Commit b15e0905 authored by's avatar Committed by Linus Torvalds
Browse files

[PATCH] vmscan: notice slab shrinking

Fix a problem identified by Andrea Arcangeli <>

kswapd will set a zone into all_unreclaimable state if it sees that we're not
successfully reclaiming LRU pages.  But that fails to notice that we're
successfully reclaiming slab obects, so we can set all_unreclaimable too soon.

So change shrink_slab() to return a success indication if it actually
reclaimed some objects, and don't assume that the zone is all_unreclaimable if
that is true.  This means that we won't enter all_unreclaimable state if we
are successfully freeing slab objects but we're not yet actually freeing slab
pages, due to internal fragmentation.

(hm, this has a shortcoming.  We could be successfully freeing ZONE_NORMAL
slab objects while being really oom on ZONE_DMA.  If that happens then kswapd
might burn a lot of CPU.  But given that there might be some slab objects in
ZONE_DMA, perhaps that is appropriate.)
Signed-off-by: default avatarAndrew Morton <>
Signed-off-by: default avatarLinus Torvalds <>
parent 39c715b7
......@@ -180,17 +180,20 @@ EXPORT_SYMBOL(remove_shrinker);
* `lru_pages' represents the number of on-LRU pages in all the zones which
* are eligible for the caller's allocation attempt. It is used for balancing
* slab reclaim versus page reclaim.
* Returns the number of slab objects which we shrunk.
static int shrink_slab(unsigned long scanned, unsigned int gfp_mask,
unsigned long lru_pages)
struct shrinker *shrinker;
int ret = 0;
if (scanned == 0)
if (!down_read_trylock(&shrinker_rwsem))
return 0;
return 1; /* Assume we'll be able to shrink next time */
list_for_each_entry(shrinker, &shrinker_list, list) {
unsigned long long delta;
......@@ -209,10 +212,14 @@ static int shrink_slab(unsigned long scanned, unsigned int gfp_mask,
while (total_scan >= SHRINK_BATCH) {
long this_scan = SHRINK_BATCH;
int shrink_ret;
int nr_before;
nr_before = (*shrinker->shrinker)(0, gfp_mask);
shrink_ret = (*shrinker->shrinker)(this_scan, gfp_mask);
if (shrink_ret == -1)
if (shrink_ret < nr_before)
ret += nr_before - shrink_ret;
mod_page_state(slabs_scanned, this_scan);
total_scan -= this_scan;
......@@ -222,7 +229,7 @@ static int shrink_slab(unsigned long scanned, unsigned int gfp_mask,
shrinker->nr += total_scan;
return 0;
return ret;
/* Called without lock on whether page is mapped, so answer is unstable */
......@@ -1079,6 +1086,7 @@ static int balance_pgdat(pg_data_t *pgdat, int nr_pages, int order)
for (i = 0; i <= end_zone; i++) {
struct zone *zone = pgdat->node_zones + i;
int nr_slab;
if (zone->present_pages == 0)
......@@ -1100,14 +1108,15 @@ static int balance_pgdat(pg_data_t *pgdat, int nr_pages, int order)
sc.swap_cluster_max = nr_pages? nr_pages : SWAP_CLUSTER_MAX;
shrink_zone(zone, &sc);
reclaim_state->reclaimed_slab = 0;
shrink_slab(sc.nr_scanned, GFP_KERNEL, lru_pages);
nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
sc.nr_reclaimed += reclaim_state->reclaimed_slab;
total_reclaimed += sc.nr_reclaimed;
total_scanned += sc.nr_scanned;
if (zone->all_unreclaimable)
if (zone->pages_scanned >= (zone->nr_active +
zone->nr_inactive) * 4)
if (nr_slab == 0 && zone->pages_scanned >=
(zone->nr_active + zone->nr_inactive) * 4)
zone->all_unreclaimable = 1;
* If we've done a decent amount of scanning and
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment