d4afb16f5a
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>
93 строки
3.6 KiB
C
93 строки
3.6 KiB
C
/* -*- 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) 2004-2007 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) 2009 Cisco Systems, Inc. All rights reserved.
|
|
* Copyright (c) 2012-2015 Los Alamos National Security, LLC.
|
|
* All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
/**
|
|
* @file
|
|
*/
|
|
#include "opal_config.h"
|
|
|
|
#ifdef HAVE_UNISTD_H
|
|
#include <unistd.h>
|
|
#endif
|
|
|
|
#include "opal/util/show_help.h"
|
|
#include "opal/util/proc.h"
|
|
#include "opal/runtime/opal_params.h"
|
|
|
|
#include "opal/mca/rcache/base/rcache_base_mem_cb.h"
|
|
#include "opal/mca/rcache/base/base.h"
|
|
|
|
#include "opal/mca/mca.h"
|
|
#include "opal/memoryhooks/memory.h"
|
|
|
|
static char msg[512];
|
|
|
|
|
|
/*
|
|
* memory hook callback, called when memory is free'd out from under
|
|
* us. Be wary of the from_alloc flag -- if you're called with
|
|
* from_alloc==true, then you cannot call malloc (or any of its
|
|
* friends)!
|
|
*/
|
|
void mca_rcache_base_mem_cb (void* base, size_t size, void* cbdata, bool from_alloc)
|
|
{
|
|
mca_rcache_base_selected_module_t* current;
|
|
int rc;
|
|
|
|
/* Only do anything meaningful if the OPAL layer is up and running
|
|
and size != 0 */
|
|
if ((from_alloc && (!opal_initialized)) || size == 0) {
|
|
return;
|
|
}
|
|
|
|
OPAL_LIST_FOREACH(current, &mca_rcache_base_modules, mca_rcache_base_selected_module_t) {
|
|
if (current->rcache_module->rcache_invalidate_range != NULL) {
|
|
rc = current->rcache_module->rcache_invalidate_range (current->rcache_module,
|
|
base, size);
|
|
if (rc != OPAL_SUCCESS) {
|
|
if (from_alloc) {
|
|
int len;
|
|
len = snprintf(msg, sizeof(msg), "[%s:%d] Attempt to free memory that is still in "
|
|
"use by an ongoing MPI communication (buffer %p, size %lu). MPI job "
|
|
"will now abort.\n", opal_proc_local_get()->proc_hostname,
|
|
getpid(), base, (unsigned long) size);
|
|
msg[sizeof(msg) - 1] = '\0';
|
|
write(2, msg, len);
|
|
} else {
|
|
opal_show_help("help-rcache-base.txt",
|
|
"cannot deregister in-use memory", true,
|
|
current->rcache_component->rcache_version.mca_component_name,
|
|
opal_proc_local_get()->proc_hostname,
|
|
base, (unsigned long) size);
|
|
}
|
|
|
|
/* We're in a callback from somewhere; we can't do
|
|
anything meaningful to pass an error back up. :-(
|
|
So just exit. Call _exit() so that we don't try to
|
|
call anything on the way out -- just exit!
|
|
(remember that we're in a callback, and state may
|
|
be very undefined at this point...) */
|
|
_exit(1);
|
|
}
|
|
}
|
|
}
|
|
}
|