[PATCH mm-unstable v15 09/14] mm: multi-gen LRU: optimize multiple memcgs

[Yu Zhao]

When multiple memcgs are available, it is possible to use generations
as a frame of reference to make better choices and improve overall
performance under global memory pressure. This patch adds a basic
optimization to select memcgs that can drop single-use unmapped clean
pages first. Doing so reduces the chance of going into the aging path
or swapping, which can be costly.

A typical example that benefits from this optimization is a server
running mixed types of workloads, e.g., heavy anon workload in one
memcg and heavy buffered I/O workload in the other.

Though this optimization can be applied to both kswapd and direct
reclaim, it is only added to kswapd to keep the patchset manageable.
Later improvements may cover the direct reclaim path.

While ensuring certain fairness to all eligible memcgs, proportional
scans of individual memcgs also require proper backoff to avoid
overshooting their aggregate reclaim target by too much. Otherwise it
can cause high direct reclaim latency. The conditions for backoff are:
1. At low priorities, for direct reclaim, if aging fairness or direct
   reclaim latency is at risk, i.e., aging one memcg multiple times or
   swapping after the target is met.
2. At high priorities, for global reclaim, if per-zone free pages are
   above respective watermarks.

Server benchmark results:
  Mixed workloads:
    fio (buffered I/O): +[19, 21]%
                IOPS         BW
      patch1-8: 1880k        7343MiB/s
      patch1-9: 2252k        8796MiB/s

    memcached (anon): +[119, 123]%
                Ops/sec      KB/sec
      patch1-8: 862768.65    33514.68
      patch1-9: 1911022.12   74234.54

  Mixed workloads:
    fio (buffered I/O): +[75, 77]%
                IOPS         BW
      5.19-rc1: 1279k        4996MiB/s
      patch1-9: 2252k        8796MiB/s

    memcached (anon): +[13, 15]%
                Ops/sec      KB/sec
      5.19-rc1: 1673524.04   65008.87
      patch1-9: 1911022.12   74234.54

  Configurations:
    (changes since patch 6)

    cat mixed.sh
    modprobe brd rd_nr=2 rd_size=56623104

    swapoff -a
    mkswap /dev/ram0
    swapon /dev/ram0

    mkfs.ext4 /dev/ram1
    mount -t ext4 /dev/ram1 /mnt

    memtier_benchmark -S /var/run/memcached/memcached.sock \
      -P memcache_binary -n allkeys --key-minimum=1 \
      --key-maximum=50000000 --key-pattern=P:P -c 1 -t 36 \
      --ratio 1:0 --pipeline 8 -d 2000

    fio -name=mglru --numjobs=36 --directory=/mnt --size=1408m \
      --buffered=1 --ioengine=io_uring --iodepth=128 \
      --iodepth_batch_submit=32 --iodepth_batch_complete=32 \
      --rw=randread --random_distribution=random --norandommap \
      --time_based --ramp_time=10m --runtime=90m --group_reporting &
    pid=$!

    sleep 200

    memtier_benchmark -S /var/run/memcached/memcached.sock \
      -P memcache_binary -n allkeys --key-minimum=1 \
      --key-maximum=50000000 --key-pattern=R:R -c 1 -t 36 \
      --ratio 0:1 --pipeline 8 --randomize --distinct-client-seed

    kill -INT $pid
    wait

Client benchmark results:
  no change (CONFIG_MEMCG=n)

Signed-off-by: Yu Zhao <yuzhao@xxxxxxxxxx>
Acked-by: Brian Geffon <bgeffon@xxxxxxxxxx>
Acked-by: Jan Alexander Steffens (heftig) <heftig@xxxxxxxxxxxxx>
Acked-by: Oleksandr Natalenko <oleksandr@xxxxxxxxxxxxxx>
Acked-by: Steven Barrett <steven@xxxxxxxxxxxx>
Acked-by: Suleiman Souhlal <suleiman@xxxxxxxxxx>
Tested-by: Daniel Byrne <djbyrne@xxxxxxx>
Tested-by: Donald Carr <d@xxxxxxxxxxxxxxx>
Tested-by: Holger Hoffstätte <holger@xxxxxxxxxxxxxxxxxxxxxx>
Tested-by: Konstantin Kharlamov <Hi-Angel@xxxxxxxxx>
Tested-by: Shuang Zhai <szhai2@xxxxxxxxxxxxxxxx>
Tested-by: Sofia Trinh <sofia.trinh@edi.works>
Tested-by: Vaibhav Jain <vaibhav@xxxxxxxxxxxxx>
---
 mm/vmscan.c | 105 +++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 96 insertions(+), 9 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index c579b254fec7..3f83325fdc71 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -131,6 +131,12 @@ struct scan_control {
 	/* Always discard instead of demoting to lower tier memory */
 	unsigned int no_demotion:1;
 
+#ifdef CONFIG_LRU_GEN
+	/* help kswapd make better choices among multiple memcgs */
+	unsigned int memcgs_need_aging:1;
+	unsigned long last_reclaimed;
+#endif
+
 	/* Allocation order */
 	s8 order;
 
@@ -4431,6 +4437,19 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
 
 	VM_WARN_ON_ONCE(!current_is_kswapd());
 
+	sc->last_reclaimed = sc->nr_reclaimed;
+
+	/*
+	 * To reduce the chance of going into the aging path, which can be
+	 * costly, optimistically skip it if the flag below was cleared in the
+	 * eviction path. This improves the overall performance when multiple
+	 * memcgs are available.
+	 */
+	if (!sc->memcgs_need_aging) {
+		sc->memcgs_need_aging = true;
+		return;
+	}
+
 	set_mm_walk(pgdat);
 
 	memcg = mem_cgroup_iter(NULL, NULL, NULL);
@@ -4842,7 +4861,8 @@ static int isolate_folios(struct lruvec *lruvec, struct scan_control *sc, int sw
 	return scanned;
 }
 
-static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness)
+static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness,
+			bool *need_swapping)
 {
 	int type;
 	int scanned;
@@ -4905,6 +4925,9 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
 
 	sc->nr_reclaimed += reclaimed;
 
+	if (need_swapping && type == LRU_GEN_ANON)
+		*need_swapping = true;
+
 	return scanned;
 }
 
@@ -4914,9 +4937,8 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
  *    reclaim.
  */
 static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc,
-				    bool can_swap)
+				    bool can_swap, bool *need_aging)
 {
-	bool need_aging;
 	unsigned long nr_to_scan;
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	DEFINE_MAX_SEQ(lruvec);
@@ -4926,8 +4948,8 @@ static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *
 	    (mem_cgroup_below_low(memcg) && !sc->memcg_low_reclaim))
 		return 0;
 
-	need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, can_swap, &nr_to_scan);
-	if (!need_aging)
+	*need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, can_swap, &nr_to_scan);
+	if (!*need_aging)
 		return nr_to_scan;
 
 	/* skip the aging path at the default priority */
@@ -4944,10 +4966,68 @@ static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *
 	return min_seq[!can_swap] + MIN_NR_GENS <= max_seq ? nr_to_scan : 0;
 }
 
+static bool should_abort_scan(struct lruvec *lruvec, unsigned long seq,
+			      struct scan_control *sc, bool need_swapping)
+{
+	int i;
+	DEFINE_MAX_SEQ(lruvec);
+
+	if (!current_is_kswapd()) {
+		/* age each memcg once to ensure fairness */
+		if (max_seq - seq > 1)
+			return true;
+
+		/* over-swapping can increase allocation latency */
+		if (sc->nr_reclaimed >= sc->nr_to_reclaim && need_swapping)
+			return true;
+
+		/* give this thread a chance to exit and free its memory */
+		if (fatal_signal_pending(current)) {
+			sc->nr_reclaimed += MIN_LRU_BATCH;
+			return true;
+		}
+
+		if (cgroup_reclaim(sc))
+			return false;
+	} else if (sc->nr_reclaimed - sc->last_reclaimed < sc->nr_to_reclaim)
+		return false;
+
+	/* keep scanning at low priorities to ensure fairness */
+	if (sc->priority > DEF_PRIORITY - 2)
+		return false;
+
+	/*
+	 * A minimum amount of work was done under global memory pressure. For
+	 * kswapd, it may be overshooting. For direct reclaim, the target isn't
+	 * met, and yet the allocation may still succeed, since kswapd may have
+	 * caught up. In either case, it's better to stop now, and restart if
+	 * necessary.
+	 */
+	for (i = 0; i <= sc->reclaim_idx; i++) {
+		unsigned long wmark;
+		struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i;
+
+		if (!managed_zone(zone))
+			continue;
+
+		wmark = current_is_kswapd() ? high_wmark_pages(zone) : low_wmark_pages(zone);
+		if (wmark > zone_page_state(zone, NR_FREE_PAGES))
+			return false;
+	}
+
+	sc->nr_reclaimed += MIN_LRU_BATCH;
+
+	return true;
+}
+
 static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 {
 	struct blk_plug plug;
+	bool need_aging = false;
+	bool need_swapping = false;
 	unsigned long scanned = 0;
+	unsigned long reclaimed = sc->nr_reclaimed;
+	DEFINE_MAX_SEQ(lruvec);
 
 	lru_add_drain();
 
@@ -4967,21 +5047,28 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
 		else
 			swappiness = 0;
 
-		nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness);
+		nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness, &need_aging);
 		if (!nr_to_scan)
-			break;
+			goto done;
 
-		delta = evict_folios(lruvec, sc, swappiness);
+		delta = evict_folios(lruvec, sc, swappiness, &need_swapping);
 		if (!delta)
-			break;
+			goto done;
 
 		scanned += delta;
 		if (scanned >= nr_to_scan)
 			break;
 
+		if (should_abort_scan(lruvec, max_seq, sc, need_swapping))
+			break;
+
 		cond_resched();
 	}
 
+	/* see the comment in lru_gen_age_node() */
+	if (sc->nr_reclaimed - reclaimed >= MIN_LRU_BATCH && !need_aging)
+		sc->memcgs_need_aging = false;
+done:
 	clear_mm_walk();
 
 	blk_finish_plug(&plug);
-- 
2.37.3.968.ga6b4b080e4-goog