[RFC PATCH] mm: vmscan: avoid anon scanning for GFP_NOIO with low swapcache

[Bo Zhang]

We have observed some cases where memory is allocated with GFP_NOIO, so
we cannot reclaim any anon folios unless they are in swapcache. We can
end up spending more than 150 ms looping in `shrink_folio_list()` scanning
non-swapcache folios without reclaiming a single folio. This is pure
overhead.

This is particularly true on systems using zRAM, where swapcache is
relatively rare. So let's check whether anon reclaim is allowed by
GFP_IO and whether there is enough swapcache to make it worthwhile. If
the swapcache is extremely low, we're essentially searching for a
needle in a haystack, so let's avoid scanning anon in the first place.

Signed-off-by: Bo Zhang <zhangbo56@xxxxxxxxxx>
---
 mm/vmscan.c | 62 ++++++++++++++++++++++++++++++++++-------------------
 1 file changed, 40 insertions(+), 22 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 56708d1d2dfd..192bd0980121 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -339,6 +339,42 @@ static bool can_demote(int nid, struct scan_control *sc,
 	return !nodes_empty(allowed_mask);
 }
 
+static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid)
+{
+	struct pglist_data *pgdat = NODE_DATA(nid);
+
+#ifdef CONFIG_MEMCG
+	if (memcg) {
+		struct lruvec *lruvec = &memcg->nodeinfo[nid]->lruvec;
+
+		/* see the comment in mem_cgroup_lruvec() */
+		if (!lruvec->pgdat)
+			lruvec->pgdat = pgdat;
+
+		return lruvec;
+	}
+#endif
+	VM_WARN_ON_ONCE(!mem_cgroup_disabled());
+
+	return &pgdat->__lruvec;
+}
+
+static inline bool reclaimable_anon_is_low(struct mem_cgroup *memcg,
+		int nid, struct scan_control *sc)
+{
+	struct lruvec *lruvec = get_lruvec(memcg, nid);
+	unsigned long anon_pages, swapcache;
+
+	if (!sc || (sc->gfp_mask & __GFP_IO))
+		return false;
+
+	anon_pages = lruvec_page_state(lruvec, NR_INACTIVE_ANON) +
+		     lruvec_page_state(lruvec, NR_ACTIVE_ANON);
+	swapcache = lruvec_page_state(lruvec, NR_SWAPCACHE);
+
+	return swapcache < min(anon_pages >> 6, SWAP_CLUSTER_MAX);
+}
+
 static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
 					  int nid,
 					  struct scan_control *sc)
@@ -348,11 +384,13 @@ static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
 		 * For non-memcg reclaim, is there
 		 * space in any swap device?
 		 */
-		if (get_nr_swap_pages() > 0)
+		if (get_nr_swap_pages() > 0 &&
+		    !reclaimable_anon_is_low(memcg, nid, sc))
 			return true;
 	} else {
 		/* Is the memcg below its swap limit? */
-		if (mem_cgroup_get_nr_swap_pages(memcg) > 0)
+		if (mem_cgroup_get_nr_swap_pages(memcg) > 0 &&
+		    !reclaimable_anon_is_low(memcg, nid, sc))
 			return true;
 	}
 
@@ -2674,26 +2712,6 @@ static bool should_clear_pmd_young(void)
 #define get_memcg_gen(seq)	((seq) % MEMCG_NR_GENS)
 #define get_memcg_bin(bin)	((bin) % MEMCG_NR_BINS)
 
-static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid)
-{
-	struct pglist_data *pgdat = NODE_DATA(nid);
-
-#ifdef CONFIG_MEMCG
-	if (memcg) {
-		struct lruvec *lruvec = &memcg->nodeinfo[nid]->lruvec;
-
-		/* see the comment in mem_cgroup_lruvec() */
-		if (!lruvec->pgdat)
-			lruvec->pgdat = pgdat;
-
-		return lruvec;
-	}
-#endif
-	VM_WARN_ON_ONCE(!mem_cgroup_disabled());
-
-	return &pgdat->__lruvec;
-}
-
 static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc)
 {
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
-- 
2.34.1