On Mon, 10 Aug 2020, Xunlei Pang wrote:
>
> diff --git a/mm/slab.h b/mm/slab.h
> index c85e2fa..a709a70 100644
> --- a/mm/slab.h
> +++ b/mm/slab.h
> @@ -616,7 +616,7 @@ struct kmem_cache_node {
> #ifdef CONFIG_SLUB
> unsigned long nr_partial;
> struct list_head partial;
> - atomic_long_t partial_free_objs;
> + atomic_long_t __percpu *partial_free_objs;
A percpu counter is never atomic. Just use unsigned long and use this_cpu
operations for this thing. That should cut down further on the overhead.
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -1775,11 +1775,21 @@ static void discard_slab(struct kmem_cache *s, struct page *page)
> /*
> * Management of partially allocated slabs.
> */
> +static inline long get_partial_free(struct kmem_cache_node *n)
> +{
> + long nr = 0;
> + int cpu;
> +
> + for_each_possible_cpu(cpu)
> + nr += atomic_long_read(per_cpu_ptr(n->partial_free_objs, cpu));
this_cpu_read(*n->partial_free_objs)
> static inline void
> __update_partial_free(struct kmem_cache_node *n, long delta)
> {
> - atomic_long_add(delta, &n->partial_free_objs);
> + atomic_long_add(delta, this_cpu_ptr(n->partial_free_objs));
this_cpu_add()
and so on.
