2022-03-14 11:37:02

by Eric Dumazet

[permalink] [raw]
Subject: Re: [mm/page_alloc] 8212a964ee: vm-scalability.throughput 30.5% improvement

On Sun, Mar 13, 2022 at 1:29 AM Vlastimil Babka <[email protected]> wrote:
>
> On 3/13/22 00:26, Eric Dumazet wrote:
> > On Sat, Mar 12, 2022 at 10:59 AM Vlastimil Babka <[email protected]> wrote:
> >>
> >> On 3/12/22 16:43, kernel test robot wrote:
> >>>
> >>>
> >>> Greeting,
> >>>
> >>> FYI, we noticed a 30.5% improvement of vm-scalability.throughput due to commit:
> >>>
> >>>
> >>> commit: 8212a964ee020471104e34dce7029dec33c218a9 ("Re: [PATCH v2] mm/page_alloc: call check_new_pages() while zone spinlock is not held")
> >>> url: https://github.com/0day-ci/linux/commits/Mel-Gorman/Re-PATCH-v2-mm-page_alloc-call-check_new_pages-while-zone-spinlock-is-not-held/20220309-203504
> >>> patch link: https://lore.kernel.org/lkml/[email protected]
> >>
> >> Heh, that's weird. I would expect some improvement from Eric's patch,
> >> but this seems to be actually about Mel's "mm/page_alloc: check
> >> high-order pages for corruption during PCP operations" applied directly
> >> on 5.17-rc7 per the github url above. This was rather expected to make
> >> performance worse if anything, so maybe the improvement is due to some
> >> unexpected side-effect of different inlining decisions or cache alignment...
> >>
> >
> > I doubt this has anything to do with inlining or cache alignment.
> >
> > I am not familiar with the benchmark, but its name
> > (anon-w-rand-hugetlb) hints at hugetlb ?
> >
> > After Mel fix, we go over 512 'struct page' to perform sanity checks,
> > thus loading into cpu caches the 512 cache lines.
>
> Ah, that's true.
>
> > This caching is done while no lock is held.
>
> But I don't think this is. The test was AFAICS done without your patch,
> so the lock is still held in rmqueue(). And it's also held in
> rmqueue_bulk() -> check_pcp_refill().

Note that Mel patch touches both check_pcp_refill() and check_new_pcp()

__rmqueue_pcplist() definitely calls check_new_pcp() while the zone
spinlock is _not_ held.

Note that it is possible to defer calls to check_pcp_refill after the
spinlock is released.

Untested patch:

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1804287c1b792b8aa0e964b17eb002b6b1115258..3c504b4c068a5dbeeaf8f386bb09b673236f7a11
100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3024,6 +3024,7 @@ static int rmqueue_bulk(struct zone *zone,
unsigned int order,
unsigned long count, struct list_head *list,
int migratetype, unsigned int alloc_flags)
{
+ struct page *page, *tmp;
int i, allocated = 0;

/*
@@ -3032,14 +3033,10 @@ static int rmqueue_bulk(struct zone *zone,
unsigned int order,
*/
spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
- struct page *page = __rmqueue(zone, order, migratetype,
- alloc_flags);
+ page = __rmqueue(zone, order, migratetype, alloc_flags);
if (unlikely(page == NULL))
break;

- if (unlikely(check_pcp_refill(page)))
- continue;
-
/*
* Split buddy pages returned by expand() are received here in
* physical page order. The page is added to the tail of
@@ -3065,6 +3062,12 @@ static int rmqueue_bulk(struct zone *zone,
unsigned int order,
*/
__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
spin_unlock(&zone->lock);
+ list_for_each_entry_safe(page, tmp, list, lru) {
+ if (unlikely(check_pcp_refill(page))) {
+ list_del(&page->lru);
+ allocated--;
+ }
+ }
return allocated;
}


2022-03-14 12:21:32

by Vlastimil Babka

[permalink] [raw]
Subject: Re: [mm/page_alloc] 8212a964ee: vm-scalability.throughput 30.5% improvement

On 3/13/22 22:10, Eric Dumazet wrote:
> On Sun, Mar 13, 2022 at 1:29 AM Vlastimil Babka <[email protected]> wrote:
>>
>> On 3/13/22 00:26, Eric Dumazet wrote:
>> > On Sat, Mar 12, 2022 at 10:59 AM Vlastimil Babka <[email protected]> wrote:
>> >>
>> >> On 3/12/22 16:43, kernel test robot wrote:
>> >>>
>> >>>
>> >>> Greeting,
>> >>>
>> >>> FYI, we noticed a 30.5% improvement of vm-scalability.throughput due to commit:
>> >>>
>> >>>
>> >>> commit: 8212a964ee020471104e34dce7029dec33c218a9 ("Re: [PATCH v2] mm/page_alloc: call check_new_pages() while zone spinlock is not held")
>> >>> url: https://github.com/0day-ci/linux/commits/Mel-Gorman/Re-PATCH-v2-mm-page_alloc-call-check_new_pages-while-zone-spinlock-is-not-held/20220309-203504
>> >>> patch link: https://lore.kernel.org/lkml/[email protected]
>> >>
>> >> Heh, that's weird. I would expect some improvement from Eric's patch,
>> >> but this seems to be actually about Mel's "mm/page_alloc: check
>> >> high-order pages for corruption during PCP operations" applied directly
>> >> on 5.17-rc7 per the github url above. This was rather expected to make
>> >> performance worse if anything, so maybe the improvement is due to some
>> >> unexpected side-effect of different inlining decisions or cache alignment...
>> >>
>> >
>> > I doubt this has anything to do with inlining or cache alignment.
>> >
>> > I am not familiar with the benchmark, but its name
>> > (anon-w-rand-hugetlb) hints at hugetlb ?
>> >
>> > After Mel fix, we go over 512 'struct page' to perform sanity checks,
>> > thus loading into cpu caches the 512 cache lines.
>>
>> Ah, that's true.
>>
>> > This caching is done while no lock is held.
>>
>> But I don't think this is. The test was AFAICS done without your patch,
>> so the lock is still held in rmqueue(). And it's also held in
>> rmqueue_bulk() -> check_pcp_refill().
>
> Note that Mel patch touches both check_pcp_refill() and check_new_pcp()
>
> __rmqueue_pcplist() definitely calls check_new_pcp() while the zone
> spinlock is _not_ held.

Yes, but the checking from check_new_pcp() is active only with
CONFIG_DEBUG_VM or enabled debug_pagealloc, which were both disabled in the
robot's report.

> Note that it is possible to defer calls to check_pcp_refill after the
> spinlock is released.
>
> Untested patch:

I'll check the latest posting.

2022-03-14 12:34:01

by Matthew Wilcox

[permalink] [raw]
Subject: Re: [mm/page_alloc] 8212a964ee: vm-scalability.throughput 30.5% improvement

On Sun, Mar 13, 2022 at 02:10:12PM -0700, Eric Dumazet wrote:
> @@ -3065,6 +3062,12 @@ static int rmqueue_bulk(struct zone *zone,
> unsigned int order,
> */
> __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
> spin_unlock(&zone->lock);
> + list_for_each_entry_safe(page, tmp, list, lru) {
> + if (unlikely(check_pcp_refill(page))) {
> + list_del(&page->lru);
> + allocated--;
> + }
> + }

... you'd need to adjust __mod_zone_page_state() too, right?

> return allocated;
> }
>

2022-03-16 21:09:27

by Eric Dumazet

[permalink] [raw]
Subject: Re: [mm/page_alloc] 8212a964ee: vm-scalability.throughput 30.5% improvement

On Sun, Mar 13, 2022 at 2:18 PM Matthew Wilcox <[email protected]> wrote:
>
> On Sun, Mar 13, 2022 at 02:10:12PM -0700, Eric Dumazet wrote:
> > @@ -3065,6 +3062,12 @@ static int rmqueue_bulk(struct zone *zone,
> > unsigned int order,
> > */
> > __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
> > spin_unlock(&zone->lock);
> > + list_for_each_entry_safe(page, tmp, list, lru) {
> > + if (unlikely(check_pcp_refill(page))) {
> > + list_del(&page->lru);
> > + allocated--;
> > + }
> > + }
>
> ... you'd need to adjust __mod_zone_page_state() too, right?

Probably !
This was only to show the basic idea, as I said, not even compiled or tested :)