diff mbox series

[08/10] mm/vmscan: Consider anonymous pages without swap

Message ID 20210401183231.8485C83D@viggo.jf.intel.com (mailing list archive)
State New, archived
Headers show
Series Migrate Pages in lieu of discard | expand

Commit Message

Dave Hansen April 1, 2021, 6:32 p.m. UTC
From: Keith Busch <kbusch@kernel.org>

Reclaim anonymous pages if a migration path is available now that
demotion provides a non-swap recourse for reclaiming anon pages.

Note that this check is subtly different from the
anon_should_be_aged() checks.  This mechanism checks whether a
specific page in a specific context *can* actually be reclaimed, given
current swap space and cgroup limits

anon_should_be_aged() is a much simpler and more preliminary check
which just says whether there is a possibility of future reclaim.

#Signed-off-by: Keith Busch <keith.busch@intel.com>
Cc: Keith Busch <kbusch@kernel.org>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: Wei Xu <weixugc@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: osalvador <osalvador@suse.de>

--

Changes from Dave 10/2020:
 * remove 'total_swap_pages' modification

Changes from Dave 06/2020:
 * rename reclaim_anon_pages()->can_reclaim_anon_pages()

Note: Keith's Intel SoB is commented out because he is no
longer at Intel and his @intel.com mail will bounce.
---

 b/mm/vmscan.c |   35 ++++++++++++++++++++++++++++++++---
 1 file changed, 32 insertions(+), 3 deletions(-)

Comments

Wei Xu April 2, 2021, 12:55 a.m. UTC | #1
On Thu, Apr 1, 2021 at 11:35 AM Dave Hansen <dave.hansen@linux.intel.com> wrote:
>
>
> From: Keith Busch <kbusch@kernel.org>
>
> Reclaim anonymous pages if a migration path is available now that
> demotion provides a non-swap recourse for reclaiming anon pages.
>
> Note that this check is subtly different from the
> anon_should_be_aged() checks.  This mechanism checks whether a
> specific page in a specific context *can* actually be reclaimed, given
> current swap space and cgroup limits
>
> anon_should_be_aged() is a much simpler and more preliminary check
> which just says whether there is a possibility of future reclaim.
>
> #Signed-off-by: Keith Busch <keith.busch@intel.com>
> Cc: Keith Busch <kbusch@kernel.org>
> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
> Reviewed-by: Yang Shi <shy828301@gmail.com>
> Cc: Wei Xu <weixugc@google.com>
> Cc: David Rientjes <rientjes@google.com>
> Cc: Huang Ying <ying.huang@intel.com>
> Cc: Dan Williams <dan.j.williams@intel.com>
> Cc: David Hildenbrand <david@redhat.com>
> Cc: osalvador <osalvador@suse.de>
>
> --
>
> Changes from Dave 10/2020:
>  * remove 'total_swap_pages' modification
>
> Changes from Dave 06/2020:
>  * rename reclaim_anon_pages()->can_reclaim_anon_pages()
>
> Note: Keith's Intel SoB is commented out because he is no
> longer at Intel and his @intel.com mail will bounce.
> ---
>
>  b/mm/vmscan.c |   35 ++++++++++++++++++++++++++++++++---
>  1 file changed, 32 insertions(+), 3 deletions(-)
>
> diff -puN mm/vmscan.c~0009-mm-vmscan-Consider-anonymous-pages-without-swap mm/vmscan.c
> --- a/mm/vmscan.c~0009-mm-vmscan-Consider-anonymous-pages-without-swap  2021-03-31 15:17:19.388000242 -0700
> +++ b/mm/vmscan.c       2021-03-31 15:17:19.407000242 -0700
> @@ -287,6 +287,34 @@ static bool writeback_throttling_sane(st
>  }
>  #endif
>
> +static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
> +                                         int node_id)
> +{
> +       if (memcg == NULL) {
> +               /*
> +                * For non-memcg reclaim, is there
> +                * space in any swap device?
> +                */
> +               if (get_nr_swap_pages() > 0)
> +                       return true;
> +       } else {
> +               /* Is the memcg below its swap limit? */
> +               if (mem_cgroup_get_nr_swap_pages(memcg) > 0)
> +                       return true;
> +       }
> +
> +       /*
> +        * The page can not be swapped.
> +        *
> +        * Can it be reclaimed from this node via demotion?
> +        */
> +       if (next_demotion_node(node_id) >= 0)
> +               return true;

When neither swap space nor RECLAIM_MIGRATE is enabled, but
next_demotion_node() is configured, inactive pages cannot be swapped out
nor demoted.  However, this check can still cause these pages to be sent
to shrink_page_list() (e.g., when can_reclaim_anon_pages() is called by
get_scan_count()) and make the THP pages being unnecessarily split there.

One fix would be to guard this next_demotion_node() check with the
RECLAIM_MIGRATE node_reclaim_mode check.  This RECLAIM_MIGRATE
check needs to be applied to other calls to next_demotion_node() in
vmscan.c as well.

> +
> +       /* No way to reclaim anon pages */
> +       return false;
> +}
> +
>  /*
>   * This misses isolated pages which are not accounted for to save counters.
>   * As the data only determines if reclaim or compaction continues, it is
> @@ -298,7 +326,7 @@ unsigned long zone_reclaimable_pages(str
>
>         nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) +
>                 zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE);
> -       if (get_nr_swap_pages() > 0)
> +       if (can_reclaim_anon_pages(NULL, zone_to_nid(zone)))
>                 nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) +
>                         zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON);
>
> @@ -2323,6 +2351,7 @@ enum scan_balance {
>  static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
>                            unsigned long *nr)
>  {
> +       struct pglist_data *pgdat = lruvec_pgdat(lruvec);
>         struct mem_cgroup *memcg = lruvec_memcg(lruvec);
>         unsigned long anon_cost, file_cost, total_cost;
>         int swappiness = mem_cgroup_swappiness(memcg);
> @@ -2333,7 +2362,7 @@ static void get_scan_count(struct lruvec
>         enum lru_list lru;
>
>         /* If we have no swap space, do not bother scanning anon pages. */
> -       if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) {
> +       if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id)) {

Demotion of anon pages still depends on sc->may_swap.  Any thoughts on
decoupling
demotion from swapping more completely?

>                 scan_balance = SCAN_FILE;
>                 goto out;
>         }
> @@ -2708,7 +2737,7 @@ static inline bool should_continue_recla
>          */
>         pages_for_compaction = compact_gap(sc->order);
>         inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE);
> -       if (get_nr_swap_pages() > 0)
> +       if (can_reclaim_anon_pages(NULL, pgdat->node_id))
>                 inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON);
>
>         return inactive_lru_pages > pages_for_compaction;
> _
>
diff mbox series

Patch

diff -puN mm/vmscan.c~0009-mm-vmscan-Consider-anonymous-pages-without-swap mm/vmscan.c
--- a/mm/vmscan.c~0009-mm-vmscan-Consider-anonymous-pages-without-swap	2021-03-31 15:17:19.388000242 -0700
+++ b/mm/vmscan.c	2021-03-31 15:17:19.407000242 -0700
@@ -287,6 +287,34 @@  static bool writeback_throttling_sane(st
 }
 #endif
 
+static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
+					  int node_id)
+{
+	if (memcg == NULL) {
+		/*
+		 * For non-memcg reclaim, is there
+		 * space in any swap device?
+		 */
+		if (get_nr_swap_pages() > 0)
+			return true;
+	} else {
+		/* Is the memcg below its swap limit? */
+		if (mem_cgroup_get_nr_swap_pages(memcg) > 0)
+			return true;
+	}
+
+	/*
+	 * The page can not be swapped.
+	 *
+	 * Can it be reclaimed from this node via demotion?
+	 */
+	if (next_demotion_node(node_id) >= 0)
+		return true;
+
+	/* No way to reclaim anon pages */
+	return false;
+}
+
 /*
  * This misses isolated pages which are not accounted for to save counters.
  * As the data only determines if reclaim or compaction continues, it is
@@ -298,7 +326,7 @@  unsigned long zone_reclaimable_pages(str
 
 	nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) +
 		zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE);
-	if (get_nr_swap_pages() > 0)
+	if (can_reclaim_anon_pages(NULL, zone_to_nid(zone)))
 		nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) +
 			zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON);
 
@@ -2323,6 +2351,7 @@  enum scan_balance {
 static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 			   unsigned long *nr)
 {
+	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	unsigned long anon_cost, file_cost, total_cost;
 	int swappiness = mem_cgroup_swappiness(memcg);
@@ -2333,7 +2362,7 @@  static void get_scan_count(struct lruvec
 	enum lru_list lru;
 
 	/* If we have no swap space, do not bother scanning anon pages. */
-	if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) {
+	if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id)) {
 		scan_balance = SCAN_FILE;
 		goto out;
 	}
@@ -2708,7 +2737,7 @@  static inline bool should_continue_recla
 	 */
 	pages_for_compaction = compact_gap(sc->order);
 	inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE);
-	if (get_nr_swap_pages() > 0)
+	if (can_reclaim_anon_pages(NULL, pgdat->node_id))
 		inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON);
 
 	return inactive_lru_pages > pages_for_compaction;