All of lore.kernel.org
 help / color / mirror / Atom feed
From: Kirill Tkhai <ktkhai@virtuozzo.com>
To: vdavydov.dev@gmail.com, 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, akpm@linux-foundation.org,
	ktkhai@virtuozzo.com
Subject: [PATCH v9 14/17] mm: Iterate only over charged shrinkers during memcg shrink_slab()
Date: Mon, 09 Jul 2018 11:39:45 +0300	[thread overview]
Message-ID: <153112558507.4097.12713813335683345488.stgit@localhost.localdomain> (raw)
In-Reply-To: <153112469064.4097.2581798353485457328.stgit@localhost.localdomain>

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>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Tested-by: Shakeel Butt <shakeelb@google.com>
---
 mm/vmscan.c |   84 +++++++++++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 75 insertions(+), 9 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index db0970ba340d..d7a5b8566869 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -364,6 +364,21 @@ int prealloc_shrinker(struct shrinker *shrinker)
 	if (!shrinker->nr_deferred)
 		return -ENOMEM;
 
+	/*
+	 * There is a window between prealloc_shrinker()
+	 * and register_shrinker_prepared(). We don't want
+	 * to clear bit of a shrinker in such the state
+	 * in shrink_slab_memcg(), since this will impose
+	 * restrictions on a code registering a shrinker
+	 * (they would have to guarantee, their LRU lists
+	 * are empty till shrinker is completely registered).
+	 * So, we differ the situation, when 1)a shrinker
+	 * is semi-registered (id is assigned, but it has
+	 * not yet linked to shrinker_list) and 2)shrinker
+	 * is not registered (id is not assigned).
+	 */
+	INIT_LIST_HEAD(&shrinker->list);
+
 	if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
 		if (prealloc_memcg_shrinker(shrinker))
 			goto free_deferred;
@@ -543,6 +558,63 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 	return freed;
 }
 
+#ifdef CONFIG_MEMCG_KMEM
+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;
+
+	map = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_map,
+					true);
+	if (unlikely(!map))
+		goto unlock;
+
+	for_each_set_bit(i, map->map, 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 (unlikely(!shrinker)) {
+			clear_bit(i, map->map);
+			continue;
+		}
+
+		/* See comment in prealloc_shrinker() */
+		if (unlikely(list_empty(&shrinker->list)))
+			continue;
+
+		ret = do_shrink_slab(&sc, shrinker, priority);
+		freed += ret;
+
+		if (rwsem_is_contended(&shrinker_rwsem)) {
+			freed = freed ? : 1;
+			break;
+		}
+	}
+unlock:
+	up_read(&shrinker_rwsem);
+	return freed;
+}
+#else /* CONFIG_MEMCG_KMEM */
+static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
+			struct mem_cgroup *memcg, int priority)
+{
+	return 0;
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
 /**
  * shrink_slab - shrink slab caches
  * @gfp_mask: allocation context
@@ -572,8 +644,8 @@ 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 && !mem_cgroup_is_root(memcg))
+		return shrink_slab_memcg(gfp_mask, nid, memcg, priority);
 
 	if (!down_read_trylock(&shrinker_rwsem))
 		goto out;
@@ -585,13 +657,7 @@ 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;
 
 		if (!(shrinker->flags & SHRINKER_NUMA_AWARE))


  parent reply	other threads:[~2018-07-09  8:40 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-07-09  8:37 [PATCH v9 00/17] Improve shrink_slab() scalability (old complexity was O(n^2), new is O(n)) Kirill Tkhai
2018-07-09  8:37 ` [PATCH v9 01/17] list_lru: Combine code under the same define Kirill Tkhai
2018-07-09  8:37 ` [PATCH v9 02/17] mm: Introduce CONFIG_MEMCG_KMEM as combination of CONFIG_MEMCG && !CONFIG_SLOB Kirill Tkhai
2018-07-09  8:37 ` [PATCH v9 03/17] mm: Assign id to every memcg-aware shrinker Kirill Tkhai
2018-07-09  8:37 ` [PATCH v9 04/17] memcg: Move up for_each_mem_cgroup{, _tree} defines Kirill Tkhai
2018-07-09  8:38 ` [PATCH v9 05/17] mm: Assign memcg-aware shrinkers bitmap to memcg Kirill Tkhai
2018-07-09  8:38 ` [PATCH v9 06/17] mm: Refactoring in workingset_init() Kirill Tkhai
2018-07-09  8:38 ` [PATCH v9 07/17] fs: Refactoring in alloc_super() Kirill Tkhai
2018-07-09  8:38 ` [PATCH v9 08/17] From: Kirill Tkhai <ktkhai@virtuozzo.com> Kirill Tkhai
2018-07-09  8:38 ` [PATCH v9 09/17] list_lru: Add memcg argument to list_lru_from_kmem() Kirill Tkhai
2018-07-09  8:39 ` [PATCH v9 10/17] From: Kirill Tkhai <ktkhai@virtuozzo.com> Kirill Tkhai
2018-07-09  8:39 ` [PATCH v9 11/17] list_lru: Pass lru argument to memcg_drain_list_lru_node() Kirill Tkhai
2018-07-09  8:39 ` [PATCH v9 12/17] mm: Export mem_cgroup_is_root() Kirill Tkhai
2018-07-09  8:39 ` [PATCH v9 13/17] mm: Set bit in memcg shrinker bitmap on first list_lru item apearance Kirill Tkhai
2018-07-09  8:39 ` Kirill Tkhai [this message]
2018-07-09  8:39 ` [PATCH v9 15/17] mm: Generalize shrink_slab() calls in shrink_node() Kirill Tkhai
2018-07-09  8:40 ` [PATCH v9 16/17] From: Kirill Tkhai <ktkhai@virtuozzo.com> Kirill Tkhai
2018-07-09  8:40 ` [PATCH v9 17/17] mm: Clear shrinker bit if there are no objects related to memcg Kirill Tkhai
2018-07-09  8:43 ` [PATCH v9 00/17] Improve shrink_slab() scalability (old complexity was O(n^2), new is O(n)) Kirill Tkhai

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=153112558507.4097.12713813335683345488.stgit@localhost.localdomain \
    --to=ktkhai@virtuozzo.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=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=vdavydov.dev@gmail.com \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@infradead.org \
    --cc=ying.huang@intel.com \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.