We have to move lru_lock into lru_note_cost, since it cycle up on memcg
tree, for future per lruvec lru_lock replace. It's a bit ugly and may
cost a bit more locking, but benefit from multiple memcg locking could
cover the lost.
Signed-off-by: Alex Shi <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: [email protected]
Cc: [email protected]
---
mm/swap.c | 5 +++--
mm/vmscan.c | 4 +---
2 files changed, 4 insertions(+), 5 deletions(-)
diff --git a/mm/swap.c b/mm/swap.c
index 906255db6006..f80ccd6f3cb4 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -269,7 +269,9 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
{
do {
unsigned long lrusize;
+ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
+ spin_lock_irq(&pgdat->lru_lock);
/* Record cost event */
if (file)
lruvec->file_cost += nr_pages;
@@ -293,15 +295,14 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
lruvec->file_cost /= 2;
lruvec->anon_cost /= 2;
}
+ spin_unlock_irq(&pgdat->lru_lock);
} while ((lruvec = parent_lruvec(lruvec)));
}
void lru_note_cost_page(struct page *page)
{
- spin_lock_irq(&page_pgdat(page)->lru_lock);
lru_note_cost(mem_cgroup_page_lruvec(page, page_pgdat(page)),
page_is_file_lru(page), thp_nr_pages(page));
- spin_unlock_irq(&page_pgdat(page)->lru_lock);
}
static void __activate_page(struct page *page, struct lruvec *lruvec)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ffccb94defaf..7b7b36bd1448 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1971,19 +1971,17 @@ static int current_may_throttle(void)
&stat, false);
spin_lock_irq(&pgdat->lru_lock);
-
move_pages_to_lru(lruvec, &page_list);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
- lru_note_cost(lruvec, file, stat.nr_pageout);
item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
if (!cgroup_reclaim(sc))
__count_vm_events(item, nr_reclaimed);
__count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
__count_vm_events(PGSTEAL_ANON + file, nr_reclaimed);
-
spin_unlock_irq(&pgdat->lru_lock);
+ lru_note_cost(lruvec, file, stat.nr_pageout);
mem_cgroup_uncharge_list(&page_list);
free_unref_page_list(&page_list);
--
1.8.3.1
On Mon, 24 Aug 2020, Alex Shi wrote:
> We have to move lru_lock into lru_note_cost, since it cycle up on memcg
> tree, for future per lruvec lru_lock replace. It's a bit ugly and may
> cost a bit more locking, but benefit from multiple memcg locking could
> cover the lost.
>
> Signed-off-by: Alex Shi <[email protected]>
Acked-by: Hugh Dickins <[email protected]>
In your lruv19 github tree, you have merged 14/32 into this one: thanks.
> Cc: Johannes Weiner <[email protected]>
> Cc: Andrew Morton <[email protected]>
> Cc: [email protected]
> Cc: [email protected]
> ---
> mm/swap.c | 5 +++--
> mm/vmscan.c | 4 +---
> 2 files changed, 4 insertions(+), 5 deletions(-)
>
> diff --git a/mm/swap.c b/mm/swap.c
> index 906255db6006..f80ccd6f3cb4 100644
> --- a/mm/swap.c
> +++ b/mm/swap.c
> @@ -269,7 +269,9 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
> {
> do {
> unsigned long lrusize;
> + struct pglist_data *pgdat = lruvec_pgdat(lruvec);
>
> + spin_lock_irq(&pgdat->lru_lock);
> /* Record cost event */
> if (file)
> lruvec->file_cost += nr_pages;
> @@ -293,15 +295,14 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
> lruvec->file_cost /= 2;
> lruvec->anon_cost /= 2;
> }
> + spin_unlock_irq(&pgdat->lru_lock);
> } while ((lruvec = parent_lruvec(lruvec)));
> }
>
> void lru_note_cost_page(struct page *page)
> {
> - spin_lock_irq(&page_pgdat(page)->lru_lock);
> lru_note_cost(mem_cgroup_page_lruvec(page, page_pgdat(page)),
> page_is_file_lru(page), thp_nr_pages(page));
> - spin_unlock_irq(&page_pgdat(page)->lru_lock);
> }
>
> static void __activate_page(struct page *page, struct lruvec *lruvec)
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index ffccb94defaf..7b7b36bd1448 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -1971,19 +1971,17 @@ static int current_may_throttle(void)
> &stat, false);
>
> spin_lock_irq(&pgdat->lru_lock);
> -
> move_pages_to_lru(lruvec, &page_list);
>
> __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
> - lru_note_cost(lruvec, file, stat.nr_pageout);
> item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
> if (!cgroup_reclaim(sc))
> __count_vm_events(item, nr_reclaimed);
> __count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
> __count_vm_events(PGSTEAL_ANON + file, nr_reclaimed);
> -
> spin_unlock_irq(&pgdat->lru_lock);
>
> + lru_note_cost(lruvec, file, stat.nr_pageout);
> mem_cgroup_uncharge_list(&page_list);
> free_unref_page_list(&page_list);
>
> --
> 1.8.3.1
>
>
On Mon, 21 Sep 2020, Hugh Dickins wrote:
> On Mon, 24 Aug 2020, Alex Shi wrote:
>
> > We have to move lru_lock into lru_note_cost, since it cycle up on memcg
> > tree, for future per lruvec lru_lock replace. It's a bit ugly and may
> > cost a bit more locking, but benefit from multiple memcg locking could
> > cover the lost.
> >
> > Signed-off-by: Alex Shi <[email protected]>
>
> Acked-by: Hugh Dickins <[email protected]>
>
> In your lruv19 github tree, you have merged 14/32 into this one: thanks.
Grr, I've only just started, and already missed some of my notes.
I wanted to point out that this patch does introduce an extra unlock+lock
in shrink_inactive_list(), even in a !CONFIG_MEMCG build. I think you've
done the right thing for now, keeping it simple, and maybe nobody will
notice the extra overhead; but I expect us to replace lru_note_cost()
by lru_note_cost_unlock_irq() later on, expecting the caller to do the
initial lock_irq().
lru_note_cost_page() looks redundant to me, but you're right not to
delete it here, unless Johannes asks you to add that in: that's his
business, and it may be dependent on the XXX at its callsite.
>
> > Cc: Johannes Weiner <[email protected]>
> > Cc: Andrew Morton <[email protected]>
> > Cc: [email protected]
> > Cc: [email protected]
> > ---
> > mm/swap.c | 5 +++--
> > mm/vmscan.c | 4 +---
> > 2 files changed, 4 insertions(+), 5 deletions(-)
> >
> > diff --git a/mm/swap.c b/mm/swap.c
> > index 906255db6006..f80ccd6f3cb4 100644
> > --- a/mm/swap.c
> > +++ b/mm/swap.c
> > @@ -269,7 +269,9 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
> > {
> > do {
> > unsigned long lrusize;
> > + struct pglist_data *pgdat = lruvec_pgdat(lruvec);
> >
> > + spin_lock_irq(&pgdat->lru_lock);
> > /* Record cost event */
> > if (file)
> > lruvec->file_cost += nr_pages;
> > @@ -293,15 +295,14 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
> > lruvec->file_cost /= 2;
> > lruvec->anon_cost /= 2;
> > }
> > + spin_unlock_irq(&pgdat->lru_lock);
> > } while ((lruvec = parent_lruvec(lruvec)));
> > }
> >
> > void lru_note_cost_page(struct page *page)
> > {
> > - spin_lock_irq(&page_pgdat(page)->lru_lock);
> > lru_note_cost(mem_cgroup_page_lruvec(page, page_pgdat(page)),
> > page_is_file_lru(page), thp_nr_pages(page));
> > - spin_unlock_irq(&page_pgdat(page)->lru_lock);
> > }
> >
> > static void __activate_page(struct page *page, struct lruvec *lruvec)
> > diff --git a/mm/vmscan.c b/mm/vmscan.c
> > index ffccb94defaf..7b7b36bd1448 100644
> > --- a/mm/vmscan.c
> > +++ b/mm/vmscan.c
> > @@ -1971,19 +1971,17 @@ static int current_may_throttle(void)
> > &stat, false);
> >
> > spin_lock_irq(&pgdat->lru_lock);
> > -
> > move_pages_to_lru(lruvec, &page_list);
> >
> > __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
> > - lru_note_cost(lruvec, file, stat.nr_pageout);
> > item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
> > if (!cgroup_reclaim(sc))
> > __count_vm_events(item, nr_reclaimed);
> > __count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
> > __count_vm_events(PGSTEAL_ANON + file, nr_reclaimed);
> > -
> > spin_unlock_irq(&pgdat->lru_lock);
> >
> > + lru_note_cost(lruvec, file, stat.nr_pageout);
> > mem_cgroup_uncharge_list(&page_list);
> > free_unref_page_list(&page_list);
> >
> > --
> > 1.8.3.1
> >
> >
>
?? 2020/9/22 ????5:36, Hugh Dickins д??:
>
>> We have to move lru_lock into lru_note_cost, since it cycle up on memcg
>> tree, for future per lruvec lru_lock replace. It's a bit ugly and may
>> cost a bit more locking, but benefit from multiple memcg locking could
>> cover the lost.
>>
>> Signed-off-by: Alex Shi <[email protected]>
> Acked-by: Hugh Dickins <[email protected]>
Thanks!
?? 2020/9/22 ????6:03, Hugh Dickins д??:
>> Acked-by: Hugh Dickins <[email protected]>
>>
>> In your lruv19 github tree, you have merged 14/32 into this one: thanks.
> Grr, I've only just started, and already missed some of my notes.
>
> I wanted to point out that this patch does introduce an extra unlock+lock
> in shrink_inactive_list(), even in a !CONFIG_MEMCG build. I think you've
> done the right thing for now, keeping it simple, and maybe nobody will
> notice the extra overhead; but I expect us to replace lru_note_cost()
> by lru_note_cost_unlock_irq() later on, expecting the caller to do the
> initial lock_irq().
>
> lru_note_cost_page() looks redundant to me, but you're right not to
> delete it here, unless Johannes asks you to add that in: that's his
> business, and it may be dependent on the XXX at its callsite.
>
Thanks for comments! And got your point. so I will leave this patch alone.
Thanks!