2013-10-23 15:59:14 +00:00
|
|
|
/* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
|
|
|
|
|
/*
|
|
|
|
|
* Copyright (c) 2013 Los Alamos National Security, LLC. All rights
|
|
|
|
|
* reserved.
|
Per the PMIx RFC:
WHAT: Merge the PMIx branch into the devel repo, creating a new
OPAL “lmix” framework to abstract PMI support for all RTEs.
Replace the ORTE daemon-level collectives with a new PMIx
server and update the ORTE grpcomm framework to support
server-to-server collectives
WHY: We’ve had problems dealing with variations in PMI implementations,
and need to extend the existing PMI definitions to meet exascale
requirements.
WHEN: Mon, Aug 25
WHERE: https://github.com/rhc54/ompi-svn-mirror.git
Several community members have been working on a refactoring of the current PMI support within OMPI. Although the APIs are common, Slurm and Cray implement a different range of capabilities, and package them differently. For example, Cray provides an integrated PMI-1/2 library, while Slurm separates the two and requires the user to specify the one to be used at runtime. In addition, several bugs in the Slurm implementations have caused problems requiring extra coding.
All this has led to a slew of #if’s in the PMI code and bugs when the corner-case logic for one implementation accidentally traps the other. Extending this support to other implementations would have increased this complexity to an unacceptable level.
Accordingly, we have:
* created a new OPAL “pmix” framework to abstract the PMI support, with separate components for Cray, Slurm PMI-1, and Slurm PMI-2 implementations.
* Replaced the current ORTE grpcomm daemon-based collective operation with an integrated PMIx server, and updated the grpcomm APIs to provide more flexible, multi-algorithm support for collective operations. At this time, only the xcast and allgather operations are supported.
* Replaced the current global collective id with a signature based on the names of the participating procs. The allows an unlimited number of collectives to be executed by any group of processes, subject to the requirement that only one collective can be active at a time for a unique combination of procs. Note that a proc can be involved in any number of simultaneous collectives - it is the specific combination of procs that is subject to the constraint
* removed the prior OMPI/OPAL modex code
* added new macros for executing modex send/recv to simplify use of the new APIs. The send macros allow the caller to specify whether or not the BTL supports async modex operations - if so, then the non-blocking “fence” operation is used, if the active PMIx component supports it. Otherwise, the default is a full blocking modex exchange as we currently perform.
* retained the current flag that directs us to use a blocking fence operation, but only to retrieve data upon demand
This commit was SVN r32570.
2014-08-21 18:56:47 +00:00
|
|
|
* Copyright (c) 2014 Intel, Inc. All rights reserved.
|
2013-10-23 15:59:14 +00:00
|
|
|
* $COPYRIGHT$
|
|
|
|
|
*
|
|
|
|
|
* Additional copyrights may follow
|
|
|
|
|
*
|
|
|
|
|
* $HEADER$
|
|
|
|
|
*/
|
|
|
|
|
|
2015-06-23 20:59:57 -07:00
|
|
|
#ifndef MCA_BTL_SCIF_ENDPOINT_H
|
2013-10-23 15:59:14 +00:00
|
|
|
#define MCA_BTL_SCIF_ENDPOINT_H
|
|
|
|
|
|
|
|
|
|
#include "btl_scif.h"
|
Per the PMIx RFC:
WHAT: Merge the PMIx branch into the devel repo, creating a new
OPAL “lmix” framework to abstract PMI support for all RTEs.
Replace the ORTE daemon-level collectives with a new PMIx
server and update the ORTE grpcomm framework to support
server-to-server collectives
WHY: We’ve had problems dealing with variations in PMI implementations,
and need to extend the existing PMI definitions to meet exascale
requirements.
WHEN: Mon, Aug 25
WHERE: https://github.com/rhc54/ompi-svn-mirror.git
Several community members have been working on a refactoring of the current PMI support within OMPI. Although the APIs are common, Slurm and Cray implement a different range of capabilities, and package them differently. For example, Cray provides an integrated PMI-1/2 library, while Slurm separates the two and requires the user to specify the one to be used at runtime. In addition, several bugs in the Slurm implementations have caused problems requiring extra coding.
All this has led to a slew of #if’s in the PMI code and bugs when the corner-case logic for one implementation accidentally traps the other. Extending this support to other implementations would have increased this complexity to an unacceptable level.
Accordingly, we have:
* created a new OPAL “pmix” framework to abstract the PMI support, with separate components for Cray, Slurm PMI-1, and Slurm PMI-2 implementations.
* Replaced the current ORTE grpcomm daemon-based collective operation with an integrated PMIx server, and updated the grpcomm APIs to provide more flexible, multi-algorithm support for collective operations. At this time, only the xcast and allgather operations are supported.
* Replaced the current global collective id with a signature based on the names of the participating procs. The allows an unlimited number of collectives to be executed by any group of processes, subject to the requirement that only one collective can be active at a time for a unique combination of procs. Note that a proc can be involved in any number of simultaneous collectives - it is the specific combination of procs that is subject to the constraint
* removed the prior OMPI/OPAL modex code
* added new macros for executing modex send/recv to simplify use of the new APIs. The send macros allow the caller to specify whether or not the BTL supports async modex operations - if so, then the non-blocking “fence” operation is used, if the active PMIx component supports it. Otherwise, the default is a full blocking modex exchange as we currently perform.
* retained the current flag that directs us to use a blocking fence operation, but only to retrieve data upon demand
This commit was SVN r32570.
2014-08-21 18:56:47 +00:00
|
|
|
#include "opal/mca/pmix/pmix.h"
|
2013-10-23 15:59:14 +00:00
|
|
|
|
|
|
|
|
typedef enum mca_btl_scif_endpoint_state_t {
|
|
|
|
|
MCA_BTL_SCIF_EP_STATE_INIT,
|
|
|
|
|
MCA_BTL_SCIF_EP_STATE_CONNECTING,
|
|
|
|
|
MCA_BTL_SCIF_EP_STATE_CONNECTED
|
|
|
|
|
} mca_btl_scif_endpoint_state_t;
|
|
|
|
|
|
|
|
|
|
typedef struct mca_btl_scif_endpoint_buffer_t {
|
|
|
|
|
unsigned char *buffer;
|
|
|
|
|
off_t scif_offset;
|
|
|
|
|
unsigned int start, end;
|
|
|
|
|
uint32_t *startp, *endp;
|
|
|
|
|
} mca_btl_scif_endpoint_buffer_t;
|
|
|
|
|
|
|
|
|
|
typedef struct mca_btl_base_endpoint_t {
|
|
|
|
|
opal_list_item_t super;
|
|
|
|
|
mca_btl_scif_module_t *btl;
|
|
|
|
|
|
|
|
|
|
/* location in the module endpoints array */
|
|
|
|
|
int id;
|
|
|
|
|
|
|
|
|
|
opal_mutex_t lock;
|
|
|
|
|
|
|
|
|
|
/* scif endpoint */
|
|
|
|
|
scif_epd_t scif_epd;
|
|
|
|
|
|
|
|
|
|
/* connection information */
|
|
|
|
|
struct scif_portID port_id;
|
|
|
|
|
|
|
|
|
|
/* buffer information */
|
|
|
|
|
mca_btl_scif_endpoint_buffer_t send_buffer;
|
|
|
|
|
mca_btl_scif_endpoint_buffer_t recv_buffer;
|
|
|
|
|
|
|
|
|
|
/* current connect state */
|
|
|
|
|
mca_btl_scif_endpoint_state_t state;
|
|
|
|
|
|
|
|
|
|
/* frags waiting for resources */
|
|
|
|
|
opal_list_t frag_wait_list;
|
|
|
|
|
|
|
|
|
|
/* associated process */
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 00:47:28 +00:00
|
|
|
opal_proc_t *peer_proc;
|
2013-10-23 15:59:14 +00:00
|
|
|
|
|
|
|
|
#if defined(SCIF_USE_SEQ)
|
|
|
|
|
uint32_t seq_next;
|
|
|
|
|
uint32_t seq_expected;
|
|
|
|
|
#endif
|
|
|
|
|
} mca_btl_base_endpoint_t;
|
|
|
|
|
|
2014-07-09 19:33:58 +00:00
|
|
|
typedef mca_btl_base_endpoint_t mca_btl_scif_endpoint_t;
|
2013-10-23 15:59:14 +00:00
|
|
|
|
2014-07-09 19:33:58 +00:00
|
|
|
OBJ_CLASS_DECLARATION(mca_btl_scif_endpoint_t);
|
|
|
|
|
|
|
|
|
|
int mca_btl_scif_ep_connect (mca_btl_scif_endpoint_t *ep);
|
2013-10-23 15:59:14 +00:00
|
|
|
int mca_btl_scif_ep_connect_start_passive (void);
|
|
|
|
|
|
2014-07-09 19:33:58 +00:00
|
|
|
static inline int mca_btl_scif_ep_init (mca_btl_scif_endpoint_t *endpoint,
|
2013-10-23 15:59:14 +00:00
|
|
|
mca_btl_scif_module_t *btl,
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 00:47:28 +00:00
|
|
|
opal_proc_t *peer_proc) {
|
2013-10-23 15:59:14 +00:00
|
|
|
mca_btl_scif_modex_t *modex;
|
|
|
|
|
size_t msg_size;
|
|
|
|
|
int rc;
|
|
|
|
|
|
2014-07-09 19:33:58 +00:00
|
|
|
OBJ_CONSTRUCT(endpoint, mca_btl_scif_endpoint_t);
|
2013-10-23 15:59:14 +00:00
|
|
|
endpoint->state = MCA_BTL_SCIF_EP_STATE_INIT;
|
|
|
|
|
|
Per the PMIx RFC:
WHAT: Merge the PMIx branch into the devel repo, creating a new
OPAL “lmix” framework to abstract PMI support for all RTEs.
Replace the ORTE daemon-level collectives with a new PMIx
server and update the ORTE grpcomm framework to support
server-to-server collectives
WHY: We’ve had problems dealing with variations in PMI implementations,
and need to extend the existing PMI definitions to meet exascale
requirements.
WHEN: Mon, Aug 25
WHERE: https://github.com/rhc54/ompi-svn-mirror.git
Several community members have been working on a refactoring of the current PMI support within OMPI. Although the APIs are common, Slurm and Cray implement a different range of capabilities, and package them differently. For example, Cray provides an integrated PMI-1/2 library, while Slurm separates the two and requires the user to specify the one to be used at runtime. In addition, several bugs in the Slurm implementations have caused problems requiring extra coding.
All this has led to a slew of #if’s in the PMI code and bugs when the corner-case logic for one implementation accidentally traps the other. Extending this support to other implementations would have increased this complexity to an unacceptable level.
Accordingly, we have:
* created a new OPAL “pmix” framework to abstract the PMI support, with separate components for Cray, Slurm PMI-1, and Slurm PMI-2 implementations.
* Replaced the current ORTE grpcomm daemon-based collective operation with an integrated PMIx server, and updated the grpcomm APIs to provide more flexible, multi-algorithm support for collective operations. At this time, only the xcast and allgather operations are supported.
* Replaced the current global collective id with a signature based on the names of the participating procs. The allows an unlimited number of collectives to be executed by any group of processes, subject to the requirement that only one collective can be active at a time for a unique combination of procs. Note that a proc can be involved in any number of simultaneous collectives - it is the specific combination of procs that is subject to the constraint
* removed the prior OMPI/OPAL modex code
* added new macros for executing modex send/recv to simplify use of the new APIs. The send macros allow the caller to specify whether or not the BTL supports async modex operations - if so, then the non-blocking “fence” operation is used, if the active PMIx component supports it. Otherwise, the default is a full blocking modex exchange as we currently perform.
* retained the current flag that directs us to use a blocking fence operation, but only to retrieve data upon demand
This commit was SVN r32570.
2014-08-21 18:56:47 +00:00
|
|
|
OPAL_MODEX_RECV(rc, &mca_btl_scif_component.super.btl_version,
|
2015-09-14 18:00:02 -04:00
|
|
|
&peer_proc->proc_name, (void **) &modex, &msg_size);
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 00:47:28 +00:00
|
|
|
if (OPAL_SUCCESS != rc) {
|
2014-05-15 15:59:51 +00:00
|
|
|
return rc;
|
|
|
|
|
}
|
2013-10-23 15:59:14 +00:00
|
|
|
assert (msg_size == sizeof (endpoint->port_id));
|
|
|
|
|
|
|
|
|
|
endpoint->port_id = modex->port_id;
|
|
|
|
|
endpoint->peer_proc = peer_proc;
|
|
|
|
|
endpoint->btl = btl;
|
|
|
|
|
|
|
|
|
|
#if defined(SCIF_USE_SEQ)
|
|
|
|
|
endpoint->seq_next = 0x00001010;
|
|
|
|
|
endpoint->seq_expected = 0x00001010;
|
|
|
|
|
#endif
|
|
|
|
|
|
2014-05-15 15:59:51 +00:00
|
|
|
free (modex);
|
|
|
|
|
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 00:47:28 +00:00
|
|
|
return OPAL_SUCCESS;
|
2013-10-23 15:59:14 +00:00
|
|
|
}
|
|
|
|
|
|
2014-07-09 19:33:58 +00:00
|
|
|
static inline int mca_btl_scif_ep_release (mca_btl_scif_endpoint_t *ep)
|
2013-10-23 15:59:14 +00:00
|
|
|
{
|
|
|
|
|
OBJ_DESTRUCT(ep);
|
George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
2014-07-26 00:47:28 +00:00
|
|
|
return OPAL_SUCCESS;
|
2013-10-23 15:59:14 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#endif /* MCA_BTL_SCIF_ENDPOINT_H */
|