[PATCH v9 14/16] mm/mglru: Avoid prolonged anon reclaim with swappiness=200

["Barry Song (Xiaomi)" <baohua@kernel.org>]

From: Gaofei Lyu <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: Gaofei Lyu <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 6cb905162cba..abefd91f5b95 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4898,8 +4898,8 @@ 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 naturally.
  */
-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;
@@ -4956,7 +4956,12 @@ 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 < AGING_PRIORITY ?
+			      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);
@@ -5144,7 +5149,7 @@ 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)
@@ -5910,7 +5915,7 @@ static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_co
 			return 0;
 
 		lruvec_evictable_size(lruvec, sc, swappiness, nr_to_scan, sc->reclaim_idx + 1);
-		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, NULL))
-- 
2.39.3 (Apple Git-146)