[PATCH mm-unstable v1 2/2] mm/mglru: fix overshooting shrinker memory

[Yu Zhao <yuzhao@google.com>]

set_initial_priority() tries to jump-start global reclaim by
estimating the priority based on cold/hot LRU pages. The estimation
does not account for shrinker objects, and it cannot do so because
their sizes can be in different units other than page.

If shrinker objects are the majority, e.g., on TrueNAS SCALE 24.04.0
where ZFS ARC can use almost all system memory,
set_initial_priority() can vastly underestimate how much memory ARC
shrinker can evict and assign extreme low values to
scan_control->priority, resulting in overshoots of shrinker objects.

To reproduce the problem, using TrueNAS SCALE 24.04.0 with 32GB DRAM,
a test ZFS pool and the following commands:

  fio --name=mglru.file --numjobs=36 --ioengine=io_uring \
      --directory=/root/test-zfs-pool/ --size=1024m --buffered=1 \
      --rw=randread --random_distribution=random \
      --time_based --runtime=1h &

  for ((i = 0; i < 20; i++))
  do
    sleep 120
    fio --name=mglru.anon --numjobs=16 --ioengine=mmap \
      --filename=/dev/zero --size=1024m --fadvise_hint=0 \
      --rw=randrw --random_distribution=random \
      --time_based --runtime=1m
  done

To fix the problem:
1. Cap scan_control->priority at or above DEF_PRIORITY/2, to prevent
   the jump-start from being overly aggressive.
2. Account for the progress from mm_account_reclaimed_pages(), to
   prevent kswapd_shrink_node() from raising the priority
   unnecessarily.

Reported-by: Alexander Motin <mav@ixsystems.com>
Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists")
Cc: stable@vger.kernel.org
Signed-off-by: Yu Zhao <yuzhao@google.com>
---
 mm/vmscan.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 6403038c776e..6216d79edb7f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4930,7 +4930,11 @@ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control
 	/* round down reclaimable and round up sc->nr_to_reclaim */
 	priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1);
 
-	sc->priority = clamp(priority, 0, DEF_PRIORITY);
+	/*
+	 * The estimation is based on LRU pages only, so cap it to prevent
+	 * overshoots of shrinker objects by large margins.
+	 */
+	sc->priority = clamp(priority, DEF_PRIORITY / 2, DEF_PRIORITY);
 }
 
 static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc)
@@ -6754,6 +6758,7 @@ static bool kswapd_shrink_node(pg_data_t *pgdat,
 {
 	struct zone *zone;
 	int z;
+	unsigned long nr_reclaimed = sc->nr_reclaimed;
 
 	/* Reclaim a number of pages proportional to the number of zones */
 	sc->nr_to_reclaim = 0;
@@ -6781,7 +6786,8 @@ static bool kswapd_shrink_node(pg_data_t *pgdat,
 	if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order))
 		sc->order = 0;
 
-	return sc->nr_scanned >= sc->nr_to_reclaim;
+	/* account for progress from mm_account_reclaimed_pages() */
+	return max(sc->nr_scanned, sc->nr_reclaimed - nr_reclaimed) >= sc->nr_to_reclaim;
 }
 
 /* Page allocator PCP high watermark is lowered if reclaim is active. */
-- 
2.45.2.993.g49e7a77208-goog