Use the page order as the only threshold for page reporting
is not flexible and has some flaws. Because scan a long free
list is not cheap, it's better to wake up the page reporting
worker when there are more pages, wake it up for a sigle page
may not worth.
This patch add a batch size as another threshold to control the
waking up of reporting worker.
Cc: Alexander Duyck <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: Dan Williams <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Alex Williamson <[email protected]>
Cc: Michael S. Tsirkin <[email protected]>
Cc: Liang Li <[email protected]>
Signed-off-by: Liang Li <[email protected]>
---
mm/page_reporting.c | 1 +
mm/page_reporting.h | 12 ++++++++++--
2 files changed, 11 insertions(+), 2 deletions(-)
diff --git a/mm/page_reporting.c b/mm/page_reporting.c
index cd8e13d41df4..694df981ddd2 100644
--- a/mm/page_reporting.c
+++ b/mm/page_reporting.c
@@ -12,6 +12,7 @@
#define PAGE_REPORTING_DELAY (2 * HZ)
static struct page_reporting_dev_info __rcu *pr_dev_info __read_mostly;
+unsigned long page_report_batch_size __read_mostly = 16 * 1024 * 1024UL;
enum {
PAGE_REPORTING_IDLE = 0,
diff --git a/mm/page_reporting.h b/mm/page_reporting.h
index 2c385dd4ddbd..b8fb3bbb345f 100644
--- a/mm/page_reporting.h
+++ b/mm/page_reporting.h
@@ -12,6 +12,8 @@
#define PAGE_REPORTING_MIN_ORDER pageblock_order
+extern unsigned long page_report_batch_size;
+
#ifdef CONFIG_PAGE_REPORTING
DECLARE_STATIC_KEY_FALSE(page_reporting_enabled);
void __page_reporting_notify(void);
@@ -33,6 +35,8 @@ static inline bool page_reported(struct page *page)
*/
static inline void page_reporting_notify_free(unsigned int order)
{
+ static long batch_size;
+
/* Called from hot path in __free_one_page() */
if (!static_branch_unlikely(&page_reporting_enabled))
return;
@@ -41,8 +45,12 @@ static inline void page_reporting_notify_free(unsigned int order)
if (order < PAGE_REPORTING_MIN_ORDER)
return;
- /* This will add a few cycles, but should be called infrequently */
- __page_reporting_notify();
+ batch_size += (1 << order) << PAGE_SHIFT;
+ if (batch_size >= page_report_batch_size) {
+ batch_size = 0;
+ /* This add a few cycles, but should be called infrequently */
+ __page_reporting_notify();
+ }
}
#else /* CONFIG_PAGE_REPORTING */
#define page_reported(_page) false
--
2.18.2
On Tue, Jan 5, 2021 at 7:47 PM Liang Li <[email protected]> wrote:
>
> Use the page order as the only threshold for page reporting
> is not flexible and has some flaws. Because scan a long free
> list is not cheap, it's better to wake up the page reporting
> worker when there are more pages, wake it up for a sigle page
> may not worth.
> This patch add a batch size as another threshold to control the
> waking up of reporting worker.
>
> Cc: Alexander Duyck <[email protected]>
> Cc: Mel Gorman <[email protected]>
> Cc: Andrea Arcangeli <[email protected]>
> Cc: Dan Williams <[email protected]>
> Cc: Dave Hansen <[email protected]>
> Cc: David Hildenbrand <[email protected]>
> Cc: Michal Hocko <[email protected]>
> Cc: Andrew Morton <[email protected]>
> Cc: Alex Williamson <[email protected]>
> Cc: Michael S. Tsirkin <[email protected]>
> Cc: Liang Li <[email protected]>
> Signed-off-by: Liang Li <[email protected]>
So you are going to need a lot more explanation for this. Page
reporting already had the concept of batching as you could only scan
once every 2 seconds as I recall. Thus the "PAGE_REPORTING_DELAY". The
change you are making doesn't make any sense without additional
context.
> ---
> mm/page_reporting.c | 1 +
> mm/page_reporting.h | 12 ++++++++++--
> 2 files changed, 11 insertions(+), 2 deletions(-)
>
> diff --git a/mm/page_reporting.c b/mm/page_reporting.c
> index cd8e13d41df4..694df981ddd2 100644
> --- a/mm/page_reporting.c
> +++ b/mm/page_reporting.c
> @@ -12,6 +12,7 @@
>
> #define PAGE_REPORTING_DELAY (2 * HZ)
> static struct page_reporting_dev_info __rcu *pr_dev_info __read_mostly;
> +unsigned long page_report_batch_size __read_mostly = 16 * 1024 * 1024UL;
>
> enum {
> PAGE_REPORTING_IDLE = 0,
> diff --git a/mm/page_reporting.h b/mm/page_reporting.h
> index 2c385dd4ddbd..b8fb3bbb345f 100644
> --- a/mm/page_reporting.h
> +++ b/mm/page_reporting.h
> @@ -12,6 +12,8 @@
>
> #define PAGE_REPORTING_MIN_ORDER pageblock_order
>
> +extern unsigned long page_report_batch_size;
> +
> #ifdef CONFIG_PAGE_REPORTING
> DECLARE_STATIC_KEY_FALSE(page_reporting_enabled);
> void __page_reporting_notify(void);
> @@ -33,6 +35,8 @@ static inline bool page_reported(struct page *page)
> */
> static inline void page_reporting_notify_free(unsigned int order)
> {
> + static long batch_size;
> +
I'm not sure this makes a tone of sense to place the value in an
inline function. It might make more sense to put this new code in
__page_reporting_notify so that all callers would be referring to the
same batch_size value and you don't have to bother with the export of
the page_report_batch_size value.
> /* Called from hot path in __free_one_page() */
> if (!static_branch_unlikely(&page_reporting_enabled))
> return;
> @@ -41,8 +45,12 @@ static inline void page_reporting_notify_free(unsigned int order)
> if (order < PAGE_REPORTING_MIN_ORDER)
> return;
>
> - /* This will add a few cycles, but should be called infrequently */
> - __page_reporting_notify();
> + batch_size += (1 << order) << PAGE_SHIFT;
> + if (batch_size >= page_report_batch_size) {
> + batch_size = 0;
I would probably run this in the opposite direction. Rather than
running batch_size to zero I would look at adding a "batch_remaining"
and then when it is < 0 you could then reset it back to
page_report_batch_size. Doing that you only have to read one variable
most of the time instead of doing a comparison against two.
> + /* This add a few cycles, but should be called infrequently */
> + __page_reporting_notify();
> + }
> }
> #else /* CONFIG_PAGE_REPORTING */
> #define page_reported(_page) false
> --
> 2.18.2
>
>
> So you are going to need a lot more explanation for this. Page
> reporting already had the concept of batching as you could only scan
> once every 2 seconds as I recall. Thus the "PAGE_REPORTING_DELAY". The
> change you are making doesn't make any sense without additional
> context.
The reason for adding a batch is mainly for page prezero, I just want to make it
configurable to control the 'cache pollution', for that case, the
reporting thread
should not be woken up too frequently.
> > ---
> > mm/page_reporting.c | 1 +
> > mm/page_reporting.h | 12 ++++++++++--
> > 2 files changed, 11 insertions(+), 2 deletions(-)
> >
> > diff --git a/mm/page_reporting.c b/mm/page_reporting.c
> > index cd8e13d41df4..694df981ddd2 100644
> > --- a/mm/page_reporting.c
> > +++ b/mm/page_reporting.c
> > @@ -12,6 +12,7 @@
> >
> > #define PAGE_REPORTING_DELAY (2 * HZ)
> > static struct page_reporting_dev_info __rcu *pr_dev_info __read_mostly;
> > +unsigned long page_report_batch_size __read_mostly = 16 * 1024 * 1024UL;
> >
> > enum {
> > PAGE_REPORTING_IDLE = 0,
> > diff --git a/mm/page_reporting.h b/mm/page_reporting.h
> > index 2c385dd4ddbd..b8fb3bbb345f 100644
> > --- a/mm/page_reporting.h
> > +++ b/mm/page_reporting.h
> > @@ -12,6 +12,8 @@
> >
> > #define PAGE_REPORTING_MIN_ORDER pageblock_order
> >
> > +extern unsigned long page_report_batch_size;
> > +
> > #ifdef CONFIG_PAGE_REPORTING
> > DECLARE_STATIC_KEY_FALSE(page_reporting_enabled);
> > void __page_reporting_notify(void);
> > @@ -33,6 +35,8 @@ static inline bool page_reported(struct page *page)
> > */
> > static inline void page_reporting_notify_free(unsigned int order)
> > {
> > + static long batch_size;
> > +
>
> I'm not sure this makes a tone of sense to place the value in an
> inline function. It might make more sense to put this new code in
> __page_reporting_notify so that all callers would be referring to the
> same batch_size value and you don't have to bother with the export of
> the page_report_batch_size value.
you are right, will change.
> > /* Called from hot path in __free_one_page() */
> > if (!static_branch_unlikely(&page_reporting_enabled))
> > return;
> > @@ -41,8 +45,12 @@ static inline void page_reporting_notify_free(unsigned int order)
> > if (order < PAGE_REPORTING_MIN_ORDER)
> > return;
> >
> > - /* This will add a few cycles, but should be called infrequently */
> > - __page_reporting_notify();
> > + batch_size += (1 << order) << PAGE_SHIFT;
> > + if (batch_size >= page_report_batch_size) {
> > + batch_size = 0;
>
> I would probably run this in the opposite direction. Rather than
> running batch_size to zero I would look at adding a "batch_remaining"
> and then when it is < 0 you could then reset it back to
> page_report_batch_size. Doing that you only have to read one variable
> most of the time instead of doing a comparison against two.
You are right again.
Thanks
Liang