b0ac6276a6
This commit improves the injection rate and latency for RDMA operations. This is done by the following improvements: - If C11's _Thread_local keyword is available then always use the same virtual device index for the same thread when using RDMA. If the keyword is not available then attempt to use any device that isn't already in use. The binding support is enabled by default but can be disabled via the btl_ugni_bind_devices MCA variable. - When posting FMA and RDMA operations always attempt to reap completions after posting the operation. This allows us to better balance the work of reaping completions across all application threads. - Limit the total number of outstanding BTE transactions. This fixes a performance bug when using many threads. - Split out RDMA and local SMSG completion queue sizes. The RDMA queue size is better tuned for performance with RMA-MT. - Split out put and get FMA limits. The old btl_ugni_fma_limit MCA variable is deprecated. The new variable names are: btl_ugni_fma_put_limit and btl_ugni_fma_get_limit. - Change how post descriptors are handled. They are no longer allocated seperately from the RDMA endpoints. - Some cleanup to move error code out of the critical path. - Disable the FMA sharing flag on the CDM when we detect that there should be enough FMA descriptors for the number of virtual devices we plan will create. If the user sets this flag we will not unset it. This change should improve the small-message RMA performance by ~ 10%. Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
92 строки
3.1 KiB
C
92 строки
3.1 KiB
C
/* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
|
|
/*
|
|
* Copyright (c) 2011-2018 Los Alamos National Security, LLC. All rights
|
|
* reserved.
|
|
* Copyright (c) 2011 UT-Battelle, LLC. All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
|
|
#include "btl_ugni.h"
|
|
#include "btl_ugni_frag.h"
|
|
|
|
static inline void mca_btl_ugni_base_frag_constructor (mca_btl_ugni_base_frag_t *frag)
|
|
{
|
|
memset ((char *) frag + sizeof (frag->base), 0, sizeof (*frag) - sizeof (frag->base));
|
|
frag->segments[0].seg_addr.pval = frag->base.super.ptr;
|
|
}
|
|
|
|
static inline void mca_btl_ugni_eager_frag_constructor (mca_btl_ugni_base_frag_t *frag)
|
|
{
|
|
struct mca_btl_ugni_reg_t *reg =
|
|
(struct mca_btl_ugni_reg_t *) frag->base.super.registration;
|
|
|
|
mca_btl_ugni_base_frag_constructor (frag);
|
|
|
|
frag->memory_handle = reg->handle;
|
|
}
|
|
|
|
OBJ_CLASS_INSTANCE(mca_btl_ugni_smsg_frag_t, mca_btl_base_descriptor_t,
|
|
mca_btl_ugni_base_frag_constructor, NULL);
|
|
|
|
OBJ_CLASS_INSTANCE(mca_btl_ugni_rdma_frag_t, mca_btl_base_descriptor_t,
|
|
mca_btl_ugni_base_frag_constructor, NULL);
|
|
|
|
OBJ_CLASS_INSTANCE(mca_btl_ugni_eager_frag_t, mca_btl_base_descriptor_t,
|
|
mca_btl_ugni_eager_frag_constructor, NULL);
|
|
|
|
static void mca_btl_ugni_post_descriptor_constructor (mca_btl_ugni_post_descriptor_t *desc)
|
|
{
|
|
desc->cq = NULL;
|
|
}
|
|
|
|
OBJ_CLASS_INSTANCE(mca_btl_ugni_post_descriptor_t, opal_free_list_item_t,
|
|
mca_btl_ugni_post_descriptor_constructor, NULL);
|
|
|
|
static void mca_btl_ugni_rdma_desc_constructor (mca_btl_ugni_rdma_desc_t *desc)
|
|
{
|
|
desc->device = NULL;
|
|
desc->gni_handle = 0;
|
|
desc->tries = 0;
|
|
}
|
|
|
|
static void mca_btl_ugni_rdma_desc_destructor (mca_btl_ugni_rdma_desc_t *desc)
|
|
{
|
|
if (0 != desc->gni_handle) {
|
|
(void) GNI_EpDestroy (desc->gni_handle);
|
|
desc->gni_handle = 0;
|
|
}
|
|
}
|
|
|
|
int mca_btl_ugni_rdma_desc_init (opal_free_list_item_t *item, void *ctx)
|
|
{
|
|
mca_btl_ugni_rdma_desc_t *rdma_desc = (mca_btl_ugni_rdma_desc_t *) item;
|
|
mca_btl_ugni_device_t *device = (mca_btl_ugni_device_t *) ctx;
|
|
gni_return_t grc;
|
|
|
|
grc = GNI_EpCreate (device->dev_handle, device->dev_rdma_local_cq.gni_handle, &rdma_desc->gni_handle);
|
|
rdma_desc->device = device;
|
|
return mca_btl_rc_ugni_to_opal (grc);
|
|
}
|
|
|
|
|
|
OBJ_CLASS_INSTANCE(mca_btl_ugni_rdma_desc_t, opal_free_list_item_t,
|
|
mca_btl_ugni_rdma_desc_constructor, mca_btl_ugni_rdma_desc_destructor);
|
|
|
|
int mca_btl_ugni_frag_init (mca_btl_ugni_base_frag_t *frag, void *id)
|
|
{
|
|
/* NTH: the id is a combination of the module id and the free list id. for now there
|
|
* is only ever one module so the module id is ignored. if this changes the code
|
|
* here and btl_ugni_add_procs.c (opal_free_list_init calls) needs to be updated */
|
|
intptr_t free_list_id = (intptr_t) id & 0xff;
|
|
mca_btl_ugni_module_t *ugni_module = mca_btl_ugni_component.modules;
|
|
|
|
frag->msg_id = opal_pointer_array_add (&ugni_module->pending_smsg_frags_bb, (void *) frag);
|
|
frag->my_list = ugni_module->frags_lists + free_list_id;
|
|
|
|
return OPAL_SUCCESS;
|
|
}
|