mm: vmstat: account per-zone stalls and pages skipped during reclaim

The vmstat allocstall was fairly useful in the general sense but
node-based LRUs change that.  It's important to know if a stall was for
an address-limited allocation request as this will require skipping
pages from other zones.  This patch adds pgstall_* counters to replace
allocstall.  The sum of the counters will equal the old allocstall so it
can be trivially recalculated.  A high number of address-limited
allocation requests may result in a lot of useless LRU scanning for
suitable pages.

As address-limited allocations require pages to be skipped, it's
important to know how much useless LRU scanning took place so this patch
adds pgskip* counters.  This yields the following model

1. The number of address-space limited stalls can be accounted for (pgstall)
2. The amount of useless work required to reclaim the data is accounted (pgskip)
3. The total number of scans is available from pgscan_kswapd and pgscan_direct
   so from that the ratio of useful to useless scans can be calculated.

[mgorman@techsingularity.net: s/pgstall/allocstall/]
  Link: http://lkml.kernel.org/r/1468404004-5085-3-git-send-email-mgorman@techsingularity.netLink: http://lkml.kernel.org/r/1467970510-21195-33-git-send-email-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@surriel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 18 insertions, 4 deletions

diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 1798ff542517..4d6ec58a8d45 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -23,6 +23,8 @@
 
 enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		FOR_ALL_ZONES(PGALLOC),
+		FOR_ALL_ZONES(ALLOCSTALL),
+		FOR_ALL_ZONES(PGSCAN_SKIP),
 		PGFREE, PGACTIVATE, PGDEACTIVATE,
 		PGFAULT, PGMAJFAULT,
 		PGLAZYFREED,
@@ -37,7 +39,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #endif
 		PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL,
 		KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
-		PAGEOUTRUN, ALLOCSTALL, PGROTATED,
+		PAGEOUTRUN, PGROTATED,
 		DROP_PAGECACHE, DROP_SLAB,
 #ifdef CONFIG_NUMA_BALANCING
 		NUMA_PTE_UPDATES,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5eaf83bf11d1..d5ee6d998b5e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1394,6 +1394,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	struct list_head *src = &lruvec->lists[lru];
 	unsigned long nr_taken = 0;
 	unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
+	unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
 	unsigned long scan, nr_pages;
 	LIST_HEAD(pages_skipped);
 
@@ -1408,6 +1409,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 
 		if (page_zonenum(page) > sc->reclaim_idx) {
 			list_move(&page->lru, &pages_skipped);
+			nr_skipped[page_zonenum(page)]++;
 			continue;
 		}
 
@@ -1436,8 +1438,17 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	 * scanning would soon rescan the same pages to skip and put the
 	 * system at risk of premature OOM.
 	 */
-	if (!list_empty(&pages_skipped))
+	if (!list_empty(&pages_skipped)) {
+		int zid;
+
 		list_splice(&pages_skipped, src);
+		for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+			if (!nr_skipped[zid])
+				continue;
+
+			__count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]);
+		}
+	}
 	*nr_scanned = scan;
 	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan,
 				    nr_taken, mode, is_file_lru(lru));
@@ -2680,7 +2691,7 @@ retry:
 	delayacct_freepages_start();
 
 	if (global_reclaim(sc))
-		count_vm_event(ALLOCSTALL);
+		__count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1);
 
 	do {
 		vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index ab7f78995c89..5caaf3f7b8ab 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -983,6 +983,8 @@ const char * const vmstat_text[] = {
 	"pswpout",
 
 	TEXTS_FOR_ZONES("pgalloc")
+	TEXTS_FOR_ZONES("allocstall")
+	TEXTS_FOR_ZONES("pgskip")
 
 	"pgfree",
 	"pgactivate",
@@ -1008,7 +1010,6 @@ const char * const vmstat_text[] = {
 	"kswapd_low_wmark_hit_quickly",
 	"kswapd_high_wmark_hit_quickly",
 	"pageoutrun",
-	"allocstall",
 
 	"pgrotated",