2a0b3a5700
This commit fixes several threading bugs: - Add an additional lock to the btl_base_endpoint_t structure to lock the list of pending frags. This allows the progress function to attempt to send pending frags without needing to drop/reaquire the lock. This should provide a small improvement in performance and fixes a potential race between adding an removing items from the pending list. - Ensure fast boxes are only set up once by updating the send count using atomics when needed and do not set the fast box buffer pointer until the fast box is set up. Closes open-mpi/ompi#1408 Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
83 строки
3.0 KiB
C
83 строки
3.0 KiB
C
/* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
|
|
/*
|
|
* Copyright (c) 2004-2011 The Trustees of Indiana University and Indiana
|
|
* University Research and Technology
|
|
* Corporation. All rights reserved.
|
|
* Copyright (c) 2004-2009 The University of Tennessee and The University
|
|
* of Tennessee Research Foundation. All rights
|
|
* reserved.
|
|
* Copyright (c) 2004-2007 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) 2009 Cisco Systems, Inc. All rights reserved.
|
|
* Copyright (c) 2010-2014 Los Alamos National Security, LLC. All rights
|
|
* reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
|
|
#include "opal_config.h"
|
|
|
|
#include "btl_vader.h"
|
|
#include "btl_vader_frag.h"
|
|
#include "btl_vader_fifo.h"
|
|
#include "btl_vader_fbox.h"
|
|
|
|
/**
|
|
* Initiate a send to the peer.
|
|
*
|
|
* @param btl (IN) BTL module
|
|
* @param peer (IN) BTL peer addressing
|
|
*/
|
|
int mca_btl_vader_send (struct mca_btl_base_module_t *btl,
|
|
struct mca_btl_base_endpoint_t *endpoint,
|
|
struct mca_btl_base_descriptor_t *descriptor,
|
|
mca_btl_base_tag_t tag)
|
|
{
|
|
mca_btl_vader_frag_t *frag = (mca_btl_vader_frag_t *) descriptor;
|
|
const size_t total_size = frag->segments[0].seg_len;
|
|
|
|
if (OPAL_LIKELY(frag->fbox)) {
|
|
mca_btl_vader_fbox_send (frag->fbox, tag);
|
|
mca_btl_vader_frag_complete (frag);
|
|
|
|
return 1;
|
|
}
|
|
|
|
/* header (+ optional inline data) */
|
|
frag->hdr->len = total_size;
|
|
/* type of message, pt-2-pt, one-sided, etc */
|
|
frag->hdr->tag = tag;
|
|
|
|
/* post the relative address of the descriptor into the peer's fifo */
|
|
if (opal_list_get_size (&endpoint->pending_frags) || !vader_fifo_write_ep (frag->hdr, endpoint)) {
|
|
frag->base.des_flags |= MCA_BTL_DES_SEND_ALWAYS_CALLBACK;
|
|
OPAL_THREAD_LOCK(&endpoint->pending_frags_lock);
|
|
opal_list_append (&endpoint->pending_frags, (opal_list_item_t *) frag);
|
|
if (!endpoint->waiting) {
|
|
OPAL_THREAD_LOCK(&mca_btl_vader_component.lock);
|
|
opal_list_append (&mca_btl_vader_component.pending_endpoints, &endpoint->super);
|
|
OPAL_THREAD_UNLOCK(&mca_btl_vader_component.lock);
|
|
endpoint->waiting = true;
|
|
}
|
|
OPAL_THREAD_UNLOCK(&endpoint->pending_frags_lock);
|
|
return OPAL_SUCCESS;
|
|
}
|
|
|
|
if ((frag->hdr->flags & MCA_BTL_VADER_FLAG_SINGLE_COPY) ||
|
|
!(frag->base.des_flags & MCA_BTL_DES_FLAGS_BTL_OWNERSHIP)) {
|
|
frag->base.des_flags |= MCA_BTL_DES_SEND_ALWAYS_CALLBACK;
|
|
|
|
return OPAL_SUCCESS;
|
|
}
|
|
|
|
/* data is gone (from the pml's perspective). frag callback/release will
|
|
happen later */
|
|
return 1;
|
|
}
|