All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Barry Song (Xiaomi)" <baohua@kernel.org>
To: akpm@linux-foundation.org, linux-mm@kvack.org
Cc: axelrasmussen@google.com, chenridong@xiaomi.com,
	david@kernel.org, hannes@cmpxchg.org, kasong@tencent.com,
	lianux.mm@gmail.com, linux-kernel@vger.kernel.org,
	ljs@kernel.org, lyugaofei@xiaomi.com, mhocko@kernel.org,
	qi.zheng@linux.dev, shakeel.butt@linux.dev,
	stevensd@chromium.org, wangzicheng@honor.com, weixugc@google.com,
	yuanchu@google.com, zhangbo56@xiaomi.com,
	baolin.wang@linux.alibaba.com, baoquan.he@linux.dev,
	"Barry Song (Xiaomi)" <baohua@kernel.org>
Subject: [RFC PATCH v4 04/16] mm/mglru: boost swappiness responsiveness in get_type_to_scan()
Date: Wed, 12 Aug 2026 20:16:46 +0800	[thread overview]
Message-ID: <20260812121658.69965-5-baohua@kernel.org> (raw)
In-Reply-To: <20260812121658.69965-1-baohua@kernel.org>

The linear weight in get_type_to_scan() can easily be overwhelmed
by historical refault costs when swappiness deviates from neutral (100).
As a result, user-configured swappiness often feels unresponsive under
memory pressure.

Apply a smooth quadratic boost based on the distance from the neutral
balance point (MAX_SWAPPINESS / 2). This amplifies the weight of the
preferred scanning type (anon vs file) while avoiding hardware division
via bitwise shift.

Assisted-by: gemini:gemini-3.6-flash
Signed-off-by: Barry Song (Xiaomi) <baohua@kernel.org>
---
 mm/vmscan.c | 28 ++++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index dddd2ecf970a..2fd1e06eb192 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4838,18 +4838,42 @@ static int get_tier_idx(struct lruvec *lruvec, int type)
 static int get_type_to_scan(struct lruvec *lruvec, int swappiness)
 {
 	struct ctrl_pos sp, pv = {};
+	int anon_gain, file_gain;
 
 	if (swappiness <= MIN_SWAPPINESS + 1)
 		return LRU_GEN_FILE;
 
 	if (swappiness >= MAX_SWAPPINESS)
 		return LRU_GEN_ANON;
+
+	/*
+	 * Apply a quadratic boost based on the distance from the neutral
+	 * balance point (swappiness = MAX_SWAPPINESS / 2).
+	 *
+	 * A linear weight is easily overwhelmed by historical refault cost
+	 * when swappiness deviates from neutral. The quadratic scaling
+	 * amplifies the weight of the preferred type smoothly.
+	 */
+	if (swappiness < MAX_SWAPPINESS / 2) {
+		int delta = (MAX_SWAPPINESS / 2) - swappiness;
+		int boost = (delta * delta) >> 4;
+
+		anon_gain = swappiness;
+		file_gain = (MAX_SWAPPINESS - swappiness) + boost;
+	} else {
+		int delta = swappiness - (MAX_SWAPPINESS / 2);
+		int boost = (delta * delta) >> 4;
+
+		anon_gain = swappiness + boost;
+		file_gain = MAX_SWAPPINESS - swappiness;
+	}
+
 	/*
 	 * Compare the sum of all tiers of anon with that of file to determine
 	 * which type to scan.
 	 */
-	read_ctrl_pos(lruvec, LRU_GEN_ANON, MAX_NR_TIERS, swappiness, &sp);
-	read_ctrl_pos(lruvec, LRU_GEN_FILE, MAX_NR_TIERS, MAX_SWAPPINESS - swappiness, &pv);
+	read_ctrl_pos(lruvec, LRU_GEN_ANON, MAX_NR_TIERS, anon_gain, &sp);
+	read_ctrl_pos(lruvec, LRU_GEN_FILE, MAX_NR_TIERS, file_gain, &pv);
 
 	return positive_ctrl_err(&sp, &pv);
 }
-- 
2.34.1


  parent reply	other threads:[~2026-08-12 12:18 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-12 12:16 [RFC PATCH v4 00/16] mm: mglru: fix swappiness behavior Barry Song (Xiaomi)
2026-08-12 12:16 ` [RFC PATCH v4 01/16] mm/mglru: improve readability of isolate_folios() Barry Song (Xiaomi)
2026-08-12 12:16 ` [RFC PATCH v4 02/16] mm/mglru: improve scan_folios() exhaustion detection Barry Song (Xiaomi)
2026-08-12 12:16 ` [RFC PATCH v4 03/16] mm/mglru: retry the same type once if isolation fails due to races Barry Song (Xiaomi)
2026-08-12 12:16 ` Barry Song (Xiaomi) [this message]
2026-08-12 12:16 ` [RFC PATCH v4 05/16] mm/mglru: batch update lrugen->nr_pages in inc_min_seq() Barry Song (Xiaomi)
2026-08-12 12:16 ` [RFC PATCH v4 06/16] mm/mglru: batch update lrugen->protected " Barry Song (Xiaomi)
2026-08-12 12:16 ` [RFC PATCH v4 07/16] mm/mglru: enhance cold/hot inversion handling " Barry Song (Xiaomi)
2026-08-12 12:16 ` [RFC PATCH v4 08/16] mm/mglru: exclude folios promoted by aging from protected " Barry Song (Xiaomi)
2026-08-12 12:16 ` [RFC PATCH v4 09/16] mm/mglru: move folios from oldest gen to second-oldest gen from head to tail Barry Song (Xiaomi)
2026-08-12 12:16 ` [RFC PATCH v4 10/16] mm/mglru: batch move folios to the second-oldest gen's LRU Barry Song (Xiaomi)
2026-08-12 12:16 ` [RFC PATCH v4 11/16] mm/mglru: skip gentle reclaim at DEF_PRIORITY for extreme swappiness Barry Song (Xiaomi)
2026-08-12 12:16 ` [RFC PATCH v4 12/16] mm/mglru: run aging if the preferred type has no reclaimable gens Barry Song (Xiaomi)
2026-08-12 12:16 ` [RFC PATCH v4 13/16] mm/mglru: remove redundant gens <= MIN_NR_GENS check in should_run_aging() Barry Song (Xiaomi)
2026-08-12 12:16 ` [RFC PATCH v4 14/16] mm/mglru: run aging when pages are severely imbalanced across gens Barry Song (Xiaomi)
2026-08-12 12:16 ` [RFC PATCH v4 15/16] mm/mglru: dynamically scale aging threshold in lru_gen_imbalanced() Barry Song (Xiaomi)
2026-08-12 12:16 ` [RFC PATCH v4 16/16] mm/mglru: reduce folios pulled from the oldest gen in inc_min_seq() Barry Song (Xiaomi)

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=20260812121658.69965-5-baohua@kernel.org \
    --to=baohua@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=axelrasmussen@google.com \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=baoquan.he@linux.dev \
    --cc=chenridong@xiaomi.com \
    --cc=david@kernel.org \
    --cc=hannes@cmpxchg.org \
    --cc=kasong@tencent.com \
    --cc=lianux.mm@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=ljs@kernel.org \
    --cc=lyugaofei@xiaomi.com \
    --cc=mhocko@kernel.org \
    --cc=qi.zheng@linux.dev \
    --cc=shakeel.butt@linux.dev \
    --cc=stevensd@chromium.org \
    --cc=wangzicheng@honor.com \
    --cc=weixugc@google.com \
    --cc=yuanchu@google.com \
    --cc=zhangbo56@xiaomi.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.