summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorJosef Bacik <jbacik@fb.com>2018-02-01 03:16:26 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2018-02-01 04:18:36 +0300
commit9092c71bb724dba2ecba849eae69e5c9d39bd3d2 (patch)
tree7651f4c5ef17afb674b0982272a0eaf513765f1e /mm
parentfcb2b0c577f145c7616843c9d4dcb4f9e5d88e29 (diff)
downloadlinux-9092c71bb724dba2ecba849eae69e5c9d39bd3d2.tar.xz
mm: use sc->priority for slab shrink targets
Previously we were using the ratio of the number of lru pages scanned to the number of eligible lru pages to determine the number of slab objects to scan. The problem with this is that these two things have nothing to do with each other, so in slab heavy work loads where there is little to no page cache we can end up with the pages scanned being a very low number. This means that we reclaim next to no slab pages and waste a lot of time reclaiming small amounts of space. Consider the following scenario, where we have the following values and the rest of the memory usage is in slab Active: 58840 kB Inactive: 46860 kB Every time we do a get_scan_count() we do this scan = size >> sc->priority where sc->priority starts at DEF_PRIORITY, which is 12. The first loop through reclaim would result in a scan target of 2 pages to 11715 total inactive pages, and 3 pages to 14710 total active pages. This is a really really small target for a system that is entirely slab pages. And this is super optimistic, this assumes we even get to scan these pages. We don't increment sc->nr_scanned unless we 1) isolate the page, which assumes it's not in use, and 2) can lock the page. Under pressure these numbers could probably go down, I'm sure there's some random pages from daemons that aren't actually in use, so the targets get even smaller. Instead use sc->priority in the same way we use it to determine scan amounts for the lru's. This generally equates to pages. Consider the following slab_pages = (nr_objects * object_size) / PAGE_SIZE What we would like to do is scan = slab_pages >> sc->priority but we don't know the number of slab pages each shrinker controls, only the objects. However say that theoretically we knew how many pages a shrinker controlled, we'd still have to convert this to objects, which would look like the following scan = shrinker_pages >> sc->priority scan_objects = (PAGE_SIZE / object_size) * scan or written another way scan_objects = (shrinker_pages >> sc->priority) * (PAGE_SIZE / object_size) which can thus be written scan_objects = ((shrinker_pages * PAGE_SIZE) / object_size) >> sc->priority which is just scan_objects = nr_objects >> sc->priority We don't need to know exactly how many pages each shrinker represents, it's objects are all the information we need. Making this change allows us to place an appropriate amount of pressure on the shrinker pools for their relative size. Link: http://lkml.kernel.org/r/1510780549-6812-1-git-send-email-josef@toxicpanda.com Signed-off-by: Josef Bacik <jbacik@fb.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Dave Chinner <david@fromorbit.com> Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/vmscan.c47
1 files changed, 13 insertions, 34 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 47d5ced51f2d..e73274a60b22 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -310,9 +310,7 @@ EXPORT_SYMBOL(unregister_shrinker);
#define SHRINK_BATCH 128
static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
- struct shrinker *shrinker,
- unsigned long nr_scanned,
- unsigned long nr_eligible)
+ struct shrinker *shrinker, int priority)
{
unsigned long freed = 0;
unsigned long long delta;
@@ -337,9 +335,9 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
total_scan = nr;
- delta = (4 * nr_scanned) / shrinker->seeks;
- delta *= freeable;
- do_div(delta, nr_eligible + 1);
+ delta = freeable >> priority;
+ delta *= 4;
+ do_div(delta, shrinker->seeks);
total_scan += delta;
if (total_scan < 0) {
pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n",
@@ -373,8 +371,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
total_scan = freeable * 2;
trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
- nr_scanned, nr_eligible,
- freeable, delta, total_scan);
+ freeable, delta, total_scan, priority);
/*
* Normally, we should not scan less than batch_size objects in one
@@ -434,8 +431,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
* @gfp_mask: allocation context
* @nid: node whose slab caches to target
* @memcg: memory cgroup whose slab caches to target
- * @nr_scanned: pressure numerator
- * @nr_eligible: pressure denominator
+ * @priority: the reclaim priority
*
* Call the shrink functions to age shrinkable caches.
*
@@ -447,20 +443,14 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
* objects from the memory cgroup specified. Otherwise, only unaware
* shrinkers are called.
*
- * @nr_scanned and @nr_eligible form a ratio that indicate how much of
- * the available objects should be scanned. Page reclaim for example
- * passes the number of pages scanned and the number of pages on the
- * LRU lists that it considered on @nid, plus a bias in @nr_scanned
- * when it encountered mapped pages. The ratio is further biased by
- * the ->seeks setting of the shrink function, which indicates the
- * cost to recreate an object relative to that of an LRU page.
+ * @priority is sc->priority, we take the number of objects and >> by priority
+ * in order to get the scan target.
*
* Returns the number of reclaimed slab objects.
*/
static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
struct mem_cgroup *memcg,
- unsigned long nr_scanned,
- unsigned long nr_eligible)
+ int priority)
{
struct shrinker *shrinker;
unsigned long freed = 0;
@@ -468,9 +458,6 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
if (memcg && (!memcg_kmem_enabled() || !mem_cgroup_online(memcg)))
return 0;
- if (nr_scanned == 0)
- nr_scanned = SWAP_CLUSTER_MAX;
-
if (!down_read_trylock(&shrinker_rwsem)) {
/*
* If we would return 0, our callers would understand that we
@@ -501,7 +488,7 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
sc.nid = 0;
- freed += do_shrink_slab(&sc, shrinker, nr_scanned, nr_eligible);
+ freed += do_shrink_slab(&sc, shrinker, priority);
}
up_read(&shrinker_rwsem);
@@ -519,8 +506,7 @@ void drop_slab_node(int nid)
freed = 0;
do {
- freed += shrink_slab(GFP_KERNEL, nid, memcg,
- 1000, 1000);
+ freed += shrink_slab(GFP_KERNEL, nid, memcg, 0);
} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
} while (freed > 10);
}
@@ -2615,14 +2601,12 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
reclaimed = sc->nr_reclaimed;
scanned = sc->nr_scanned;
-
shrink_node_memcg(pgdat, memcg, sc, &lru_pages);
node_lru_pages += lru_pages;
if (memcg)
shrink_slab(sc->gfp_mask, pgdat->node_id,
- memcg, sc->nr_scanned - scanned,
- lru_pages);
+ memcg, sc->priority);
/* Record the group's reclaim efficiency */
vmpressure(sc->gfp_mask, memcg, false,
@@ -2646,14 +2630,9 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
}
} while ((memcg = mem_cgroup_iter(root, memcg, &reclaim)));
- /*
- * Shrink the slab caches in the same proportion that
- * the eligible LRU pages were scanned.
- */
if (global_reclaim(sc))
shrink_slab(sc->gfp_mask, pgdat->node_id, NULL,
- sc->nr_scanned - nr_scanned,
- node_lru_pages);
+ sc->priority);
if (reclaim_state) {
sc->nr_reclaimed += reclaim_state->reclaimed_slab;