* University Research and Technology
|
|
* Corporation. All rights reserved.
|
|
* Copyright (c) 2004-2005 The University of Tennessee and The University
|
|
* of Tennessee Research Foundation. All rights
|
|
* reserved.
|
|
* Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
|
|
* University of Stuttgart. All rights reserved.
|
|
* Copyright (c) 2004-2005 The Regents of the University of California.
|
|
* All rights reserved.
|
|
* Copyright (c) 2011-2012 Los Alamos National Security, LLC.
|
|
* All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
/**
|
|
* @file
|
|
*
|
|
* The OpenRTE Daemon's Local Launch Subsystem
|
|
*
|
|
*/
|
|
|
|
#ifndef ORTE_MCA_ODLS_H
|
|
#define ORTE_MCA_ODLS_H
|
|
|
|
#include "orte_config.h"
|
|
#include "orte/types.h"
|
|
|
|
#include "opal/mca/mca.h"
|
|
#include "opal/class/opal_pointer_array.h"
|
|
|
|
#include "opal/dss/dss_types.h"
|
|
#include "orte/mca/rml/rml_types.h"
|
|
#include "orte/runtime/orte_globals.h"
|
|
|
|
#include "orte/mca/odls/odls_types.h"
|
|
|
|
BEGIN_C_DECLS
|
|
|
|
/*
|
|
* odls module functions
|
|
*/
|
|
|
|
/*
|
|
* Construct a buffer for use in adding local processes
|
|
* In order to reuse daemons, we need a way for the HNP to construct a buffer that
|
|
* contains the data needed by the active ODLS component to launch a local process. Since the
|
|
* only one that knows what a particular ODLS component needs is that component, we require an
|
|
* entry point that the HNP can call to get the required buffer. This is constructed
|
|
* for *all* nodes - the individual orteds then parse that data to find the specific launch info
|
|
* for procs on their node
|
|
*/
|
|
typedef int (*orte_odls_base_module_get_add_procs_data_fn_t)(opal_buffer_t *data,
|
|
orte_jobid_t job);
|
|
|
|
/**
|
|
* Locally launch the provided processes
|
|
*/
|
|
typedef int (*orte_odls_base_module_launch_local_processes_fn_t)(opal_buffer_t *data);
|
|
|
|
/**
|
|
* Kill the local processes on this node
|
|
*/
|
|
typedef int (*orte_odls_base_module_kill_local_processes_fn_t)(opal_pointer_array_t *procs);
|
|
|
|
/**
|
|
* Signal local processes
|
|
*/
|
|
typedef int (*orte_odls_base_module_signal_local_process_fn_t)(const orte_process_name_t *proc,
|
|
int32_t signal);
|
|
|
|
/**
|
|
* Deliver a message to local processes
|
|
*/
|
|
typedef int (*orte_odls_base_module_deliver_message_fn_t)(orte_jobid_t job, opal_buffer_t *buffer,
|
|
orte_rml_tag_t tag);
|
|
|
|
/**
|
|
* Restart a local process
|
|
*/
|
|
typedef int (*orte_odls_base_module_restart_proc_fn_t)(orte_proc_t *child);
|
|
|
|
/**
|
|
* pls module version
|
|
*/
|
|
struct orte_odls_base_module_1_3_0_t {
|
|
orte_odls_base_module_get_add_procs_data_fn_t get_add_procs_data;
|
|
orte_odls_base_module_launch_local_processes_fn_t launch_local_procs;
|
|
orte_odls_base_module_kill_local_processes_fn_t kill_local_procs;
|
|
orte_odls_base_module_signal_local_process_fn_t signal_local_procs;
|
|
orte_odls_base_module_deliver_message_fn_t deliver_message;
|
|
orte_odls_base_module_restart_proc_fn_t restart_proc;
|
|
};
|
|
|
|
/** shorten orte_odls_base_module_1_3_0_t declaration */
|
|
typedef struct orte_odls_base_module_1_3_0_t orte_odls_base_module_1_3_0_t;
|
|
/** shorten orte_odls_base_module_t declaration */
|
|
typedef struct orte_odls_base_module_1_3_0_t orte_odls_base_module_t;
|
|
|
|
/**
|
|
* odls component
|
|
*/
|
|
struct orte_odls_base_component_2_0_0_t {
|
|
/** component version */
|
|
mca_base_component_t version;
|
|
/** component data */
|
|
mca_base_component_data_t base_data;
|
|
};
|
|
/** Convenience typedef */
|
|
typedef struct orte_odls_base_component_2_0_0_t orte_odls_base_component_2_0_0_t;
|
|
/** Convenience typedef */
|
|
typedef orte_odls_base_component_2_0_0_t orte_odls_base_component_t;
|
|
|
|
|
|
/**
|
|
* Macro for use in modules that are of type odls
|
|
*/
|
|
#define ORTE_ODLS_BASE_VERSION_2_0_0 \
|
|
MCA_BASE_VERSION_2_0_0, \
|
|
"odls", 2, 0, 0
|
|
|
|
/* Global structure for accessing ODLS functions
|
|
*/
|
|
ORTE_DECLSPEC extern orte_odls_base_module_t orte_odls; /* holds selected module's function pointers */
|
|
|
|
END_C_DECLS
|
|
|
|
#endif /* MCA_ODLS_H */
|