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, 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 v5 11/13] mm: Iterate only over charged shrinkers during memcg shrink_slab()
Date: Tue, 15 May 2018 08:44:45 +0300	[thread overview]
Message-ID: <20180515054445.nhe4zigtelkois4p@esperanza> (raw)
In-Reply-To: <152594603565.22949.12428911301395699065.stgit@localhost.localdomain>

On Thu, May 10, 2018 at 12:53:55PM +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>
> ---
>  include/linux/memcontrol.h |    1 +
>  mm/vmscan.c                |   70 ++++++++++++++++++++++++++++++++++++++------
>  2 files changed, 62 insertions(+), 9 deletions(-)
> 
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 82f892e77637..436691a66500 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -760,6 +760,7 @@ void mem_cgroup_split_huge_fixup(struct page *head);
>  #define MEM_CGROUP_ID_MAX	0
>  
>  struct mem_cgroup;
> +#define root_mem_cgroup NULL

Let's instead export mem_cgroup_is_root(). In case if MEMCG is disabled
it will always return false.

>  
>  static inline bool mem_cgroup_disabled(void)
>  {
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index d8a2870710e0..a2e38e05adb5 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -376,6 +376,7 @@ int prealloc_shrinker(struct shrinker *shrinker)
>  			goto free_deferred;
>  	}
>  
> +	INIT_LIST_HEAD(&shrinker->list);

IMO this shouldn't be here, see my comment below.

>  	return 0;
>  
>  free_deferred:
> @@ -547,6 +548,63 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
>  	return freed;
>  }
>  
> +#ifdef CONFIG_MEMCG_SHRINKER
> +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 (!memcg_kmem_enabled() || !mem_cgroup_online(memcg))
> +		return 0;
> +
> +	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.

            ^^
Nit: space missing here :-)

> +	 */
> +	map = rcu_dereference_protected(MEMCG_SHRINKER_MAP(memcg, nid), true);
> +	BUG_ON(!map);
> +
> +	for_each_set_bit(i, map->map, memcg_shrinker_nr_max) {
> +		struct shrink_control sc = {
> +			.gfp_mask = gfp_mask,
> +			.nid = nid,
> +			.memcg = memcg,
> +		};
> +		struct shrinker *shrinker;
> +
> +		shrinker = idr_find(&shrinker_idr, i);
> +		if (!shrinker) {
> +			clear_bit(i, map->map);
> +			continue;
> +		}

The shrinker must be memcg aware so please add

  BUG_ON((shrinker->flags & SHRINKER_MEMCG_AWARE) == 0);

> +		if (list_empty(&shrinker->list))
> +			continue;

I don't like using shrinker->list as an indicator that the shrinker has
been initialized. IMO if you do need such a check, you should split
shrinker_idr registration in two steps - allocate a slot in 'prealloc'
and set the pointer in 'register'. However, can we really encounter an
unregistered shrinker here? AFAIU a bit can be set in the shrinker map
only after the corresponding shrinker has been initialized, no?

> +
> +		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;
> +}
> +#else /* CONFIG_MEMCG_SHRINKER */
> +static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
> +			struct mem_cgroup *memcg, int priority)
> +{
> +	return 0;
> +}
> +#endif /* CONFIG_MEMCG_SHRINKER */
> +
>  /**
>   * shrink_slab - shrink slab caches
>   * @gfp_mask: allocation context
> @@ -576,8 +634,8 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
>  	struct shrinker *shrinker;
>  	unsigned long freed = 0;
>  
> -	if (memcg && (!memcg_kmem_enabled() || !mem_cgroup_online(memcg)))
> -		return 0;
> +	if (memcg && memcg != root_mem_cgroup)

if (!mem_cgroup_is_root(memcg))

> +		return shrink_slab_memcg(gfp_mask, nid, memcg, priority);
>  
>  	if (!down_read_trylock(&shrinker_rwsem))
>  		goto out;
> @@ -589,13 +647,7 @@ 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))
> +		if (!!memcg != !!(shrinker->flags & SHRINKER_MEMCG_AWARE))
>  			continue;

I want this check gone. It's easy to achieve, actually - just remove the
following lines from shrink_node()

		if (global_reclaim(sc))
			shrink_slab(sc->gfp_mask, pgdat->node_id, NULL,
				    sc->priority);

>  
>  		if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
> 

  reply	other threads:[~2018-05-15  5:44 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-10  9:52 [PATCH v5 00/13] Improve shrink_slab() scalability (old complexity was O(n^2), new is O(n)) Kirill Tkhai
2018-05-10  9:52 ` [PATCH v5 01/13] mm: Assign id to every memcg-aware shrinker Kirill Tkhai
2018-05-13  5:15   ` Vladimir Davydov
2018-05-14  9:03     ` Kirill Tkhai
2018-05-15  3:29       ` Vladimir Davydov
2018-05-10  9:52 ` [PATCH v5 02/13] memcg: Move up for_each_mem_cgroup{, _tree} defines Kirill Tkhai
2018-05-10  9:52 ` [PATCH v5 03/13] mm: Assign memcg-aware shrinkers bitmap to memcg Kirill Tkhai
2018-05-13 16:47   ` Vladimir Davydov
2018-05-14  9:34     ` Kirill Tkhai
2018-05-15  3:54       ` Vladimir Davydov
2018-05-10  9:52 ` [PATCH v5 04/13] mm: Refactoring in workingset_init() Kirill Tkhai
2018-05-10  9:52 ` [PATCH v5 05/13] fs: Refactoring in alloc_super() Kirill Tkhai
2018-05-10  9:53 ` [PATCH v5 06/13] fs: Propagate shrinker::id to list_lru Kirill Tkhai
2018-05-13 16:57   ` Vladimir Davydov
2018-05-10  9:53 ` [PATCH v5 07/13] list_lru: Add memcg argument to list_lru_from_kmem() Kirill Tkhai
2018-05-10  9:53 ` [PATCH v5 08/13] list_lru: Pass dst_memcg argument to memcg_drain_list_lru_node() Kirill Tkhai
2018-05-10  9:53 ` [PATCH v5 09/13] list_lru: Pass lru " Kirill Tkhai
2018-05-10  9:53 ` [PATCH v5 10/13] mm: Set bit in memcg shrinker bitmap on first list_lru item apearance Kirill Tkhai
2018-05-15  4:08   ` Vladimir Davydov
2018-05-10  9:53 ` [PATCH v5 11/13] mm: Iterate only over charged shrinkers during memcg shrink_slab() Kirill Tkhai
2018-05-15  5:44   ` Vladimir Davydov [this message]
2018-05-15 10:12     ` Kirill Tkhai
2018-05-17  4:33       ` Vladimir Davydov
2018-05-17 11:39         ` Kirill Tkhai
2018-05-15 14:49     ` Kirill Tkhai
2018-05-17  4:16       ` Vladimir Davydov
2018-05-17 11:49         ` Kirill Tkhai
2018-05-17 13:51           ` Vladimir Davydov
2018-05-10  9:54 ` [PATCH v5 12/13] mm: Add SHRINK_EMPTY shrinker methods return value Kirill Tkhai
2018-05-10  9:54 ` [PATCH v5 13/13] mm: Clear shrinker bit if there are no objects related to memcg Kirill Tkhai
2018-05-15  5:59   ` Vladimir Davydov
2018-05-15  8:55     ` Kirill Tkhai
2018-05-17  4:49       ` 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=20180515054445.nhe4zigtelkois4p@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=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 v5 11/13] 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).