LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Vladimir Davydov <vdavydov.dev@gmail.com>
To: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: akpm@linux-foundation.org, shakeelb@google.com,
	viro@zeniv.linux.org.uk, hannes@cmpxchg.org, mhocko@kernel.org,
	tglx@linutronix.de, pombredanne@nexb.com,
	stummala@codeaurora.org, gregkh@linuxfoundation.org,
	sfr@canb.auug.org.au, guro@fb.com, mka@chromium.org,
	penguin-kernel@I-love.SAKURA.ne.jp, chris@chris-wilson.co.uk,
	longman@redhat.com, minchan@kernel.org, hillf.zj@alibaba-inc.com,
	ying.huang@intel.com, mgorman@techsingularity.net, jbacik@fb.com,
	linux@roeck-us.net, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, willy@infradead.org, lirongqing@baidu.com,
	aryabinin@virtuozzo.com
Subject: Re: [PATCH v2 10/12] mm: Iterate only over charged shrinkers during memcg shrink_slab()
Date: Sun, 22 Apr 2018 21:19:11 +0300	[thread overview]
Message-ID: <20180422181911.axqiabv3cl7qtrpc@esperanza> (raw)
In-Reply-To: <152399127400.3456.6644633244163904030.stgit@localhost.localdomain>

On Tue, Apr 17, 2018 at 09:54:34PM +0300, Kirill Tkhai wrote:
> Using the preparations made in previous patches, in case of memcg
> shrink, we may avoid shrinkers, which are not set in memcg's shrinkers
> bitmap. To do that, we separate iterations over memcg-aware and
> !memcg-aware shrinkers, and memcg-aware shrinkers are chosen
> via for_each_set_bit() from the bitmap. In case of big nodes,
> having many isolated environments, this gives significant
> performance growth. See next patches for the details.
> 
> Note, that the patch does not respect to empty memcg shrinkers,
> since we never clear the bitmap bits after we set it once.
> Their shrinkers will be called again, with no shrinked objects
> as result. This functionality is provided by next patches.
> 
> Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
> ---
>  mm/vmscan.c |   88 ++++++++++++++++++++++++++++++++++++++++++++++++-----------
>  1 file changed, 72 insertions(+), 16 deletions(-)
> 
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 34cd1d9b8b22..b81b8a7727b5 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -169,6 +169,20 @@ unsigned long vm_total_pages;
>  static LIST_HEAD(shrinker_list);
>  static DECLARE_RWSEM(shrinker_rwsem);
>  
> +static void link_shrinker(struct shrinker *shrinker)
> +{
> +	down_write(&shrinker_rwsem);
> +	list_add_tail(&shrinker->list, &shrinker_list);
> +	up_write(&shrinker_rwsem);
> +}
> +
> +static void unlink_shrinker(struct shrinker *shrinker)
> +{
> +	down_write(&shrinker_rwsem);
> +	list_del(&shrinker->list);
> +	up_write(&shrinker_rwsem);
> +}
> +
>  #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
>  static DEFINE_IDR(shrinkers_id_idr);
>  
> @@ -221,11 +235,13 @@ static void del_memcg_shrinker(struct shrinker *shrinker)
>  #else /* CONFIG_MEMCG && !CONFIG_SLOB */
>  static int add_memcg_shrinker(struct shrinker *shrinker, int nr, va_list args)
>  {
> +	link_shrinker(shrinker);
>  	return 0;
>  }
>  
>  static void del_memcg_shrinker(struct shrinker *shrinker)
>  {
> +	unlink_shrinker(shrinker);
>  }
>  #endif /* CONFIG_MEMCG && !CONFIG_SLOB */
>  
> @@ -382,11 +398,9 @@ int __register_shrinker(struct shrinker *shrinker, int nr, ...)
>  		va_end(args);
>  		if (ret)
>  			goto free_deferred;
> -	}
> +	} else
> +		link_shrinker(shrinker);
>  
> -	down_write(&shrinker_rwsem);
> -	list_add_tail(&shrinker->list, &shrinker_list);
> -	up_write(&shrinker_rwsem);
>  	return 0;
>  
>  free_deferred:
> @@ -405,9 +419,8 @@ void unregister_shrinker(struct shrinker *shrinker)
>  		return;
>  	if (shrinker->flags & SHRINKER_MEMCG_AWARE)
>  		del_memcg_shrinker(shrinker);
> -	down_write(&shrinker_rwsem);
> -	list_del(&shrinker->list);
> -	up_write(&shrinker_rwsem);
> +	else
> +		unlink_shrinker(shrinker);

I really don't like that depending on the config, the shrinker_list
stores either all shrinkers or only memcg-unaware ones. I think it
should always store all shrinkers and it should be used in case of
global reclaim. That is IMO shrink_slab should look like this:

shrink_slab(memcg)
{
        if (!mem_cgroup_is_root(memcg))
                return shrink_slab_memcg()
        list_for_each(shrinker, shrinker_list, link)
                do_shrink_slab()
}

Yeah, that means that for the root mem cgroup we will always call all
shrinkers, but IMO it is OK as there's the only root mem cgroup out
there and it is visited only on global reclaim so it shouldn't degrade
performance.

>  	kfree(shrinker->nr_deferred);
>  	shrinker->nr_deferred = NULL;
>  }
> @@ -532,6 +545,53 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
>  	return freed;
>  }
>  
> +#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
> +static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
> +				       struct mem_cgroup *memcg,
> +				       int priority)
> +{
> +	struct memcg_shrinker_map *map;
> +	unsigned long freed = 0;
> +	int ret, i;
> +
> +	if (!down_read_trylock(&shrinker_rwsem))
> +		return 0;
> +
> +	/*
> +	 * 1)Caller passes only alive memcg, so map can't be NULL.
> +	 * 2)shrinker_rwsem protects from maps expanding.
> +	 */
> +	map = rcu_dereference_protected(SHRINKERS_MAP(memcg, nid), true);
> +	BUG_ON(!map);
> +
> +	for_each_set_bit(i, map->map, shrinkers_max_nr) {
> +		struct shrink_control sc = {
> +			.gfp_mask = gfp_mask,
> +			.nid = nid,
> +			.memcg = memcg,
> +		};
> +		struct shrinker *shrinker;
> +
> +		shrinker = idr_find(&shrinkers_id_idr, i);
> +		if (!shrinker) {
> +			clear_bit(i, map->map);
> +			continue;
> +		}
> +
> +		ret = do_shrink_slab(&sc, shrinker, priority);
> +		freed += ret;
> +
> +		if (rwsem_is_contended(&shrinker_rwsem)) {
> +			freed = freed ? : 1;
> +			break;
> +		}
> +	}
> +
> +	up_read(&shrinker_rwsem);
> +	return freed;
> +}
> +#endif
> +
>  /**
>   * shrink_slab - shrink slab caches
>   * @gfp_mask: allocation context
> @@ -564,6 +624,11 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
>  	if (memcg && (!memcg_kmem_enabled() || !mem_cgroup_online(memcg)))
>  		return 0;

The check above should be moved to shrink_slab_memcg.

>  
> +#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)

Please don't use ifdef here - define a stub function for no-memcg case.

> +	if (memcg)
> +		return shrink_slab_memcg(gfp_mask, nid, memcg, priority);
> +#endif
> +
>  	if (!down_read_trylock(&shrinker_rwsem))
>  		goto out;
>  
> @@ -574,15 +639,6 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
>  			.memcg = memcg,
>  		};
>  
> -		/*
> -		 * If kernel memory accounting is disabled, we ignore
> -		 * SHRINKER_MEMCG_AWARE flag and call all shrinkers
> -		 * passing NULL for memcg.
> -		 */
> -		if (memcg_kmem_enabled() &&
> -		    !!memcg != !!(shrinker->flags & SHRINKER_MEMCG_AWARE))
> -			continue;
> -
>  		if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
>  			sc.nid = 0;
>  
> 

  reply	other threads:[~2018-04-22 18:19 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-04-17 18:52 [PATCH v2 00/12] Improve shrink_slab() scalability (old complexity was O(n^2), new is O(n)) Kirill Tkhai
2018-04-17 18:53 ` [PATCH v2 01/12] mm: Assign id to every memcg-aware shrinker Kirill Tkhai
2018-04-18 14:14   ` Tetsuo Handa
2018-04-18 14:27     ` Kirill Tkhai
2018-04-18 14:32       ` Tetsuo Handa
2018-04-18 15:02         ` Kirill Tkhai
2018-04-22 17:16   ` Vladimir Davydov
2018-04-17 18:53 ` [PATCH v2 02/12] memcg: Refactoring in mem_cgroup_alloc() Kirill Tkhai
2018-04-17 18:53 ` [PATCH v2 03/12] memcg: Refactoring in alloc_mem_cgroup_per_node_info() Kirill Tkhai
2018-04-17 18:53 ` [PATCH v2 04/12] mm: Assign memcg-aware shrinkers bitmap to memcg Kirill Tkhai
2018-04-18 12:55   ` kbuild test robot
2018-04-18 13:05     ` Kirill Tkhai
2018-04-22 17:59   ` Vladimir Davydov
2018-04-23 10:54     ` Kirill Tkhai
2018-04-24 11:28       ` Vladimir Davydov
2018-04-24 11:38         ` Kirill Tkhai
2018-04-24 12:15           ` Vladimir Davydov
2018-04-24 12:24             ` Kirill Tkhai
2018-04-28 15:08               ` Vladimir Davydov
2018-05-03 11:15                 ` Kirill Tkhai
2018-04-24 12:13         ` Kirill Tkhai
2018-04-23 11:02     ` Kirill Tkhai
2018-04-23 11:06     ` Kirill Tkhai
2018-04-24 11:08       ` Vladimir Davydov
2018-04-17 18:53 ` [PATCH v2 05/12] fs: Propagate shrinker::id to list_lru Kirill Tkhai
2018-04-22 18:03   ` Vladimir Davydov
2018-04-17 18:53 ` [PATCH v2 06/12] list_lru: Add memcg argument to list_lru_from_kmem() Kirill Tkhai
2018-04-17 18:54 ` [PATCH v2 07/12] list_lru: Pass dst_memcg argument to memcg_drain_list_lru_node() Kirill Tkhai
2018-04-17 18:54 ` [PATCH v2 08/12] list_lru: Pass lru " Kirill Tkhai
2018-04-17 18:54 ` [PATCH v2 09/12] mm: Set bit in memcg shrinker bitmap on first list_lru item apearance Kirill Tkhai
2018-04-17 18:54 ` [PATCH v2 10/12] mm: Iterate only over charged shrinkers during memcg shrink_slab() Kirill Tkhai
2018-04-22 18:19   ` Vladimir Davydov [this message]
2018-04-17 18:54 ` [PATCH v2 11/12] mm: Add SHRINK_EMPTY shrinker methods return value Kirill Tkhai
2018-04-17 18:54 ` [PATCH v2 12/12] mm: Clear shrinker bit if there are no objects related to memcg Kirill Tkhai
2018-04-22 18:21   ` Vladimir Davydov
2018-04-23 10:01     ` Kirill Tkhai
2018-04-24 10:56       ` Vladimir Davydov

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180422181911.axqiabv3cl7qtrpc@esperanza \
    --to=vdavydov.dev@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=aryabinin@virtuozzo.com \
    --cc=chris@chris-wilson.co.uk \
    --cc=gregkh@linuxfoundation.org \
    --cc=guro@fb.com \
    --cc=hannes@cmpxchg.org \
    --cc=hillf.zj@alibaba-inc.com \
    --cc=jbacik@fb.com \
    --cc=ktkhai@virtuozzo.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux@roeck-us.net \
    --cc=lirongqing@baidu.com \
    --cc=longman@redhat.com \
    --cc=mgorman@techsingularity.net \
    --cc=mhocko@kernel.org \
    --cc=minchan@kernel.org \
    --cc=mka@chromium.org \
    --cc=penguin-kernel@I-love.SAKURA.ne.jp \
    --cc=pombredanne@nexb.com \
    --cc=sfr@canb.auug.org.au \
    --cc=shakeelb@google.com \
    --cc=stummala@codeaurora.org \
    --cc=tglx@linutronix.de \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@infradead.org \
    --cc=ying.huang@intel.com \
    --subject='Re: [PATCH v2 10/12] mm: Iterate only over charged shrinkers during memcg shrink_slab()' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).