[PATCH v3 0/2] fix numa spreading for large hash tables

[PATCH v3 0/2] fix numa spreading for large hash tables

[Chen Wandun]

[PATCH v3 1/2] fix numa spreading problem
[PATCH v3 2/2] optimization about performance

v1 ==> v2:
1. do a minimal fix in [PATCH v2 1/2]
2. add some comments

v2 ==> v3:
remote redundant code

based on commit 14a60b114a8560de785df502fdc5687a969eae81

Chen Wandun (2):
  mm/vmalloc: fix numa spreading for large hash tables
  mm/vmalloc: introduce alloc_pages_bulk_array_mempolicy to accelerate
    memory allocation

 include/linux/gfp.h |  4 +++
 mm/mempolicy.c      | 82 +++++++++++++++++++++++++++++++++++++++++++++
 mm/vmalloc.c        | 27 +++++++++++----
 3 files changed, 107 insertions(+), 6 deletions(-)

-- 
2.25.1

[PATCH v3 1/2] mm/vmalloc: fix numa spreading for large hash tables

[Chen Wandun]

Eric Dumazet reported a strange numa spreading info in [1], and found
commit 121e6f3258fe ("mm/vmalloc: hugepage vmalloc mappings") introduced
this issue [2].

Dig into the difference before and after this patch, page allocation has
some difference:

before:
alloc_large_system_hash
    __vmalloc
        __vmalloc_node(..., NUMA_NO_NODE, ...)
            __vmalloc_node_range
                __vmalloc_area_node
                    alloc_page /* because NUMA_NO_NODE, so choose alloc_page branch */
                        alloc_pages_current
                            alloc_page_interleave /* can be proved by print policy mode */

after:
alloc_large_system_hash
    __vmalloc
        __vmalloc_node(..., NUMA_NO_NODE, ...)
            __vmalloc_node_range
                __vmalloc_area_node
                    alloc_pages_node /* choose nid by nuam_mem_id() */
                        __alloc_pages_node(nid, ....)

So after commit 121e6f3258fe ("mm/vmalloc: hugepage vmalloc mappings"),
it will allocate memory in current node instead of interleaving allocate
memory.

[1]
https://lore.kernel.org/linux-mm/CANn89iL6AAyWhfxdHO+jaT075iOa3XcYn9k6JJc7JR2XYn6k_Q@mail.gmail.com/

[2]
https://lore.kernel.org/linux-mm/CANn89iLofTR=AK-QOZY87RdUZENCZUT4O6a0hvhu3_EwRMerOg@mail.gmail.com/

Fixes: 121e6f3258fe ("mm/vmalloc: hugepage vmalloc mappings")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Chen Wandun <chenwandun@huawei.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
---
 mm/vmalloc.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index d77830ff604c..e8a807c78110 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2816,6 +2816,8 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 		unsigned int order, unsigned int nr_pages, struct page **pages)
 {
 	unsigned int nr_allocated = 0;
+	struct page *page;
+	int i;
 
 	/*
 	 * For order-0 pages we make use of bulk allocator, if
@@ -2823,7 +2825,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 	 * to fails, fallback to a single page allocator that is
 	 * more permissive.
 	 */
-	if (!order) {
+	if (!order && nid != NUMA_NO_NODE) {
 		while (nr_allocated < nr_pages) {
 			unsigned int nr, nr_pages_request;
 
@@ -2848,7 +2850,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 			if (nr != nr_pages_request)
 				break;
 		}
-	} else
+	} else if (order)
 		/*
 		 * Compound pages required for remap_vmalloc_page if
 		 * high-order pages.
@@ -2856,11 +2858,12 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 		gfp |= __GFP_COMP;
 
 	/* High-order pages or fallback path if "bulk" fails. */
-	while (nr_allocated < nr_pages) {
-		struct page *page;
-		int i;
 
-		page = alloc_pages_node(nid, gfp, order);
+	while (nr_allocated < nr_pages) {
+		if (nid == NUMA_NO_NODE)
+			page = alloc_pages(gfp, order);
+		else
+			page = alloc_pages_node(nid, gfp, order);
 		if (unlikely(!page))
 			break;
 
-- 
2.25.1

[PATCH v3 2/2] mm/vmalloc: introduce alloc_pages_bulk_array_mempolicy to accelerate memory allocation

[Chen Wandun]

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.

[1]: https://lore.kernel.org/lkml/CALvZod4G3SzP3kWxQYn0fj+VgG-G3yWXz=gz17+3N57ru1iajw@mail.gmail.com/t/#m750c8e3231206134293b089feaa090590afa0f60

Reviewed-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Chen Wandun <chenwandun@huawei.com>
---
 include/linux/gfp.h |  4 +++
 mm/mempolicy.c      | 82 +++++++++++++++++++++++++++++++++++++++++++++
 mm/vmalloc.c        | 20 ++++++++---
 3 files changed, 102 insertions(+), 4 deletions(-)

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 55b2ec1f965a..cd98c858fc74 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -535,6 +535,10 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
 				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)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 1592b081c58e..56bb1fe4d179 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2202,6 +2202,88 @@ struct page *alloc_pages(gfp_t gfp, unsigned order)
 }
 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;
+}
+
+/* alloc pages bulk and mempolicy should be considered at the
+ * same time in some situation such as vmalloc.
+ *
+ * It can accelerate memory allocation especially interleaving
+ * allocate memory.
+ */
+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));
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index e8a807c78110..c3ab25d408dd 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2825,7 +2825,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 	 * to fails, fallback to a single page allocator that is
 	 * more permissive.
 	 */
-	if (!order && nid != NUMA_NO_NODE) {
+	if (!order) {
 		while (nr_allocated < nr_pages) {
 			unsigned int nr, nr_pages_request;
 
@@ -2837,8 +2837,20 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 			 */
 			nr_pages_request = min(100U, nr_pages - nr_allocated);
 
-			nr = alloc_pages_bulk_array_node(gfp, nid,
-				nr_pages_request, pages + nr_allocated);
+			/* memory allocation should consider mempolicy, we cant
+			 * wrongly use nearest node when nid == NUMA_NO_NODE,
+			 * otherwise memory may be allocated in only one node,
+			 * but mempolcy want to alloc memory by interleaving.
+			 */
+			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();
@@ -2850,7 +2862,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 			if (nr != nr_pages_request)
 				break;
 		}
-	} else if (order)
+	} else
 		/*
 		 * Compound pages required for remap_vmalloc_page if
 		 * high-order pages.
-- 
2.25.1

Re: [PATCH v3 2/2] mm/vmalloc: introduce alloc_pages_bulk_array_mempolicy to accelerate memory allocation

[Andrew Morton]

On Thu, 21 Oct 2021 16:07:44 +0800 Chen Wandun <chenwandun@huawei.com> wrote:

> It

What is "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.

This v3 patch didn't incorporate my two fixes, below.  It is usual to
incorporate such fixes prior to resending.  I have retained those two
fixes, now against v3.


From: Andrew Morton <akpm@linux-foundation.org>
Subject: mm-vmalloc-introduce-alloc_pages_bulk_array_mempolicy-to-accelerate-memory-allocation-fix

make two functions static

Cc: Chen Wandun <chenwandun@huawei.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Hanjun Guo <guohanjun@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/mempolicy.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/mm/mempolicy.c~mm-vmalloc-introduce-alloc_pages_bulk_array_mempolicy-to-accelerate-memory-allocation-fix
+++ a/mm/mempolicy.c
@@ -2196,7 +2196,7 @@ struct page *alloc_pages(gfp_t gfp, unsi
 }
 EXPORT_SYMBOL(alloc_pages);
 
-unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp,
+static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp,
 		struct mempolicy *pol, unsigned long nr_pages,
 		struct page **page_array)
 {
@@ -2231,7 +2231,7 @@ unsigned long alloc_pages_bulk_array_int
 	return total_allocated;
 }
 
-unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid,
+static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid,
 		struct mempolicy *pol, unsigned long nr_pages,
 		struct page **page_array)
 {
_




From: Andrew Morton <akpm@linux-foundation.org>
Subject: mm-vmalloc-introduce-alloc_pages_bulk_array_mempolicy-to-accelerate-memory-allocation-fix-2

fix CONFIG_NUMA=n build.  alloc_pages_bulk_array_mempolicy() was undefined

Cc: Chen Wandun <chenwandun@huawei.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Hanjun Guo <guohanjun@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/vmalloc.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/mm/vmalloc.c~mm-vmalloc-introduce-alloc_pages_bulk_array_mempolicy-to-accelerate-memory-allocation-fix-2
+++ a/mm/vmalloc.c
@@ -2860,7 +2860,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 			 * otherwise memory may be allocated in only one node,
 			 * but mempolcy want to alloc memory by interleaving.
 			 */
-			if (nid == NUMA_NO_NODE)
+			if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE)
 				nr = alloc_pages_bulk_array_mempolicy(gfp,
 							nr_pages_request,
 							pages + nr_allocated);
_

Re: [PATCH v3 2/2] mm/vmalloc: introduce alloc_pages_bulk_array_mempolicy to accelerate memory allocation

[Chen Wandun]

在 2021/10/22 11:26, Andrew Morton 写道:
> On Thu, 21 Oct 2021 16:07:44 +0800 Chen Wandun <chenwandun@huawei.com> wrote:
> 
>> It
> 
> What is "it"?
it == > [PATCH] mm/vmalloc: fix numa spreading for large hash tables;
> 
>> 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.
> 
> This v3 patch didn't incorporate my two fixes, below.  It is usual to
> incorporate such fixes prior to resending.  I have retained those two
> fixes, now against v3.
> 
> 
> From: Andrew Morton <akpm@linux-foundation.org>
> Subject: mm-vmalloc-introduce-alloc_pages_bulk_array_mempolicy-to-accelerate-memory-allocation-fix
> 
> make two functions static
> 
> Cc: Chen Wandun <chenwandun@huawei.com>
> Cc: Eric Dumazet <edumazet@google.com>
> Cc: Hanjun Guo <guohanjun@huawei.com>
> Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
> Cc: Nicholas Piggin <npiggin@gmail.com>
> Cc: Shakeel Butt <shakeelb@google.com>
> Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
> ---
> 
>   mm/mempolicy.c |    4 ++--
>   1 file changed, 2 insertions(+), 2 deletions(-)
> 
> --- a/mm/mempolicy.c~mm-vmalloc-introduce-alloc_pages_bulk_array_mempolicy-to-accelerate-memory-allocation-fix
> +++ a/mm/mempolicy.c
> @@ -2196,7 +2196,7 @@ struct page *alloc_pages(gfp_t gfp, unsi
>   }
>   EXPORT_SYMBOL(alloc_pages);
>   
> -unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp,
> +static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp,
>   		struct mempolicy *pol, unsigned long nr_pages,
>   		struct page **page_array)
>   {
> @@ -2231,7 +2231,7 @@ unsigned long alloc_pages_bulk_array_int
>   	return total_allocated;
>   }
>   
> -unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid,
> +static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid,
>   		struct mempolicy *pol, unsigned long nr_pages,
>   		struct page **page_array)
>   {
> _
> 
> 
> 
> 
> From: Andrew Morton <akpm@linux-foundation.org>
> Subject: mm-vmalloc-introduce-alloc_pages_bulk_array_mempolicy-to-accelerate-memory-allocation-fix-2
> 
> fix CONFIG_NUMA=n build.  alloc_pages_bulk_array_mempolicy() was undefined
> 
> Cc: Chen Wandun <chenwandun@huawei.com>
> Cc: Eric Dumazet <edumazet@google.com>
> Cc: Hanjun Guo <guohanjun@huawei.com>
> Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
> Cc: Nicholas Piggin <npiggin@gmail.com>
> Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
> ---
> 
>   mm/vmalloc.c |    2 +-
>   1 file changed, 1 insertion(+), 1 deletion(-)
> 
> --- a/mm/vmalloc.c~mm-vmalloc-introduce-alloc_pages_bulk_array_mempolicy-to-accelerate-memory-allocation-fix-2
> +++ a/mm/vmalloc.c
> @@ -2860,7 +2860,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
>   			 * otherwise memory may be allocated in only one node,
>   			 * but mempolcy want to alloc memory by interleaving.
>   			 */
> -			if (nid == NUMA_NO_NODE)
> +			if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE)
>   				nr = alloc_pages_bulk_array_mempolicy(gfp,
>   							nr_pages_request,
>   							pages + nr_allocated);
> _
> 
> .
>