Re: [v7 PATCH 08/12] mm: vmscan: add per memcg shrinker nr_deferred

[Roman Gushchin <guro@fb.com>]

On Tue, Feb 09, 2021 at 09:46:42AM -0800, Yang Shi wrote:
> Currently the number of deferred objects are per shrinker, but some slabs, for example,
> vfs inode/dentry cache are per memcg, this would result in poor isolation among memcgs.
> 
> The deferred objects typically are generated by __GFP_NOFS allocations, one memcg with
> excessive __GFP_NOFS allocations may blow up deferred objects, then other innocent memcgs
> may suffer from over shrink, excessive reclaim latency, etc.
> 
> For example, two workloads run in memcgA and memcgB respectively, workload in B is vfs
> heavy workload.  Workload in A generates excessive deferred objects, then B's vfs cache
> might be hit heavily (drop half of caches) by B's limit reclaim or global reclaim.
> 
> We observed this hit in our production environment which was running vfs heavy workload
> shown as the below tracing log:
> 
> <...>-409454 [016] .... 28286961.747146: mm_shrink_slab_start: super_cache_scan+0x0/0x1a0 ffff9a83046f3458:
> nid: 1 objects to shrink 3641681686040 gfp_flags GFP_HIGHUSER_MOVABLE|__GFP_ZERO pgs_scanned 1 lru_pgs 15721
> cache items 246404277 delta 31345 total_scan 123202138
> <...>-409454 [022] .... 28287105.928018: mm_shrink_slab_end: super_cache_scan+0x0/0x1a0 ffff9a83046f3458:
> nid: 1 unused scan count 3641681686040 new scan count 3641798379189 total_scan 602
> last shrinker return val 123186855
> 
> The vfs cache and page cache ratio was 10:1 on this machine, and half of caches were dropped.
> This also resulted in significant amount of page caches were dropped due to inodes eviction.
> 
> Make nr_deferred per memcg for memcg aware shrinkers would solve the unfairness and bring
> better isolation.
> 
> When memcg is not enabled (!CONFIG_MEMCG or memcg disabled), the shrinker's nr_deferred
> would be used.  And non memcg aware shrinkers use shrinker's nr_deferred all the time.
> 
> Signed-off-by: Yang Shi <shy828301@gmail.com>
> ---
>  include/linux/memcontrol.h |  7 +++---
>  mm/vmscan.c                | 49 +++++++++++++++++++++++++-------------
>  2 files changed, 37 insertions(+), 19 deletions(-)
> 
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 4c9253896e25..c457fc7bc631 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -93,12 +93,13 @@ struct lruvec_stat {
>  };
>  
>  /*
> - * Bitmap of shrinker::id corresponding to memcg-aware shrinkers,
> - * which have elements charged to this memcg.
> + * Bitmap and deferred work of shrinker::id corresponding to memcg-aware
> + * shrinkers, which have elements charged to this memcg.
>   */
>  struct shrinker_info {
>  	struct rcu_head rcu;
> -	unsigned long map[];
> +	atomic_long_t *nr_deferred;
> +	unsigned long *map;
>  };
>  
>  /*
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index a047980536cf..d4b030a0b2a9 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -187,9 +187,13 @@ static DECLARE_RWSEM(shrinker_rwsem);
>  #ifdef CONFIG_MEMCG
>  static int shrinker_nr_max;
>  
> +/* The shrinker_info is expanded in a batch of BITS_PER_LONG */
>  #define NR_MAX_TO_SHR_MAP_SIZE(nr_max) \
>  	(DIV_ROUND_UP(nr_max, BITS_PER_LONG) * sizeof(unsigned long))
>  
> +#define NR_MAX_TO_SHR_DEF_SIZE(nr_max) \
> +	(round_up(nr_max, BITS_PER_LONG) * sizeof(atomic_long_t))
> +
>  static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg,
>  						     int nid)
>  {
> @@ -203,10 +207,12 @@ static void free_shrinker_info_rcu(struct rcu_head *head)
>  }
>  
>  static int expand_one_shrinker_info(struct mem_cgroup *memcg,
> -				   int size, int old_size)
> +				    int m_size, int d_size,
> +				    int old_m_size, int old_d_size)
>  {
>  	struct shrinker_info *new, *old;
>  	int nid;
> +	int size = m_size + d_size;
>  
>  	for_each_node(nid) {
>  		old = shrinker_info_protected(memcg, nid);
> @@ -218,9 +224,15 @@ static int expand_one_shrinker_info(struct mem_cgroup *memcg,
>  		if (!new)
>  			return -ENOMEM;
>  
> -		/* Set all old bits, clear all new bits */
> -		memset(new->map, (int)0xff, old_size);
> -		memset((void *)new->map + old_size, 0, size - old_size);
> +		new->nr_deferred = (atomic_long_t *)(new + 1);
> +		new->map = (void *)new->nr_deferred + d_size;
> +
> +		/* map: set all old bits, clear all new bits */
> +		memset(new->map, (int)0xff, old_m_size);
> +		memset((void *)new->map + old_m_size, 0, m_size - old_m_size);
> +		/* nr_deferred: copy old values, clear all new values */
> +		memcpy(new->nr_deferred, old->nr_deferred, old_d_size);
> +		memset((void *)new->nr_deferred + old_d_size, 0, d_size - old_d_size);
>  
>  		rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, new);
>  		call_rcu(&old->rcu, free_shrinker_info_rcu);
> @@ -235,9 +247,6 @@ void free_shrinker_info(struct mem_cgroup *memcg)
>  	struct shrinker_info *info;
>  	int nid;
>  
> -	if (mem_cgroup_is_root(memcg))
> -		return;
> -
>  	for_each_node(nid) {
>  		pn = mem_cgroup_nodeinfo(memcg, nid);
>  		info = shrinker_info_protected(memcg, nid);
> @@ -250,12 +259,13 @@ int alloc_shrinker_info(struct mem_cgroup *memcg)
>  {
>  	struct shrinker_info *info;
>  	int nid, size, ret = 0;
> -
> -	if (mem_cgroup_is_root(memcg))
> -		return 0;
> +	int m_size, d_size = 0;
>  
>  	down_write(&shrinker_rwsem);
> -	size = NR_MAX_TO_SHR_MAP_SIZE(shrinker_nr_max);
> +	m_size = NR_MAX_TO_SHR_MAP_SIZE(shrinker_nr_max);
> +	d_size = NR_MAX_TO_SHR_DEF_SIZE(shrinker_nr_max);
> +	size = m_size + d_size;
> +
>  	for_each_node(nid) {
>  		info = kvzalloc_node(sizeof(*info) + size, GFP_KERNEL, nid);
>  		if (!info) {
> @@ -263,6 +273,8 @@ int alloc_shrinker_info(struct mem_cgroup *memcg)
>  			ret = -ENOMEM;
>  			break;
>  		}
> +		info->nr_deferred = (atomic_long_t *)(info + 1);
> +		info->map = (void *)info->nr_deferred + d_size;
>  		rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info);
>  	}
>  	up_write(&shrinker_rwsem);
> @@ -274,10 +286,16 @@ static int expand_shrinker_info(int new_id)
>  {
>  	int size, old_size, ret = 0;
>  	int new_nr_max = new_id + 1;
> +	int m_size, d_size = 0;
> +	int old_m_size, old_d_size = 0;
>  	struct mem_cgroup *memcg;
>  
> -	size = NR_MAX_TO_SHR_MAP_SIZE(new_nr_max);
> -	old_size = NR_MAX_TO_SHR_MAP_SIZE(shrinker_nr_max);
> +	m_size = NR_MAX_TO_SHR_MAP_SIZE(new_nr_max);
> +	d_size = NR_MAX_TO_SHR_DEF_SIZE(new_nr_max);
> +	size = m_size + d_size;
> +	old_m_size = NR_MAX_TO_SHR_MAP_SIZE(shrinker_nr_max);
> +	old_d_size = NR_MAX_TO_SHR_DEF_SIZE(shrinker_nr_max);
> +	old_size = old_m_size + old_d_size;
>  	if (size <= old_size)
>  		goto out;

It looks correct, but a bit bulky. Can we check that the new maximum
number of elements is larger than then the old one here?

>  
> @@ -286,9 +304,8 @@ static int expand_shrinker_info(int new_id)
>  
>  	memcg = mem_cgroup_iter(NULL, NULL, NULL);
>  	do {
> -		if (mem_cgroup_is_root(memcg))
> -			continue;
> -		ret = expand_one_shrinker_info(memcg, size, old_size);
> +		ret = expand_one_shrinker_info(memcg, m_size, d_size,
> +					       old_m_size, old_d_size);

Pass the old and the new numbers to expand_one_shrinker_info() and
have all size manipulation there?

>  		if (ret) {
>  			mem_cgroup_iter_break(NULL, memcg);
>  			goto out;
> -- 
> 2.26.2
>