summaryrefslogtreecommitdiffstats
path: root/mm/slub.c
diff options
context:
space:
mode:
authorJoonsoo Kim <js1304@gmail.com>2012-06-09 02:23:16 +0900
committerPekka Enberg <penberg@kernel.org>2012-06-20 10:17:45 +0300
commit43d77867a4f333de4e4189114c480dd365133c09 (patch)
tree63eefd04b561b7563eb6e92a4ca923b378a30f7a /mm/slub.c
parentd24ac77f71ded6a013bacb09f359eac0b0f29a80 (diff)
downloadop-kernel-dev-43d77867a4f333de4e4189114c480dd365133c09.zip
op-kernel-dev-43d77867a4f333de4e4189114c480dd365133c09.tar.gz
slub: refactoring unfreeze_partials()
Current implementation of unfreeze_partials() is so complicated, but benefit from it is insignificant. In addition many code in do {} while loop have a bad influence to a fail rate of cmpxchg_double_slab. Under current implementation which test status of cpu partial slab and acquire list_lock in do {} while loop, we don't need to acquire a list_lock and gain a little benefit when front of the cpu partial slab is to be discarded, but this is a rare case. In case that add_partial is performed and cmpxchg_double_slab is failed, remove_partial should be called case by case. I think that these are disadvantages of current implementation, so I do refactoring unfreeze_partials(). Minimizing code in do {} while loop introduce a reduced fail rate of cmpxchg_double_slab. Below is output of 'slabinfo -r kmalloc-256' when './perf stat -r 33 hackbench 50 process 4000 > /dev/null' is done. ** before ** Cmpxchg_double Looping ------------------------ Locked Cmpxchg Double redos 182685 Unlocked Cmpxchg Double redos 0 ** after ** Cmpxchg_double Looping ------------------------ Locked Cmpxchg Double redos 177995 Unlocked Cmpxchg Double redos 1 We can see cmpxchg_double_slab fail rate is improved slightly. Bolow is output of './perf stat -r 30 hackbench 50 process 4000 > /dev/null'. ** before ** Performance counter stats for './hackbench 50 process 4000' (30 runs): 108517.190463 task-clock # 7.926 CPUs utilized ( +- 0.24% ) 2,919,550 context-switches # 0.027 M/sec ( +- 3.07% ) 100,774 CPU-migrations # 0.929 K/sec ( +- 4.72% ) 124,201 page-faults # 0.001 M/sec ( +- 0.15% ) 401,500,234,387 cycles # 3.700 GHz ( +- 0.24% ) <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 250,576,913,354 instructions # 0.62 insns per cycle ( +- 0.13% ) 45,934,956,860 branches # 423.297 M/sec ( +- 0.14% ) 188,219,787 branch-misses # 0.41% of all branches ( +- 0.56% ) 13.691837307 seconds time elapsed ( +- 0.24% ) ** after ** Performance counter stats for './hackbench 50 process 4000' (30 runs): 107784.479767 task-clock # 7.928 CPUs utilized ( +- 0.22% ) 2,834,781 context-switches # 0.026 M/sec ( +- 2.33% ) 93,083 CPU-migrations # 0.864 K/sec ( +- 3.45% ) 123,967 page-faults # 0.001 M/sec ( +- 0.15% ) 398,781,421,836 cycles # 3.700 GHz ( +- 0.22% ) <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 250,189,160,419 instructions # 0.63 insns per cycle ( +- 0.09% ) 45,855,370,128 branches # 425.436 M/sec ( +- 0.10% ) 169,881,248 branch-misses # 0.37% of all branches ( +- 0.43% ) 13.596272341 seconds time elapsed ( +- 0.22% ) No regression is found, but rather we can see slightly better result. Acked-by: Christoph Lameter <cl@linux.com> Signed-off-by: Joonsoo Kim <js1304@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Diffstat (limited to 'mm/slub.c')
-rw-r--r--mm/slub.c48
1 files changed, 14 insertions, 34 deletions
diff --git a/mm/slub.c b/mm/slub.c
index 4f406cd..f96d8bc 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1879,18 +1879,24 @@ redo:
*/
static void unfreeze_partials(struct kmem_cache *s)
{
- struct kmem_cache_node *n = NULL;
+ struct kmem_cache_node *n = NULL, *n2 = NULL;
struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab);
struct page *page, *discard_page = NULL;
while ((page = c->partial)) {
- enum slab_modes { M_PARTIAL, M_FREE };
- enum slab_modes l, m;
struct page new;
struct page old;
c->partial = page->next;
- l = M_FREE;
+
+ n2 = get_node(s, page_to_nid(page));
+ if (n != n2) {
+ if (n)
+ spin_unlock(&n->list_lock);
+
+ n = n2;
+ spin_lock(&n->list_lock);
+ }
do {
@@ -1903,43 +1909,17 @@ static void unfreeze_partials(struct kmem_cache *s)
new.frozen = 0;
- if (!new.inuse && (!n || n->nr_partial > s->min_partial))
- m = M_FREE;
- else {
- struct kmem_cache_node *n2 = get_node(s,
- page_to_nid(page));
-
- m = M_PARTIAL;
- if (n != n2) {
- if (n)
- spin_unlock(&n->list_lock);
-
- n = n2;
- spin_lock(&n->list_lock);
- }
- }
-
- if (l != m) {
- if (l == M_PARTIAL) {
- remove_partial(n, page);
- stat(s, FREE_REMOVE_PARTIAL);
- } else {
- add_partial(n, page,
- DEACTIVATE_TO_TAIL);
- stat(s, FREE_ADD_PARTIAL);
- }
-
- l = m;
- }
-
} while (!__cmpxchg_double_slab(s, page,
old.freelist, old.counters,
new.freelist, new.counters,
"unfreezing slab"));
- if (m == M_FREE) {
+ if (unlikely(!new.inuse && n->nr_partial > s->min_partial)) {
page->next = discard_page;
discard_page = page;
+ } else {
+ add_partial(n, page, DEACTIVATE_TO_TAIL);
+ stat(s, FREE_ADD_PARTIAL);
}
}
OpenPOWER on IntegriCloud