linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Kinsey Ho <kinseyho@google.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	 Yu Zhao <yuzhao@google.com>,
	Donet Tom <donettom@linux.vnet.ibm.com>,
	 "Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>,
	Kinsey Ho <kinseyho@google.com>
Subject: [PATCH mm-unstable v1 5/5] mm/mglru: improve swappiness handling
Date: Wed, 14 Feb 2024 06:05:38 +0000	[thread overview]
Message-ID: <20240214060538.3524462-6-kinseyho@google.com> (raw)
In-Reply-To: <20240214060538.3524462-1-kinseyho@google.com>

The reclaimable number of anon pages used to set initial reclaim
priority is only based on get_swappiness(). Use can_reclaim_anon_pages()
to include NUMA node demotion.

Also move the swappiness handling of when !__GFP_IO in
try_to_shrink_lruvec() into isolate_folios().

Signed-off-by: Kinsey Ho <kinseyho@google.com>
---
 mm/vmscan.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index f1019afa7813..0daf932feb86 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4307,7 +4307,7 @@ static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct sca
 {
 	bool success;
 
-	/* swapping inhibited */
+	/* swap constrained */
 	if (!(sc->gfp_mask & __GFP_IO) &&
 	    (folio_test_dirty(folio) ||
 	     (folio_test_anon(folio) && !folio_test_swapcache(folio))))
@@ -4476,9 +4476,11 @@ static int isolate_folios(struct lruvec *lruvec, struct scan_control *sc, int sw
 	DEFINE_MIN_SEQ(lruvec);
 
 	/*
-	 * Try to make the obvious choice first. When anon and file are both
-	 * available from the same generation, interpret swappiness 1 as file
-	 * first and MAX_SWAPPINESS as anon first.
+	 * Try to make the obvious choice first, and if anon and file are both
+	 * available from the same generation,
+	 * 1. Interpret swappiness 1 as file first and MAX_SWAPPINESS as anon first.
+	 * 2. If !__GFP_IO, file first since clean pagecache is more likely to
+	 *    exist than clean swapcache.
 	 */
 	if (!swappiness)
 		type = LRU_GEN_FILE;
@@ -4488,6 +4490,8 @@ static int isolate_folios(struct lruvec *lruvec, struct scan_control *sc, int sw
 		type = LRU_GEN_FILE;
 	else if (swappiness == MAX_SWAPPINESS)
 		type = LRU_GEN_ANON;
+	else if (!(sc->gfp_mask & __GFP_IO))
+		type = LRU_GEN_FILE;
 	else
 		type = get_type_to_scan(lruvec, swappiness, &tier);
 
@@ -4731,10 +4735,6 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 	unsigned long scanned = 0;
 	int swappiness = get_swappiness(lruvec, sc);
 
-	/* clean file folios are more likely to exist */
-	if (swappiness && !(sc->gfp_mask & __GFP_IO))
-		swappiness = 1;
-
 	while (true) {
 		int delta;
 
@@ -4897,7 +4897,6 @@ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control
 {
 	int priority;
 	unsigned long reclaimable;
-	struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat);
 
 	if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH)
 		return;
@@ -4907,7 +4906,7 @@ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control
 	 * where reclaimed_to_scanned_ratio = inactive / total.
 	 */
 	reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE);
-	if (get_swappiness(lruvec, sc))
+	if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc))
 		reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON);
 
 	/* round down reclaimable and round up sc->nr_to_reclaim */
-- 
2.43.0.687.g38aa6559b0-goog



      parent reply	other threads:[~2024-02-14  6:06 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-02-14  6:05 [PATCH mm-unstable v1 0/5] mm/mglru: code cleanup and Kinsey Ho
2024-02-14  6:05 ` [PATCH mm-unstable v1 1/5] mm/mglru: drop unused parameter Kinsey Ho
2024-02-14  6:05 ` [PATCH mm-unstable v1 2/5] mm/mglru: improve should_run_aging() Kinsey Ho
2024-02-14  6:05 ` [PATCH mm-unstable v1 3/5] mm/mglru: improve reset_mm_stats() Kinsey Ho
2024-02-14  6:05 ` [PATCH mm-unstable v1 4/5] mm/mglru: improve struct lru_gen_mm_walk Kinsey Ho
2024-02-14  6:05 ` Kinsey Ho [this message]

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=20240214060538.3524462-6-kinseyho@google.com \
    --to=kinseyho@google.com \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@linux.ibm.com \
    --cc=donettom@linux.vnet.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=yuzhao@google.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