1
1
openmpi/opal/class/ompi_free_list.h

295 строки
12 KiB
C
Исходник Обычный вид История

/* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
/*
* Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
* University Research and Technology
* Corporation. All rights reserved.
* Copyright (c) 2004-2013 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) 2010 IBM Corporation. All rights reserved.
* Copyright (c) 2010 Cisco Systems, Inc. All rights reserved.
* Copyright (c) 2014 Los Alamos National Security, LLC. All rights
* reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
#ifndef OMPI_FREE_LIST_H
#define OMPI_FREE_LIST_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 04:47:28 +04:00
#include "opal_config.h"
#include "opal/class/opal_lifo.h"
#include "opal/prefetch.h"
#include "opal/threads/condition.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 04:47:28 +04:00
#include "opal/constants.h"
#include "opal/runtime/opal.h"
- Replace combinations of #if defined (c_plusplus) defined (__cplusplus) followed by extern "C" { and the closing counterpart by BEGIN_C_DECLS and END_C_DECLS. Notable exceptions are: - opal/include/opal_config_bottom.h: This is our generated code, that itself defines BEGIN_C_DECL and END_C_DECL - ompi/mpi/cxx/mpicxx.h: Here we do not include opal_config_bottom.h: - Belongs to external code: opal/mca/backtrace/darwin/MoreBacktrace/MoreDebugging/MoreBacktrace.c opal/mca/backtrace/darwin/MoreBacktrace/MoreDebugging/MoreBacktrace.h - opal/include/opal/prefetch.h: Has C++ specific macros that are protected: - Had #if ... } #endif _and_ END_C_DECLS (aka end up with 2x END_C_DECLS) ompi/mca/btl/openib/btl_openib.h - opal/event/event.h has #ifdef __cplusplus as BEGIN_C_DECLS... - opal/win32/ompi_process.h: had extern "C"\n {... opal/win32/ompi_process.h: dito - ompi/mca/btl/pcie/btl_pcie_lex.l: needed to add *_C_DECLS ompi/mpi/f90/test/align_c.c: dito - ompi/debuggers/msgq_interface.h: used #ifdef __cplusplus - ompi/mpi/f90/xml/common-C.xsl: Amend Tested on linux using --with-openib and --with-mx The following do not contain either opal_config.h, orte_config.h or ompi_config.h (but possibly other header files, that include one of the above): ompi/mca/bml/r2/bml_r2_ft.h ompi/mca/btl/gm/btl_gm_endpoint.h ompi/mca/btl/gm/btl_gm_proc.h ompi/mca/btl/mx/btl_mx_endpoint.h ompi/mca/btl/ofud/btl_ofud_endpoint.h ompi/mca/btl/ofud/btl_ofud_frag.h ompi/mca/btl/ofud/btl_ofud_proc.h ompi/mca/btl/openib/btl_openib_mca.h ompi/mca/btl/portals/btl_portals_endpoint.h ompi/mca/btl/portals/btl_portals_frag.h ompi/mca/btl/sctp/btl_sctp_endpoint.h ompi/mca/btl/sctp/btl_sctp_proc.h ompi/mca/btl/tcp/btl_tcp_endpoint.h ompi/mca/btl/tcp/btl_tcp_ft.h ompi/mca/btl/tcp/btl_tcp_proc.h ompi/mca/btl/template/btl_template_endpoint.h ompi/mca/btl/template/btl_template_proc.h ompi/mca/btl/udapl/btl_udapl_eager_rdma.h ompi/mca/btl/udapl/btl_udapl_endpoint.h ompi/mca/btl/udapl/btl_udapl_mca.h ompi/mca/btl/udapl/btl_udapl_proc.h ompi/mca/mtl/mx/mtl_mx_endpoint.h ompi/mca/mtl/mx/mtl_mx.h ompi/mca/mtl/psm/mtl_psm_endpoint.h ompi/mca/mtl/psm/mtl_psm.h ompi/mca/pml/cm/pml_cm_component.h ompi/mca/pml/csum/pml_csum_comm.h ompi/mca/pml/dr/pml_dr_comm.h ompi/mca/pml/dr/pml_dr_component.h ompi/mca/pml/dr/pml_dr_endpoint.h ompi/mca/pml/dr/pml_dr_recvfrag.h ompi/mca/pml/example/pml_example.h ompi/mca/pml/ob1/pml_ob1_comm.h ompi/mca/pml/ob1/pml_ob1_component.h ompi/mca/pml/ob1/pml_ob1_endpoint.h ompi/mca/pml/ob1/pml_ob1_rdmafrag.h ompi/mca/pml/ob1/pml_ob1_recvfrag.h ompi/mca/pml/v/pml_v_output.h opal/include/opal/prefetch.h opal/mca/timer/aix/timer_aix.h opal/util/qsort.h test/support/components.h This commit was SVN r21855. The following SVN revision numbers were found above: r2 --> open-mpi/ompi@58fdc188553052bc2e893ba28fb28fddbe78435a
2009-08-20 15:42:18 +04:00
BEGIN_C_DECLS
struct mca_mem_pool_t;
This commit brings in two major things: 1. Galen's fine-grain control of queue pair resources in the openib BTL. 1. Pasha's new implementation of asychronous HCA event handling. Pasha's new implementation doesn't take much explanation, but the new "multifrag" stuff does. Note that "svn merge" was not used to bring this new code from the /tmp/ib_multifrag branch -- something Bad happened in the periodic trunk pulls on that branch making an actual merge back to the trunk effectively impossible (i.e., lots and lots of arbitrary conflicts and artifical changes). :-( == Fine-grain control of queue pair resources == Galen's fine-grain control of queue pair resources to the OpenIB BTL (thanks to Gleb for fixing broken code and providing additional functionality, Pasha for finding broken code, and Jeff for doing all the svn work and regression testing). Prior to this commit, the OpenIB BTL created two queue pairs: one for eager size fragments and one for max send size fragments. When the use of the shared receive queue (SRQ) was specified (via "-mca btl_openib_use_srq 1"), these QPs would use a shared receive queue for receive buffers instead of the default per-peer (PP) receive queues and buffers. One consequence of this design is that receive buffer utilization (the size of the data received as a percentage of the receive buffer used for the data) was quite poor for a number of applications. The new design allows multiple QPs to be specified at runtime. Each QP can be setup to use PP or SRQ receive buffers as well as giving fine-grained control over receive buffer size, number of receive buffers to post, when to replenish the receive queue (low water mark) and for SRQ QPs, the number of outstanding sends can also be specified. The following is an example of the syntax to describe QPs to the OpenIB BTL using the new MCA parameter btl_openib_receive_queues: {{{ -mca btl_openib_receive_queues \ "P,128,16,4;S,1024,256,128,32;S,4096,256,128,32;S,65536,256,128,32" }}} Each QP description is delimited by ";" (semicolon) with individual fields of the QP description delimited by "," (comma). The above example therefore describes 4 QPs. The first QP is: P,128,16,4 Meaning: per-peer receive buffer QPs are indicated by a starting field of "P"; the first QP (shown above) is therefore a per-peer based QP. The second field indicates the size of the receive buffer in bytes (128 bytes). The third field indicates the number of receive buffers to allocate to the QP (16). The fourth field indicates the low watermark for receive buffers at which time the BTL will repost receive buffers to the QP (4). The second QP is: S,1024,256,128,32 Shared receive queue based QPs are indicated by a starting field of "S"; the second QP (shown above) is therefore a shared receive queue based QP. The second, third and fourth fields are the same as in the per-peer based QP. The fifth field is the number of outstanding sends that are allowed at a given time on the QP (32). This provides a "good enough" mechanism of flow control for some regular communication patterns. QPs MUST be specified in ascending receive buffer size order. This requirement may be removed prior to 1.3 release. This commit was SVN r15474.
2007-07-18 05:15:59 +04:00
struct ompi_free_list_item_t;
typedef void (*ompi_free_list_item_init_fn_t) (
struct ompi_free_list_item_t*, void* ctx);
struct ompi_free_list_t
{
opal_lifo_t super;
size_t fl_max_to_alloc;
size_t fl_num_allocated;
size_t fl_num_per_alloc;
size_t fl_num_waiting;
size_t fl_frag_size; /* size of the fragment descriptor */
size_t fl_frag_alignment; /* fragment descriptor alignment */
size_t fl_payload_buffer_size; /* size of payload buffer */
size_t fl_payload_buffer_alignment; /* payload buffer alignment */
opal_class_t* fl_frag_class;
struct mca_mpool_base_module_t* fl_mpool;
opal_mutex_t fl_lock;
opal_condition_t fl_condition;
opal_list_t fl_allocations;
This commit brings in two major things: 1. Galen's fine-grain control of queue pair resources in the openib BTL. 1. Pasha's new implementation of asychronous HCA event handling. Pasha's new implementation doesn't take much explanation, but the new "multifrag" stuff does. Note that "svn merge" was not used to bring this new code from the /tmp/ib_multifrag branch -- something Bad happened in the periodic trunk pulls on that branch making an actual merge back to the trunk effectively impossible (i.e., lots and lots of arbitrary conflicts and artifical changes). :-( == Fine-grain control of queue pair resources == Galen's fine-grain control of queue pair resources to the OpenIB BTL (thanks to Gleb for fixing broken code and providing additional functionality, Pasha for finding broken code, and Jeff for doing all the svn work and regression testing). Prior to this commit, the OpenIB BTL created two queue pairs: one for eager size fragments and one for max send size fragments. When the use of the shared receive queue (SRQ) was specified (via "-mca btl_openib_use_srq 1"), these QPs would use a shared receive queue for receive buffers instead of the default per-peer (PP) receive queues and buffers. One consequence of this design is that receive buffer utilization (the size of the data received as a percentage of the receive buffer used for the data) was quite poor for a number of applications. The new design allows multiple QPs to be specified at runtime. Each QP can be setup to use PP or SRQ receive buffers as well as giving fine-grained control over receive buffer size, number of receive buffers to post, when to replenish the receive queue (low water mark) and for SRQ QPs, the number of outstanding sends can also be specified. The following is an example of the syntax to describe QPs to the OpenIB BTL using the new MCA parameter btl_openib_receive_queues: {{{ -mca btl_openib_receive_queues \ "P,128,16,4;S,1024,256,128,32;S,4096,256,128,32;S,65536,256,128,32" }}} Each QP description is delimited by ";" (semicolon) with individual fields of the QP description delimited by "," (comma). The above example therefore describes 4 QPs. The first QP is: P,128,16,4 Meaning: per-peer receive buffer QPs are indicated by a starting field of "P"; the first QP (shown above) is therefore a per-peer based QP. The second field indicates the size of the receive buffer in bytes (128 bytes). The third field indicates the number of receive buffers to allocate to the QP (16). The fourth field indicates the low watermark for receive buffers at which time the BTL will repost receive buffers to the QP (4). The second QP is: S,1024,256,128,32 Shared receive queue based QPs are indicated by a starting field of "S"; the second QP (shown above) is therefore a shared receive queue based QP. The second, third and fourth fields are the same as in the per-peer based QP. The fifth field is the number of outstanding sends that are allowed at a given time on the QP (32). This provides a "good enough" mechanism of flow control for some regular communication patterns. QPs MUST be specified in ascending receive buffer size order. This requirement may be removed prior to 1.3 release. This commit was SVN r15474.
2007-07-18 05:15:59 +04:00
ompi_free_list_item_init_fn_t item_init;
void* ctx;
};
typedef struct ompi_free_list_t ompi_free_list_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 04:47:28 +04:00
OPAL_DECLSPEC OBJ_CLASS_DECLARATION(ompi_free_list_t);
struct mca_mpool_base_registration_t;
struct ompi_free_list_item_t
{
opal_list_item_t super;
struct mca_mpool_base_registration_t *registration;
void *ptr;
};
typedef struct ompi_free_list_item_t ompi_free_list_item_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 04:47:28 +04:00
OPAL_DECLSPEC OBJ_CLASS_DECLARATION(ompi_free_list_item_t);
/**
* Initialize a free list.
*
* @param free_list (IN) Free list.
* @param element_size (IN) Size of each element.
* @param element_class (IN) opal_class_t of element - used to initialize allocated elements.
* @param num_elements_to_alloc Initial number of elements to allocate.
* @param max_elements_to_alloc Maximum number of elements to allocate.
* @param num_elements_per_alloc Number of elements to grow by per allocation.
* @param mpool Optional memory pool for allocation.s
*/
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 04:47:28 +04:00
OPAL_DECLSPEC int ompi_free_list_init_ex(
ompi_free_list_t *free_list,
size_t element_size,
size_t alignment,
opal_class_t* element_class,
int num_elements_to_alloc,
int max_elements_to_alloc,
int num_elements_per_alloc,
This commit brings in two major things: 1. Galen's fine-grain control of queue pair resources in the openib BTL. 1. Pasha's new implementation of asychronous HCA event handling. Pasha's new implementation doesn't take much explanation, but the new "multifrag" stuff does. Note that "svn merge" was not used to bring this new code from the /tmp/ib_multifrag branch -- something Bad happened in the periodic trunk pulls on that branch making an actual merge back to the trunk effectively impossible (i.e., lots and lots of arbitrary conflicts and artifical changes). :-( == Fine-grain control of queue pair resources == Galen's fine-grain control of queue pair resources to the OpenIB BTL (thanks to Gleb for fixing broken code and providing additional functionality, Pasha for finding broken code, and Jeff for doing all the svn work and regression testing). Prior to this commit, the OpenIB BTL created two queue pairs: one for eager size fragments and one for max send size fragments. When the use of the shared receive queue (SRQ) was specified (via "-mca btl_openib_use_srq 1"), these QPs would use a shared receive queue for receive buffers instead of the default per-peer (PP) receive queues and buffers. One consequence of this design is that receive buffer utilization (the size of the data received as a percentage of the receive buffer used for the data) was quite poor for a number of applications. The new design allows multiple QPs to be specified at runtime. Each QP can be setup to use PP or SRQ receive buffers as well as giving fine-grained control over receive buffer size, number of receive buffers to post, when to replenish the receive queue (low water mark) and for SRQ QPs, the number of outstanding sends can also be specified. The following is an example of the syntax to describe QPs to the OpenIB BTL using the new MCA parameter btl_openib_receive_queues: {{{ -mca btl_openib_receive_queues \ "P,128,16,4;S,1024,256,128,32;S,4096,256,128,32;S,65536,256,128,32" }}} Each QP description is delimited by ";" (semicolon) with individual fields of the QP description delimited by "," (comma). The above example therefore describes 4 QPs. The first QP is: P,128,16,4 Meaning: per-peer receive buffer QPs are indicated by a starting field of "P"; the first QP (shown above) is therefore a per-peer based QP. The second field indicates the size of the receive buffer in bytes (128 bytes). The third field indicates the number of receive buffers to allocate to the QP (16). The fourth field indicates the low watermark for receive buffers at which time the BTL will repost receive buffers to the QP (4). The second QP is: S,1024,256,128,32 Shared receive queue based QPs are indicated by a starting field of "S"; the second QP (shown above) is therefore a shared receive queue based QP. The second, third and fourth fields are the same as in the per-peer based QP. The fifth field is the number of outstanding sends that are allowed at a given time on the QP (32). This provides a "good enough" mechanism of flow control for some regular communication patterns. QPs MUST be specified in ascending receive buffer size order. This requirement may be removed prior to 1.3 release. This commit was SVN r15474.
2007-07-18 05:15:59 +04:00
struct mca_mpool_base_module_t*,
ompi_free_list_item_init_fn_t item_init,
void *ctx
);
static inline int ompi_free_list_init(
ompi_free_list_t *free_list,
size_t element_size,
opal_class_t* element_class,
int num_elements_to_alloc,
int max_elements_to_alloc,
int num_elements_per_alloc,
struct mca_mpool_base_module_t* mpool)
{
return ompi_free_list_init_ex(free_list, element_size, opal_cache_line_size,
element_class, num_elements_to_alloc, max_elements_to_alloc,
This commit brings in two major things: 1. Galen's fine-grain control of queue pair resources in the openib BTL. 1. Pasha's new implementation of asychronous HCA event handling. Pasha's new implementation doesn't take much explanation, but the new "multifrag" stuff does. Note that "svn merge" was not used to bring this new code from the /tmp/ib_multifrag branch -- something Bad happened in the periodic trunk pulls on that branch making an actual merge back to the trunk effectively impossible (i.e., lots and lots of arbitrary conflicts and artifical changes). :-( == Fine-grain control of queue pair resources == Galen's fine-grain control of queue pair resources to the OpenIB BTL (thanks to Gleb for fixing broken code and providing additional functionality, Pasha for finding broken code, and Jeff for doing all the svn work and regression testing). Prior to this commit, the OpenIB BTL created two queue pairs: one for eager size fragments and one for max send size fragments. When the use of the shared receive queue (SRQ) was specified (via "-mca btl_openib_use_srq 1"), these QPs would use a shared receive queue for receive buffers instead of the default per-peer (PP) receive queues and buffers. One consequence of this design is that receive buffer utilization (the size of the data received as a percentage of the receive buffer used for the data) was quite poor for a number of applications. The new design allows multiple QPs to be specified at runtime. Each QP can be setup to use PP or SRQ receive buffers as well as giving fine-grained control over receive buffer size, number of receive buffers to post, when to replenish the receive queue (low water mark) and for SRQ QPs, the number of outstanding sends can also be specified. The following is an example of the syntax to describe QPs to the OpenIB BTL using the new MCA parameter btl_openib_receive_queues: {{{ -mca btl_openib_receive_queues \ "P,128,16,4;S,1024,256,128,32;S,4096,256,128,32;S,65536,256,128,32" }}} Each QP description is delimited by ";" (semicolon) with individual fields of the QP description delimited by "," (comma). The above example therefore describes 4 QPs. The first QP is: P,128,16,4 Meaning: per-peer receive buffer QPs are indicated by a starting field of "P"; the first QP (shown above) is therefore a per-peer based QP. The second field indicates the size of the receive buffer in bytes (128 bytes). The third field indicates the number of receive buffers to allocate to the QP (16). The fourth field indicates the low watermark for receive buffers at which time the BTL will repost receive buffers to the QP (4). The second QP is: S,1024,256,128,32 Shared receive queue based QPs are indicated by a starting field of "S"; the second QP (shown above) is therefore a shared receive queue based QP. The second, third and fourth fields are the same as in the per-peer based QP. The fifth field is the number of outstanding sends that are allowed at a given time on the QP (32). This provides a "good enough" mechanism of flow control for some regular communication patterns. QPs MUST be specified in ascending receive buffer size order. This requirement may be removed prior to 1.3 release. This commit was SVN r15474.
2007-07-18 05:15:59 +04:00
num_elements_per_alloc, mpool, NULL, NULL);
}
/**
* Initialize a free list. - this will replace ompi_free_list_init_ex
*
* @param free_list (IN) Free list.
* @param frag_size (IN) Size of each element - allocated by malloc.
* @param frag_alignment (IN) Fragment alignment.
* @param frag_class (IN) opal_class_t of element - used to initialize allocated elements.
* @param payload_buffer_size (IN) Size of payload buffer - allocated from mpool.
* @param payload_buffer_alignment (IN) Payload buffer alignment.
* @param num_elements_to_alloc (IN) Initial number of elements to allocate.
* @param max_elements_to_alloc (IN) Maximum number of elements to allocate.
* @param num_elements_per_alloc (IN) Number of elements to grow by per allocation.
* @param mpool (IN) Optional memory pool for allocation.s
* @param item_init (IN)
* @param ctx (IN)
*/
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 04:47:28 +04:00
OPAL_DECLSPEC int ompi_free_list_init_ex_new(
ompi_free_list_t *free_list,
size_t frag_size,
size_t frag_alignment,
opal_class_t* frag_class,
size_t payload_buffer_size,
size_t payload_buffer_alignment,
int num_elements_to_alloc,
int max_elements_to_alloc,
int num_elements_per_alloc,
struct mca_mpool_base_module_t*,
ompi_free_list_item_init_fn_t item_init,
void *ctx
);
/**
* Initialize a free list. - this will replace ompi_free_list_init
*
* @param free_list (IN) Free list.
* @param frag_size (IN) Size of each element - allocated by malloc.
* @param frag_alignment (IN) Fragment alignment.
* @param frag_class (IN) opal_class_t of element - used to initialize allocated elements.
* @param payload_buffer_size (IN) Size of payload buffer - allocated from mpool.
* @param payload_buffer_alignment (IN) Payload buffer alignment.
* @param num_elements_to_alloc (IN) Initial number of elements to allocate.
* @param max_elements_to_alloc (IN) Maximum number of elements to allocate.
* @param num_elements_per_alloc (IN) Number of elements to grow by per allocation.
* @param mpool (IN) Optional memory pool for allocation.s
*/
static inline int ompi_free_list_init_new(
ompi_free_list_t *free_list,
size_t frag_size,
size_t frag_alignment,
opal_class_t* frag_class,
size_t payload_buffer_size,
size_t payload_buffer_alignment,
int num_elements_to_alloc,
int max_elements_to_alloc,
int num_elements_per_alloc,
struct mca_mpool_base_module_t* mpool)
{
return ompi_free_list_init_ex_new(free_list,
frag_size, frag_alignment, frag_class,
payload_buffer_size, payload_buffer_alignment,
num_elements_to_alloc, max_elements_to_alloc,
num_elements_per_alloc, mpool, NULL, NULL);
}
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 04:47:28 +04:00
OPAL_DECLSPEC int ompi_free_list_grow(ompi_free_list_t* flist, size_t num_elements);
/* Grow the free list to be *at least* size elements. This function
will not shrink the list if it is already larger than size and may
grow it past size if necessary (it will grow in
num_elements_per_alloc chunks) */
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 04:47:28 +04:00
OPAL_DECLSPEC int ompi_free_list_resize_mt(ompi_free_list_t *flist, size_t size);
/**
* Attemp to obtain an item from a free list.
*
* @param fl (IN) Free list.
* @param item (OUT) Allocated item.
*
* If the requested item is not available the free list is grown to
* accomodate the request - unless the max number of allocations has
* been reached. If this is the case - a NULL pointer is returned
* to the caller.
*/
#define OMPI_FREE_LIST_GET_MT(fl, item) \
{ \
item = (ompi_free_list_item_t*) opal_lifo_pop (&((fl)->super)); \
if( OPAL_UNLIKELY(NULL == item) ) { \
if(opal_using_threads()) { \
opal_mutex_lock(&((fl)->fl_lock)); \
ompi_free_list_grow((fl), (fl)->fl_num_per_alloc); \
opal_mutex_unlock(&((fl)->fl_lock)); \
} else { \
ompi_free_list_grow((fl), (fl)->fl_num_per_alloc); \
} \
item = (ompi_free_list_item_t*) opal_lifo_pop(&((fl)->super)); \
} \
}
/**
* Blocking call to obtain an item from a free list.
*
* @param fl (IN) Free list.
* @param item (OUT) Allocated item.
*
* If the requested item is not available the free list is grown to
* accomodate the request - unless the max number of allocations has
* been reached. In this case the caller is blocked until an item
* is returned to the list.
*/
#define OMPI_FREE_LIST_WAIT_MT(fl, item) \
__ompi_free_list_wait_mt( (fl), &(item) )
static inline void __ompi_free_list_wait_mt( ompi_free_list_t* fl,
ompi_free_list_item_t** item )
{
*item = (ompi_free_list_item_t*)opal_lifo_pop(&((fl)->super));
while( NULL == *item ) {
if( !OPAL_THREAD_TRYLOCK(&((fl)->fl_lock)) ) {
if((fl)->fl_max_to_alloc <= (fl)->fl_num_allocated) {
(fl)->fl_num_waiting++;
opal_condition_wait(&((fl)->fl_condition), &((fl)->fl_lock));
(fl)->fl_num_waiting--;
} else {
if(ompi_free_list_grow((fl), (fl)->fl_num_per_alloc)
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 04:47:28 +04:00
== OPAL_SUCCESS) {
if( 0 < (fl)->fl_num_waiting ) {
if( 1 == (fl)->fl_num_waiting ) {
opal_condition_signal(&((fl)->fl_condition));
} else {
opal_condition_broadcast(&((fl)->fl_condition));
}
}
} else {
(fl)->fl_num_waiting++;
opal_condition_wait(&((fl)->fl_condition), &((fl)->fl_lock));
(fl)->fl_num_waiting--;
}
}
} else {
/* If I wasn't able to get the lock in the begining when I finaly grab it
* the one holding the lock in the begining already grow the list. I will
* release the lock and try to get a new element until I succeed.
*/
OPAL_THREAD_LOCK(&((fl)->fl_lock));
}
OPAL_THREAD_UNLOCK(&((fl)->fl_lock));
*item = (ompi_free_list_item_t*)opal_lifo_pop(&((fl)->super));
}
}
/**
* Return an item to a free list.
*
* @param fl (IN) Free list.
* @param item (OUT) Allocated item.
*
*/
#define OMPI_FREE_LIST_RETURN_MT(fl, item) \
do { \
opal_list_item_t* original; \
\
original = opal_lifo_push( &(fl)->super, &(item)->super); \
if( &(fl)->super.opal_lifo_ghost == original ) { \
OPAL_THREAD_LOCK(&(fl)->fl_lock); \
if((fl)->fl_num_waiting > 0) { \
if( 1 == (fl)->fl_num_waiting ) { \
opal_condition_signal(&((fl)->fl_condition)); \
} else { \
opal_condition_broadcast(&((fl)->fl_condition)); \
} \
} \
OPAL_THREAD_UNLOCK(&(fl)->fl_lock); \
} \
} while(0)
- Replace combinations of #if defined (c_plusplus) defined (__cplusplus) followed by extern "C" { and the closing counterpart by BEGIN_C_DECLS and END_C_DECLS. Notable exceptions are: - opal/include/opal_config_bottom.h: This is our generated code, that itself defines BEGIN_C_DECL and END_C_DECL - ompi/mpi/cxx/mpicxx.h: Here we do not include opal_config_bottom.h: - Belongs to external code: opal/mca/backtrace/darwin/MoreBacktrace/MoreDebugging/MoreBacktrace.c opal/mca/backtrace/darwin/MoreBacktrace/MoreDebugging/MoreBacktrace.h - opal/include/opal/prefetch.h: Has C++ specific macros that are protected: - Had #if ... } #endif _and_ END_C_DECLS (aka end up with 2x END_C_DECLS) ompi/mca/btl/openib/btl_openib.h - opal/event/event.h has #ifdef __cplusplus as BEGIN_C_DECLS... - opal/win32/ompi_process.h: had extern "C"\n {... opal/win32/ompi_process.h: dito - ompi/mca/btl/pcie/btl_pcie_lex.l: needed to add *_C_DECLS ompi/mpi/f90/test/align_c.c: dito - ompi/debuggers/msgq_interface.h: used #ifdef __cplusplus - ompi/mpi/f90/xml/common-C.xsl: Amend Tested on linux using --with-openib and --with-mx The following do not contain either opal_config.h, orte_config.h or ompi_config.h (but possibly other header files, that include one of the above): ompi/mca/bml/r2/bml_r2_ft.h ompi/mca/btl/gm/btl_gm_endpoint.h ompi/mca/btl/gm/btl_gm_proc.h ompi/mca/btl/mx/btl_mx_endpoint.h ompi/mca/btl/ofud/btl_ofud_endpoint.h ompi/mca/btl/ofud/btl_ofud_frag.h ompi/mca/btl/ofud/btl_ofud_proc.h ompi/mca/btl/openib/btl_openib_mca.h ompi/mca/btl/portals/btl_portals_endpoint.h ompi/mca/btl/portals/btl_portals_frag.h ompi/mca/btl/sctp/btl_sctp_endpoint.h ompi/mca/btl/sctp/btl_sctp_proc.h ompi/mca/btl/tcp/btl_tcp_endpoint.h ompi/mca/btl/tcp/btl_tcp_ft.h ompi/mca/btl/tcp/btl_tcp_proc.h ompi/mca/btl/template/btl_template_endpoint.h ompi/mca/btl/template/btl_template_proc.h ompi/mca/btl/udapl/btl_udapl_eager_rdma.h ompi/mca/btl/udapl/btl_udapl_endpoint.h ompi/mca/btl/udapl/btl_udapl_mca.h ompi/mca/btl/udapl/btl_udapl_proc.h ompi/mca/mtl/mx/mtl_mx_endpoint.h ompi/mca/mtl/mx/mtl_mx.h ompi/mca/mtl/psm/mtl_psm_endpoint.h ompi/mca/mtl/psm/mtl_psm.h ompi/mca/pml/cm/pml_cm_component.h ompi/mca/pml/csum/pml_csum_comm.h ompi/mca/pml/dr/pml_dr_comm.h ompi/mca/pml/dr/pml_dr_component.h ompi/mca/pml/dr/pml_dr_endpoint.h ompi/mca/pml/dr/pml_dr_recvfrag.h ompi/mca/pml/example/pml_example.h ompi/mca/pml/ob1/pml_ob1_comm.h ompi/mca/pml/ob1/pml_ob1_component.h ompi/mca/pml/ob1/pml_ob1_endpoint.h ompi/mca/pml/ob1/pml_ob1_rdmafrag.h ompi/mca/pml/ob1/pml_ob1_recvfrag.h ompi/mca/pml/v/pml_v_output.h opal/include/opal/prefetch.h opal/mca/timer/aix/timer_aix.h opal/util/qsort.h test/support/components.h This commit was SVN r21855. The following SVN revision numbers were found above: r2 --> open-mpi/ompi@58fdc188553052bc2e893ba28fb28fddbe78435a
2009-08-20 15:42:18 +04:00
END_C_DECLS
#endif