mm: vmscan: have kswapd writeback pages based on dirty pages encountered, not priority

Currently kswapd queues dirty pages for writeback if scanning at an
elevated priority but the priority kswapd scans at is not related to the
number of unqueued dirty encountered.  Since commit "mm: vmscan: Flatten
kswapd priority loop", the priority is related to the size of the LRU
and the zone watermark which is no indication as to whether kswapd
should write pages or not.

This patch tracks if an excessive number of unqueued dirty pages are
being encountered at the end of the LRU.  If so, it indicates that dirty
pages are being recycled before flusher threads can clean them and flags
the zone so that kswapd will start writing pages until the zone is
balanced.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Tested-by: Zlatko Calusic <zcalusic@bitsync.net>
Cc: dormando <dormando@rydia.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 25 insertions, 6 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1505c573719..d6c916d808b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -676,13 +676,14 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				      struct zone *zone,
 				      struct scan_control *sc,
 				      enum ttu_flags ttu_flags,
-				      unsigned long *ret_nr_dirty,
+				      unsigned long *ret_nr_unqueued_dirty,
 				      unsigned long *ret_nr_writeback,
 				      bool force_reclaim)
 {
 	LIST_HEAD(ret_pages);
 	LIST_HEAD(free_pages);
 	int pgactivate = 0;
+	unsigned long nr_unqueued_dirty = 0;
 	unsigned long nr_dirty = 0;
 	unsigned long nr_congested = 0;
 	unsigned long nr_reclaimed = 0;
@@ -808,14 +809,17 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		if (PageDirty(page)) {
 			nr_dirty++;
 
+			if (!PageWriteback(page))
+				nr_unqueued_dirty++;
+
 			/*
 			 * Only kswapd can writeback filesystem pages to
-			 * avoid risk of stack overflow but do not writeback
-			 * unless under significant pressure.
+			 * avoid risk of stack overflow but only writeback
+			 * if many dirty pages have been encountered.
 			 */
 			if (page_is_file_cache(page) &&
 					(!current_is_kswapd() ||
-					 sc->priority >= DEF_PRIORITY - 2)) {
+					 !zone_is_reclaim_dirty(zone))) {
 				/*
 				 * Immediately reclaim when written back.
 				 * Similar in principal to deactivate_page()
@@ -960,7 +964,7 @@ keep:
 	list_splice(&ret_pages, page_list);
 	count_vm_events(PGACTIVATE, pgactivate);
 	mem_cgroup_uncharge_end();
-	*ret_nr_dirty += nr_dirty;
+	*ret_nr_unqueued_dirty += nr_unqueued_dirty;
 	*ret_nr_writeback += nr_writeback;
 	return nr_reclaimed;
 }
@@ -1373,6 +1377,15 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 			(nr_taken >> (DEF_PRIORITY - sc->priority)))
 		wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10);
 
+	/*
+	 * Similarly, if many dirty pages are encountered that are not
+	 * currently being written then flag that kswapd should start
+	 * writing back pages.
+	 */
+	if (global_reclaim(sc) && nr_dirty &&
+			nr_dirty >= (nr_taken >> (DEF_PRIORITY - sc->priority)))
+		zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY);
+
 	trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id,
 		zone_idx(zone),
 		nr_scanned, nr_reclaimed,
@@ -2769,8 +2782,12 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 				end_zone = i;
 				break;
 			} else {
-				/* If balanced, clear the congested flag */
+				/*
+				 * If balanced, clear the dirty and congested
+				 * flags
+				 */
 				zone_clear_flag(zone, ZONE_CONGESTED);
+				zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY);
 			}
 		}
 
@@ -2888,8 +2905,10 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 				 * possible there are dirty pages backed by
 				 * congested BDIs but as pressure is relieved,
 				 * speculatively avoid congestion waits
+				 * or writing pages from kswapd context.
 				 */
 				zone_clear_flag(zone, ZONE_CONGESTED);
+				zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY);
 		}
 
 		/*