From: Barry Song <21cnbao@gmail.com>
To: gaoxu <gaoxu2@honor.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
"linux-mm@kvack.org" <linux-mm@kvack.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Suren Baghdasaryan <surenb@google.com>, Shaohua Li <shli@fb.com>,
yipengxiang <yipengxiang@honor.com>,
fengbaopeng <fengbaopeng@honor.com>,
Kalesh Singh <kaleshsingh@google.com>
Subject: Re: [PATCH v2] mm: add lazyfree folio to lru tail
Date: Tue, 20 Aug 2024 22:11:23 +1200 [thread overview]
Message-ID: <CAGsJ_4xTW5y4O6BoVuXKk=awhoiZV0zitPYYbfsX1pmqZgY9WQ@mail.gmail.com> (raw)
In-Reply-To: <f29f64e29c08427b95e3df30a5770056@honor.com>
On Fri, Aug 16, 2024 at 7:48 PM gaoxu <gaoxu2@honor.com> wrote:
>
> Replace lruvec_add_folio with lruvec_add_folio_tail in the lru_lazyfree_fn:
> 1. The lazy-free folio is added to the LRU_INACTIVE_FILE list. If it's
> moved to the LRU tail, it allows for faster release lazy-free folio and
> reduces the impact on file refault.
> 2. When mglru is enabled, the lazy-free folio is reclaimabled and should be
> added using lru_gen_add_folio(lruvec, folio, true) instead of
> lru_gen_add_folio(lruvec, folio, false) for adding to gen.
>
> With the change in place, workingset_refault_file is reduced by 33% in the
> continuous startup testing of the applications in the Android system.
>
Hi Gao,
Just curious, in which scenario are we frequently calling
MADV_FREE but not MADV_DONTNEED?
> Signed-off-by: gao xu <gaoxu2@hihonor.com>
> ---
> V1 -> V2: Based on the latest mm-unstable, recreate the patch.
>
> mm/swap.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/mm/swap.c b/mm/swap.c
> index 6b838986d..e0dbfc983 100644
> --- a/mm/swap.c
> +++ b/mm/swap.c
> @@ -641,7 +641,7 @@ static void lru_lazyfree(struct lruvec *lruvec, struct folio *folio)
> * anonymous folios
> */
> folio_clear_swapbacked(folio);
> - lruvec_add_folio(lruvec, folio);
> + lruvec_add_folio_tail(lruvec, folio);
>
> __count_vm_events(PGLAZYFREE, nr_pages);
> __count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages);
> --
> 2.17.1
next prev parent reply other threads:[~2024-08-20 10:11 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-08-16 7:48 gaoxu
2024-08-16 10:19 ` David Hildenbrand
2024-08-16 10:21 ` David Hildenbrand
2024-08-19 16:11 ` Suren Baghdasaryan
2024-08-20 10:11 ` Barry Song [this message]
2024-08-20 11:53 ` 回复: " gaoxu
2024-08-20 21:46 ` Barry Song
2024-08-21 12:46 ` Michal Hocko
2024-08-21 21:47 ` Barry Song
2024-08-23 23:39 ` Suren Baghdasaryan
2024-08-26 16:37 ` Lokesh Gidra
2024-08-26 19:54 ` Barry Song
2024-08-27 0:12 ` Lokesh Gidra
2024-08-27 2:21 ` Barry Song
2024-08-27 4:07 ` 回复: " gaoxu
2024-08-27 17:56 ` Minchan Kim
2024-08-29 3:55 ` 回复: " gaoxu
2024-09-10 8:51 ` Barry Song
2024-08-27 2:13 ` Hailong Liu
2024-08-27 2:18 ` Barry Song
2024-08-27 2:29 ` Hailong Liu
2024-09-09 22:22 ` Andrew Morton
2024-09-10 8:20 ` Michal Hocko
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to='CAGsJ_4xTW5y4O6BoVuXKk=awhoiZV0zitPYYbfsX1pmqZgY9WQ@mail.gmail.com' \
--to=21cnbao@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=fengbaopeng@honor.com \
--cc=gaoxu2@honor.com \
--cc=kaleshsingh@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=shli@fb.com \
--cc=surenb@google.com \
--cc=yipengxiang@honor.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox