Re: [PATCH v20 00/20] per memcg lru lock

在 2020/11/5 上午12:59, Johannes Weiner 写道: > On Wed, Nov 04, 2020 at 07:55:39PM +0800, Alex Shi wrote: >> @@ -1380,6 +1383,14 @@ struct lruvec *mem_cgroup_page_lruvec(struct page >> *page, struct pglist_data *pgd >> return lruvec; >> } >> >> +/** >> + * lock_page_lruvec - return lruvec f

Re: [PATCH v20 00/20] per memcg lru lock

On Wed, Nov 04, 2020 at 07:55:39PM +0800, Alex Shi wrote: > @@ -1380,6 +1383,14 @@ struct lruvec *mem_cgroup_page_lruvec(struct page > *page, struct pglist_data *pgd > return lruvec; > } > > +/** > + * lock_page_lruvec - return lruvec for the locked page. I would say "lock and return th

Re: [PATCH v20 00/20] per memcg lru lock

Hi Johannes & all, Thanks for all comments and suggestions, here is a patch base on v20, as a summary for all you suggested: Is this ok? Many thanks! Alex diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0c97292834fa..0fe4172c8c14 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -20,6

[PATCH v20 00/20] per memcg lru lock

This version just a rebase on v5.10-rc1. and moves the lru_lock position down after lists[] in lruvec, which resolves a fio.read regression that revealed by Rong Chen -- Intel LKP. Many thanks for line by line review by Hugh Dickins and Alexander Duyck. So now this patchset includes 3 parts: 1, s