diff mbox series

[2/2] mm, memcg: introduce passive reclaim counters for non-root memcg

Message ID 1573106889-4939-2-git-send-email-laoar.shao@gmail.com (mailing list archive)
State New, archived
Headers show
Series [1/2] mm, memcg: introduce multiple levels memory low protection | expand

Commit Message

Yafang Shao Nov. 7, 2019, 6:08 a.m. UTC 
The memory.{min, low} protection can prevent the reclaimers to reclaim the
pages from a memcg when there're memory pressure outside of a memcg.
We'd better introduce some counters to show this behavior.
This patch introduce two counters, pgscan_passive and pgsteal_passive.
	pgscan_passive:
		pages scanned due to memory pressure outside this memcg
	pgsteal_passive:
		pages reclaimed due to memory pressure outside this memcg

memcg set with higher memory.{min, low} setting, will get a lower
pgscan_passive and pgsteal_passive. For example, if memory.min is equal to
memory.max, then these passive reclaim counters should always be zero.

These counters are only for non-root memory cgroup. It's not easy to
introduce some container-only vmstat counters, because it will make lots
of changes. So I introduce some global vmstat counters, but they are
always zero for root memory cgroup.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
---
 Documentation/admin-guide/cgroup-v2.rst | 10 ++++++++++
 include/linux/vm_event_item.h           |  2 ++
 mm/memcontrol.c                         |  4 ++++
 mm/vmscan.c                             | 11 +++++++++--
 mm/vmstat.c                             |  2 ++
 5 files changed, 27 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index cdacc9c..11e0129 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1336,10 +1336,20 @@  PAGE_SIZE multiple when read back.
 
 		Amount of scanned pages (in an inactive LRU list)
 
+          pgscan_passive
+
+                Amount of scanned pages due to memory pressure outside this
+                memcg
+
 	  pgsteal
 
 		Amount of reclaimed pages
 
+          pgsteal_passive
+
+                Amount of reclaimed pages due to memory pressure outside
+                this memcg
+
 	  pgactivate
 
 		Amount of pages moved to the active LRU list
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 47a3441..0fcdaa3 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -32,8 +32,10 @@  enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		PGREFILL,
 		PGSTEAL_KSWAPD,
 		PGSTEAL_DIRECT,
+		PGSTEAL_PASSIVE,
 		PGSCAN_KSWAPD,
 		PGSCAN_DIRECT,
+		PGSCAN_PASSIVE,
 		PGSCAN_DIRECT_THROTTLE,
 #ifdef CONFIG_NUMA
 		PGSCAN_ZONE_RECLAIM_FAILED,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9da4ef9..0a2bf9a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1443,9 +1443,13 @@  static char *memory_stat_format(struct mem_cgroup *memcg)
 	seq_buf_printf(&s, "pgscan %lu\n",
 		       memcg_events(memcg, PGSCAN_KSWAPD) +
 		       memcg_events(memcg, PGSCAN_DIRECT));
+	seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGSCAN_PASSIVE),
+		       memcg_events(memcg, PGSCAN_PASSIVE));
 	seq_buf_printf(&s, "pgsteal %lu\n",
 		       memcg_events(memcg, PGSTEAL_KSWAPD) +
 		       memcg_events(memcg, PGSTEAL_DIRECT));
+	seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGSTEAL_PASSIVE),
+		       memcg_events(memcg, PGSTEAL_PASSIVE));
 	seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGACTIVATE),
 		       memcg_events(memcg, PGACTIVATE));
 	seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGDEACTIVATE),
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 3b08e85..0ea6c4a0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1910,6 +1910,7 @@  static int current_may_throttle(void)
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
 	bool stalled = false;
+	struct mem_cgroup *memcg;
 
 	while (unlikely(too_many_isolated(pgdat, file, sc))) {
 		if (stalled)
@@ -1934,10 +1935,13 @@  static int current_may_throttle(void)
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
 	reclaim_stat->recent_scanned[file] += nr_taken;
 
+	memcg = lruvec_memcg(lruvec);
 	item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT;
 	if (!cgroup_reclaim(sc))
 		__count_vm_events(item, nr_scanned);
-	__count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned);
+	if (memcg != sc->target_mem_cgroup)
+		__count_memcg_events(memcg, PGSCAN_PASSIVE, nr_scanned);
+	__count_memcg_events(memcg, item, nr_scanned);
 	spin_unlock_irq(&pgdat->lru_lock);
 
 	if (nr_taken == 0)
@@ -1948,10 +1952,13 @@  static int current_may_throttle(void)
 
 	spin_lock_irq(&pgdat->lru_lock);
 
+	memcg = lruvec_memcg(lruvec);
 	item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
 	if (!cgroup_reclaim(sc))
 		__count_vm_events(item, nr_reclaimed);
-	__count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
+	if (memcg != sc->target_mem_cgroup)
+		__count_memcg_events(memcg, PGSTEAL_PASSIVE, nr_reclaimed);
+	__count_memcg_events(memcg, item, nr_reclaimed);
 	reclaim_stat->recent_rotated[0] += stat.nr_activate[0];
 	reclaim_stat->recent_rotated[1] += stat.nr_activate[1];
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 78d5337..5d2a053 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1196,8 +1196,10 @@  int fragmentation_index(struct zone *zone, unsigned int order)
 	"pgrefill",
 	"pgsteal_kswapd",
 	"pgsteal_direct",
+	"pgsteal_passive",
 	"pgscan_kswapd",
 	"pgscan_direct",
+	"pgscan_passive",
 	"pgscan_direct_throttle",
 
 #ifdef CONFIG_NUMA