[PATCH v4] mm, vmscan: retry kswapd's priority loop with cache_trim_mode off on failure

[Byungchul Park]

With cache_trim_mode on, reclaim logic doesn't bother reclaiming anon
pages.  However, it should be more careful to use the mode because it's
going to prevent anon pages from being reclaimed even if there are a
huge number of anon pages that are cold and should be reclaimed.  Even
worse, that leads kswapd_failures to reach MAX_RECLAIM_RETRIES and
stopping kswapd from functioning until direct reclaim eventually works
to resume kswapd.

So kswapd needs to retry its scan priority loop with cache_trim_mode
off again if the mode doesn't work for reclaim.

The problematic behavior can be reproduced by:

   CONFIG_NUMA_BALANCING enabled
   sysctl_numa_balancing_mode set to NUMA_BALANCING_MEMORY_TIERING
   numa node0 (8GB local memory, 16 CPUs)
   numa node1 (8GB slow tier memory, no CPUs)

   Sequence:

   1) echo 3 > /proc/sys/vm/drop_caches
   2) To emulate the system with full of cold memory in local DRAM, run
      the following dummy program and never touch the region:

         mmap(0, 8 * 1024 * 1024 * 1024, PROT_READ | PROT_WRITE,
              MAP_ANONYMOUS | MAP_PRIVATE | MAP_POPULATE, -1, 0);

   3) Run any memory intensive work e.g. XSBench.
   4) Check if numa balancing is working e.i. promotion/demotion.
   5) Iterate 1) ~ 4) until numa balancing stops.

With this, you could see that promotion/demotion are not working because
kswapd has stopped due to ->kswapd_failures >= MAX_RECLAIM_RETRIES.

Interesting vmstat delta's differences between before and after are like:

   +-----------------------+-------------------------------+
   | interesting vmstat    | before        | after         |
   +-----------------------+-------------------------------+
   | nr_inactive_anon      | 321935        | 1646193       |
   | nr_active_anon        | 1780700       | 456388        |
   | nr_inactive_file      | 30425         | 27836         |
   | nr_active_file        | 14961         | 1217          |
   | pgpromote_success     | 356           | 1310120       |
   | pgpromote_candidate   | 21953245      | 1736872       |
   | pgactivate            | 1844523       | 3292443       |
   | pgdeactivate          | 50634         | 1526701       |
   | pgfault               | 31100294      | 6715375       |
   | pgdemote_kswapd       | 30856         | 1954199       |
   | pgscan_kswapd         | 1861981       | 7100099       |
   | pgscan_anon           | 1822930       | 7061135       |
   | pgscan_file           | 39051         | 38964         |
   | pgsteal_anon          | 386           | 1925214       |
   | pgsteal_file          | 30470         | 28985         |
   | pageoutrun            | 30            | 500           |
   | numa_hint_faults      | 27418279      | 3090773       |
   | numa_pages_migrated   | 356           | 1310120       |
   +-----------------------+-------------------------------+

Signed-off-by: Byungchul Park <byungchul@xxxxxx>
---
 mm/vmscan.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index bba207f41b14..7ec1fbcba7d4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -108,6 +108,9 @@ struct scan_control {
 	/* Can folios be swapped as part of reclaim? */
 	unsigned int may_swap:1;
 
+	/* Can cache_trim_mode be turned on as part of reclaim? */
+	unsigned int may_cache_trim_mode:1;
+
 	/* Proactive reclaim invoked by userspace through memory.reclaim */
 	unsigned int proactive:1;
 
@@ -2268,7 +2271,8 @@ static void prepare_scan_control(pg_data_t *pgdat, struct scan_control *sc)
 	 * anonymous pages.
 	 */
 	file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE);
-	if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE))
+	if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE) &&
+	    sc->may_cache_trim_mode)
 		sc->cache_trim_mode = 1;
 	else
 		sc->cache_trim_mode = 0;
@@ -6744,6 +6748,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx)
 		.gfp_mask = GFP_KERNEL,
 		.order = order,
 		.may_unmap = 1,
+		.may_cache_trim_mode = 1,
 	};
 
 	set_task_reclaim_state(current, &sc.reclaim_state);
@@ -6898,8 +6903,14 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx)
 			sc.priority--;
 	} while (sc.priority >= 1);
 
-	if (!sc.nr_reclaimed)
+	if (!sc.nr_reclaimed) {
+		if (sc.may_cache_trim_mode) {
+			sc.may_cache_trim_mode = 0;
+			goto restart;
+		}
+
 		pgdat->kswapd_failures++;
+	}
 
 out:
 	clear_reclaim_active(pgdat, highest_zoneidx);
-- 
2.17.1