[Devel] [PATCH RHEL7 COMMIT] mm/vmscan: collect reclaim stats across zone

[Konstantin Khorenko]

The commit is pushed to "branch-rh7-3.10.0-693.11.6.vz7.42.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-693.11.6.vz7.42.4
------>
commit 3a090b2339fd652adb8e8fa7849e97ab745436e2
Author: Andrey Ryabinin <aryabinin at virtuozzo.com>
Date:   Wed Jan 31 18:29:33 2018 +0300

    mm/vmscan: collect reclaim stats across zone
    
    Currently we collect reclaim stats per-lru list and set zone
    flags based on these stats. This seems wrong, as lrus a per-memcg
    thus one zone could have hundreds of them.
    
    So add reclaim_stats pointer into shrink_control struct and sum
    counters we need while iterating lrus in zone. Don't use them
    yet, that's would be the next patch.
    
    https://jira.sw.ru/browse/PSBM-61409
    Signed-off-by: Andrey Ryabinin <aryabinin at virtuozzo.com>
---
 mm/vmscan.c | 39 ++++++++++++++++++++++++++++-----------
 1 file changed, 28 insertions(+), 11 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index f974f57dd546..e6dde1e15a54 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -57,6 +57,18 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/vmscan.h>
 
+struct reclaim_stat {
+	unsigned nr_dirty;
+	unsigned nr_unqueued_dirty;
+	unsigned nr_congested;
+	unsigned nr_writeback;
+	unsigned nr_immediate;
+	unsigned nr_activate;
+	unsigned nr_ref_keep;
+	unsigned nr_unmap_fail;
+	unsigned nr_taken;
+};
+
 struct scan_control {
 	/* Incremented by the number of inactive pages that were scanned */
 	unsigned long nr_scanned;
@@ -97,6 +109,8 @@ struct scan_control {
 	 */
 	struct mem_cgroup *target_mem_cgroup;
 
+	struct reclaim_stat *stat;
+
 	/*
 	 * Nodemask of nodes allowed by the caller. If NULL, all nodes
 	 * are scanned.
@@ -845,17 +859,6 @@ static void page_check_dirty_writeback(struct page *page,
 		mapping->a_ops->is_dirty_writeback(page, dirty, writeback);
 }
 
-struct reclaim_stat {
-	unsigned nr_dirty;
-	unsigned nr_unqueued_dirty;
-	unsigned nr_congested;
-	unsigned nr_writeback;
-	unsigned nr_immediate;
-	unsigned nr_activate;
-	unsigned nr_ref_keep;
-	unsigned nr_unmap_fail;
-};
-
 /*
  * shrink_page_list() returns the number of reclaimed pages
  */
@@ -1616,6 +1619,15 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	mem_cgroup_uncharge_list(&page_list);
 	free_hot_cold_page_list(&page_list, true);
 
+	if (sc->stat) {
+		sc->stat->nr_taken += nr_taken;
+		sc->stat->nr_dirty += stat.nr_dirty;
+		sc->stat->nr_unqueued_dirty += stat.nr_unqueued_dirty;
+		sc->stat->nr_congested += stat.nr_congested;
+		sc->stat->nr_writeback += stat.nr_writeback;
+		sc->stat->nr_immediate += stat.nr_immediate;
+	}
+
 	/*
 	 * If reclaim is isolating dirty pages under writeback, it implies
 	 * that the long-lived page allocation rate is exceeding the page
@@ -2418,6 +2430,9 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc,
 		};
 		unsigned long zone_lru_pages = 0;
 		struct mem_cgroup *memcg;
+		struct reclaim_stat stat = {};
+
+		sc->stat = &stat;
 
 		nr_reclaimed = sc->nr_reclaimed;
 		nr_scanned = sc->nr_scanned;
@@ -2912,6 +2927,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
 						struct zone *zone,
 						unsigned long *nr_scanned)
 {
+	struct reclaim_stat stat = {};
 	struct scan_control sc = {
 		.nr_scanned = 0,
 		.nr_to_reclaim = SWAP_CLUSTER_MAX,
@@ -2921,6 +2937,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
 		.order = 0,
 		.priority = 0,
 		.target_mem_cgroup = memcg,
+		.stat = &stat,
 	};
 	struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);
 	unsigned long lru_pages;