Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1727147 > unrolled thread

[PATCH] mm/page_alloc: don't reserve ZONE_HIGHMEM for ZONE_MOVABLE request

Started byjs1304@gmail.com
First post2017-09-06 06:40 +0200
Last post2017-09-06 10:00 +0200
Articles 2 — 2 participants

Back to article view | Back to linux.kernel

Contents

  [PATCH] mm/page_alloc: don't reserve ZONE_HIGHMEM for ZONE_MOVABLE request js1304@gmail.com - 2017-09-06 06:40 +0200
    Re: [PATCH] mm/page_alloc: don't reserve ZONE_HIGHMEM for  ZONE_MOVABLE request Vlastimil Babka <vbabka@suse.cz> - 2017-09-06 10:00 +0200

#1727147 — [PATCH] mm/page_alloc: don't reserve ZONE_HIGHMEM for ZONE_MOVABLE request

Fromjs1304@gmail.com
Date2017-09-06 06:40 +0200
Subject[PATCH] mm/page_alloc: don't reserve ZONE_HIGHMEM for ZONE_MOVABLE request
Message-ID<umAi6-4Cl-5@gated-at.bofh.it>
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>

Freepage on ZONE_HIGHMEM doesn't work for kernel memory so it's not that
important to reserve. When ZONE_MOVABLE is used, this problem would
theorectically cause to decrease usable memory for GFP_HIGHUSER_MOVABLE
allocation request which is mainly used for page cache and anon page
allocation. So, fix it by setting 0 to
sysctl_lowmem_reserve_ratio[ZONE_HIGHMEM].

And, defining sysctl_lowmem_reserve_ratio array by MAX_NR_ZONES - 1 size
makes code complex. For example, if there is highmem system, following
reserve ratio is activated for *NORMAL ZONE* which would be easyily
misleading people.

 #ifdef CONFIG_HIGHMEM
 32
 #endif

This patch also fix this situation by defining sysctl_lowmem_reserve_ratio
array by MAX_NR_ZONES and place "#ifdef" to right place.

Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
---
 Documentation/sysctl/vm.txt |  5 ++---
 include/linux/mmzone.h      |  2 +-
 mm/page_alloc.c             | 25 ++++++++++++++-----------
 3 files changed, 17 insertions(+), 15 deletions(-)

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 9baf66a..e9059d3 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -336,8 +336,6 @@ The lowmem_reserve_ratio is an array. You can see them by reading this file.
 % cat /proc/sys/vm/lowmem_reserve_ratio
 256     256     32
 -
-Note: # of this elements is one fewer than number of zones. Because the highest
-      zone's value is not necessary for following calculation.
 
 But, these values are not used directly. The kernel calculates # of protection
 pages for each zones from them. These are shown as array of protection pages
@@ -388,7 +386,8 @@ As above expression, they are reciprocal number of ratio.
 pages of higher zones on the node.
 
 If you would like to protect more pages, smaller values are effective.
-The minimum value is 1 (1/1 -> 100%).
+The minimum value is 1 (1/1 -> 100%). The value less than 1 completely
+disables protection of the pages.
 
 ==============================================================
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 356a814..d549c4e 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -890,7 +890,7 @@ int min_free_kbytes_sysctl_handler(struct ctl_table *, int,
 					void __user *, size_t *, loff_t *);
 int watermark_scale_factor_sysctl_handler(struct ctl_table *, int,
 					void __user *, size_t *, loff_t *);
-extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1];
+extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES];
 int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int,
 					void __user *, size_t *, loff_t *);
 int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0f34356..2a7f7e9 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -203,17 +203,18 @@ static void __free_pages_ok(struct page *page, unsigned int order);
  * TBD: should special case ZONE_DMA32 machines here - in those we normally
  * don't need any ZONE_NORMAL reservation
  */
-int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = {
+int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES] = {
 #ifdef CONFIG_ZONE_DMA
-	 256,
+	[ZONE_DMA] = 256,
 #endif
 #ifdef CONFIG_ZONE_DMA32
-	 256,
+	[ZONE_DMA32] = 256,
 #endif
+	[ZONE_NORMAL] = 32,
 #ifdef CONFIG_HIGHMEM
-	 32,
+	[ZONE_HIGHMEM] = 0,
 #endif
-	 32,
+	[ZONE_MOVABLE] = 0,
 };
 
 EXPORT_SYMBOL(totalram_pages);
@@ -6921,13 +6922,15 @@ static void setup_per_zone_lowmem_reserve(void)
 				struct zone *lower_zone;
 
 				idx--;
-
-				if (sysctl_lowmem_reserve_ratio[idx] < 1)
-					sysctl_lowmem_reserve_ratio[idx] = 1;
-
 				lower_zone = pgdat->node_zones + idx;
-				lower_zone->lowmem_reserve[j] = managed_pages /
-					sysctl_lowmem_reserve_ratio[idx];
+
+				if (sysctl_lowmem_reserve_ratio[idx] < 1) {
+					sysctl_lowmem_reserve_ratio[idx] = 0;
+					lower_zone->lowmem_reserve[j] = 0;
+				} else {
+					lower_zone->lowmem_reserve[j] =
+						managed_pages / sysctl_lowmem_reserve_ratio[idx];
+				}
 				managed_pages += lower_zone->managed_pages;
 			}
 		}
-- 
2.7.4

[toc] | [next] | [standalone]

#1727190 — Re: [PATCH] mm/page_alloc: don't reserve ZONE_HIGHMEM for ZONE_MOVABLE request

FromVlastimil Babka <vbabka@suse.cz>
Date2017-09-06 10:00 +0200
SubjectRe: [PATCH] mm/page_alloc: don't reserve ZONE_HIGHMEM for ZONE_MOVABLE request
Message-ID<umDpE-6TS-9@gated-at.bofh.it>
In reply to#1727147
+CC linux-api

On 09/06/2017 06:35 AM, js1304@gmail.com wrote:
> From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
> 
> Freepage on ZONE_HIGHMEM doesn't work for kernel memory so it's not that
> important to reserve. When ZONE_MOVABLE is used, this problem would
> theorectically cause to decrease usable memory for GFP_HIGHUSER_MOVABLE
> allocation request which is mainly used for page cache and anon page
> allocation. So, fix it by setting 0 to
> sysctl_lowmem_reserve_ratio[ZONE_HIGHMEM].
> 
> And, defining sysctl_lowmem_reserve_ratio array by MAX_NR_ZONES - 1 size
> makes code complex. For example, if there is highmem system, following
> reserve ratio is activated for *NORMAL ZONE* which would be easyily
> misleading people.
> 
>  #ifdef CONFIG_HIGHMEM
>  32
>  #endif
> 
> This patch also fix this situation by defining sysctl_lowmem_reserve_ratio
> array by MAX_NR_ZONES and place "#ifdef" to right place.
> 
> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
> Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
> ---
>  Documentation/sysctl/vm.txt |  5 ++---
>  include/linux/mmzone.h      |  2 +-
>  mm/page_alloc.c             | 25 ++++++++++++++-----------
>  3 files changed, 17 insertions(+), 15 deletions(-)
> 
> diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
> index 9baf66a..e9059d3 100644
> --- a/Documentation/sysctl/vm.txt
> +++ b/Documentation/sysctl/vm.txt
> @@ -336,8 +336,6 @@ The lowmem_reserve_ratio is an array. You can see them by reading this file.
>  % cat /proc/sys/vm/lowmem_reserve_ratio
>  256     256     32
>  -
> -Note: # of this elements is one fewer than number of zones. Because the highest
> -      zone's value is not necessary for following calculation.
>  
>  But, these values are not used directly. The kernel calculates # of protection
>  pages for each zones from them. These are shown as array of protection pages
> @@ -388,7 +386,8 @@ As above expression, they are reciprocal number of ratio.
>  pages of higher zones on the node.
>  
>  If you would like to protect more pages, smaller values are effective.
> -The minimum value is 1 (1/1 -> 100%).
> +The minimum value is 1 (1/1 -> 100%). The value less than 1 completely
> +disables protection of the pages.
>  
>  ==============================================================
>  
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 356a814..d549c4e 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -890,7 +890,7 @@ int min_free_kbytes_sysctl_handler(struct ctl_table *, int,
>  					void __user *, size_t *, loff_t *);
>  int watermark_scale_factor_sysctl_handler(struct ctl_table *, int,
>  					void __user *, size_t *, loff_t *);
> -extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1];
> +extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES];
>  int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int,
>  					void __user *, size_t *, loff_t *);
>  int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int,
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 0f34356..2a7f7e9 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -203,17 +203,18 @@ static void __free_pages_ok(struct page *page, unsigned int order);
>   * TBD: should special case ZONE_DMA32 machines here - in those we normally
>   * don't need any ZONE_NORMAL reservation
>   */
> -int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = {
> +int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES] = {
>  #ifdef CONFIG_ZONE_DMA
> -	 256,
> +	[ZONE_DMA] = 256,
>  #endif
>  #ifdef CONFIG_ZONE_DMA32
> -	 256,
> +	[ZONE_DMA32] = 256,
>  #endif
> +	[ZONE_NORMAL] = 32,
>  #ifdef CONFIG_HIGHMEM
> -	 32,
> +	[ZONE_HIGHMEM] = 0,
>  #endif
> -	 32,
> +	[ZONE_MOVABLE] = 0,
>  };
>  
>  EXPORT_SYMBOL(totalram_pages);
> @@ -6921,13 +6922,15 @@ static void setup_per_zone_lowmem_reserve(void)
>  				struct zone *lower_zone;
>  
>  				idx--;
> -
> -				if (sysctl_lowmem_reserve_ratio[idx] < 1)
> -					sysctl_lowmem_reserve_ratio[idx] = 1;
> -
>  				lower_zone = pgdat->node_zones + idx;
> -				lower_zone->lowmem_reserve[j] = managed_pages /
> -					sysctl_lowmem_reserve_ratio[idx];
> +
> +				if (sysctl_lowmem_reserve_ratio[idx] < 1) {
> +					sysctl_lowmem_reserve_ratio[idx] = 0;
> +					lower_zone->lowmem_reserve[j] = 0;
> +				} else {
> +					lower_zone->lowmem_reserve[j] =
> +						managed_pages / sysctl_lowmem_reserve_ratio[idx];
> +				}
>  				managed_pages += lower_zone->managed_pages;
>  			}
>  		}
>

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web