Linux-mm Archive on 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 <baohua@kernel.org>
Subject: [RFC PATCH v4 14/16] mm/mglru: run aging when pages are severely imbalanced across gens
Date: Wed, 12 Aug 2026 20:16:56 +0800	[thread overview]
Message-ID: <20260812121658.69965-15-baohua@kernel.org> (raw)
In-Reply-To: <20260812121658.69965-1-baohua@kernel.org>

From: lyugaofei <lyugaofei@xiaomi.com>

This partially restores the reclaim behavior introduced in Yu
Zhao's initial MGLRU commit, ac35a4902370 ("mm: multi-gen LRU:
minimal implementation"):
	/*
	 * It's also ideal to spread pages out evenly, i.e., 1/(MIN_NR_GENS+1)
	 * of the total number of pages for each generation. A reasonable range
	 * for this average portion is [1/MIN_NR_GENS, 1/(MIN_NR_GENS+2)]. The
	 * aging cares about the upper bound of hot pages, while the eviction
	 * cares about the lower bound of cold pages.
	 */
	if (young * MIN_NR_GENS > total)
		return true;
	if (old * (MIN_NR_GENS + 2) < total)
		return true;

But with a stricter condition: the younger generations must
contain at least MAX_NR_GENS times as many folios as the older
generations.
We also consider the cost of inc_min_seq(). If the oldest generation
of the other type has fallen significantly behind, pulling those
folios from the oldest generation to the second oldest generation
can be very expensive. In this case, skip imbalance aging unless
extreme swappiness is in use.

Signed-off-by: lyugaofei <lyugaofei@xiaomi.com>
Co-developed-by: Barry Song (Xiaomi) <baohua@kernel.org>
Signed-off-by: Barry Song (Xiaomi) <baohua@kernel.org>
---
 mm/vmscan.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 50 insertions(+), 7 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index a276560bc66b..d6fac5b91ac1 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4219,20 +4219,28 @@ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control
 	sc->priority = clamp(priority, DEF_PRIORITY / 2, DEF_PRIORITY);
 }
 
+static inline unsigned long lruvec_gen_size(struct lru_gen_folio *lrugen,
+		int type, unsigned long seq)
+{
+	int gen = lru_gen_from_seq(seq);
+	unsigned long size = 0;
+
+	for (int zone = 0; zone < MAX_NR_ZONES; zone++)
+		size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
+	return size;
+}
+
 static unsigned long lruvec_evictable_size(struct lruvec *lruvec, int swappiness)
 {
-	int gen, type, zone;
+	int type;
 	unsigned long seq, total = 0;
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
 	DEFINE_MAX_SEQ(lruvec);
 	DEFINE_MIN_SEQ(lruvec);
 
 	for_each_evictable_type(type, swappiness) {
-		for (seq = min_seq[type]; seq <= max_seq; seq++) {
-			gen = lru_gen_from_seq(seq);
-			for (zone = 0; zone < MAX_NR_ZONES; zone++)
-				total += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
-		}
+		for (seq = min_seq[type]; seq <= max_seq; seq++)
+			total += lruvec_gen_size(lrugen, type, seq);
 	}
 
 	return total;
@@ -5092,6 +5100,37 @@ static int evict_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
 	return scanned;
 }
 
+static bool lru_gen_imbalanced(struct lruvec *lruvec, unsigned long max_seq,
+		struct scan_control *sc, int type, int swappiness)
+{
+	struct lru_gen_folio *lrugen = &lruvec->lrugen;
+	unsigned long young = 0, old = 0, lag = 0;
+	DEFINE_MIN_SEQ(lruvec);
+
+	/* we still have enough generations to reclaim */
+	if (min_seq[type] + MIN_NR_GENS < max_seq)
+		return false;
+
+	/*
+	 * Trigger aging if the preferred type is running low on reclaimable
+	 * folios, provided the generation lag of the other type remains small
+	 * enough that inc_min_seq() introduces negligible overhead
+	 */
+	for (unsigned long seq = min_seq[type]; seq <= max_seq; seq++) {
+		unsigned long size = lruvec_gen_size(lrugen, type, seq);
+
+		if (seq + MIN_NR_GENS > max_seq)
+			young += size;
+		else
+			old += size;
+	}
+	if (min_seq[!type] + MAX_NR_GENS == max_seq + 1)
+		lag += lruvec_gen_size(lrugen, !type, min_seq[!type]);
+
+	return young > old * MAX_NR_GENS && (lag < MAX_LRU_BATCH ||
+	       (is_extreme_swappiness(swappiness) && sc->priority > 2));
+}
+
 static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq,
 			     struct scan_control *sc, int swappiness)
 {
@@ -5110,7 +5149,11 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq,
 		return false;
 
 	/* better to run aging even though eviction is still possible */
-	return evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS == max_seq;
+	if (evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS == max_seq)
+		return true;
+
+	/* Run aging if the preferred type is severely imbalanced across gens */
+	return lru_gen_imbalanced(lruvec, max_seq, sc, type, swappiness);
 }
 
 static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc,
-- 
2.34.1



  parent reply	other threads:[~2026-08-12 12:19 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 ` [RFC PATCH v4 04/16] mm/mglru: boost swappiness responsiveness in get_type_to_scan() Barry Song (Xiaomi)
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 ` Barry Song (Xiaomi) [this message]
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=20260812121658.69965-15-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox