From: "Barry Song (Xiaomi)" <baohua@kernel.org>
To: akpm@linux-foundation.org, linux-mm@kvack.org
Cc: axelrasmussen@google.com, baolin.wang@linux.alibaba.com,
baoquan.he@linux.dev, hannes@cmpxchg.org, hui.zhu@linux.dev,
kasong@tencent.com, kunwu.chan@gmail.com, liam@infradead.org,
lianux.mm@gmail.com, linux-kernel@vger.kernel.org,
liuxiang.277@bytedance.com, lyugaofei@xiaomi.com,
mhocko@kernel.org, mhocko@suse.com, qi.zheng@linux.dev,
ridong.chen@linux.dev, rppt@kernel.org, ryncsn@gmail.com,
shakeel.butt@linux.dev, surenb@google.com, wangzicheng@honor.com,
weixugc@google.com, yuanchu@google.com, zhangbo56@xiaomi.com,
zhuhui@kylinos.cn, sidchintamaneni@gmail.com,
Barry Song <baohua@kernel.org>
Subject: [PATCH v6 13/15] mm/mglru: Avoid prolonged anon reclaim with swappiness=200
Date: Wed, 11 Nov 2026 04:20:23 +0800 [thread overview]
Message-ID: <20261110202025.25736-14-baohua@kernel.org> (raw)
In-Reply-To: <20261110202025.25736-1-baohua@kernel.org>
From: lyugaofei <lyugaofei@xiaomi.com>
It has been observed that swappiness=200 can significantly slow down
reclaim on some machines, with some workloads running 3x slower
under MGLRU than under CLRU.
This is because swappiness=200 currently results in file_factor=0.
Give file reclaim a small factor at lower priorities, for example,
when sc->priority < DEF_PRIORITY / 2.
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 | 15 ++++++++++-----
1 file changed, 10 insertions(+), 5 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 34faabe617ae..5d6fc5d4d761 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4888,8 +4888,8 @@ static int get_tier_idx(struct lruvec *lruvec, int type)
* We don't calculate the scan cost, MGLRU uses lazy promotion, which will
* cancel the scan budget natually.
*/
-static void lru_gen_balance_scan(struct lruvec *lruvec, int swappiness,
- unsigned long total_scan, unsigned long nr[])
+static void lru_gen_balance_scan(struct lruvec *lruvec, struct scan_control *sc,
+ int swappiness, unsigned long total_scan, unsigned long nr[])
{
struct lru_gen_folio *lrugen = &lruvec->lrugen;
u64 refault_rate[ANON_AND_FILE], anon_factor, file_factor;
@@ -4946,7 +4946,12 @@ static void lru_gen_balance_scan(struct lruvec *lruvec, int swappiness,
file_weight = nr[LRU_GEN_FILE] + nr[LRU_GEN_ANON] / size_bias;
anon_factor = (u64)swappiness * refault_rate[LRU_GEN_FILE] * anon_weight;
- file_factor = (u64)(MAX_SWAPPINESS - swappiness) * refault_rate[LRU_GEN_ANON] * file_weight;
+ if (swappiness == MAX_SWAPPINESS)
+ file_factor = sc->priority < DEF_PRIORITY / 2 ?
+ refault_rate[LRU_GEN_ANON] * file_weight : 0;
+ else
+ file_factor = (u64)(MAX_SWAPPINESS - swappiness) *
+ refault_rate[LRU_GEN_ANON] * file_weight;
/* Cross-multiply the ratio above. */
anon_scan = mul_u64_u64_div_u64(total_scan, anon_factor, anon_factor + file_factor);
@@ -5137,7 +5142,7 @@ static void lru_gen_prepare_scan(struct lruvec *lruvec, struct scan_control *sc,
total = apply_proportional_protection(memcg, sc, total);
total >>= sc->priority;
- lru_gen_balance_scan(lruvec, swappiness, total, nr_to_scan);
+ lru_gen_balance_scan(lruvec, sc, swappiness, total, nr_to_scan);
}
static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc)
@@ -5880,7 +5885,7 @@ static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_co
return 0;
lruvec_evictable_size(lruvec, swappiness, nr_to_scan);
- lru_gen_balance_scan(lruvec, swappiness,
+ lru_gen_balance_scan(lruvec, sc, swappiness,
nr_to_reclaim - sc->nr_reclaimed, nr_to_scan);
if (!evict_folio_lists(nr_to_scan, lruvec, sc, swappiness, MAX_LRU_BATCH))
--
2.34.1
next prev parent reply other threads:[~2026-11-10 20:21 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-10 20:20 [PATCH v6 00/15] mm: mglru: fix swappiness behavior Barry Song (Xiaomi)
2026-11-10 20:20 ` [PATCH v6 01/15] mm/mglru: report evictable sizes per type Barry Song (Xiaomi)
2026-11-10 20:20 ` [PATCH v6 02/15] mm/mglru: extract lruvec_populated_min_seq() helper Barry Song (Xiaomi)
2026-11-10 20:20 ` [PATCH v6 03/15] mm/mglru: reclaim from the oldest populated gen Barry Song (Xiaomi)
2026-11-10 20:20 ` [PATCH v6 04/15] mm/mglru: lift the forced protection of reclaimer Barry Song (Xiaomi)
2026-11-10 20:20 ` [PATCH v6 05/15] mm/mglru: skip zones above reclaim_idx instead of rotating them Barry Song (Xiaomi)
2026-11-10 20:56 ` sashiko-bot
2026-11-10 21:25 ` Barry Song
2026-11-10 20:20 ` [PATCH v6 06/15] mm/mglru: return for unavailable anon reclaim earlier Barry Song (Xiaomi)
2026-11-10 20:20 ` [PATCH v6 07/15] mm/mglru: balance anon and file scan budget by refault rate Barry Song (Xiaomi)
2026-11-10 20:56 ` sashiko-bot
2026-11-11 22:01 ` Barry Song
2026-11-10 20:20 ` [PATCH v6 08/15] mm/mglru: lift youngest gen protection for higher priority Barry Song (Xiaomi)
2026-11-10 20:56 ` sashiko-bot
2026-11-10 20:20 ` [PATCH v6 09/15] mm/mglru: Avoid placing rejected folios below populated gen Barry Song (Xiaomi)
2026-11-10 20:56 ` sashiko-bot
2026-11-11 0:09 ` Barry Song
2026-11-10 20:20 ` [PATCH v6 10/15] mm/mglru: Run aging when pages are rare outside the youngest gen Barry Song (Xiaomi)
2026-11-10 20:20 ` [PATCH v6 11/15] mm/mglru: Restrict eviction accounting to eligible zones Barry Song (Xiaomi)
2026-11-10 20:56 ` sashiko-bot
2026-11-10 21:08 ` Barry Song
2026-11-10 20:20 ` [PATCH v6 12/15] mm/mglru: Reduce LRU lock contention by shrinking folio batches in inc_min_seq Barry Song (Xiaomi)
2026-11-10 20:20 ` Barry Song (Xiaomi) [this message]
2026-11-10 20:20 ` [PATCH v6 14/15] mm/mglru: Make swappiness=1 file reclaim more aggressive Barry Song (Xiaomi)
2026-11-10 20:20 ` [PATCH v6 15/15] mm/mglru: Avoid scan anon while swapcache is low for GFP_NOIO allocation Barry Song (Xiaomi)
2026-11-10 20:56 ` sashiko-bot
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=20261110202025.25736-14-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=hannes@cmpxchg.org \
--cc=hui.zhu@linux.dev \
--cc=kasong@tencent.com \
--cc=kunwu.chan@gmail.com \
--cc=liam@infradead.org \
--cc=lianux.mm@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=liuxiang.277@bytedance.com \
--cc=lyugaofei@xiaomi.com \
--cc=mhocko@kernel.org \
--cc=mhocko@suse.com \
--cc=qi.zheng@linux.dev \
--cc=ridong.chen@linux.dev \
--cc=rppt@kernel.org \
--cc=ryncsn@gmail.com \
--cc=shakeel.butt@linux.dev \
--cc=sidchintamaneni@gmail.com \
--cc=surenb@google.com \
--cc=wangzicheng@honor.com \
--cc=weixugc@google.com \
--cc=yuanchu@google.com \
--cc=zhangbo56@xiaomi.com \
--cc=zhuhui@kylinos.cn \
/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.