summaryrefslogtreecommitdiffstats
path: root/mm/vmscan.c
diff options
context:
space:
mode:
authorJohannes Weiner <hannes@cmpxchg.org>2016-01-15 00:21:32 +0100
committerLinus Torvalds <torvalds@linux-foundation.org>2016-01-15 01:00:49 +0100
commit8e8ae645249b85c8ed6c178557f8db8613a6bcc7 (patch)
treee1c347c9b18cad1a979dda026a1dff6f310d8977 /mm/vmscan.c
parentmm: memcontrol: account socket memory in unified hierarchy memory controller (diff)
downloadlinux-8e8ae645249b85c8ed6c178557f8db8613a6bcc7.tar.xz
linux-8e8ae645249b85c8ed6c178557f8db8613a6bcc7.zip
mm: memcontrol: hook up vmpressure to socket pressure
Let the networking stack know when a memcg is under reclaim pressure so that it can clamp its transmit windows accordingly. Whenever the reclaim efficiency of a cgroup's LRU lists drops low enough for a MEDIUM or HIGH vmpressure event to occur, assert a pressure state in the socket and tcp memory code that tells it to curb consumption growth from sockets associated with said control group. Traditionally, vmpressure reports for the entire subtree of a memcg under pressure, which drops useful information on the individual groups reclaimed. However, it's too late to change the userinterface, so add a second reporting mode that reports on the level of reclaim instead of at the level of pressure, and use that report for sockets. vmpressure events are naturally edge triggered, so for hysteresis assert socket pressure for a second to allow for subsequent vmpressure events to occur before letting the socket code return to normal. This will likely need finetuning for a wider variety of workloads, but for now stick to the vmpressure presets and keep hysteresis simple. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: David S. Miller <davem@davemloft.net> Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to '')
-rw-r--r--mm/vmscan.c10
1 files changed, 9 insertions, 1 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e36d766dade9..bb0cbd4c9f01 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2396,6 +2396,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
memcg = mem_cgroup_iter(root, NULL, &reclaim);
do {
unsigned long lru_pages;
+ unsigned long reclaimed;
unsigned long scanned;
struct lruvec *lruvec;
int swappiness;
@@ -2408,6 +2409,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
lruvec = mem_cgroup_zone_lruvec(zone, memcg);
swappiness = mem_cgroup_swappiness(memcg);
+ reclaimed = sc->nr_reclaimed;
scanned = sc->nr_scanned;
shrink_lruvec(lruvec, swappiness, sc, &lru_pages);
@@ -2418,6 +2420,11 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
memcg, sc->nr_scanned - scanned,
lru_pages);
+ /* Record the group's reclaim efficiency */
+ vmpressure(sc->gfp_mask, memcg, false,
+ sc->nr_scanned - scanned,
+ sc->nr_reclaimed - reclaimed);
+
/*
* Direct reclaim and kswapd have to scan all memory
* cgroups to fulfill the overall scan target for the
@@ -2449,7 +2456,8 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
reclaim_state->reclaimed_slab = 0;
}
- vmpressure(sc->gfp_mask, sc->target_mem_cgroup,
+ /* Record the subtree's reclaim efficiency */
+ vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true,
sc->nr_scanned - nr_scanned,
sc->nr_reclaimed - nr_reclaimed);