* [to-be-updated] mm-vmalloc-introduce-alloc_pages_bulk_array_mempolicy-to-accelerate-memory-allocation.patch removed from -mm tree
@ 2021-10-22 3:21 akpm
0 siblings, 0 replies; only message in thread
From: akpm @ 2021-10-22 3:21 UTC (permalink / raw)
To: chenwandun, edumazet, guohanjun, mm-commits, npiggin, urezki,
wangkefeng.wang
The patch titled
Subject: mm/vmalloc: introduce alloc_pages_bulk_array_mempolicy to accelerate memory allocation
has been removed from the -mm tree. Its filename was
mm-vmalloc-introduce-alloc_pages_bulk_array_mempolicy-to-accelerate-memory-allocation.patch
This patch was dropped because an updated version will be merged
------------------------------------------------------
From: Chen Wandun <chenwandun@huawei.com>
Subject: mm/vmalloc: introduce alloc_pages_bulk_array_mempolicy to accelerate memory allocation
It will cause significant performance regressions in some situations as
Andrew mentioned in [1]. The main situation is vmalloc, vmalloc will
allocate pages with NUMA_NO_NODE by default, that will result in alloc
page one by one;
In order to solve this, __alloc_pages_bulk and mempolicy should be
considered at the same time.
1) If node is specified in memory allocation request, it will alloc all
pages by __alloc_pages_bulk.
2) If interleaving allocate memory, it will cauculate how many pages
should be allocated in each node, and use __alloc_pages_bulk to alloc
pages in each node.
Based on "[PATCH] mm/vmalloc: fix numa spreading for large hash
tables".
[1]: https://lore.kernel.org/lkml/CALvZod4G3SzP3kWxQYn0fj+VgG-G3yWXz=gz17+3N57ru1iajw@mail.gmail.com/t/#m750c8e3231206134293b089feaa090590afa0f60
Link: https://lkml.kernel.org/r/20211014092952.1500982-1-chenwandun@huawei.com
Signed-off-by: Chen Wandun <chenwandun@huawei.com>
Reviewed-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Hanjun Guo <guohanjun@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/gfp.h | 4 ++
mm/mempolicy.c | 76 ++++++++++++++++++++++++++++++++++++++++++
mm/vmalloc.c | 19 ++--------
3 files changed, 85 insertions(+), 14 deletions(-)
--- a/include/linux/gfp.h~mm-vmalloc-introduce-alloc_pages_bulk_array_mempolicy-to-accelerate-memory-allocation
+++ a/include/linux/gfp.h
@@ -535,6 +535,10 @@ unsigned long __alloc_pages_bulk(gfp_t g
struct list_head *page_list,
struct page **page_array);
+unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp,
+ unsigned long nr_pages,
+ struct page **page_array);
+
/* Bulk allocate order-0 pages */
static inline unsigned long
alloc_pages_bulk_list(gfp_t gfp, unsigned long nr_pages, struct list_head *list)
--- a/mm/mempolicy.c~mm-vmalloc-introduce-alloc_pages_bulk_array_mempolicy-to-accelerate-memory-allocation
+++ a/mm/mempolicy.c
@@ -2196,6 +2196,82 @@ struct page *alloc_pages(gfp_t gfp, unsi
}
EXPORT_SYMBOL(alloc_pages);
+unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp,
+ struct mempolicy *pol, unsigned long nr_pages,
+ struct page **page_array)
+{
+ int nodes;
+ unsigned long nr_pages_per_node;
+ int delta;
+ int i;
+ unsigned long nr_allocated;
+ unsigned long total_allocated = 0;
+
+ nodes = nodes_weight(pol->nodes);
+ nr_pages_per_node = nr_pages / nodes;
+ delta = nr_pages - nodes * nr_pages_per_node;
+
+ for (i = 0; i < nodes; i++) {
+ if (delta) {
+ nr_allocated = __alloc_pages_bulk(gfp,
+ interleave_nodes(pol), NULL,
+ nr_pages_per_node + 1, NULL,
+ page_array);
+ delta--;
+ } else {
+ nr_allocated = __alloc_pages_bulk(gfp,
+ interleave_nodes(pol), NULL,
+ nr_pages_per_node, NULL, page_array);
+ }
+
+ page_array += nr_allocated;
+ total_allocated += nr_allocated;
+ }
+
+ return total_allocated;
+}
+
+unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid,
+ struct mempolicy *pol, unsigned long nr_pages,
+ struct page **page_array)
+{
+ gfp_t preferred_gfp;
+ unsigned long nr_allocated = 0;
+
+ preferred_gfp = gfp | __GFP_NOWARN;
+ preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
+
+ nr_allocated = __alloc_pages_bulk(preferred_gfp, nid, &pol->nodes,
+ nr_pages, NULL, page_array);
+
+ if (nr_allocated < nr_pages)
+ nr_allocated += __alloc_pages_bulk(gfp, numa_node_id(), NULL,
+ nr_pages - nr_allocated, NULL,
+ page_array + nr_allocated);
+ return nr_allocated;
+}
+
+unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp,
+ unsigned long nr_pages, struct page **page_array)
+{
+ struct mempolicy *pol = &default_policy;
+
+ if (!in_interrupt() && !(gfp & __GFP_THISNODE))
+ pol = get_task_policy(current);
+
+ if (pol->mode == MPOL_INTERLEAVE)
+ return alloc_pages_bulk_array_interleave(gfp, pol,
+ nr_pages, page_array);
+
+ if (pol->mode == MPOL_PREFERRED_MANY)
+ return alloc_pages_bulk_array_preferred_many(gfp,
+ numa_node_id(), pol, nr_pages, page_array);
+
+ return __alloc_pages_bulk(gfp, policy_node(gfp, pol, numa_node_id()),
+ policy_nodemask(gfp, pol), nr_pages, NULL,
+ page_array);
+}
+
int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
{
struct mempolicy *pol = mpol_dup(vma_policy(src));
--- a/mm/vmalloc.c~mm-vmalloc-introduce-alloc_pages_bulk_array_mempolicy-to-accelerate-memory-allocation
+++ a/mm/vmalloc.c
@@ -2856,23 +2856,14 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
*/
nr_pages_request = min(100U, nr_pages - nr_allocated);
- if (nid == NUMA_NO_NODE) {
- for (i = 0; i < nr_pages_request; i++) {
- page = alloc_page(gfp);
- if (page)
- pages[nr_allocated + i] = page;
- else {
- nr = i;
- break;
- }
- }
- if (i >= nr_pages_request)
- nr = nr_pages_request;
- } else {
+ if (nid == NUMA_NO_NODE)
+ nr = alloc_pages_bulk_array_mempolicy(gfp,
+ nr_pages_request,
+ pages + nr_allocated);
+ else
nr = alloc_pages_bulk_array_node(gfp, nid,
nr_pages_request,
pages + nr_allocated);
- }
nr_allocated += nr;
cond_resched();
_
Patches currently in -mm which might be from chenwandun@huawei.com are
mm-vmalloc-fix-numa-spreading-for-large-hash-tables.patch
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2021-10-22 3:21 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-10-22 3:21 [to-be-updated] mm-vmalloc-introduce-alloc_pages_bulk_array_mempolicy-to-accelerate-memory-allocation.patch removed from -mm tree akpm
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.