[PATCH v3 1/3] mm, lru_gen: try to prefetch next page when scanning LRU

[Kairui Song <ryncsn@gmail.com>]

From: Kairui Song <kasong@tencent.com>

Prefetch for inactive/active LRU have been long exiting, apply the same
optimization for MGLRU.

Test 1: Ramdisk fio ro test in a 4G memcg on a EPYC 7K62:
  fio -name=mglru --numjobs=16 --directory=/mnt --size=960m \
    --buffered=1 --ioengine=io_uring --iodepth=128 \
    --iodepth_batch_submit=32 --iodepth_batch_complete=32 \
    --rw=randread --random_distribution=zipf:0.5 --norandommap \
    --time_based --ramp_time=1m --runtime=6m --group_reporting

Before this patch:
bw (  MiB/s): min= 7758, max= 9239, per=100.00%, avg=8747.59, stdev=16.51, samples=11488
iops        : min=1986251, max=2365323, avg=2239380.87, stdev=4225.93, samples=11488

After this patch (+7.2%):
bw (  MiB/s): min= 8360, max= 9771, per=100.00%, avg=9381.31, stdev=15.67, samples=11488
iops        : min=2140296, max=2501385, avg=2401613.91, stdev=4010.41, samples=11488

Test 2: Ramdisk fio hybrid test for 30m in a 4G memcg on a EPYC 7K62 (3 times):
  fio --buffered=1 --numjobs=8 --size=960m --directory=/mnt \
    --time_based --ramp_time=1m --runtime=30m \
    --ioengine=io_uring --iodepth=128 --iodepth_batch_submit=32 \
    --iodepth_batch_complete=32 --norandommap \
    --name=mglru-ro --rw=randread --random_distribution=zipf:0.7 \
    --name=mglru-rw --rw=randrw --random_distribution=zipf:0.7

Before this patch:
 READ: 6622.0 MiB/s. Stdev: 22.090722
WRITE: 1256.3 MiB/s. Stdev: 5.249339

After this patch (+4.6%, +3.3%):
 READ: 6926.6 MiB/s, Stdev: 37.950260
WRITE: 1297.3 MiB/s, Stdev: 7.408704

Test 3: 30m of MySQL test in 6G memcg (12 times):
  echo 'set GLOBAL innodb_buffer_pool_size=16106127360;' | \
    mysql -u USER -h localhost --password=PASS

  sysbench /usr/share/sysbench/oltp_read_only.lua \
    --mysql-user=USER --mysql-password=PASS --mysql-db=DB \
    --tables=48 --table-size=2000000 --threads=16 --time=1800 run

Before this patch
Avg: 134743.714545 qps. Stdev: 582.242189

After this patch (+0.2%):
Avg: 135005.779091 qps. Stdev: 295.299027

Test 4: Build linux kernel in 2G memcg with make -j48 with SSD swap
        (for memory stress, 18 times):

Before this patch:
Avg: 1456.768899 s. Stdev: 20.106973

After this patch (+0.0%):
Avg: 1455.659254 s. Stdev: 15.274481

Test 5: Memtier test in a 4G cgroup using brd as swap (18 times):
  memcached -u nobody -m 16384 -s /tmp/memcached.socket \
    -a 0766 -t 16 -B binary &
  memtier_benchmark -S /tmp/memcached.socket \
    -P memcache_binary -n allkeys \
    --key-minimum=1 --key-maximum=16000000 -d 1024 \
    --ratio=1:0 --key-pattern=P:P -c 1 -t 16 --pipeline 8 -x 3

Before this patch:
Avg: 50317.984000 Ops/sec. Stdev: 2568.965458

After this patch (-5.7%):
Avg: 47691.343500 Ops/sec. Stdev: 3925.772473

It seems prefetch is helpful in most cases, but the memtier test is
either hitting a case where prefetch causes higher cache miss or it's
just too noisy (high stdev).

Signed-off-by: Kairui Song <kasong@tencent.com>
---
 mm/vmscan.c | 30 ++++++++++++++++++++++++++----
 1 file changed, 26 insertions(+), 4 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4f9c854ce6cc..03631cedb3ab 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3681,15 +3681,26 @@ static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap)
 	/* prevent cold/hot inversion if force_scan is true */
 	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
 		struct list_head *head = &lrugen->folios[old_gen][type][zone];
+		struct folio *prev = NULL;
 
-		while (!list_empty(head)) {
-			struct folio *folio = lru_to_folio(head);
+		if (!list_empty(head))
+			prev = lru_to_folio(head);
+
+		while (prev) {
+			struct folio *folio = prev;
 
 			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);
 
+			if (unlikely(list_is_first(&folio->lru, head))) {
+				prev = NULL;
+			} else {
+				prev = lru_to_folio(&folio->lru);
+				prefetchw(&prev->flags);
+			}
+
 			new_gen = folio_inc_gen(lruvec, folio, false);
 			list_move_tail(&folio->lru, &lrugen->folios[new_gen][type][zone]);
 
@@ -4341,11 +4352,15 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc,
 	for (i = MAX_NR_ZONES; i > 0; i--) {
 		LIST_HEAD(moved);
 		int skipped_zone = 0;
+		struct folio *prev = NULL;
 		int zone = (sc->reclaim_idx + i) % MAX_NR_ZONES;
 		struct list_head *head = &lrugen->folios[gen][type][zone];
 
-		while (!list_empty(head)) {
-			struct folio *folio = lru_to_folio(head);
+		if (!list_empty(head))
+			prev = lru_to_folio(head);
+
+		while (prev) {
+			struct folio *folio = prev;
 			int delta = folio_nr_pages(folio);
 
 			VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio);
@@ -4355,6 +4370,13 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc,
 
 			scanned += delta;
 
+			if (unlikely(list_is_first(&folio->lru, head))) {
+				prev = NULL;
+			} else {
+				prev = lru_to_folio(&folio->lru);
+				prefetchw(&prev->flags);
+			}
+
 			if (sort_folio(lruvec, folio, sc, tier))
 				sorted += delta;
 			else if (isolate_folio(lruvec, folio, sc)) {
-- 
2.43.0