ports/openmpi
ports/openmpi
1
1
Форкнуть 0
Код Релизы Активность
43186e494b
openmpi/opal/mca/btl/usnic/btl_usnic_recv.c

370 строки
14 KiB
C
Исходник Обычный вид История

First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
/*
* Copyright (c) 2004-2008 The Trustees of Indiana University and Indiana
* University Research and Technology
* Corporation. All rights reserved.
* Copyright (c) 2004-2011 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) 2006 Sandia National Laboratories. All rights
* reserved.
btl/usnic: remove all calls to abort() Inspired by https://github.com/open-mpi/ompi/pull/5205, finally remove all calls to abort() from the usnic BTL. Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
2018-05-31 13:47:52 +03:00
* Copyright (c) 2008-2019 Cisco Systems, Inc. All rights reserved
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
* Copyright (c) 2012 Los Alamos National Security, LLC. All rights
usnic: remove all trailing whitespace Style cleanup only; no code changes. This commit was SVN r32366.
2014-07-31 00:56:15 +04:00
* reserved.
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
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"
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
#include <unistd.h>
#include "opal_stdint.h"
#include "opal/mca/memchecker/base/base.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"
usnic: convert from verbs to libfabric (yay!) This commit represents the conversion of the usnic BTL from verbs to libfabric. For the moment, libfabric is embedded in Open MPI (currently in the usnic BTL). This is because the libfabric API is still changing, and also has not yet been released. Ultimately, this embedded copy of libfabric will likely disappear and the usnic BTL will rely on an external installation of libfabric. New configure options: * --with-libfabric: will cause configure to fail if libfabric support cannot be built * --without-libfabric: will prevent libfabric support from being built * --with-libfabric=DIR: use an external libfabric installation * --with-libfabric-libdir=LIBDIR: when paired with --with-libfabric=DIR, use LIBDIR for the libfabric installation library dir The --with-libnl3[-libdir] arguments are now gone.
2014-12-03 00:09:46 +03:00
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 04:47:28 +04:00
#include "opal/mca/btl/btl.h"
#include "opal/mca/btl/base/base.h"
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
#include "btl_usnic.h"
#include "btl_usnic_frag.h"
#include "btl_usnic_endpoint.h"
#include "btl_usnic_module.h"
#include "btl_usnic_proc.h"
#include "btl_usnic_ack.h"
#include "btl_usnic_recv.h"
#include "btl_usnic_util.h"
/*
usnic: remove all trailing whitespace Style cleanup only; no code changes. This commit was SVN r32366.
2014-07-31 00:56:15 +04:00
* We have received a segment, take action based on the
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
* packet type in the BTL header
*/
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
void opal_btl_usnic_recv_call(opal_btl_usnic_module_t *module,
opal_btl_usnic_recv_segment_t *seg,
usnic: convert from verbs to libfabric (yay!) This commit represents the conversion of the usnic BTL from verbs to libfabric. For the moment, libfabric is embedded in Open MPI (currently in the usnic BTL). This is because the libfabric API is still changing, and also has not yet been released. Ultimately, this embedded copy of libfabric will likely disappear and the usnic BTL will rely on an external installation of libfabric. New configure options: * --with-libfabric: will cause configure to fail if libfabric support cannot be built * --without-libfabric: will prevent libfabric support from being built * --with-libfabric=DIR: use an external libfabric installation * --with-libfabric-libdir=LIBDIR: when paired with --with-libfabric=DIR, use LIBDIR for the libfabric installation library dir The --with-libnl3[-libdir] arguments are now gone.
2014-12-03 00:09:46 +03:00
opal_btl_usnic_channel_t *channel)
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
{
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 04:47:28 +04:00
opal_btl_usnic_segment_t *bseg;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
mca_btl_active_message_callback_t* reg;
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_btl_usnic_endpoint_t *endpoint;
opal_btl_usnic_btl_chunk_header_t *chunk_hdr;
opal_btl_usnic_btl_header_t *hdr;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
uint32_t window_index;
new bookkeeping code should return value indicating whether packet is good or not. Authored-by: Reese Faucette <rfaucett@cisco.com> Should be included in usnic v1.7.3 roll-up CMR (refs trac:3760) This commit was SVN r29136. The following Trac tickets were found above: Ticket 3760 --> https://svn.open-mpi.org/trac/ompi/ticket/3760
2013-09-06 07:19:32 +04:00
int rc;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
#if MSGDEBUG1
usnic: convert from verbs to libfabric (yay!) This commit represents the conversion of the usnic BTL from verbs to libfabric. For the moment, libfabric is embedded in Open MPI (currently in the usnic BTL). This is because the libfabric API is still changing, and also has not yet been released. Ultimately, this embedded copy of libfabric will likely disappear and the usnic BTL will rely on an external installation of libfabric. New configure options: * --with-libfabric: will cause configure to fail if libfabric support cannot be built * --without-libfabric: will prevent libfabric support from being built * --with-libfabric=DIR: use an external libfabric installation * --with-libfabric-libdir=LIBDIR: when paired with --with-libfabric=DIR, use LIBDIR for the libfabric installation library dir The --with-libnl3[-libdir] arguments are now gone.
2014-12-03 00:09:46 +03:00
char local_ip[IPV4STRADDRLEN];
char remote_ip[IPV4STRADDRLEN];
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
#endif
bseg = &seg->rs_base;
Move all usNIC stats to _stats.c|h and export them as MPI_T pvars. This commit moves all the module stats into their own struct so that the stats only need to appear as a single line in the module_t definition, and then moves all the logic for reporting the stats into btl_usnic_stats.c|h. Further, the stats are now exported as MPI_T_BIND_NO_OBJECT entities (i.e., not bound to any particular MPI handle), and are marked as READONLY and CONTINUOUS. They currently all default to verbose level 5 ("Application tuner / detailed", according to https://svn.open-mpi.org/trac/ompi/wiki/MCAParamLevels). Most of the statistics are counters, but a small number are high watermark values. Due to how counters are reported via MPI_T, none of the counters are exported through MPI_T if the MCA param btl_usnic_stats_relative=1 (i.e., the module resets the stats back to zero at a given frequency). When MPI_T_pvar_handle_alloc() is invoked on any of these pvars, it will return a count that is equal to the number of active usnic BTL modules. The values returned for any given pvar (e.g., num_total_sends) are an array containing one value for each active usnic BTL module. The ordering of values in the array is both consistent across all usnic pvars and stable throughout a single job: array slot 0 corresponds to module X, array slot 1 corresponds to module Y, etc. Mapping which array slot corresponds to which underlying Linux usnic_X device works as follows: * The btl_usnic_devices MPI_T state pvar is associated with a btl_usnic_device MPI_T enum, and be obtained via MPI_T_pvar_get_info(). * If all usNIC pvars are of length N, the values [0,N) in the btl_usnic_device enum are associated with strings of the corresponding underlying Linux device. For exampe, to look up which Linux device is reported in all usNIC pvars' array slot 1, look up the int value 1 in the btl_usnic_devices enum. Its corresponding string value is underlying Linux device name (e.g., "usnic_1"). cmr=v1.7.4:subject="usnic BTL MPI_T pvars" This commit was SVN r29545.
2013-10-29 02:23:08 +04:00
++module->stats.num_total_recvs;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
/* Valgrind help */
usnic: convert from verbs to libfabric (yay!) This commit represents the conversion of the usnic BTL from verbs to libfabric. For the moment, libfabric is embedded in Open MPI (currently in the usnic BTL). This is because the libfabric API is still changing, and also has not yet been released. Ultimately, this embedded copy of libfabric will likely disappear and the usnic BTL will rely on an external installation of libfabric. New configure options: * --with-libfabric: will cause configure to fail if libfabric support cannot be built * --without-libfabric: will prevent libfabric support from being built * --with-libfabric=DIR: use an external libfabric installation * --with-libfabric-libdir=LIBDIR: when paired with --with-libfabric=DIR, use LIBDIR for the libfabric installation library dir The --with-libnl3[-libdir] arguments are now gone.
2014-12-03 00:09:46 +03:00
opal_memchecker_base_mem_defined((void*)(seg->rs_protocol_header),
seg->rs_len);
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
/* Find out who sent this segment */
usnic: Basket of performance changes including: - round segment buffer allocation to cache-line - split some routines into an inline fast section and a called slower section - introduce receive fastpath in component_progress that: o returns immediately if there is a packet available on priority queue and fastpath is enabled o disables fastpath for 1 time after use to provide fairness to other processing o defers receive buffer posting o defers bookeeping for receive until next call to usnic_component_progress Authored-by: Reese Faucette <rfaucett@cisco.com> Should be included in usnic v1.7.3 roll-up CMR (refs trac:3760) This commit was SVN r29133. The following Trac tickets were found above: Ticket 3760 --> https://svn.open-mpi.org/trac/ompi/ticket/3760
2013-09-06 07:18:57 +04:00
endpoint = seg->rs_endpoint;
usnic: minor code cleanups
2015-07-10 20:09:15 +03:00
if (FAKE_RECV_DROP || OPAL_UNLIKELY(NULL == endpoint)) {
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
/* No idea who this was from, so drop it */
#if MSGDEBUG1
usnic: convert from verbs to libfabric (yay!) This commit represents the conversion of the usnic BTL from verbs to libfabric. For the moment, libfabric is embedded in Open MPI (currently in the usnic BTL). This is because the libfabric API is still changing, and also has not yet been released. Ultimately, this embedded copy of libfabric will likely disappear and the usnic BTL will rely on an external installation of libfabric. New configure options: * --with-libfabric: will cause configure to fail if libfabric support cannot be built * --without-libfabric: will prevent libfabric support from being built * --with-libfabric=DIR: use an external libfabric installation * --with-libfabric-libdir=LIBDIR: when paired with --with-libfabric=DIR, use LIBDIR for the libfabric installation library dir The --with-libnl3[-libdir] arguments are now gone.
2014-12-03 00:09:46 +03:00
opal_output(0, "=== Unknown sender; dropped: seq %" UDSEQ,
usnic: Shrink sequence numbers to 16 bits Authored-by: Reese Faucette <rfaucett@cisco.com> Reviewed-by: Jeff Squyres <jsquyres@cisco.com> cmr=v1.7.5:ticket=trac:4253 This commit was SVN r30834. The following Trac tickets were found above: Ticket 4253 --> https://svn.open-mpi.org/trac/ompi/ticket/4253
2014-02-26 11:40:10 +04:00
bseg->us_btl_header->pkt_seq);
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
#endif
Move all usNIC stats to _stats.c|h and export them as MPI_T pvars. This commit moves all the module stats into their own struct so that the stats only need to appear as a single line in the module_t definition, and then moves all the logic for reporting the stats into btl_usnic_stats.c|h. Further, the stats are now exported as MPI_T_BIND_NO_OBJECT entities (i.e., not bound to any particular MPI handle), and are marked as READONLY and CONTINUOUS. They currently all default to verbose level 5 ("Application tuner / detailed", according to https://svn.open-mpi.org/trac/ompi/wiki/MCAParamLevels). Most of the statistics are counters, but a small number are high watermark values. Due to how counters are reported via MPI_T, none of the counters are exported through MPI_T if the MCA param btl_usnic_stats_relative=1 (i.e., the module resets the stats back to zero at a given frequency). When MPI_T_pvar_handle_alloc() is invoked on any of these pvars, it will return a count that is equal to the number of active usnic BTL modules. The values returned for any given pvar (e.g., num_total_sends) are an array containing one value for each active usnic BTL module. The ordering of values in the array is both consistent across all usnic pvars and stable throughout a single job: array slot 0 corresponds to module X, array slot 1 corresponds to module Y, etc. Mapping which array slot corresponds to which underlying Linux usnic_X device works as follows: * The btl_usnic_devices MPI_T state pvar is associated with a btl_usnic_device MPI_T enum, and be obtained via MPI_T_pvar_get_info(). * If all usNIC pvars are of length N, the values [0,N) in the btl_usnic_device enum are associated with strings of the corresponding underlying Linux device. For exampe, to look up which Linux device is reported in all usNIC pvars' array slot 1, look up the int value 1 in the btl_usnic_devices enum. Its corresponding string value is underlying Linux device name (e.g., "usnic_1"). cmr=v1.7.4:subject="usnic BTL MPI_T pvars" This commit was SVN r29545.
2013-10-29 02:23:08 +04:00
++module->stats.num_unk_recvs;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
goto repost_no_endpoint;
}
usnic: convert from verbs to libfabric (yay!) This commit represents the conversion of the usnic BTL from verbs to libfabric. For the moment, libfabric is embedded in Open MPI (currently in the usnic BTL). This is because the libfabric API is still changing, and also has not yet been released. Ultimately, this embedded copy of libfabric will likely disappear and the usnic BTL will rely on an external installation of libfabric. New configure options: * --with-libfabric: will cause configure to fail if libfabric support cannot be built * --without-libfabric: will prevent libfabric support from being built * --with-libfabric=DIR: use an external libfabric installation * --with-libfabric-libdir=LIBDIR: when paired with --with-libfabric=DIR, use LIBDIR for the libfabric installation library dir The --with-libnl3[-libdir] arguments are now gone.
2014-12-03 00:09:46 +03:00
#if MSGDEBUG1
struct opal_btl_usnic_modex_t *modex;
modex = &module->local_modex;
opal_btl_usnic_snprintf_ipv4_addr(local_ip, sizeof(local_ip),
modex->ipv4_addr,
modex->netmask);
modex = &endpoint->endpoint_remote_modex;
opal_btl_usnic_snprintf_ipv4_addr(remote_ip, sizeof(remote_ip),
modex->ipv4_addr,
modex->netmask);
#endif
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
/***********************************************************************/
/* Segment is an incoming frag */
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
if (OPAL_BTL_USNIC_PAYLOAD_TYPE_FRAG == bseg->us_btl_header->payload_type) {
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
usnic: "bookeeping" --> "bookkeeping" Should be included in usnic v1.7.3 roll-up CMR (refs trac:3760) This commit was SVN r29135. The following Trac tickets were found above: Ticket 3760 --> https://svn.open-mpi.org/trac/ompi/ticket/3760
2013-09-06 07:19:20 +04:00
/* do the receive bookkeeping */
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
rc = opal_btl_usnic_recv_frag_bookkeeping(module, seg, channel);
new bookkeeping code should return value indicating whether packet is good or not. Authored-by: Reese Faucette <rfaucett@cisco.com> Should be included in usnic v1.7.3 roll-up CMR (refs trac:3760) This commit was SVN r29136. The following Trac tickets were found above: Ticket 3760 --> https://svn.open-mpi.org/trac/ompi/ticket/3760
2013-09-06 07:19:32 +04:00
if (rc != 0) {
return;
}
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
Cisco CSCuj12520: various problems running c_fence_put_1 - tag needs to be sent in *our* header, not the PML header - usnic_alloc() should return smaller value if too much data requested - be careful about callbacks vs removing items from lists (we need to remove from outr lists *before* the callback) - improve send callback handling - add some more MSGDEBUG2 logging and cleanup This commit was SVN r29181.
2013-09-17 11:20:44 +04:00
hdr = seg->rs_base.us_btl_header;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
#if MSGDEBUG1
opal_output(0, "<-- Received FRAG ep %p, seq %" UDSEQ ", len=%d\n",
usnic: Shrink sequence numbers to 16 bits Authored-by: Reese Faucette <rfaucett@cisco.com> Reviewed-by: Jeff Squyres <jsquyres@cisco.com> cmr=v1.7.5:ticket=trac:4253 This commit was SVN r30834. The following Trac tickets were found above: Ticket 4253 --> https://svn.open-mpi.org/trac/ompi/ticket/4253
2014-02-26 11:40:10 +04:00
(void*) endpoint, hdr->pkt_seq, hdr->payload_len);
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
#if 0
opal_output(0, "<-- Received FRAG ep %p, seq %" UDSEQ " from %s to %s: GOOD! (rel seq %d, lowest seq %" UDSEQ ", highest seq: %" UDSEQ ", rwstart %d) seg %p, module %p\n",
(void*) endpoint,
usnic: Shrink sequence numbers to 16 bits Authored-by: Reese Faucette <rfaucett@cisco.com> Reviewed-by: Jeff Squyres <jsquyres@cisco.com> cmr=v1.7.5:ticket=trac:4253 This commit was SVN r30834. The following Trac tickets were found above: Ticket 4253 --> https://svn.open-mpi.org/trac/ompi/ticket/4253
2014-02-26 11:40:10 +04:00
seg->rs_base.us_btl_header->pkt_seq,
usnic: convert from verbs to libfabric (yay!) This commit represents the conversion of the usnic BTL from verbs to libfabric. For the moment, libfabric is embedded in Open MPI (currently in the usnic BTL). This is because the libfabric API is still changing, and also has not yet been released. Ultimately, this embedded copy of libfabric will likely disappear and the usnic BTL will rely on an external installation of libfabric. New configure options: * --with-libfabric: will cause configure to fail if libfabric support cannot be built * --without-libfabric: will prevent libfabric support from being built * --with-libfabric=DIR: use an external libfabric installation * --with-libfabric-libdir=LIBDIR: when paired with --with-libfabric=DIR, use LIBDIR for the libfabric installation library dir The --with-libnl3[-libdir] arguments are now gone.
2014-12-03 00:09:46 +03:00
remote_ip, local_ip,
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
window_index,
endpoint->endpoint_next_contig_seq_to_recv,
endpoint->endpoint_highest_seq_rcvd,
endpoint->endpoint_rfstart,
(void*) seg, (void*) module);
Cisco CSCuj12520: various problems running c_fence_put_1 - tag needs to be sent in *our* header, not the PML header - usnic_alloc() should return smaller value if too much data requested - be careful about callbacks vs removing items from lists (we need to remove from outr lists *before* the callback) - improve send callback handling - add some more MSGDEBUG2 logging and cleanup This commit was SVN r29181.
2013-09-17 11:20:44 +04:00
if (hdr->put_addr != NULL) {
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
opal_output(0, " put_addr = %p\n",
seg->rs_base.us_btl_header->put_addr);
}
#endif
#endif
/* If this it not a PUT, Pass this segment up to the PML.
* Be sure to get the payload length from the BTL header because
* the L2 layer may artificially inflate (or otherwise change)
* the frame length to meet minimum sizes, add protocol information,
* etc.
*/
Cisco CSCuj12520: various problems running c_fence_put_1 - tag needs to be sent in *our* header, not the PML header - usnic_alloc() should return smaller value if too much data requested - be careful about callbacks vs removing items from lists (we need to remove from outr lists *before* the callback) - improve send callback handling - add some more MSGDEBUG2 logging and cleanup This commit was SVN r29181.
2013-09-17 11:20:44 +04:00
if (hdr->put_addr == NULL) {
reg = mca_btl_base_active_message_trigger + hdr->tag;
seg->rs_segment.seg_len = hdr->payload_len;
Clean up debugging logging a bit. MSGDEBUG2 now means "print a one-liner for all PML calls into BTL, and also when BTL calls PML with a recv completion (not send completions)" MSGDEBUG1 means print more internal gory detail MSGDEBUG is gone, replaced by MSGDEBUG1 In the process also found that PUT_DEST style fragments could potentially be leaked in usnic_free() since send_fragment tests were being applied to see if it was eligible to be freed. This commit was SVN r29185.
2013-09-17 11:29:40 +04:00
#if MSGDEBUG2
opal_output(0, "small recv complete, pass up %u bytes, tag=%d\n",
(unsigned)bseg->us_btl_header->payload_len,
(int)bseg->us_btl_header->tag);
#endif
Cisco CSCuj12520: various problems running c_fence_put_1 - tag needs to be sent in *our* header, not the PML header - usnic_alloc() should return smaller value if too much data requested - be careful about callbacks vs removing items from lists (we need to remove from outr lists *before* the callback) - improve send callback handling - add some more MSGDEBUG2 logging and cleanup This commit was SVN r29181.
2013-09-17 11:20:44 +04:00
reg->cbfunc(&module->super, hdr->tag, &seg->rs_desc, reg->cbdata);
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
/*
* If this is a PUT, need to copy it to user buffer
*/
} else {
#if MSGDEBUG1
usnic: remove all trailing whitespace Style cleanup only; no code changes. This commit was SVN r32366.
2014-07-31 00:56:15 +04:00
opal_output(0, "Copy %d PUT bytes to %p\n",
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
seg->rs_base.us_btl_header->payload_len,
usnic: stomp format specifier warnings The usnic BTL now builds cleanly under `--enable-picky` when `MSGDEBUG1` is set. Reviewed-by: jsquyres cmr=v1.7.4:reviewer=jsquyres This commit was SVN r29097.
2013-08-30 03:24:14 +04:00
(void*)seg->rs_base.us_btl_header->put_addr);
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
#endif
memcpy(seg->rs_base.us_btl_header->put_addr,
seg->rs_base.us_payload.raw,
seg->rs_base.us_btl_header->payload_len);
}
usnic: "bookeeping" --> "bookkeeping" Should be included in usnic v1.7.3 roll-up CMR (refs trac:3760) This commit was SVN r29135. The following Trac tickets were found above: Ticket 3760 --> https://svn.open-mpi.org/trac/ompi/ticket/3760
2013-09-06 07:19:20 +04:00
/* do not jump to repost, already done by bookkeeping */
usnic: Basket of performance changes including: - round segment buffer allocation to cache-line - split some routines into an inline fast section and a called slower section - introduce receive fastpath in component_progress that: o returns immediately if there is a packet available on priority queue and fastpath is enabled o disables fastpath for 1 time after use to provide fairness to other processing o defers receive buffer posting o defers bookeeping for receive until next call to usnic_component_progress Authored-by: Reese Faucette <rfaucett@cisco.com> Should be included in usnic v1.7.3 roll-up CMR (refs trac:3760) This commit was SVN r29133. The following Trac tickets were found above: Ticket 3760 --> https://svn.open-mpi.org/trac/ompi/ticket/3760
2013-09-06 07:18:57 +04:00
return;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
}
/***********************************************************************/
/* Segment is an incoming chunk */
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
if (OPAL_BTL_USNIC_PAYLOAD_TYPE_CHUNK == bseg->us_btl_header->payload_type) {
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
int frag_index;
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_btl_usnic_rx_frag_info_t *fip;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
/* Is incoming sequence # ok? */
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
if (OPAL_UNLIKELY(opal_btl_usnic_check_rx_seq(endpoint, seg,
new bookkeeping code should return value indicating whether packet is good or not. Authored-by: Reese Faucette <rfaucett@cisco.com> Should be included in usnic v1.7.3 roll-up CMR (refs trac:3760) This commit was SVN r29136. The following Trac tickets were found above: Ticket 3760 --> https://svn.open-mpi.org/trac/ompi/ticket/3760
2013-09-06 07:19:32 +04:00
&window_index) != 0)) {
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
goto repost;
}
#if MSGDEBUG1
opal_output(0, "<-- Received CHUNK fid %d ep %p, seq %" UDSEQ " from %s to %s: GOOD! (rel seq %d, lowest seq %" UDSEQ ", highest seq: %" UDSEQ ", rwstart %d) seg %p, module %p\n",
seg->rs_base.us_btl_chunk_header->ch_frag_id,
(void*) endpoint,
usnic: Shrink sequence numbers to 16 bits Authored-by: Reese Faucette <rfaucett@cisco.com> Reviewed-by: Jeff Squyres <jsquyres@cisco.com> cmr=v1.7.5:ticket=trac:4253 This commit was SVN r30834. The following Trac tickets were found above: Ticket 4253 --> https://svn.open-mpi.org/trac/ompi/ticket/4253
2014-02-26 11:40:10 +04:00
seg->rs_base.us_btl_chunk_header->ch_hdr.pkt_seq,
usnic: convert from verbs to libfabric (yay!) This commit represents the conversion of the usnic BTL from verbs to libfabric. For the moment, libfabric is embedded in Open MPI (currently in the usnic BTL). This is because the libfabric API is still changing, and also has not yet been released. Ultimately, this embedded copy of libfabric will likely disappear and the usnic BTL will rely on an external installation of libfabric. New configure options: * --with-libfabric: will cause configure to fail if libfabric support cannot be built * --without-libfabric: will prevent libfabric support from being built * --with-libfabric=DIR: use an external libfabric installation * --with-libfabric-libdir=LIBDIR: when paired with --with-libfabric=DIR, use LIBDIR for the libfabric installation library dir The --with-libnl3[-libdir] arguments are now gone.
2014-12-03 00:09:46 +03:00
remote_ip, local_ip,
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
window_index,
endpoint->endpoint_next_contig_seq_to_recv,
endpoint->endpoint_highest_seq_rcvd,
endpoint->endpoint_rfstart,
(void*) seg, (void*) module);
#endif
/* start a new fragment if not one in progress
* alloc memory, etc. when last byte arrives, dealloc the
* frag_id and pass data to PML
*/
chunk_hdr = seg->rs_base.us_btl_chunk_header;
frag_index = chunk_hdr->ch_frag_id % MAX_ACTIVE_FRAGS;
fip = &(endpoint->endpoint_rx_frag_info[frag_index]);
/* frag_id == 0 means this slot it empty, grab it! */
if (0 == fip->rfi_frag_id) {
fip->rfi_frag_id = chunk_hdr->ch_frag_id;
fip->rfi_frag_size = chunk_hdr->ch_frag_size;
if (chunk_hdr->ch_hdr.put_addr == NULL) {
int pool;
fip->rfi_data = NULL;
/* See which data pool this should come from,
* or if it should be malloc()ed
*/
usnic: fix 'fls' warnings+errors The old version caused compilation errors on Solaris. Thanks to Paul Hargrove for testing and reporting the bug: http://www.open-mpi.org/community/lists/devel/2013/12/13520.php cmr=v1.7.4:reviewer=jsquyres This commit was SVN r30025.
2013-12-20 21:37:22 +04:00
pool = usnic_fls(chunk_hdr->ch_frag_size-1);
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
if (pool >= module->first_pool &&
pool <= module->last_pool) {
usnic: update to new mpool API NOTE: Have not added cross-compatibility with v1.8 branch yet
2015-02-23 19:07:45 +03:00
opal_free_list_item_t* item;
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_btl_usnic_rx_buf_t *rx_buf;
usnic: restore compatibility with the v1.8 branch Also include two other minor changes: 1. More C99-style member initialization in the component struct 1. Fix the BTL module member initialization to not be redundant
2015-02-25 16:37:51 +03:00
USNIC_COMPAT_FREE_LIST_GET(&module->module_recv_buffers[pool], item);
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
rx_buf = (opal_btl_usnic_rx_buf_t *)item;
usnic: fix module_recv_buffers perf regression Cisco v1.6 git commit 913ec6c and upstream trunk r29593 (segfault fix) introduced a performance regression by inadvertently disabling the `module_recv_buffers` functionality. With those changes in place, the `btl_usnic_recv.c` logic would end up mallocing a buffer that should have otherwise come from a `module_recv_buffers` pool. It also resulted in a small, bounded memory leak (128 buffers at each power-of-two size interval). The new version just places the buffer after the free list item with a flexible array member. I bumped the pool to allocate all 128 elements up front because the deferred allocation was modestly impacting IMB Sendrecv performance at a few sizes. Reviewed-by: Reese Faucette <rfaucett@cisco.com> This commit was SVN r29631. The following SVN revision numbers were found above: r29593 --> open-mpi/ompi@1ed9b8ff437ccae973d78df593283eb224e58510
2013-11-07 05:27:31 +04:00
if (OPAL_LIKELY(NULL != rx_buf)) {
usnic: fix segfault at finalize time Without this commit, if you run IMB pingpong between two nodes with only one usnic selected (e.g., via `--mca btl_usnic_if_include usnic_0`) then the run will seem fine but will segfault at MPI_Finalize time. This behavior has happened since Cisco v1.6 git commit ec7ddf8, upstream trunk r29484, and upstream v1.7 r29507. Root cause was that the free list element was being used as the recv buffer instead of the data buffer associated with the element. So the reassembly code would stomp all over the free list element, which would cause the destructor to explode when the free list attempted to clean up all of its elements. This surprisingly did not cause any other problems until now. Reviewed-by: Reese Faucette <rfaucett@cisco.com> This commit was SVN r29593. The following SVN revision numbers were found above: r29484 --> open-mpi/ompi@a6ed232a1076b784e8c6b500a6b46b8f760bbf4d r29507 --> open-mpi/ompi@790d269ce8dd390cff0dec3690f1d226e60457f6
2013-11-05 02:52:14 +04:00
fip->rfi_fl_elt = item;
usnic: fix module_recv_buffers perf regression Cisco v1.6 git commit 913ec6c and upstream trunk r29593 (segfault fix) introduced a performance regression by inadvertently disabling the `module_recv_buffers` functionality. With those changes in place, the `btl_usnic_recv.c` logic would end up mallocing a buffer that should have otherwise come from a `module_recv_buffers` pool. It also resulted in a small, bounded memory leak (128 buffers at each power-of-two size interval). The new version just places the buffer after the free list item with a flexible array member. I bumped the pool to allocate all 128 elements up front because the deferred allocation was modestly impacting IMB Sendrecv performance at a few sizes. Reviewed-by: Reese Faucette <rfaucett@cisco.com> This commit was SVN r29631. The following SVN revision numbers were found above: r29593 --> open-mpi/ompi@1ed9b8ff437ccae973d78df593283eb224e58510
2013-11-07 05:27:31 +04:00
fip->rfi_data = rx_buf->buf;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
fip->rfi_data_pool = pool;
usnic: properly differentiate data pool vs. malloc usnic_fls() can actually return 0, leading us to incorrectly free() a buffer instead of OMPI_FREE_LIST_RETURN_MT'ing it. So add an explicit bool in the struct that tracks whether the buffer came from malloc or a freelist. This was CID 1269660.
2015-02-12 22:15:58 +03:00
fip->rfi_data_in_pool = true;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
}
}
if (fip->rfi_data == NULL) {
fip->rfi_data = malloc(chunk_hdr->ch_frag_size);
usnic: properly differentiate data pool vs. malloc usnic_fls() can actually return 0, leading us to incorrectly free() a buffer instead of OMPI_FREE_LIST_RETURN_MT'ing it. So add an explicit bool in the struct that tracks whether the buffer came from malloc or a freelist. This was CID 1269660.
2015-02-12 22:15:58 +03:00
fip->rfi_data_in_pool = false;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
}
if (fip->rfi_data == NULL) {
btl/usnic: remove all calls to abort() Inspired by https://github.com/open-mpi/ompi/pull/5205, finally remove all calls to abort() from the usnic BTL. Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
2018-05-31 13:47:52 +03:00
opal_btl_usnic_util_abort("malloc failed", __FILE__, __LINE__);
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
}
Clean up debugging logging a bit. MSGDEBUG2 now means "print a one-liner for all PML calls into BTL, and also when BTL calls PML with a recv completion (not send completions)" MSGDEBUG1 means print more internal gory detail MSGDEBUG is gone, replaced by MSGDEBUG1 In the process also found that PUT_DEST style fragments could potentially be leaked in usnic_free() since send_fragment tests were being applied to see if it was eligible to be freed. This commit was SVN r29185.
2013-09-17 11:29:40 +04:00
#if MSGDEBUG1
usnic: SEGV in OSU benchmarks Prevent frag from being freed out from under us in the case the PML callback routine calls usnic_free(). We accomplish this by delaying decrement of sf_bytes_to_ack until after the callback is performed, since sf_bytes_to_ack == 0 is condition of freeing the frag. Fixes Cisco bug CSCuj45094. Authored-by: Reese Faucette <rfaucett@cisco.com> cmr=v1.7.3 This commit was SVN r29264.
2013-09-27 01:48:04 +04:00
opal_output(0, "Start large recv to %p, size=%"PRIu32"\n",
(void *)fip->rfi_data, chunk_hdr->ch_frag_size);
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
#endif
} else {
Clean up debugging logging a bit. MSGDEBUG2 now means "print a one-liner for all PML calls into BTL, and also when BTL calls PML with a recv completion (not send completions)" MSGDEBUG1 means print more internal gory detail MSGDEBUG is gone, replaced by MSGDEBUG1 In the process also found that PUT_DEST style fragments could potentially be leaked in usnic_free() since send_fragment tests were being applied to see if it was eligible to be freed. This commit was SVN r29185.
2013-09-17 11:29:40 +04:00
#if MSGDEBUG1
usnic: SEGV in OSU benchmarks Prevent frag from being freed out from under us in the case the PML callback routine calls usnic_free(). We accomplish this by delaying decrement of sf_bytes_to_ack until after the callback is performed, since sf_bytes_to_ack == 0 is condition of freeing the frag. Fixes Cisco bug CSCuj45094. Authored-by: Reese Faucette <rfaucett@cisco.com> cmr=v1.7.3 This commit was SVN r29264.
2013-09-27 01:48:04 +04:00
opal_output(0, "Start PUT to %p\n",
(void *)chunk_hdr->ch_hdr.put_addr);
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
#endif
fip->rfi_data = chunk_hdr->ch_hdr.put_addr;
}
fip->rfi_bytes_left = chunk_hdr->ch_frag_size;
fip->rfi_frag_id = chunk_hdr->ch_frag_id;
/* frag_id is not 0 - it must match, drop if not */
} else if (fip->rfi_frag_id != chunk_hdr->ch_frag_id) {
Move all usNIC stats to _stats.c|h and export them as MPI_T pvars. This commit moves all the module stats into their own struct so that the stats only need to appear as a single line in the module_t definition, and then moves all the logic for reporting the stats into btl_usnic_stats.c|h. Further, the stats are now exported as MPI_T_BIND_NO_OBJECT entities (i.e., not bound to any particular MPI handle), and are marked as READONLY and CONTINUOUS. They currently all default to verbose level 5 ("Application tuner / detailed", according to https://svn.open-mpi.org/trac/ompi/wiki/MCAParamLevels). Most of the statistics are counters, but a small number are high watermark values. Due to how counters are reported via MPI_T, none of the counters are exported through MPI_T if the MCA param btl_usnic_stats_relative=1 (i.e., the module resets the stats back to zero at a given frequency). When MPI_T_pvar_handle_alloc() is invoked on any of these pvars, it will return a count that is equal to the number of active usnic BTL modules. The values returned for any given pvar (e.g., num_total_sends) are an array containing one value for each active usnic BTL module. The ordering of values in the array is both consistent across all usnic pvars and stable throughout a single job: array slot 0 corresponds to module X, array slot 1 corresponds to module Y, etc. Mapping which array slot corresponds to which underlying Linux usnic_X device works as follows: * The btl_usnic_devices MPI_T state pvar is associated with a btl_usnic_device MPI_T enum, and be obtained via MPI_T_pvar_get_info(). * If all usNIC pvars are of length N, the values [0,N) in the btl_usnic_device enum are associated with strings of the corresponding underlying Linux device. For exampe, to look up which Linux device is reported in all usNIC pvars' array slot 1, look up the int value 1 in the btl_usnic_devices enum. Its corresponding string value is underlying Linux device name (e.g., "usnic_1"). cmr=v1.7.4:subject="usnic BTL MPI_T pvars" This commit was SVN r29545.
2013-10-29 02:23:08 +04:00
++module->stats.num_badfrag_recvs;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
goto repost;
}
#if MSGDEBUG1
opal_output(0, "put_addr=%p, copy_addr=%p, off=%d\n",
chunk_hdr->ch_hdr.put_addr,
fip->rfi_data+chunk_hdr->ch_frag_offset,
chunk_hdr->ch_frag_offset);
#endif
/* Stats */
Move all usNIC stats to _stats.c|h and export them as MPI_T pvars. This commit moves all the module stats into their own struct so that the stats only need to appear as a single line in the module_t definition, and then moves all the logic for reporting the stats into btl_usnic_stats.c|h. Further, the stats are now exported as MPI_T_BIND_NO_OBJECT entities (i.e., not bound to any particular MPI handle), and are marked as READONLY and CONTINUOUS. They currently all default to verbose level 5 ("Application tuner / detailed", according to https://svn.open-mpi.org/trac/ompi/wiki/MCAParamLevels). Most of the statistics are counters, but a small number are high watermark values. Due to how counters are reported via MPI_T, none of the counters are exported through MPI_T if the MCA param btl_usnic_stats_relative=1 (i.e., the module resets the stats back to zero at a given frequency). When MPI_T_pvar_handle_alloc() is invoked on any of these pvars, it will return a count that is equal to the number of active usnic BTL modules. The values returned for any given pvar (e.g., num_total_sends) are an array containing one value for each active usnic BTL module. The ordering of values in the array is both consistent across all usnic pvars and stable throughout a single job: array slot 0 corresponds to module X, array slot 1 corresponds to module Y, etc. Mapping which array slot corresponds to which underlying Linux usnic_X device works as follows: * The btl_usnic_devices MPI_T state pvar is associated with a btl_usnic_device MPI_T enum, and be obtained via MPI_T_pvar_get_info(). * If all usNIC pvars are of length N, the values [0,N) in the btl_usnic_device enum are associated with strings of the corresponding underlying Linux device. For exampe, to look up which Linux device is reported in all usNIC pvars' array slot 1, look up the int value 1 in the btl_usnic_devices enum. Its corresponding string value is underlying Linux device name (e.g., "usnic_1"). cmr=v1.7.4:subject="usnic BTL MPI_T pvars" This commit was SVN r29545.
2013-10-29 02:23:08 +04:00
++module->stats.num_chunk_recvs;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
/* validate offset and len to be within fragment */
assert(chunk_hdr->ch_frag_offset + chunk_hdr->ch_hdr.payload_len <=
fip->rfi_frag_size);
assert(fip->rfi_frag_size == chunk_hdr->ch_frag_size);
/* copy the data into place */
memcpy(fip->rfi_data + chunk_hdr->ch_frag_offset, (char *)(chunk_hdr+1),
chunk_hdr->ch_hdr.payload_len);
/* update sliding window */
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_btl_usnic_update_window(endpoint, window_index);
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
fip->rfi_bytes_left -= chunk_hdr->ch_hdr.payload_len;
if (0 == fip->rfi_bytes_left) {
mca_btl_base_descriptor_t desc;
mca_btl_base_segment_t segment;
Cisco CSCuj12520: various problems running c_fence_put_1 - tag needs to be sent in *our* header, not the PML header - usnic_alloc() should return smaller value if too much data requested - be careful about callbacks vs removing items from lists (we need to remove from outr lists *before* the callback) - improve send callback handling - add some more MSGDEBUG2 logging and cleanup This commit was SVN r29181.
2013-09-17 11:20:44 +04:00
segment.seg_addr.pval = fip->rfi_data;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
segment.seg_len = fip->rfi_frag_size;
usnic: convert from verbs to libfabric (yay!) This commit represents the conversion of the usnic BTL from verbs to libfabric. For the moment, libfabric is embedded in Open MPI (currently in the usnic BTL). This is because the libfabric API is still changing, and also has not yet been released. Ultimately, this embedded copy of libfabric will likely disappear and the usnic BTL will rely on an external installation of libfabric. New configure options: * --with-libfabric: will cause configure to fail if libfabric support cannot be built * --without-libfabric: will prevent libfabric support from being built * --with-libfabric=DIR: use an external libfabric installation * --with-libfabric-libdir=LIBDIR: when paired with --with-libfabric=DIR, use LIBDIR for the libfabric installation library dir The --with-libnl3[-libdir] arguments are now gone.
2014-12-03 00:09:46 +03:00
desc.USNIC_RECV_LOCAL = &segment;
desc.USNIC_RECV_LOCAL_COUNT = 1;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
/* only up to PML if this was not a put */
if (chunk_hdr->ch_hdr.put_addr == NULL) {
/* Pass this segment up to the PML */
#if MSGDEBUG2
Clean up debugging logging a bit. MSGDEBUG2 now means "print a one-liner for all PML calls into BTL, and also when BTL calls PML with a recv completion (not send completions)" MSGDEBUG1 means print more internal gory detail MSGDEBUG is gone, replaced by MSGDEBUG1 In the process also found that PUT_DEST style fragments could potentially be leaked in usnic_free() since send_fragment tests were being applied to see if it was eligible to be freed. This commit was SVN r29185.
2013-09-17 11:29:40 +04:00
opal_output(0, "large recv complete, pass up %p, %u bytes, tag=%d\n",
usnic: convert from verbs to libfabric (yay!) This commit represents the conversion of the usnic BTL from verbs to libfabric. For the moment, libfabric is embedded in Open MPI (currently in the usnic BTL). This is because the libfabric API is still changing, and also has not yet been released. Ultimately, this embedded copy of libfabric will likely disappear and the usnic BTL will rely on an external installation of libfabric. New configure options: * --with-libfabric: will cause configure to fail if libfabric support cannot be built * --without-libfabric: will prevent libfabric support from being built * --with-libfabric=DIR: use an external libfabric installation * --with-libfabric-libdir=LIBDIR: when paired with --with-libfabric=DIR, use LIBDIR for the libfabric installation library dir The --with-libnl3[-libdir] arguments are now gone.
2014-12-03 00:09:46 +03:00
desc.USNIC_RECV_LOCAL->seg_addr.pval,
(unsigned)desc.USNIC_RECV_LOCAL->seg_len,
Cisco CSCuj13135: Data corruption in MPI_Bsend_ator_c Do not assume that the "size" passed to alloc_send() will be the same as the size of the message the resulting fragment will hold when usnic_send() is called. This means usnic_send()/usnic_put() can never trust any pre-computed size values, and are only allowed to look at the lengths and pointers of the elements in the desc SG list. This commit was SVN r29183.
2013-09-17 11:25:05 +04:00
(int)chunk_hdr->ch_hdr.tag);
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
#endif
Cisco CSCuj12520: various problems running c_fence_put_1 - tag needs to be sent in *our* header, not the PML header - usnic_alloc() should return smaller value if too much data requested - be careful about callbacks vs removing items from lists (we need to remove from outr lists *before* the callback) - improve send callback handling - add some more MSGDEBUG2 logging and cleanup This commit was SVN r29181.
2013-09-17 11:20:44 +04:00
reg = mca_btl_base_active_message_trigger +
chunk_hdr->ch_hdr.tag;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
/* mca_pml_ob1_recv_frag_callback_frag() */
Cisco CSCuj12520: various problems running c_fence_put_1 - tag needs to be sent in *our* header, not the PML header - usnic_alloc() should return smaller value if too much data requested - be careful about callbacks vs removing items from lists (we need to remove from outr lists *before* the callback) - improve send callback handling - add some more MSGDEBUG2 logging and cleanup This commit was SVN r29181.
2013-09-17 11:20:44 +04:00
reg->cbfunc(&module->super, chunk_hdr->ch_hdr.tag,
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
&desc, reg->cbdata);
/* free temp buffer for non-put */
usnic: properly differentiate data pool vs. malloc usnic_fls() can actually return 0, leading us to incorrectly free() a buffer instead of OMPI_FREE_LIST_RETURN_MT'ing it. So add an explicit bool in the struct that tracks whether the buffer came from malloc or a freelist. This was CID 1269660.
2015-02-12 22:15:58 +03:00
if (fip->rfi_data_in_pool) {
usnic: restore compatibility with the v1.8 branch Also include two other minor changes: 1. More C99-style member initialization in the component struct 1. Fix the BTL module member initialization to not be redundant
2015-02-25 16:37:51 +03:00
USNIC_COMPAT_FREE_LIST_RETURN(&module->module_recv_buffers[fip->rfi_data_pool],
fip->rfi_fl_elt);
usnic: properly differentiate data pool vs. malloc usnic_fls() can actually return 0, leading us to incorrectly free() a buffer instead of OMPI_FREE_LIST_RETURN_MT'ing it. So add an explicit bool in the struct that tracks whether the buffer came from malloc or a freelist. This was CID 1269660.
2015-02-12 22:15:58 +03:00
} else {
free(fip->rfi_data);
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
}
Clean up debugging logging a bit. MSGDEBUG2 now means "print a one-liner for all PML calls into BTL, and also when BTL calls PML with a recv completion (not send completions)" MSGDEBUG1 means print more internal gory detail MSGDEBUG is gone, replaced by MSGDEBUG1 In the process also found that PUT_DEST style fragments could potentially be leaked in usnic_free() since send_fragment tests were being applied to see if it was eligible to be freed. This commit was SVN r29185.
2013-09-17 11:29:40 +04:00
#if MSGDEBUG1
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
} else {
Clean up debugging logging a bit. MSGDEBUG2 now means "print a one-liner for all PML calls into BTL, and also when BTL calls PML with a recv completion (not send completions)" MSGDEBUG1 means print more internal gory detail MSGDEBUG is gone, replaced by MSGDEBUG1 In the process also found that PUT_DEST style fragments could potentially be leaked in usnic_free() since send_fragment tests were being applied to see if it was eligible to be freed. This commit was SVN r29185.
2013-09-17 11:29:40 +04:00
opal_output(0, "PUT recv complete, no callback\n");
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
#endif
}
/* release the fragment ID */
fip->rfi_frag_id = 0;
/* force immediate ACK */
endpoint->endpoint_acktime = 0;
}
goto repost;
}
/***********************************************************************/
/* Frag is an incoming ACK */
usnic: remove all trailing whitespace Style cleanup only; no code changes. This commit was SVN r32366.
2014-07-31 00:56:15 +04:00
else if (OPAL_LIKELY(OPAL_BTL_USNIC_PAYLOAD_TYPE_ACK ==
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
bseg->us_btl_header->payload_type)) {
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_btl_usnic_seq_t ack_seq;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
/* sequence being ACKed */
ack_seq = bseg->us_btl_header->ack_seq;
/* Stats */
Move all usNIC stats to _stats.c|h and export them as MPI_T pvars. This commit moves all the module stats into their own struct so that the stats only need to appear as a single line in the module_t definition, and then moves all the logic for reporting the stats into btl_usnic_stats.c|h. Further, the stats are now exported as MPI_T_BIND_NO_OBJECT entities (i.e., not bound to any particular MPI handle), and are marked as READONLY and CONTINUOUS. They currently all default to verbose level 5 ("Application tuner / detailed", according to https://svn.open-mpi.org/trac/ompi/wiki/MCAParamLevels). Most of the statistics are counters, but a small number are high watermark values. Due to how counters are reported via MPI_T, none of the counters are exported through MPI_T if the MCA param btl_usnic_stats_relative=1 (i.e., the module resets the stats back to zero at a given frequency). When MPI_T_pvar_handle_alloc() is invoked on any of these pvars, it will return a count that is equal to the number of active usnic BTL modules. The values returned for any given pvar (e.g., num_total_sends) are an array containing one value for each active usnic BTL module. The ordering of values in the array is both consistent across all usnic pvars and stable throughout a single job: array slot 0 corresponds to module X, array slot 1 corresponds to module Y, etc. Mapping which array slot corresponds to which underlying Linux usnic_X device works as follows: * The btl_usnic_devices MPI_T state pvar is associated with a btl_usnic_device MPI_T enum, and be obtained via MPI_T_pvar_get_info(). * If all usNIC pvars are of length N, the values [0,N) in the btl_usnic_device enum are associated with strings of the corresponding underlying Linux device. For exampe, to look up which Linux device is reported in all usNIC pvars' array slot 1, look up the int value 1 in the btl_usnic_devices enum. Its corresponding string value is underlying Linux device name (e.g., "usnic_1"). cmr=v1.7.4:subject="usnic BTL MPI_T pvars" This commit was SVN r29545.
2013-10-29 02:23:08 +04:00
++module->stats.num_ack_recvs;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
#if MSGDEBUG1
opal_output(0, " Received ACK for sequence number %" UDSEQ " from %s to %s\n",
usnic: convert from verbs to libfabric (yay!) This commit represents the conversion of the usnic BTL from verbs to libfabric. For the moment, libfabric is embedded in Open MPI (currently in the usnic BTL). This is because the libfabric API is still changing, and also has not yet been released. Ultimately, this embedded copy of libfabric will likely disappear and the usnic BTL will rely on an external installation of libfabric. New configure options: * --with-libfabric: will cause configure to fail if libfabric support cannot be built * --without-libfabric: will prevent libfabric support from being built * --with-libfabric=DIR: use an external libfabric installation * --with-libfabric-libdir=LIBDIR: when paired with --with-libfabric=DIR, use LIBDIR for the libfabric installation library dir The --with-libnl3[-libdir] arguments are now gone.
2014-12-03 00:09:46 +03:00
bseg->us_btl_header->ack_seq, remote_ip, local_ip);
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
#endif
Added MPI_THREAD_MULTIPLE support for btl/usnic.
2016-06-02 21:52:32 +03:00
OPAL_THREAD_LOCK(&btl_usnic_lock);
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_btl_usnic_handle_ack(endpoint, ack_seq);
Added MPI_THREAD_MULTIPLE support for btl/usnic.
2016-06-02 21:52:32 +03:00
OPAL_THREAD_UNLOCK(&btl_usnic_lock);
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
goto repost;
}
/***********************************************************************/
/* Have no idea what the frag is; drop it */
else {
Move all usNIC stats to _stats.c|h and export them as MPI_T pvars. This commit moves all the module stats into their own struct so that the stats only need to appear as a single line in the module_t definition, and then moves all the logic for reporting the stats into btl_usnic_stats.c|h. Further, the stats are now exported as MPI_T_BIND_NO_OBJECT entities (i.e., not bound to any particular MPI handle), and are marked as READONLY and CONTINUOUS. They currently all default to verbose level 5 ("Application tuner / detailed", according to https://svn.open-mpi.org/trac/ompi/wiki/MCAParamLevels). Most of the statistics are counters, but a small number are high watermark values. Due to how counters are reported via MPI_T, none of the counters are exported through MPI_T if the MCA param btl_usnic_stats_relative=1 (i.e., the module resets the stats back to zero at a given frequency). When MPI_T_pvar_handle_alloc() is invoked on any of these pvars, it will return a count that is equal to the number of active usnic BTL modules. The values returned for any given pvar (e.g., num_total_sends) are an array containing one value for each active usnic BTL module. The ordering of values in the array is both consistent across all usnic pvars and stable throughout a single job: array slot 0 corresponds to module X, array slot 1 corresponds to module Y, etc. Mapping which array slot corresponds to which underlying Linux usnic_X device works as follows: * The btl_usnic_devices MPI_T state pvar is associated with a btl_usnic_device MPI_T enum, and be obtained via MPI_T_pvar_get_info(). * If all usNIC pvars are of length N, the values [0,N) in the btl_usnic_device enum are associated with strings of the corresponding underlying Linux device. For exampe, to look up which Linux device is reported in all usNIC pvars' array slot 1, look up the int value 1 in the btl_usnic_devices enum. Its corresponding string value is underlying Linux device name (e.g., "usnic_1"). cmr=v1.7.4:subject="usnic BTL MPI_T pvars" This commit was SVN r29545.
2013-10-29 02:23:08 +04:00
++module->stats.num_unk_recvs;
usnic: convert from verbs to libfabric (yay!) This commit represents the conversion of the usnic BTL from verbs to libfabric. For the moment, libfabric is embedded in Open MPI (currently in the usnic BTL). This is because the libfabric API is still changing, and also has not yet been released. Ultimately, this embedded copy of libfabric will likely disappear and the usnic BTL will rely on an external installation of libfabric. New configure options: * --with-libfabric: will cause configure to fail if libfabric support cannot be built * --without-libfabric: will prevent libfabric support from being built * --with-libfabric=DIR: use an external libfabric installation * --with-libfabric-libdir=LIBDIR: when paired with --with-libfabric=DIR, use LIBDIR for the libfabric installation library dir The --with-libnl3[-libdir] arguments are now gone.
2014-12-03 00:09:46 +03:00
if (module->stats.num_unk_recvs < 10) {
usnic: only output unknown frames in verbose mode Per https://www.mail-archive.com/users@lists.open-mpi.org/msg31758.html, only output unknown frames when we're outputting verbose BTL messages. Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
2017-11-10 22:14:05 +03:00
opal_output_verbose(15, USNIC_OUT, "unrecognized payload type %d", bseg->us_btl_header->payload_type);
opal_output_verbose(15, USNIC_OUT, "base = %p, proto = %p, hdr = %p", bseg->us_list.ptr, seg->rs_protocol_header, (void*) bseg->us_btl_header);
opal_btl_usnic_dump_hex(15, USNIC_OUT, bseg->us_list.ptr, 96+sizeof(*bseg->us_btl_header));
usnic: convert from verbs to libfabric (yay!) This commit represents the conversion of the usnic BTL from verbs to libfabric. For the moment, libfabric is embedded in Open MPI (currently in the usnic BTL). This is because the libfabric API is still changing, and also has not yet been released. Ultimately, this embedded copy of libfabric will likely disappear and the usnic BTL will rely on an external installation of libfabric. New configure options: * --with-libfabric: will cause configure to fail if libfabric support cannot be built * --without-libfabric: will prevent libfabric support from being built * --with-libfabric=DIR: use an external libfabric installation * --with-libfabric-libdir=LIBDIR: when paired with --with-libfabric=DIR, use LIBDIR for the libfabric installation library dir The --with-libnl3[-libdir] arguments are now gone.
2014-12-03 00:09:46 +03:00
}
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
goto repost;
}
/***********************************************************************/
repost:
/* if endpoint exiting, and all ACKs received, release the endpoint */
if (endpoint->endpoint_exiting && ENDPOINT_DRAINED(endpoint)) {
usnic: unify teardown between trunk and v1.8 branches Make the del_procs, module finalize, and endpoint destructors be the same between trunk and v1.8, with one exception: the very beginning of v1.8 module_finalize calls del_procs for each proc to simulate/pretend the trunk/v1.9 PML behavior of calling del_procs before module_finalize. This commit was SVN r32437.
2014-08-06 02:31:55 +04:00
OBJ_RELEASE(endpoint);
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
}
repost_no_endpoint:
Move all usNIC stats to _stats.c|h and export them as MPI_T pvars. This commit moves all the module stats into their own struct so that the stats only need to appear as a single line in the module_t definition, and then moves all the logic for reporting the stats into btl_usnic_stats.c|h. Further, the stats are now exported as MPI_T_BIND_NO_OBJECT entities (i.e., not bound to any particular MPI handle), and are marked as READONLY and CONTINUOUS. They currently all default to verbose level 5 ("Application tuner / detailed", according to https://svn.open-mpi.org/trac/ompi/wiki/MCAParamLevels). Most of the statistics are counters, but a small number are high watermark values. Due to how counters are reported via MPI_T, none of the counters are exported through MPI_T if the MCA param btl_usnic_stats_relative=1 (i.e., the module resets the stats back to zero at a given frequency). When MPI_T_pvar_handle_alloc() is invoked on any of these pvars, it will return a count that is equal to the number of active usnic BTL modules. The values returned for any given pvar (e.g., num_total_sends) are an array containing one value for each active usnic BTL module. The ordering of values in the array is both consistent across all usnic pvars and stable throughout a single job: array slot 0 corresponds to module X, array slot 1 corresponds to module Y, etc. Mapping which array slot corresponds to which underlying Linux usnic_X device works as follows: * The btl_usnic_devices MPI_T state pvar is associated with a btl_usnic_device MPI_T enum, and be obtained via MPI_T_pvar_get_info(). * If all usNIC pvars are of length N, the values [0,N) in the btl_usnic_device enum are associated with strings of the corresponding underlying Linux device. For exampe, to look up which Linux device is reported in all usNIC pvars' array slot 1, look up the int value 1 in the btl_usnic_devices enum. Its corresponding string value is underlying Linux device name (e.g., "usnic_1"). cmr=v1.7.4:subject="usnic BTL MPI_T pvars" This commit was SVN r29545.
2013-10-29 02:23:08 +04:00
++module->stats.num_recv_reposts;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
/* Add recv to linked list for reposting */
usnic: convert from verbs to libfabric (yay!) This commit represents the conversion of the usnic BTL from verbs to libfabric. For the moment, libfabric is embedded in Open MPI (currently in the usnic BTL). This is because the libfabric API is still changing, and also has not yet been released. Ultimately, this embedded copy of libfabric will likely disappear and the usnic BTL will rely on an external installation of libfabric. New configure options: * --with-libfabric: will cause configure to fail if libfabric support cannot be built * --without-libfabric: will prevent libfabric support from being built * --with-libfabric=DIR: use an external libfabric installation * --with-libfabric-libdir=LIBDIR: when paired with --with-libfabric=DIR, use LIBDIR for the libfabric installation library dir The --with-libnl3[-libdir] arguments are now gone.
2014-12-03 00:09:46 +03:00
seg->rs_next = channel->repost_recv_head;
channel->repost_recv_head = seg;
First commit of the Cisco usNIC BTL. This BTL accesses the Cisco usNIC Linux device via the Linux verbs API via Unreliable Datagram queue pairs. A few noteworthy points: * This BTL does most of its own fragmentation; it tells the PML that it has a very high max_send_size (much higher than the network MTU). * Since UD fragments are, by definition, unreliable, the usnic BTL handles all of its own reliability via a sliding window approach using the opal_hotel construct and many tricks stolen from the corpus of knowledge surrounding efficient TCP. * There is a fun PML latency-metric based optimization for NUMA awareness of short messages. * Note that this is ''not'' a generic UD verbs BTL; it is specific to the Cisco usNIC device. This commit was SVN r28879.
2013-07-20 02:13:58 +04:00
}
Копировать постоянную ссылку