2015-01-05 15:07:24 -07:00
|
|
|
/* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
|
2005-06-15 19:10:26 +00:00
|
|
|
/*
|
2007-03-16 23:11:45 +00:00
|
|
|
* Copyright (c) 2004-2007 The Trustees of Indiana University and Indiana
|
2005-11-05 19:57:48 +00:00
|
|
|
* University Research and Technology
|
|
|
|
* Corporation. All rights reserved.
|
2009-04-10 16:44:37 +00:00
|
|
|
* Copyright (c) 2004-2009 The University of Tennessee and The University
|
2005-11-05 19:57:48 +00:00
|
|
|
* of Tennessee Research Foundation. All rights
|
|
|
|
* reserved.
|
2005-06-15 19:10:26 +00:00
|
|
|
* 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.
|
2015-01-05 15:07:24 -07:00
|
|
|
* Copyright (c) 2014-2015 Los Alamos National Security, LLC. All rights
|
|
|
|
* reserved.
|
2005-06-15 19:10:26 +00:00
|
|
|
* $COPYRIGHT$
|
|
|
|
*
|
|
|
|
* Additional copyrights may follow
|
|
|
|
*
|
|
|
|
* $HEADER$
|
|
|
|
*/
|
|
|
|
/**
|
|
|
|
* @file
|
|
|
|
*/
|
2005-06-30 05:50:55 +00:00
|
|
|
#ifndef MCA_BTL_SELF_H
|
|
|
|
#define MCA_BTL_SELF_H
|
2005-06-15 19:10:26 +00:00
|
|
|
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 00:47:28 +00:00
|
|
|
#include "opal_config.h"
|
2009-03-04 15:35:54 +00:00
|
|
|
|
2005-12-10 22:04:28 +00:00
|
|
|
#ifdef HAVE_STDLIB_H
|
2005-06-15 19:10:26 +00:00
|
|
|
#include <stdlib.h>
|
2005-12-10 22:04:28 +00:00
|
|
|
#endif /* HAVE_STDLIB_H */
|
|
|
|
#ifdef HAVE_SYS_TYPES_H
|
2005-06-15 19:10:26 +00:00
|
|
|
#include <sys/types.h>
|
2005-12-10 22:04:28 +00:00
|
|
|
#endif /* HAVE_SYS_TYPES_H */
|
Update libevent to the 2.0 series, currently at 2.0.7rc. We will update to their final release when it becomes available. Currently known errors exist in unused portions of the libevent code. This revision passes the IBM test suite on a Linux machine and on a standalone Mac.
This is a fairly intrusive change, but outside of the moving of opal/event to opal/mca/event, the only changes involved (a) changing all calls to opal_event functions to reflect the new framework instead, and (b) ensuring that all opal_event_t objects are properly constructed since they are now true opal_objects.
Note: Shiqing has just returned from vacation and has not yet had a chance to complete the Windows integration. Thus, this commit almost certainly breaks Windows support on the trunk. However, I want this to have a chance to soak for as long as possible before I become less available a week from today (going to be at a class for 5 days, and thus will only be sparingly available) so we can find and fix any problems.
Biggest change is moving the libevent code from opal/event to a new opal/mca/event framework. This was done to make it much easier to update libevent in the future. New versions can be inserted as a new component and tested in parallel with the current version until validated, then we can remove the earlier version if we so choose. This is a statically built framework ala installdirs, so only one component will build at a time. There is no selection logic - the sole compiled component simply loads its function pointers into the opal_event struct.
I have gone thru the code base and converted all the libevent calls I could find. However, I cannot compile nor test every environment. It is therefore quite likely that errors remain in the system. Please keep an eye open for two things:
1. compile-time errors: these will be obvious as calls to the old functions (e.g., opal_evtimer_new) must be replaced by the new framework APIs (e.g., opal_event.evtimer_new)
2. run-time errors: these will likely show up as segfaults due to missing constructors on opal_event_t objects. It appears that it became a typical practice for people to "init" an opal_event_t by simply using memset to zero it out. This will no longer work - you must either OBJ_NEW or OBJ_CONSTRUCT an opal_event_t. I tried to catch these cases, but may have missed some. Believe me, you'll know when you hit it.
There is also the issue of the new libevent "no recursion" behavior. As I described on a recent email, we will have to discuss this and figure out what, if anything, we need to do.
This commit was SVN r23925.
2010-10-24 18:35:54 +00:00
|
|
|
#include "opal/mca/event/event.h"
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 00:47:28 +00:00
|
|
|
#include "opal/class/ompi_free_list.h"
|
|
|
|
#include "opal/mca/btl/btl.h"
|
|
|
|
#include "opal/mca/btl/base/base.h"
|
2005-06-15 19:10:26 +00:00
|
|
|
|
2009-08-20 11:42:18 +00:00
|
|
|
BEGIN_C_DECLS
|
2005-06-15 19:10:26 +00:00
|
|
|
|
|
|
|
/**
|
2005-06-30 05:50:55 +00:00
|
|
|
* Shared Memory (SELF) BTL module.
|
2005-06-15 19:10:26 +00:00
|
|
|
*/
|
2005-06-30 05:50:55 +00:00
|
|
|
struct mca_btl_self_component_t {
|
2015-01-05 15:07:24 -07:00
|
|
|
mca_btl_base_component_3_0_0_t super; /**< base BTL component */
|
2005-06-15 19:10:26 +00:00
|
|
|
int free_list_num; /**< initial size of free lists */
|
|
|
|
int free_list_max; /**< maximum size of free lists */
|
|
|
|
int free_list_inc; /**< number of elements to alloc when growing free lists */
|
2005-07-03 22:45:48 +00:00
|
|
|
opal_mutex_t self_lock;
|
2005-06-15 19:10:26 +00:00
|
|
|
ompi_free_list_t self_frags_eager; /**< free list of self first */
|
|
|
|
ompi_free_list_t self_frags_send; /**< free list of self second */
|
|
|
|
ompi_free_list_t self_frags_rdma; /**< free list of self second */
|
|
|
|
};
|
2005-06-30 05:50:55 +00:00
|
|
|
typedef struct mca_btl_self_component_t mca_btl_self_component_t;
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 00:47:28 +00:00
|
|
|
OPAL_MODULE_DECLSPEC extern mca_btl_self_component_t mca_btl_self_component;
|
2005-06-15 19:10:26 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Register shared memory module parameters with the MCA framework
|
|
|
|
*/
|
2006-10-26 23:03:12 +00:00
|
|
|
int mca_btl_self_component_open(void);
|
2005-06-15 19:10:26 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Any final cleanup before being unloaded.
|
|
|
|
*/
|
2006-10-26 23:03:12 +00:00
|
|
|
int mca_btl_self_component_close(void);
|
2005-06-15 19:10:26 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* SELF module initialization.
|
|
|
|
*
|
2005-06-30 05:50:55 +00:00
|
|
|
* @param num_btls (OUT) Number of BTLs returned in BTL array.
|
|
|
|
* @param enable_progress_threads (IN) Flag indicating whether BTL is allowed to have progress threads
|
|
|
|
* @param enable_mpi_threads (IN) Flag indicating whether BTL must support multilple simultaneous invocations from different threads
|
2005-06-15 19:10:26 +00:00
|
|
|
*
|
|
|
|
*/
|
2006-10-26 23:03:12 +00:00
|
|
|
mca_btl_base_module_t** mca_btl_self_component_init(
|
2005-06-30 05:50:55 +00:00
|
|
|
int *num_btls,
|
2005-06-15 19:10:26 +00:00
|
|
|
bool enable_progress_threads,
|
|
|
|
bool enable_mpi_threads
|
|
|
|
);
|
|
|
|
|
2005-06-30 05:50:55 +00:00
|
|
|
extern mca_btl_base_module_t mca_btl_self;
|
2005-06-15 19:10:26 +00:00
|
|
|
|
|
|
|
|
|
|
|
/**
|
2005-06-30 05:50:55 +00:00
|
|
|
* Cleanup any resources held by the BTL.
|
2005-06-15 19:10:26 +00:00
|
|
|
*
|
2005-06-30 05:50:55 +00:00
|
|
|
* @param btl BTL instance.
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 00:47:28 +00:00
|
|
|
* @return OPAL_SUCCESS or error status on failure.
|
2005-06-15 19:10:26 +00:00
|
|
|
*/
|
|
|
|
|
2006-10-26 23:03:12 +00:00
|
|
|
int mca_btl_self_finalize(
|
2005-06-30 05:50:55 +00:00
|
|
|
struct mca_btl_base_module_t* btl
|
2005-06-15 19:10:26 +00:00
|
|
|
);
|
|
|
|
|
|
|
|
|
|
|
|
/**
|
2005-06-30 05:50:55 +00:00
|
|
|
* PML->BTL notification of change in the process list.
|
|
|
|
* PML->BTL Notification that a receive fragment has been matched.
|
2005-06-15 19:10:26 +00:00
|
|
|
* Called for message that is send from process with the virtual
|
|
|
|
* address of the shared memory segment being different than that of
|
|
|
|
* the receiver.
|
|
|
|
*
|
2005-06-30 05:50:55 +00:00
|
|
|
* @param btl (IN)
|
2005-06-15 19:10:26 +00:00
|
|
|
* @param proc (IN)
|
|
|
|
* @param peer (OUT)
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 00:47:28 +00:00
|
|
|
* @return OPAL_SUCCESS or error status on failure.
|
2005-06-15 19:10:26 +00:00
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
2006-10-26 23:03:12 +00:00
|
|
|
int mca_btl_self_add_procs(
|
2005-06-30 05:50:55 +00:00
|
|
|
struct mca_btl_base_module_t* btl,
|
2005-06-15 19:10:26 +00:00
|
|
|
size_t nprocs,
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 00:47:28 +00:00
|
|
|
struct opal_proc_t **procs,
|
2005-06-30 05:50:55 +00:00
|
|
|
struct mca_btl_base_endpoint_t** peers,
|
2009-03-03 22:25:13 +00:00
|
|
|
struct opal_bitmap_t* reachability
|
2005-06-15 19:10:26 +00:00
|
|
|
);
|
|
|
|
|
|
|
|
|
|
|
|
/**
|
2005-06-30 05:50:55 +00:00
|
|
|
* PML->BTL notification of change in the process list.
|
2005-06-15 19:10:26 +00:00
|
|
|
*
|
2005-06-30 05:50:55 +00:00
|
|
|
* @param btl (IN) BTL instance
|
2005-06-15 19:10:26 +00:00
|
|
|
* @param proc (IN) Peer process
|
|
|
|
* @param peer (IN) Peer addressing information.
|
|
|
|
* @return Status indicating if cleanup was successful
|
|
|
|
*
|
|
|
|
*/
|
2006-10-26 23:03:12 +00:00
|
|
|
int mca_btl_self_del_procs(
|
2005-06-30 05:50:55 +00:00
|
|
|
struct mca_btl_base_module_t* btl,
|
2005-06-15 19:10:26 +00:00
|
|
|
size_t nprocs,
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 00:47:28 +00:00
|
|
|
struct opal_proc_t **procs,
|
2005-06-30 05:50:55 +00:00
|
|
|
struct mca_btl_base_endpoint_t **peers
|
2005-06-15 19:10:26 +00:00
|
|
|
);
|
|
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Allocate a segment.
|
|
|
|
*
|
2005-06-30 05:50:55 +00:00
|
|
|
* @param btl (IN) BTL module
|
2005-06-15 19:10:26 +00:00
|
|
|
* @param size (IN) Request segment size.
|
|
|
|
*/
|
2006-10-26 23:03:12 +00:00
|
|
|
mca_btl_base_descriptor_t* mca_btl_self_alloc(
|
2005-06-30 05:50:55 +00:00
|
|
|
struct mca_btl_base_module_t* btl,
|
2007-12-09 14:00:42 +00:00
|
|
|
struct mca_btl_base_endpoint_t* endpoint,
|
2007-05-24 19:51:26 +00:00
|
|
|
uint8_t order,
|
2007-12-09 14:08:01 +00:00
|
|
|
size_t size,
|
|
|
|
uint32_t flags
|
2005-06-15 19:10:26 +00:00
|
|
|
);
|
|
|
|
|
|
|
|
/**
|
2005-06-30 05:50:55 +00:00
|
|
|
* Return a segment allocated by this BTL.
|
2005-06-15 19:10:26 +00:00
|
|
|
*
|
2005-06-30 05:50:55 +00:00
|
|
|
* @param btl (IN) BTL module
|
2005-06-15 19:10:26 +00:00
|
|
|
* @param segment (IN) Allocated segment.
|
|
|
|
*/
|
2006-10-26 23:03:12 +00:00
|
|
|
int mca_btl_self_free(
|
2005-06-30 05:50:55 +00:00
|
|
|
struct mca_btl_base_module_t* btl,
|
|
|
|
mca_btl_base_descriptor_t* segment
|
2005-06-15 19:10:26 +00:00
|
|
|
);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Pack data
|
|
|
|
*
|
2005-06-30 05:50:55 +00:00
|
|
|
* @param btl (IN) BTL module
|
|
|
|
* @param peer (IN) BTL peer addressing
|
2005-06-15 19:10:26 +00:00
|
|
|
*/
|
2005-06-30 05:50:55 +00:00
|
|
|
struct mca_btl_base_descriptor_t* mca_btl_self_prepare_src(
|
|
|
|
struct mca_btl_base_module_t* btl,
|
|
|
|
struct mca_btl_base_endpoint_t* endpoint,
|
- Split the datatype engine into two parts: an MPI specific part in
OMPI
and a language agnostic part in OPAL. The convertor is completely
moved into OPAL. This offers several benefits as described in RFC
http://www.open-mpi.org/community/lists/devel/2009/07/6387.php
namely:
- Fewer basic types (int* and float* types, boolean and wchar
- Fixing naming scheme to ompi-nomenclature.
- Usability outside of the ompi-layer.
- Due to the fixed nature of simple opal types, their information is
completely
known at compile time and therefore constified
- With fewer datatypes (22), the actual sizes of bit-field types may be
reduced
from 64 to 32 bits, allowing reorganizing the opal_datatype
structure, eliminating holes and keeping data required in convertor
(upon send/recv) in one cacheline...
This has implications to the convertor-datastructure and other parts
of the code.
- Several performance tests have been run, the netpipe latency does not
change with
this patch on Linux/x86-64 on the smoky cluster.
- Extensive tests have been done to verify correctness (no new
regressions) using:
1. mpi_test_suite on linux/x86-64 using clean ompi-trunk and
ompi-ddt:
a. running both trunk and ompi-ddt resulted in no differences
(except for MPI_SHORT_INT and MPI_TYPE_MIX_LB_UB do now run
correctly).
b. with --enable-memchecker and running under valgrind (one buglet
when run with static found in test-suite, commited)
2. ibm testsuite on linux/x86-64 using clean ompi-trunk and ompi-ddt:
all passed (except for the dynamic/ tests failed!! as trunk/MTT)
3. compilation and usage of HDF5 tests on Jaguar using PGI and
PathScale compilers.
4. compilation and usage on Scicortex.
- Please note, that for the heterogeneous case, (-m32 compiled
binaries/ompi), neither
ompi-trunk, nor ompi-ddt branch would successfully launch.
This commit was SVN r21641.
2009-07-13 04:56:31 +00:00
|
|
|
struct opal_convertor_t* convertor,
|
2007-05-24 19:51:26 +00:00
|
|
|
uint8_t order,
|
2005-06-15 19:10:26 +00:00
|
|
|
size_t reserve,
|
2007-12-09 14:08:01 +00:00
|
|
|
size_t* size,
|
|
|
|
uint32_t flags
|
2005-06-15 19:10:26 +00:00
|
|
|
);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Initiate a send to the peer.
|
|
|
|
*
|
2005-06-30 05:50:55 +00:00
|
|
|
* @param btl (IN) BTL module
|
|
|
|
* @param peer (IN) BTL peer addressing
|
2005-06-15 19:10:26 +00:00
|
|
|
*/
|
2006-10-26 23:03:12 +00:00
|
|
|
int mca_btl_self_send(
|
2005-06-30 05:50:55 +00:00
|
|
|
struct mca_btl_base_module_t* btl,
|
|
|
|
struct mca_btl_base_endpoint_t* endpoint,
|
|
|
|
struct mca_btl_base_descriptor_t* descriptor,
|
|
|
|
mca_btl_base_tag_t tag
|
2005-06-15 19:10:26 +00:00
|
|
|
);
|
|
|
|
|
2007-03-16 23:11:45 +00:00
|
|
|
/**
|
|
|
|
* Fault Tolerance Event Notification Function
|
|
|
|
* @param state Checkpoint Stae
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 00:47:28 +00:00
|
|
|
* @return OPAL_SUCCESS or failure status
|
2007-03-16 23:11:45 +00:00
|
|
|
*/
|
|
|
|
int mca_btl_self_ft_event(int state);
|
|
|
|
|
2009-08-20 11:42:18 +00:00
|
|
|
END_C_DECLS
|
2006-08-24 16:38:08 +00:00
|
|
|
|
2005-06-15 19:10:26 +00:00
|
|
|
#endif
|
|
|
|
|