Commit 801faf0d authored by Joonsoo Kim's avatar Joonsoo Kim Committed by Linus Torvalds

mm/slab: lockless decision to grow cache

To check whether free objects exist or not precisely, we need to grab a
lock.  But, accuracy isn't that important because race window would be
even small and if there is too much free object, cache reaper would reap
it.  So, this patch makes the check for free object exisistence not to
hold a lock.  This will reduce lock contention in heavily allocation
case.

Note that until now, n->shared can be freed during the processing by
writing slabinfo, but, with some trick in this patch, we can access it
freely within interrupt disabled period.

Below is the result of concurrent allocation/free in slab allocation
benchmark made by Christoph a long time ago.  I make the output simpler.
The number shows cycle count during alloc/free respectively so less is
better.

  * Before
  Kmalloc N*alloc N*free(32): Average=248/966
  Kmalloc N*alloc N*free(64): Average=261/949
  Kmalloc N*alloc N*free(128): Average=314/1016
  Kmalloc N*alloc N*free(256): Average=741/1061
  Kmalloc N*alloc N*free(512): Average=1246/1152
  Kmalloc N*alloc N*free(1024): Average=2437/1259
  Kmalloc N*alloc N*free(2048): Average=4980/1800
  Kmalloc N*alloc N*free(4096): Average=9000/2078

  * After
  Kmalloc N*alloc N*free(32): Average=344/792
  Kmalloc N*alloc N*free(64): Average=347/882
  Kmalloc N*alloc N*free(128): Average=390/959
  Kmalloc N*alloc N*free(256): Average=393/1067
  Kmalloc N*alloc N*free(512): Average=683/1229
  Kmalloc N*alloc N*free(1024): Average=1295/1325
  Kmalloc N*alloc N*free(2048): Average=2513/1664
  Kmalloc N*alloc N*free(4096): Average=4742/2172

It shows that allocation performance decreases for the object size up to
128 and it may be due to extra checks in cache_alloc_refill().  But,
with considering improvement of free performance, net result looks the
same.  Result for other size class looks very promising, roughly, 50%
performance improvement.
Signed-off-by: default avatarJoonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 213b4695
...@@ -965,6 +965,15 @@ static int setup_kmem_cache_node(struct kmem_cache *cachep, ...@@ -965,6 +965,15 @@ static int setup_kmem_cache_node(struct kmem_cache *cachep,
spin_unlock_irq(&n->list_lock); spin_unlock_irq(&n->list_lock);
slabs_destroy(cachep, &list); slabs_destroy(cachep, &list);
/*
* To protect lockless access to n->shared during irq disabled context.
* If n->shared isn't NULL in irq disabled context, accessing to it is
* guaranteed to be valid until irq is re-enabled, because it will be
* freed after synchronize_sched().
*/
if (force_change)
synchronize_sched();
fail: fail:
kfree(old_shared); kfree(old_shared);
kfree(new_shared); kfree(new_shared);
...@@ -2893,7 +2902,7 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags) ...@@ -2893,7 +2902,7 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
{ {
int batchcount; int batchcount;
struct kmem_cache_node *n; struct kmem_cache_node *n;
struct array_cache *ac; struct array_cache *ac, *shared;
int node; int node;
void *list = NULL; void *list = NULL;
struct page *page; struct page *page;
...@@ -2914,11 +2923,16 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags) ...@@ -2914,11 +2923,16 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
n = get_node(cachep, node); n = get_node(cachep, node);
BUG_ON(ac->avail > 0 || !n); BUG_ON(ac->avail > 0 || !n);
shared = READ_ONCE(n->shared);
if (!n->free_objects && (!shared || !shared->avail))
goto direct_grow;
spin_lock(&n->list_lock); spin_lock(&n->list_lock);
shared = READ_ONCE(n->shared);
/* See if we can refill from the shared array */ /* See if we can refill from the shared array */
if (n->shared && transfer_objects(ac, n->shared, batchcount)) { if (shared && transfer_objects(ac, shared, batchcount)) {
n->shared->touched = 1; shared->touched = 1;
goto alloc_done; goto alloc_done;
} }
...@@ -2940,6 +2954,7 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags) ...@@ -2940,6 +2954,7 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
spin_unlock(&n->list_lock); spin_unlock(&n->list_lock);
fixup_objfreelist_debug(cachep, &list); fixup_objfreelist_debug(cachep, &list);
direct_grow:
if (unlikely(!ac->avail)) { if (unlikely(!ac->avail)) {
/* Check if we can use obj in pfmemalloc slab */ /* Check if we can use obj in pfmemalloc slab */
if (sk_memalloc_socks()) { if (sk_memalloc_socks()) {
......
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