The Linux Kernel Mailing List
 help / color / mirror / Atom feed
From: Ridong Chen <ridong.chen@linux.dev>
To: "Barry Song (Xiaomi)" <baohua@kernel.org>,
	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,
	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
Subject: Re: [PATCH v9 05/16] mm/mglru: skip zones above reclaim_idx instead of rotating them
Date: Wed, 18 Nov 2026 19:22:25 +0800	[thread overview]
Message-ID: <caceeef7-5148-4795-9947-dfcffff7b1f3@linux.dev> (raw)
In-Reply-To: <20261114200803.23129-6-baohua@kernel.org>



On 11/15/2026 4:07 AM, Barry Song (Xiaomi) wrote:
> From: Kairui Song <kasong@tencent.com>
> 
> scan_folios() used to visit every zone. Folios in zones above
> sc->reclaim_idx can never be isolated, so sort_folio() rotated them to
> a younger generation, the "ineligible" branch, or, when only one gen
> was left, skipped them. This wasted scan work on every pass, and the
> rotation kept the protected folios from aging.
> 
> Restrict both the scan and the gen selection to the eligible zones,
> like the legacy LRU, which only isolates folios in zones up to
> reclaim_idx:
> 
> - lruvec_populated_min_seq() takes a zone_limit, so the oldest
>    populated gen is searched only among the zones the scan can
>    reclaim from. A gen populated only in protected zones no longer
>    stalls the scan.
> - scan_folios() iterates the eligible zones in the descending order
>    of the legacy zonelist walk, draining the zone at reclaim_idx
>    first.
> - The ineligible branch of sort_folio() is now dead and removed,
>    with a VM_WARN_ON_ONCE_FOLIO() guarding the new invariant.
> 
> try_to_inc_min_seq() still considers all zones, so min_seq[type] is
> only bumped once the oldest gen is empty everywhere. At DEF_PRIORITY
> the search bound stays min_seq[type], so the scan still starts from
> the oldest gen regardless of whether it is populated.
> 
> Signed-off-by: Kairui Song <kasong@tencent.com>
> Signed-off-by: Barry Song (Xiaomi) <baohua@kernel.org>
> ---
>   mm/vmscan.c | 47 +++++++++++++++++++----------------------------
>   1 file changed, 19 insertions(+), 28 deletions(-)
> 
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 603fb7c73f94..b3ce4a550a62 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -3992,7 +3992,7 @@ static bool inc_min_seq(struct lruvec *lruvec, int type, int swappiness)
>   
>   /* Similar to lruvec_evictable_size, return the oldest populated seq of the type */
>   static unsigned long lruvec_populated_min_seq(struct lruvec *lruvec, int type,
> -					      unsigned long max_seq)
> +					      int zone_limit, unsigned long max_seq)
>   {
>   	int gen, zone;
>   	unsigned long min_seq;
> @@ -4003,7 +4003,7 @@ static unsigned long lruvec_populated_min_seq(struct lruvec *lruvec, int type,
>   	min_seq = READ_ONCE(lrugen->min_seq[type]);
>   	while (min_seq < max_seq) {
>   		gen = lru_gen_from_seq(min_seq);
> -		for (zone = 0; zone < MAX_NR_ZONES; zone++) {
> +		for (zone = 0; zone < zone_limit; zone++) {
>   			if (!list_empty(&lrugen->folios[gen][type][zone]))
>   				return min_seq;
>   		}
> @@ -4026,7 +4026,7 @@ static void try_to_inc_min_seq(struct lruvec *lruvec, int swappiness)
>   	/* Requires at least MIN_NR_GENS gens for basic functionality */
>   	seq = lrugen->max_seq - MIN_NR_GENS;
>   	for_each_evictable_type(type, swappiness) {
> -		min_seq[type] = lruvec_populated_min_seq(lruvec, type, seq + 1);
> +		min_seq[type] = lruvec_populated_min_seq(lruvec, type, MAX_NR_ZONES, seq + 1);
>   		if (min_seq[type] > lrugen->min_seq[type])
>   			seq_inc_flag = true;
>   	}
> @@ -4689,6 +4689,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
>   	struct lru_gen_folio *lrugen = &lruvec->lrugen;
>   
>   	VM_WARN_ON_ONCE_FOLIO(gen >= MAX_NR_GENS, folio);
> +	VM_WARN_ON_ONCE_FOLIO(zone > sc->reclaim_idx, folio);
>   
>   	/* unevictable: let it through and the generic path will cull it */
>   	if (!folio_evictable(folio))
> @@ -4705,10 +4706,8 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
>   	 * longer be promoted or protected, so just isolate them. The one
>   	 * exception is lru_gen_reparent_memcg(), which is handled above.
>   	 */
> -	if (min_gen == max_gen) {
> -		VM_WARN_ON_ONCE(zone > sc->reclaim_idx);
> +	if (min_gen == max_gen)
>   		return false;
> -	}
>   
>   	/* protected */
>   	if (tier > tier_idx || refs + workingset == BIT(LRU_REFS_WIDTH) + 1) {
> @@ -4725,13 +4724,6 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
>   		return true;
>   	}
>   
> -	/* ineligible */
> -	if (zone > sc->reclaim_idx) {
> -		gen = folio_inc_gen(lruvec, folio, min_gen);
> -		list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]);
> -		return true;
> -	}
> -
>   	return false;
>   }
>   
> @@ -4763,16 +4755,17 @@ static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
>   		       struct scan_control *sc, int type, int tier,
>   		       struct list_head *list, int *isolatedp)
>   {
> -	int i;
>   	enum node_stat_item item;
> +	int zone_idx;
>   	int sorted = 0;
>   	int scanned = 0;
>   	int isolated = 0;
>   	int skipped = 0;
>   	int gen, max_gen;
> -	unsigned long min_seq;
> +	unsigned long seq;
>   	unsigned long remaining = nr_to_scan;
>   	struct lru_gen_folio *lrugen = &lruvec->lrugen;
> +	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
>   	DEFINE_MAX_SEQ(lruvec);
>   
>   	VM_WARN_ON_ONCE(nr_to_scan > MAX_LRU_BATCH);
> @@ -4784,24 +4777,22 @@ static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
>   	 * when under pressure to respect swappiness more and reduce IO cost.
>   	 */
>   	if (sc->priority == DEF_PRIORITY)
> -		min_seq = lrugen->min_seq[type];
> +		seq = lrugen->min_seq[type];
>   	else
> -		min_seq = lruvec_populated_min_seq(lruvec, type, lrugen->max_seq);
> +		seq = lrugen->max_seq;
>   
> -	gen = lru_gen_from_seq(min_seq);
> +	seq = lruvec_populated_min_seq(lruvec, type, sc->reclaim_idx + 1, seq);
> +	gen = lru_gen_from_seq(seq);
>   	max_gen = lru_gen_from_seq(max_seq);
>   
> -	for (i = MAX_NR_ZONES; i > 0; i--) {
> +	/* Scan eligible zones in descending order. */
> +	for (zone_idx = sc->reclaim_idx; zone_idx >= 0; zone_idx--) {
>   		LIST_HEAD(moved);
>   		int skipped_zone = 0;
> -		int zone = (sc->reclaim_idx + i) % MAX_NR_ZONES;
> -		struct list_head *head = &lrugen->folios[gen][type][zone];
> +		struct zone *zone = &pgdat->node_zones[zone_idx];
> +		struct list_head *head = &lrugen->folios[gen][type][zone_idx];
>   
> -		/*
> -		 * If there is only one gen left, rotating the unreclaimable
> -		 * zone become meaningless, just skip them.
> -		 */
> -		if (gen == max_gen && zone > sc->reclaim_idx)
> +		if (!managed_zone(zone))
>   			continue;
>   
>   		while (!list_empty(head)) {
> @@ -4811,7 +4802,7 @@ static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
>   			VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio);
>   			VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio);
>   			VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio);
> -			VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio);
> +			VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone_idx, folio);
>   
>   			scanned += delta;
>   			if (sort_folio(lruvec, folio, sc, gen, max_gen, tier))
> @@ -4830,7 +4821,7 @@ static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
>   
>   		if (skipped_zone) {
>   			list_splice(&moved, head);
> -			__count_zid_vm_events(PGSCAN_SKIP, zone, skipped_zone);
> +			__count_zid_vm_events(PGSCAN_SKIP, zone_idx, skipped_zone);
>   			skipped += skipped_zone;
>   		}
>   

Reviewed-by: Ridong Chen <ridong.chen@linux.dev>
Thanks.

-- 
Best regards
Ridong


  reply	other threads:[~2026-11-18 11:22 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-14 20:07 [PATCH v9 00/16] mm: mglru: fix swappiness behavior Barry Song (Xiaomi)
2026-11-14 20:07 ` [PATCH v9 01/16] mm/mglru: report evictable sizes per type Barry Song (Xiaomi)
2026-11-16 11:29   ` Ridong Chen
2026-11-14 20:07 ` [PATCH v9 02/16] mm/mglru: extract lruvec_populated_min_seq() helper Barry Song (Xiaomi)
2026-11-16 11:58   ` Ridong Chen
2026-11-14 20:07 ` [PATCH v9 03/16] mm/mglru: reclaim from the oldest populated gen Barry Song (Xiaomi)
2026-11-16 12:27   ` Ridong Chen
2026-11-14 20:07 ` [PATCH v9 04/16] mm/mglru: lift the forced protection of reclaimer Barry Song (Xiaomi)
2026-11-18 10:50   ` Ridong Chen
2026-11-14 20:07 ` [PATCH v9 05/16] mm/mglru: skip zones above reclaim_idx instead of rotating them Barry Song (Xiaomi)
2026-11-18 11:22   ` Ridong Chen [this message]
2026-11-14 20:07 ` [PATCH v9 06/16] mm/mglru: return for unavailable anon reclaim earlier Barry Song (Xiaomi)
2026-11-18 11:23   ` Ridong Chen
2026-11-14 20:07 ` [PATCH v9 07/16] mm/mglru: balance anon and file scan budget by refault rate Barry Song (Xiaomi)
2026-11-14 20:07 ` [PATCH v9 08/16] mm/mglru: lift youngest gen protection for higher priority Barry Song (Xiaomi)
2026-11-14 20:07 ` [PATCH v9 09/16] mm/mglru: Avoid placing rejected folios below populated gen Barry Song (Xiaomi)
2026-11-15 15:15   ` Kairui Song
2026-11-14 20:07 ` [PATCH v9 10/16] mm/mglru: Run aging when pages are rare outside the youngest gen Barry Song (Xiaomi)
2026-11-15 15:54   ` Kairui Song
2026-11-16  4:25     ` Barry Song (Xiaomi)
2026-11-16  4:50       ` Andrew Morton
2026-11-16  5:29         ` Barry Song
2026-11-14 20:07 ` [PATCH v9 11/16] mm/mglru: Run aging when one type is drained Barry Song (Xiaomi)
2026-11-14 20:07 ` [PATCH v9 12/16] mm/mglru: Restrict eviction accounting to eligible zones Barry Song (Xiaomi)
2026-11-14 20:08 ` [PATCH v9 13/16] mm/mglru: Reduce LRU lock contention by shrinking folio batches in inc_min_seq Barry Song (Xiaomi)
2026-11-15 15:52   ` Kairui Song
2026-11-14 20:08 ` [PATCH v9 14/16] mm/mglru: Avoid prolonged anon reclaim with swappiness=200 Barry Song (Xiaomi)
2026-11-14 20:08 ` [PATCH v9 15/16] mm/mglru: Make swappiness=1 file reclaim more aggressive Barry Song (Xiaomi)
2026-11-14 20:08 ` [PATCH v9 16/16] mm/mglru: Avoid scan anon while swapcache is low for GFP_NOIO allocation Barry Song (Xiaomi)
2026-11-14 22:09 ` [PATCH v9 00/16] mm: mglru: fix swappiness behavior Andrew Morton

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=caceeef7-5148-4795-9947-dfcffff7b1f3@linux.dev \
    --to=ridong.chen@linux.dev \
    --cc=akpm@linux-foundation.org \
    --cc=axelrasmussen@google.com \
    --cc=baohua@kernel.org \
    --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=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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox