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>
Cc: Zlatko Calusic <zcalusic@bitsync.net>
Cc: dormando <dormando@rydia.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 5c76737d836b1edc218bfba700fb26c09e62408a..2aaf72f7e345f0841261db1a25a8c91e529f6f07 100644 (file)
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -495,6 +495,10 @@ typedef enum {
        ZONE_CONGESTED,                 /* zone has many dirty pages backed by
                                         * a congested BDI
                                         */
+       ZONE_TAIL_LRU_DIRTY,            /* reclaim scanning has recently found
+                                        * many dirty file pages at the tail
+                                        * of the LRU.
+                                        */
 } zone_flags_t;
 
 static inline void zone_set_flag(struct zone *zone, zone_flags_t flag)
@@ -517,6 +521,11 @@ static inline int zone_is_reclaim_congested(const struct zone *zone)
        return test_bit(ZONE_CONGESTED, &zone->flags);
 }
 
+static inline int zone_is_reclaim_dirty(const struct zone *zone)
+{
+       return test_bit(ZONE_TAIL_LRU_DIRTY, &zone->flags);
+}
+
 static inline int zone_is_reclaim_locked(const struct zone *zone)
 {
        return test_bit(ZONE_RECLAIM_LOCKED, &zone->flags);

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1505c573719d9c4722eb6c52e915dfdb5e8c8353..d6c916d808ba2248e112a3dc3767647abf857fc3 100644 (file)
--- 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);
                }
 
                /*