1
1
openmpi/opal/mca/btl/vader/btl_vader_endpoint.h

122 строки
4.2 KiB
C
Исходник Обычный вид История

/* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
/*
* Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
* University Research and Technology
* Corporation. All rights reserved.
* Copyright (c) 2004-2005 The University of Tennessee and The University
* of Tennessee Research Foundation. All rights
* reserved.
* Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
* University of Stuttgart. All rights reserved.
* Copyright (c) 2004-2005 The Regents of the University of California.
* All rights reserved.
* Copyright (c) 2006-2007 Voltaire. All rights reserved.
* Copyright (c) 2012-2016 Los Alamos National Security, LLC. All rights
* reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
/**
* @file
*/
#ifndef MCA_BTL_VADER_ENDPOINT_H
#define MCA_BTL_VADER_ENDPOINT_H
#include "opal_config.h"
#include "btl_vader_xpmem.h"
opal: rework mpool and rcache frameworks This commit rewrites both the mpool and rcache frameworks. Summary of changes: - Before this change a significant portion of the rcache functionality lived in mpool components. This meant that it was impossible to add a new memory pool to use with rdma networks (ugni, openib, etc) without duplicating the functionality of an existing mpool component. All the registration functionality has been removed from the mpool and placed in the rcache framework. - All registration cache mpools components (udreg, grdma, gpusm, rgpusm) have been changed to rcache components. rcaches are allocated and released in the same way mpool components were. - It is now valid to pass NULL as the resources argument when creating an rcache. At this time the gpusm and rgpusm components support this. All other rcache components require non-NULL resources. - A new mpool component has been added: hugepage. This component supports huge page allocations on linux. - Memory pools are now allocated using "hints". Each mpool component is queried with the hints and returns a priority. The current hints supported are NULL (uses posix_memalign/malloc), page_size=x (huge page mpool), and mpool=x. - The sm mpool has been moved to common/sm. This reflects that the sm mpool is specialized and not meant for any general allocations. This mpool may be moved back into the mpool framework if there is any objection. - The opal_free_list_init arguments have been updated. The unused0 argument is not used to pass in the registration cache module. The mpool registration flags are now rcache registration flags. - All components have been updated to make use of the new framework interfaces. As this commit makes significant changes to both the mpool and rcache frameworks both versions have been bumped to 3.0.0. Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2015-11-02 12:07:08 -07:00
#include "opal/mca/rcache/base/rcache_base_vma.h"
#define MCA_BTL_VADER_FBOX_ALIGNMENT 32
#define MCA_BTL_VADER_FBOX_ALIGNMENT_MASK (MCA_BTL_VADER_FBOX_ALIGNMENT - 1)
struct vader_fifo_t;
/**
* An abstraction that represents a connection to a endpoint process.
* An instance of mca_ptl_base_endpoint_t is associated w/ each process
* and BTL pair at startup.
*/
struct mca_btl_vader_fbox_t;
typedef struct mca_btl_base_endpoint_t {
opal_list_item_t super;
/* per peer buffers */
struct {
unsigned char *buffer; /**< starting address of peer's fast box out */
uint32_t *startp;
unsigned int start;
uint16_t seq;
} fbox_in;
struct {
unsigned char *buffer; /**< starting address of peer's fast box in */
uint32_t *startp; /**< pointer to location storing start offset */
unsigned int start, end;
uint16_t seq;
} fbox_out;
int32_t peer_smp_rank; /**< my peer's SMP process rank. Used for accessing
* SMP specfic data structures. */
volatile size_t send_count; /**< number of fragments sent to this peer */
char *segment_base; /**< start of the peer's segment (in the address space
* of this process) */
struct vader_fifo_t *fifo; /**< */
opal_mutex_t lock; /**< lock to protect endpoint structures from concurrent
* access */
union {
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_BTL_VADER_HAVE_XPMEM
struct {
opal: rework mpool and rcache frameworks This commit rewrites both the mpool and rcache frameworks. Summary of changes: - Before this change a significant portion of the rcache functionality lived in mpool components. This meant that it was impossible to add a new memory pool to use with rdma networks (ugni, openib, etc) without duplicating the functionality of an existing mpool component. All the registration functionality has been removed from the mpool and placed in the rcache framework. - All registration cache mpools components (udreg, grdma, gpusm, rgpusm) have been changed to rcache components. rcaches are allocated and released in the same way mpool components were. - It is now valid to pass NULL as the resources argument when creating an rcache. At this time the gpusm and rgpusm components support this. All other rcache components require non-NULL resources. - A new mpool component has been added: hugepage. This component supports huge page allocations on linux. - Memory pools are now allocated using "hints". Each mpool component is queried with the hints and returns a priority. The current hints supported are NULL (uses posix_memalign/malloc), page_size=x (huge page mpool), and mpool=x. - The sm mpool has been moved to common/sm. This reflects that the sm mpool is specialized and not meant for any general allocations. This mpool may be moved back into the mpool framework if there is any objection. - The opal_free_list_init arguments have been updated. The unused0 argument is not used to pass in the registration cache module. The mpool registration flags are now rcache registration flags. - All components have been updated to make use of the new framework interfaces. As this commit makes significant changes to both the mpool and rcache frameworks both versions have been bumped to 3.0.0. Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2015-11-02 12:07:08 -07:00
mca_rcache_base_vma_module_t *vma_module;
xpmem_apid_t apid; /**< xpmem apid for remote peer */
} xpmem;
#endif
struct {
pid_t pid; /**< pid of remote peer (used for CMA) */
opal_shmem_ds_t *seg_ds; /**< stored segment information for detach */
} other;
} segment_data;
opal_mutex_t pending_frags_lock; /**< protect pending_frags */
opal_list_t pending_frags; /**< fragments pending fast box space */
bool waiting; /**< endpoint is on the component wait list */
} mca_btl_base_endpoint_t;
typedef mca_btl_base_endpoint_t mca_btl_vader_endpoint_t;
OBJ_CLASS_DECLARATION(mca_btl_vader_endpoint_t);
static inline void mca_btl_vader_endpoint_setup_fbox_recv (struct mca_btl_base_endpoint_t *endpoint, void *base)
{
endpoint->fbox_in.startp = (uint32_t *) base;
endpoint->fbox_in.start = MCA_BTL_VADER_FBOX_ALIGNMENT;
endpoint->fbox_in.seq = 0;
opal_atomic_wmb ();
endpoint->fbox_in.buffer = base;
}
static inline void mca_btl_vader_endpoint_setup_fbox_send (struct mca_btl_base_endpoint_t *endpoint, void *base)
{
endpoint->fbox_out.start = MCA_BTL_VADER_FBOX_ALIGNMENT;
endpoint->fbox_out.end = MCA_BTL_VADER_FBOX_ALIGNMENT;
endpoint->fbox_out.startp = (uint32_t *) base;
endpoint->fbox_out.startp[0] = MCA_BTL_VADER_FBOX_ALIGNMENT;
endpoint->fbox_out.seq = 0;
/* zero out the first header in the fast box */
memset ((char *) base + MCA_BTL_VADER_FBOX_ALIGNMENT, 0, MCA_BTL_VADER_FBOX_ALIGNMENT);
opal_atomic_wmb ();
endpoint->fbox_out.buffer = base;
}
#endif /* MCA_BTL_VADER_ENDPOINT_H */