Re: [PATCH 6/9] mm: vmscan: use per memcg nr_deferred of shrinker

From: Roman Gushchin <guro@fb.com>
To: Yang Shi <shy828301@gmail.com>
Cc: <ktkhai@virtuozzo.com>, <shakeelb@google.com>,
	<david@fromorbit.com>, <hannes@cmpxchg.org>, <mhocko@suse.com>,
	<akpm@linux-foundation.org>, <linux-mm@kvack.org>,
	<linux-fsdevel@vger.kernel.org>, <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 6/9] mm: vmscan: use per memcg nr_deferred of shrinker
Date: Wed, 2 Dec 2020 19:08:41 -0800	[thread overview]
Message-ID: <20201203030841.GH1375014@carbon.DHCP.thefacebook.com> (raw)
In-Reply-To: <20201202182725.265020-7-shy828301@gmail.com>

On Wed, Dec 02, 2020 at 10:27:22AM -0800, Yang Shi wrote:
> Use per memcg's nr_deferred for memcg aware shrinkers.  The shrinker's nr_deferred
> will be used in the following cases:
>     1. Non memcg aware shrinkers
>     2. !CONFIG_MEMCG
>     3. memcg is disabled by boot parameter
> 
> Signed-off-by: Yang Shi <shy828301@gmail.com>
> ---
>  mm/vmscan.c | 88 +++++++++++++++++++++++++++++++++++++++++++++++++----
>  1 file changed, 82 insertions(+), 6 deletions(-)
> 
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index cba0bc8d4661..d569fdcaba79 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -203,6 +203,12 @@ static DECLARE_RWSEM(shrinker_rwsem);
>  static DEFINE_IDR(shrinker_idr);
>  static int shrinker_nr_max;
>  
> +static inline bool is_deferred_memcg_aware(struct shrinker *shrinker)
> +{
> +	return (shrinker->flags & SHRINKER_MEMCG_AWARE) &&
> +		!mem_cgroup_disabled();
> +}
> +
>  static int prealloc_memcg_shrinker(struct shrinker *shrinker)
>  {
>  	int id, ret = -ENOMEM;
> @@ -271,7 +277,58 @@ static bool writeback_throttling_sane(struct scan_control *sc)
>  #endif
>  	return false;
>  }
> +
> +static inline long count_nr_deferred(struct shrinker *shrinker,
> +				     struct shrink_control *sc)
> +{
> +	bool per_memcg_deferred = is_deferred_memcg_aware(shrinker) && sc->memcg;
> +	struct memcg_shrinker_deferred *deferred;
> +	struct mem_cgroup *memcg = sc->memcg;
> +	int nid = sc->nid;
> +	int id = shrinker->id;
> +	long nr;
> +
> +	if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
> +		nid = 0;
> +
> +	if (per_memcg_deferred) {
> +		deferred = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_deferred,
> +						     true);
> +		nr = atomic_long_xchg(&deferred->nr_deferred[id], 0);
> +	} else
> +		nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
> +
> +	return nr;
> +}
> +
> +static inline long set_nr_deferred(long nr, struct shrinker *shrinker,
> +				   struct shrink_control *sc)
> +{
> +	bool per_memcg_deferred = is_deferred_memcg_aware(shrinker) && sc->memcg;
> +	struct memcg_shrinker_deferred *deferred;
> +	struct mem_cgroup *memcg = sc->memcg;
> +	int nid = sc->nid;
> +	int id = shrinker->id;
> +	long new_nr;
> +
> +	if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
> +		nid = 0;
> +
> +	if (per_memcg_deferred) {
> +		deferred = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_deferred,
> +						     true);
> +		new_nr = atomic_long_add_return(nr, &deferred->nr_deferred[id]);
> +	} else
> +		new_nr = atomic_long_add_return(nr, &shrinker->nr_deferred[nid]);
> +
> +	return new_nr;
> +}
>  #else
> +static inline bool is_deferred_memcg_aware(struct shrinker *shrinker)
> +{
> +	return false;
> +}
> +
>  static int prealloc_memcg_shrinker(struct shrinker *shrinker)
>  {
>  	return 0;
> @@ -290,6 +347,29 @@ static bool writeback_throttling_sane(struct scan_control *sc)
>  {
>  	return true;
>  }
> +
> +static inline long count_nr_deferred(struct shrinker *shrinker,
> +				     struct shrink_control *sc)
> +{
> +	int nid = sc->nid;
> +
> +	if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
> +		nid = 0;
> +
> +	return atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
> +}
> +
> +static inline long set_nr_deferred(long nr, struct shrinker *shrinker,
> +				   struct shrink_control *sc)
> +{
> +	int nid = sc->nid;
> +
> +	if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
> +		nid = 0;
> +
> +	return atomic_long_add_return(nr,
> +				      &shrinker->nr_deferred[nid]);
> +}
>  #endif
>  
>  /*
> @@ -429,13 +509,10 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
>  	long freeable;
>  	long nr;
>  	long new_nr;
> -	int nid = shrinkctl->nid;
>  	long batch_size = shrinker->batch ? shrinker->batch
>  					  : SHRINK_BATCH;
>  	long scanned = 0, next_deferred;
>  
> -	if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
> -		nid = 0;
>  
>  	freeable = shrinker->count_objects(shrinker, shrinkctl);
>  	if (freeable == 0 || freeable == SHRINK_EMPTY)
> @@ -446,7 +523,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
>  	 * and zero it so that other concurrent shrinker invocations
>  	 * don't also do this scanning work.
>  	 */
> -	nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
> +	nr = count_nr_deferred(shrinker, shrinkctl);
>  
>  	total_scan = nr;
>  	if (shrinker->seeks) {
> @@ -539,8 +616,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
>  	 * move the unused scan count back into the shrinker in a
>  	 * manner that handles concurrent updates.
>  	 */
> -	new_nr = atomic_long_add_return(next_deferred,
> -					&shrinker->nr_deferred[nid]);
> +	new_nr = set_nr_deferred(next_deferred, shrinker, shrinkctl);

Ok, I think patch (1) can be just merged into this and then it would make total sense.