diff mbox series

[RESEND,v2,09/12] mm: memcontrol: convert vmstat slab counters to bytes

Message ID 20201206101451.14706-10-songmuchun@bytedance.com (mailing list archive)
State New, archived
Headers show
Series Convert all vmstat counters to pages or bytes | expand

Commit Message

Muchun Song Dec. 6, 2020, 10:14 a.m. UTC 
the global and per-node counters are stored in pages, however memcg
and lruvec counters are stored in bytes. This scheme looks weird.
So convert all vmstat slab counters to bytes.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 include/linux/vmstat.h | 17 ++++++++++-------
 mm/vmstat.c            | 21 ++++++++++-----------
 2 files changed, 20 insertions(+), 18 deletions(-)

Comments

Roman Gushchin Dec. 7, 2020, 7:46 p.m. UTC | #1 
On Sun, Dec 06, 2020 at 06:14:48PM +0800, Muchun Song wrote:
> the global and per-node counters are stored in pages, however memcg
> and lruvec counters are stored in bytes. This scheme looks weird.
> So convert all vmstat slab counters to bytes.

There is a reason for this weird scheme:
percpu caches (see struct per_cpu_nodestat) are s8, so counting in bytes
will lead to overfills. Switching to s32 can lead to an increase in
the cache thrashing, especially on small machines.

> 
> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> ---
>  include/linux/vmstat.h | 17 ++++++++++-------
>  mm/vmstat.c            | 21 ++++++++++-----------
>  2 files changed, 20 insertions(+), 18 deletions(-)
> 
> diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
> index 322dcbfcc933..fd1a3d5d4926 100644
> --- a/include/linux/vmstat.h
> +++ b/include/linux/vmstat.h
> @@ -197,18 +197,26 @@ static inline
>  unsigned long global_node_page_state_pages(enum node_stat_item item)
>  {
>  	long x = atomic_long_read(&vm_node_stat[item]);
> +
>  #ifdef CONFIG_SMP
>  	if (x < 0)
>  		x = 0;
>  #endif
> +	if (vmstat_item_in_bytes(item))
> +		x >>= PAGE_SHIFT;
>  	return x;
>  }
>  
>  static inline unsigned long global_node_page_state(enum node_stat_item item)
>  {
> -	VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
> +	long x = atomic_long_read(&vm_node_stat[item]);
>  
> -	return global_node_page_state_pages(item);
> +	VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
> +#ifdef CONFIG_SMP
> +	if (x < 0)
> +		x = 0;
> +#endif
> +	return x;
>  }
>  
>  static inline unsigned long zone_page_state(struct zone *zone,
> @@ -312,11 +320,6 @@ static inline void __mod_zone_page_state(struct zone *zone,
>  static inline void __mod_node_page_state(struct pglist_data *pgdat,
>  			enum node_stat_item item, int delta)
>  {
> -	if (vmstat_item_in_bytes(item)) {
> -		VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1));
> -		delta >>= PAGE_SHIFT;
> -	}
> -
>  	node_page_state_add(delta, pgdat, item);
>  }
>  
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index 8d77ee426e22..7fb0c7cb9516 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -345,11 +345,6 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
>  	long x;
>  	long t;
>  
> -	if (vmstat_item_in_bytes(item)) {
> -		VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1));
> -		delta >>= PAGE_SHIFT;
> -	}
> -
>  	x = delta + __this_cpu_read(*p);
>  
>  	t = __this_cpu_read(pcp->stat_threshold);
> @@ -554,11 +549,6 @@ static inline void mod_node_state(struct pglist_data *pgdat,
>  	s8 __percpu *p = pcp->vm_node_stat_diff + item;
>  	long o, n, t, z;
>  
> -	if (vmstat_item_in_bytes(item)) {
> -		VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1));
> -		delta >>= PAGE_SHIFT;
> -	}
> -
>  	do {
>  		z = 0;  /* overflow to node counters */
>  
> @@ -1012,19 +1002,28 @@ unsigned long node_page_state_pages(struct pglist_data *pgdat,
>  				    enum node_stat_item item)
>  {
>  	long x = atomic_long_read(&pgdat->vm_stat[item]);
> +
>  #ifdef CONFIG_SMP
>  	if (x < 0)
>  		x = 0;
>  #endif
> +	if (vmstat_item_in_bytes(item))
> +		x >>= PAGE_SHIFT;
>  	return x;
>  }
>  
>  unsigned long node_page_state(struct pglist_data *pgdat,
>  			      enum node_stat_item item)
>  {
> +	long x = atomic_long_read(&pgdat->vm_stat[item]);
> +
>  	VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
>  
> -	return node_page_state_pages(pgdat, item);
> +#ifdef CONFIG_SMP
> +	if (x < 0)
> +		x = 0;
> +#endif
> +	return x;
>  }
>  #endif
>  
> -- 
> 2.11.0
>
Roman Gushchin Dec. 7, 2020, 8:01 p.m. UTC | #2 
On Mon, Dec 07, 2020 at 11:46:22AM -0800, Roman Gushchin wrote:
> On Sun, Dec 06, 2020 at 06:14:48PM +0800, Muchun Song wrote:
> > the global and per-node counters are stored in pages, however memcg
> > and lruvec counters are stored in bytes. This scheme looks weird.
> > So convert all vmstat slab counters to bytes.
> 
> There is a reason for this weird scheme:
> percpu caches (see struct per_cpu_nodestat) are s8, so counting in bytes
> will lead to overfills. Switching to s32 can lead to an increase in
> the cache thrashing, especially on small machines.

JFYI:
I've tried to convert all slab counters to bytes and change those s8 percpu batches to s32
about a year ago. Here is a link to that thread:
https://patchwork.kernel.org/project/linux-mm/patch/20191018002820.307763-3-guro@fb.com/

Thanks!
Muchun Song Dec. 8, 2020, 2:44 a.m. UTC | #3 
On Tue, Dec 8, 2020 at 3:46 AM Roman Gushchin <guro@fb.com> wrote:
>
> On Sun, Dec 06, 2020 at 06:14:48PM +0800, Muchun Song wrote:
> > the global and per-node counters are stored in pages, however memcg
> > and lruvec counters are stored in bytes. This scheme looks weird.
> > So convert all vmstat slab counters to bytes.
>
> There is a reason for this weird scheme:
> percpu caches (see struct per_cpu_nodestat) are s8, so counting in bytes
> will lead to overfills. Switching to s32 can lead to an increase in
> the cache thrashing, especially on small machines.

Thanks Roman. I see now.

>
> >
> > Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> > ---
> >  include/linux/vmstat.h | 17 ++++++++++-------
> >  mm/vmstat.c            | 21 ++++++++++-----------
> >  2 files changed, 20 insertions(+), 18 deletions(-)
> >
> > diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
> > index 322dcbfcc933..fd1a3d5d4926 100644
> > --- a/include/linux/vmstat.h
> > +++ b/include/linux/vmstat.h
> > @@ -197,18 +197,26 @@ static inline
> >  unsigned long global_node_page_state_pages(enum node_stat_item item)
> >  {
> >       long x = atomic_long_read(&vm_node_stat[item]);
> > +
> >  #ifdef CONFIG_SMP
> >       if (x < 0)
> >               x = 0;
> >  #endif
> > +     if (vmstat_item_in_bytes(item))
> > +             x >>= PAGE_SHIFT;
> >       return x;
> >  }
> >
> >  static inline unsigned long global_node_page_state(enum node_stat_item item)
> >  {
> > -     VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
> > +     long x = atomic_long_read(&vm_node_stat[item]);
> >
> > -     return global_node_page_state_pages(item);
> > +     VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
> > +#ifdef CONFIG_SMP
> > +     if (x < 0)
> > +             x = 0;
> > +#endif
> > +     return x;
> >  }
> >
> >  static inline unsigned long zone_page_state(struct zone *zone,
> > @@ -312,11 +320,6 @@ static inline void __mod_zone_page_state(struct zone *zone,
> >  static inline void __mod_node_page_state(struct pglist_data *pgdat,
> >                       enum node_stat_item item, int delta)
> >  {
> > -     if (vmstat_item_in_bytes(item)) {
> > -             VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1));
> > -             delta >>= PAGE_SHIFT;
> > -     }
> > -
> >       node_page_state_add(delta, pgdat, item);
> >  }
> >
> > diff --git a/mm/vmstat.c b/mm/vmstat.c
> > index 8d77ee426e22..7fb0c7cb9516 100644
> > --- a/mm/vmstat.c
> > +++ b/mm/vmstat.c
> > @@ -345,11 +345,6 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
> >       long x;
> >       long t;
> >
> > -     if (vmstat_item_in_bytes(item)) {
> > -             VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1));
> > -             delta >>= PAGE_SHIFT;
> > -     }
> > -
> >       x = delta + __this_cpu_read(*p);
> >
> >       t = __this_cpu_read(pcp->stat_threshold);
> > @@ -554,11 +549,6 @@ static inline void mod_node_state(struct pglist_data *pgdat,
> >       s8 __percpu *p = pcp->vm_node_stat_diff + item;
> >       long o, n, t, z;
> >
> > -     if (vmstat_item_in_bytes(item)) {
> > -             VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1));
> > -             delta >>= PAGE_SHIFT;
> > -     }
> > -
> >       do {
> >               z = 0;  /* overflow to node counters */
> >
> > @@ -1012,19 +1002,28 @@ unsigned long node_page_state_pages(struct pglist_data *pgdat,
> >                                   enum node_stat_item item)
> >  {
> >       long x = atomic_long_read(&pgdat->vm_stat[item]);
> > +
> >  #ifdef CONFIG_SMP
> >       if (x < 0)
> >               x = 0;
> >  #endif
> > +     if (vmstat_item_in_bytes(item))
> > +             x >>= PAGE_SHIFT;
> >       return x;
> >  }
> >
> >  unsigned long node_page_state(struct pglist_data *pgdat,
> >                             enum node_stat_item item)
> >  {
> > +     long x = atomic_long_read(&pgdat->vm_stat[item]);
> > +
> >       VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
> >
> > -     return node_page_state_pages(pgdat, item);
> > +#ifdef CONFIG_SMP
> > +     if (x < 0)
> > +             x = 0;
> > +#endif
> > +     return x;
> >  }
> >  #endif
> >
> > --
> > 2.11.0
> >
diff mbox series

Patch

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 322dcbfcc933..fd1a3d5d4926 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -197,18 +197,26 @@  static inline
 unsigned long global_node_page_state_pages(enum node_stat_item item)
 {
 	long x = atomic_long_read(&vm_node_stat[item]);
+
 #ifdef CONFIG_SMP
 	if (x < 0)
 		x = 0;
 #endif
+	if (vmstat_item_in_bytes(item))
+		x >>= PAGE_SHIFT;
 	return x;
 }
 
 static inline unsigned long global_node_page_state(enum node_stat_item item)
 {
-	VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
+	long x = atomic_long_read(&vm_node_stat[item]);
 
-	return global_node_page_state_pages(item);
+	VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 
 static inline unsigned long zone_page_state(struct zone *zone,
@@ -312,11 +320,6 @@  static inline void __mod_zone_page_state(struct zone *zone,
 static inline void __mod_node_page_state(struct pglist_data *pgdat,
 			enum node_stat_item item, int delta)
 {
-	if (vmstat_item_in_bytes(item)) {
-		VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1));
-		delta >>= PAGE_SHIFT;
-	}
-
 	node_page_state_add(delta, pgdat, item);
 }
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 8d77ee426e22..7fb0c7cb9516 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -345,11 +345,6 @@  void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
 	long x;
 	long t;
 
-	if (vmstat_item_in_bytes(item)) {
-		VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1));
-		delta >>= PAGE_SHIFT;
-	}
-
 	x = delta + __this_cpu_read(*p);
 
 	t = __this_cpu_read(pcp->stat_threshold);
@@ -554,11 +549,6 @@  static inline void mod_node_state(struct pglist_data *pgdat,
 	s8 __percpu *p = pcp->vm_node_stat_diff + item;
 	long o, n, t, z;
 
-	if (vmstat_item_in_bytes(item)) {
-		VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1));
-		delta >>= PAGE_SHIFT;
-	}
-
 	do {
 		z = 0;  /* overflow to node counters */
 
@@ -1012,19 +1002,28 @@  unsigned long node_page_state_pages(struct pglist_data *pgdat,
 				    enum node_stat_item item)
 {
 	long x = atomic_long_read(&pgdat->vm_stat[item]);
+
 #ifdef CONFIG_SMP
 	if (x < 0)
 		x = 0;
 #endif
+	if (vmstat_item_in_bytes(item))
+		x >>= PAGE_SHIFT;
 	return x;
 }
 
 unsigned long node_page_state(struct pglist_data *pgdat,
 			      enum node_stat_item item)
 {
+	long x = atomic_long_read(&pgdat->vm_stat[item]);
+
 	VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
 
-	return node_page_state_pages(pgdat, item);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 #endif