public inbox for linux-mm@kvack.org
 help / color / mirror / Atom feed
From: Axel Rasmussen <axelrasmussen@google.com>
To: kasong@tencent.com
Cc: linux-mm@kvack.org, Andrew Morton <akpm@linux-foundation.org>,
	 Yuanchu Xie <yuanchu@google.com>, Wei Xu <weixugc@google.com>,
	 Johannes Weiner <hannes@cmpxchg.org>,
	David Hildenbrand <david@kernel.org>,
	Michal Hocko <mhocko@kernel.org>,
	 Qi Zheng <zhengqi.arch@bytedance.com>,
	Shakeel Butt <shakeel.butt@linux.dev>,
	 Lorenzo Stoakes <ljs@kernel.org>, Barry Song <baohua@kernel.org>,
	David Stevens <stevensd@google.com>,
	 Chen Ridong <chenridong@huaweicloud.com>,
	Leno Hou <lenohou@gmail.com>,  Yafang Shao <laoar.shao@gmail.com>,
	Yu Zhao <yuzhao@google.com>,
	 Zicheng Wang <wangzicheng@honor.com>,
	Kalesh Singh <kaleshsingh@google.com>,
	 Suren Baghdasaryan <surenb@google.com>,
	Chris Li <chrisl@kernel.org>, Vernon Yang <vernon2gm@gmail.com>,
	 linux-kernel@vger.kernel.org
Subject: Re: [PATCH 2/8] mm/mglru: relocate the LRU scan batch limit to callers
Date: Fri, 20 Mar 2026 14:00:19 -0700	[thread overview]
Message-ID: <CAJHvVch+S6MDoBp0SRhPC-v5nVpizF2Y9NEYn6B9bCVqR9Mv-w@mail.gmail.com> (raw)
In-Reply-To: <20260318-mglru-reclaim-v1-2-2c46f9eb0508@tencent.com>

On Tue, Mar 17, 2026 at 12:11 PM Kairui Song via B4 Relay
<devnull+kasong.tencent.com@kernel.org> wrote:
>
> From: Kairui Song <kasong@tencent.com>
>
> Same as active / inactive LRU, MGLRU isolates and scans folios in
> batches.  The batch split is done hidden deep in the helper, which
> makes the code harder to follow.  The helper's arguments are also
> confusing since callers usually request more folios than the batch
> size, so the helper almost never processes the full requested amount.
>
> Move the batch splitting into the top loop to make it cleaner, there
> should be no behavior change.
>
> Signed-off-by: Kairui Song <kasong@tencent.com>

Reviewed-by: Axel Rasmussen <axelrasmussen@google.com>

To Chen's concern, I see patch 5 makes use of this refactor for example.

I don't have a super strong opinion on keeping this separate here vs.
squashing into patch 5. I slightly prefer keeping this
no-functional-change part separate, then patch 5 becomes very easy to
review.

> ---
>  mm/vmscan.c | 19 +++++++++++--------
>  1 file changed, 11 insertions(+), 8 deletions(-)
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index d7fc7f1fe06d..d48074f9bd87 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -4689,10 +4689,10 @@ static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
>         int scanned = 0;
>         int isolated = 0;
>         int skipped = 0;
> -       int scan_batch = min(nr_to_scan, MAX_LRU_BATCH);
> -       int remaining = scan_batch;
> +       unsigned long remaining = nr_to_scan;
>         struct lru_gen_folio *lrugen = &lruvec->lrugen;
>
> +       VM_WARN_ON_ONCE(nr_to_scan > MAX_LRU_BATCH);
>         VM_WARN_ON_ONCE(!list_empty(list));
>
>         if (get_nr_gens(lruvec, type) == MIN_NR_GENS)
> @@ -4745,7 +4745,7 @@ static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
>         mod_lruvec_state(lruvec, item, isolated);
>         mod_lruvec_state(lruvec, PGREFILL, sorted);
>         mod_lruvec_state(lruvec, PGSCAN_ANON + type, isolated);
> -       trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, scan_batch,
> +       trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan,
>                                 scanned, skipped, isolated,
>                                 type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON);
>         if (type == LRU_GEN_FILE)
> @@ -4827,7 +4827,8 @@ static int isolate_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
>
>                 *type_scanned = type;
>
> -               scanned = scan_folios(nr_to_scan, lruvec, sc, type, tier, list);
> +               scanned = scan_folios(nr_to_scan, lruvec, sc,
> +                                     type, tier, list);
>                 if (scanned)
>                         return scanned;
>
> @@ -4999,7 +5000,7 @@ static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc)
>
>  static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
>  {
> -       long nr_to_scan;
> +       long nr_batch, nr_to_scan;
>         unsigned long scanned = 0;
>         int swappiness = get_swappiness(lruvec, sc);
>
> @@ -5010,7 +5011,8 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
>                 if (nr_to_scan <= 0)
>                         break;
>
> -               delta = evict_folios(nr_to_scan, lruvec, sc, swappiness);
> +               nr_batch = min(nr_to_scan, MAX_LRU_BATCH);
> +               delta = evict_folios(nr_batch, lruvec, sc, swappiness);
>                 if (!delta)
>                         break;
>
> @@ -5615,6 +5617,7 @@ static int run_aging(struct lruvec *lruvec, unsigned long seq,
>  static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc,
>                         int swappiness, unsigned long nr_to_reclaim)
>  {
> +       int nr_batch;
>         DEFINE_MAX_SEQ(lruvec);
>
>         if (seq + MIN_NR_GENS > max_seq)
> @@ -5631,8 +5634,8 @@ static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_co
>                 if (sc->nr_reclaimed >= nr_to_reclaim)
>                         return 0;
>
> -               if (!evict_folios(nr_to_reclaim - sc->nr_reclaimed, lruvec, sc,
> -                                 swappiness))
> +               nr_batch = min(nr_to_reclaim - sc->nr_reclaimed, MAX_LRU_BATCH);
> +               if (!evict_folios(nr_batch, lruvec, sc, swappiness))
>                         return 0;
>
>                 cond_resched();
>
> --
> 2.53.0
>
>


  parent reply	other threads:[~2026-03-20 21:01 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-17 19:08 [PATCH 0/8] mm/mglru: improve reclaim loop and dirty folio handling Kairui Song via B4 Relay
2026-03-17 19:08 ` [PATCH 1/8] mm/mglru: consolidate common code for retrieving evitable size Kairui Song via B4 Relay
2026-03-17 19:55   ` Yuanchu Xie
2026-03-18  9:42   ` Barry Song
2026-03-18  9:57     ` Kairui Song
2026-03-19  1:40   ` Chen Ridong
2026-03-20 19:51     ` Axel Rasmussen
2026-03-22 16:10       ` Kairui Song
2026-03-26  6:25   ` Baolin Wang
2026-03-17 19:08 ` [PATCH 2/8] mm/mglru: relocate the LRU scan batch limit to callers Kairui Song via B4 Relay
2026-03-19  2:00   ` Chen Ridong
2026-03-19  4:12     ` Kairui Song
2026-03-20 21:00   ` Axel Rasmussen [this message]
2026-03-22  8:14   ` Barry Song
2026-03-24  6:05     ` Kairui Song
2026-03-17 19:08 ` [PATCH 3/8] mm/mglru: restructure the reclaim loop Kairui Song via B4 Relay
2026-03-20 20:09   ` Axel Rasmussen
2026-03-22 16:11     ` Kairui Song
2026-03-24  6:41   ` Chen Ridong
2026-03-26  7:31   ` Baolin Wang
2026-03-26  8:37     ` Kairui Song
2026-03-17 19:09 ` [PATCH 4/8] mm/mglru: scan and count the exact number of folios Kairui Song via B4 Relay
2026-03-20 20:57   ` Axel Rasmussen
2026-03-22 16:20     ` Kairui Song
2026-03-24  7:22       ` Chen Ridong
2026-03-24  8:05         ` Kairui Song
2026-03-24  9:10           ` Chen Ridong
2026-03-24  9:29             ` Kairui Song
2026-03-17 19:09 ` [PATCH 5/8] mm/mglru: use a smaller batch for reclaim Kairui Song via B4 Relay
2026-03-20 20:58   ` Axel Rasmussen
2026-03-24  7:51   ` Chen Ridong
2026-03-17 19:09 ` [PATCH 6/8] mm/mglru: don't abort scan immediately right after aging Kairui Song via B4 Relay
2026-03-17 19:09 ` [PATCH 7/8] mm/mglru: simplify and improve dirty writeback handling Kairui Song via B4 Relay
2026-03-20 21:18   ` Axel Rasmussen
2026-03-22 16:22     ` Kairui Song
2026-03-24  8:57   ` Chen Ridong
2026-03-24 11:09     ` Kairui Song
2026-03-26  7:56   ` Baolin Wang
2026-03-17 19:09 ` [PATCH 8/8] mm/vmscan: remove sc->file_taken Kairui Song via B4 Relay
2026-03-20 21:19   ` Axel Rasmussen
2026-03-25  4:49 ` [PATCH 0/8] mm/mglru: improve reclaim loop and dirty folio handling Eric Naim
2026-03-25  5:47   ` Kairui Song
2026-03-25  9:26     ` Eric Naim
2026-03-25  9:47       ` Kairui Song

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=CAJHvVch+S6MDoBp0SRhPC-v5nVpizF2Y9NEYn6B9bCVqR9Mv-w@mail.gmail.com \
    --to=axelrasmussen@google.com \
    --cc=akpm@linux-foundation.org \
    --cc=baohua@kernel.org \
    --cc=chenridong@huaweicloud.com \
    --cc=chrisl@kernel.org \
    --cc=david@kernel.org \
    --cc=hannes@cmpxchg.org \
    --cc=kaleshsingh@google.com \
    --cc=kasong@tencent.com \
    --cc=laoar.shao@gmail.com \
    --cc=lenohou@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=ljs@kernel.org \
    --cc=mhocko@kernel.org \
    --cc=shakeel.butt@linux.dev \
    --cc=stevensd@google.com \
    --cc=surenb@google.com \
    --cc=vernon2gm@gmail.com \
    --cc=wangzicheng@honor.com \
    --cc=weixugc@google.com \
    --cc=yuanchu@google.com \
    --cc=yuzhao@google.com \
    --cc=zhengqi.arch@bytedance.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