[PATCH v3 04/14] mm/mglru: restructure the reclaim loop
From: Kairui Song via B4 Relay
Date: Thu Apr 02 2026 - 14:53:57 EST
From: Kairui Song <kasong@xxxxxxxxxxx>
The current loop will calculate the scan number on each iteration. The
number of folios to scan is based on the LRU length, with some unclear
behaviors, eg, the scan number is only shifted by reclaim priority when
aging is not needed or when at the default priority, and it couples
the number calculation with aging and rotation.
Adjust, simplify it, and decouple aging and rotation. Just calculate the
scan number for once at the beginning of the reclaim, always respect the
reclaim priority, and make the aging and rotation more explicit.
This slightly changes how aging and offline memcg reclaim works:
Previously, aging was always skipped at DEF_PRIORITY even when
eviction was impossible. Now, aging is always triggered when it
is necessary to make progress. The old behavior may waste a reclaim
iteration only to escalate priority, potentially causing over-reclaim
of slab and breaking reclaim balance in multi-cgroup setups.
Similar for offline memcg. Previously, offline memcg wouldn't be
aged unless it didn't have any evictable folios. Now, we might age
it if it has only 3 generations and the reclaim priority is less
than DEF_PRIORITY, which should be fine. On one hand, offline memcg
might still hold long-term folios, and in fact, a long-existing offline
memcg must be pinned by some long-term folios like shmem. These folios
might be used by other memcg, so aging them as ordinary memcg seems
correct. Besides, aging enables further reclaim of an offlined memcg,
which will certainly happen if we keep shrinking it. And offline
memcg might soon be no longer an issue with reparenting.
Overall, the memcg LRU rotation, as described in mmzone.h,
remains the same.
Reviewed-by: Axel Rasmussen <axelrasmussen@xxxxxxxxxx>
Signed-off-by: Kairui Song <kasong@xxxxxxxxxxx>
---
mm/vmscan.c | 74 +++++++++++++++++++++++++++++++++----------------------------
1 file changed, 40 insertions(+), 34 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 963362523782..93ffb3d98fed 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4913,49 +4913,44 @@ static int evict_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
}
static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq,
- int swappiness, unsigned long *nr_to_scan)
+ struct scan_control *sc, int swappiness)
{
DEFINE_MIN_SEQ(lruvec);
- *nr_to_scan = 0;
/* have to run aging, since eviction is not possible anymore */
if (evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS > max_seq)
return true;
- *nr_to_scan = lruvec_evictable_size(lruvec, swappiness);
+ /* try to get away with not aging at the default priority */
+ if (sc->priority == DEF_PRIORITY)
+ return false;
+
/* better to run aging even though eviction is still possible */
return evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS == max_seq;
}
-/*
- * For future optimizations:
- * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg
- * reclaim.
- */
-static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, int swappiness)
+static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc,
+ struct mem_cgroup *memcg, int swappiness)
{
- bool need_aging;
- unsigned long nr_to_scan;
- struct mem_cgroup *memcg = lruvec_memcg(lruvec);
- DEFINE_MAX_SEQ(lruvec);
-
- if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg))
- return -1;
-
- need_aging = should_run_aging(lruvec, max_seq, swappiness, &nr_to_scan);
+ unsigned long evictable, nr_to_scan;
+ evictable = lruvec_evictable_size(lruvec, swappiness);
+ nr_to_scan = evictable;
/* try to scrape all its memory if this memcg was deleted */
- if (nr_to_scan && !mem_cgroup_online(memcg))
+ if (!mem_cgroup_online(memcg))
return nr_to_scan;
nr_to_scan = apply_proportional_protection(memcg, sc, nr_to_scan);
- /* try to get away with not aging at the default priority */
- if (!need_aging || sc->priority == DEF_PRIORITY)
- return nr_to_scan >> sc->priority;
+ /*
+ * Always respect scan priority, minimally target some folios
+ * to keep reclaim moving forwards.
+ */
+ nr_to_scan >>= sc->priority;
+ if (!nr_to_scan)
+ nr_to_scan = min(evictable, SWAP_CLUSTER_MAX);
- /* stop scanning this lruvec as it's low on cold folios */
- return try_to_inc_max_seq(lruvec, max_seq, swappiness, false) ? -1 : 0;
+ return nr_to_scan;
}
static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc)
@@ -4985,31 +4980,43 @@ static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc)
return true;
}
+/*
+ * For future optimizations:
+ * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg
+ * reclaim.
+ */
static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
{
+ bool need_rotate = false;
long nr_batch, nr_to_scan;
- unsigned long scanned = 0;
int swappiness = get_swappiness(lruvec, sc);
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
- while (true) {
+ nr_to_scan = get_nr_to_scan(lruvec, sc, memcg, swappiness);
+ while (nr_to_scan > 0) {
int delta;
+ DEFINE_MAX_SEQ(lruvec);
- nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness);
- if (nr_to_scan <= 0)
+ if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg)) {
+ need_rotate = true;
break;
+ }
+
+ if (should_run_aging(lruvec, max_seq, sc, swappiness)) {
+ if (try_to_inc_max_seq(lruvec, max_seq, swappiness, false))
+ need_rotate = true;
+ break;
+ }
nr_batch = min(nr_to_scan, MAX_LRU_BATCH);
delta = evict_folios(nr_batch, lruvec, sc, swappiness);
if (!delta)
break;
- scanned += delta;
- if (scanned >= nr_to_scan)
- break;
-
if (should_abort_scan(lruvec, sc))
break;
+ nr_to_scan -= delta;
cond_resched();
}
@@ -5035,8 +5042,7 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK);
}
- /* whether this lruvec should be rotated */
- return nr_to_scan < 0;
+ return need_rotate;
}
static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
--
2.53.0