LKML Archive on lore.kernel.org
 help / color / 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 17/17] mm: Clear shrinker bit if there are no objects related to memcg
Date: Mon, 09 Jul 2018 11:40:17 +0300
Message-ID: <153112561772.4097.11011071937553113003.stgit@localhost.localdomain> (raw)
In-Reply-To: <153112469064.4097.2581798353485457328.stgit@localhost.localdomain>

To avoid further unneed calls of do_shrink_slab()
for shrinkers, which already do not have any charged
objects in a memcg, their bits have to be cleared.

This patch introduces a lockless mechanism to do that
without races without parallel list lru add. After
do_shrink_slab() returns SHRINK_EMPTY the first time,
we clear the bit and call it once again. Then we restore
the bit, if the new return value is different.

Note, that single smp_mb__after_atomic() in shrink_slab_memcg()
covers two situations:

1)list_lru_add()     shrink_slab_memcg
    list_add_tail()    for_each_set_bit() <--- read bit
                         do_shrink_slab() <--- missed list update (no barrier)
    <MB>                 <MB>
    set_bit()            do_shrink_slab() <--- seen list update

This situation, when the first do_shrink_slab() sees set bit,
but it doesn't see list update (i.e., race with the first element
queueing), is rare. So we don't add <MB> before the first call
of do_shrink_slab() instead of this to do not slow down generic
case. Also, it's need the second call as seen in below in (2).

2)list_lru_add()      shrink_slab_memcg()
    list_add_tail()     ...
    set_bit()           ...
  ...                   for_each_set_bit()
  do_shrink_slab()        do_shrink_slab()
    clear_bit()           ...
  ...                     ...
  list_lru_add()          ...
    list_add_tail()       clear_bit()
    <MB>                  <MB>
    set_bit()             do_shrink_slab()

The barriers guarantees, the second do_shrink_slab()
in the right side task sees list update if really
cleared the bit. This case is drawn in the code comment.

[Results/performance of the patchset]

After the whole patchset applied the below test shows signify
increase of performance:

$echo 1 > /sys/fs/cgroup/memory/memory.use_hierarchy
$mkdir /sys/fs/cgroup/memory/ct
$echo 4000M > /sys/fs/cgroup/memory/ct/memory.kmem.limit_in_bytes
    $for i in `seq 0 4000`; do mkdir /sys/fs/cgroup/memory/ct/$i;
			    echo $$ > /sys/fs/cgroup/memory/ct/$i/cgroup.procs;
			    mkdir -p s/$i; mount -t tmpfs $i s/$i;
			    touch s/$i/file; done

Then, 5 sequential calls of drop caches:
$time echo 3 > /proc/sys/vm/drop_caches

1)Before:
0.00user 13.78system 0:13.78elapsed 99%CPU
0.00user 5.59system 0:05.60elapsed 99%CPU
0.00user 5.48system 0:05.48elapsed 99%CPU
0.00user 8.35system 0:08.35elapsed 99%CPU
0.00user 8.34system 0:08.35elapsed 99%CPU

2)After
0.00user 1.10system 0:01.10elapsed 99%CPU
0.00user 0.00system 0:00.01elapsed 64%CPU
0.00user 0.01system 0:00.01elapsed 82%CPU
0.00user 0.00system 0:00.01elapsed 64%CPU
0.00user 0.01system 0:00.01elapsed 82%CPU

The results show the performance increases at least in 548 times.

Shakeel Butt tested this patchset with fork-bomb on his configuration:

 > I created 255 memcgs, 255 ext4 mounts and made each memcg create a
 > file containing few KiBs on corresponding mount. Then in a separate
 > memcg of 200 MiB limit ran a fork-bomb.
 >
 > I ran the "perf record -ag -- sleep 60" and below are the results:
 >
 > Without the patch series:
 > Samples: 4M of event 'cycles', Event count (approx.): 3279403076005
 > +  36.40%            fb.sh  [kernel.kallsyms]    [k] shrink_slab
 > +  18.97%            fb.sh  [kernel.kallsyms]    [k] list_lru_count_one
 > +   6.75%            fb.sh  [kernel.kallsyms]    [k] super_cache_count
 > +   0.49%            fb.sh  [kernel.kallsyms]    [k] down_read_trylock
 > +   0.44%            fb.sh  [kernel.kallsyms]    [k] mem_cgroup_iter
 > +   0.27%            fb.sh  [kernel.kallsyms]    [k] up_read
 > +   0.21%            fb.sh  [kernel.kallsyms]    [k] osq_lock
 > +   0.13%            fb.sh  [kernel.kallsyms]    [k] shmem_unused_huge_count
 > +   0.08%            fb.sh  [kernel.kallsyms]    [k] shrink_node_memcg
 > +   0.08%            fb.sh  [kernel.kallsyms]    [k] shrink_node
 >
 > With the patch series:
 > Samples: 4M of event 'cycles', Event count (approx.): 2756866824946
 > +  47.49%            fb.sh  [kernel.kallsyms]    [k] down_read_trylock
 > +  30.72%            fb.sh  [kernel.kallsyms]    [k] up_read
 > +   9.51%            fb.sh  [kernel.kallsyms]    [k] mem_cgroup_iter
 > +   1.69%            fb.sh  [kernel.kallsyms]    [k] shrink_node_memcg
 > +   1.35%            fb.sh  [kernel.kallsyms]    [k] mem_cgroup_protected
 > +   1.05%            fb.sh  [kernel.kallsyms]    [k] queued_spin_lock_slowpath
 > +   0.85%            fb.sh  [kernel.kallsyms]    [k] _raw_spin_lock
 > +   0.78%            fb.sh  [kernel.kallsyms]    [k] lruvec_lru_size
 > +   0.57%            fb.sh  [kernel.kallsyms]    [k] shrink_node
 > +   0.54%            fb.sh  [kernel.kallsyms]    [k] queue_work_on
 > +   0.46%            fb.sh  [kernel.kallsyms]    [k] shrink_slab_memcg

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Tested-by: Shakeel Butt <shakeelb@google.com>
---
 mm/memcontrol.c |    2 ++
 mm/vmscan.c     |   26 ++++++++++++++++++++++++--
 2 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 70881f04775d..bd1e3823236f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -430,6 +430,8 @@ void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id)
 
 		rcu_read_lock();
 		map = rcu_dereference(memcg->nodeinfo[nid]->shrinker_map);
+		/* Pairs with smp mb in shrink_slab() */
+		smp_mb__before_atomic();
 		set_bit(shrinker_id, map->map);
 		rcu_read_unlock();
 	}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8199e1b9a204..93fdd0375b64 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -596,8 +596,30 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
 			continue;
 
 		ret = do_shrink_slab(&sc, shrinker, priority);
-		if (ret == SHRINK_EMPTY)
-			ret = 0;
+		if (ret == SHRINK_EMPTY) {
+			clear_bit(i, map->map);
+			/*
+			 * After the shrinker reported that it had no objects to
+			 * free, but before we cleared the corresponding bit in
+			 * the memcg shrinker map, a new object might have been
+			 * added. To make sure, we have the bit set in this
+			 * case, we invoke the shrinker one more time and reset
+			 * the bit if it reports that it is not empty anymore.
+			 * The memory barrier here pairs with the barrier in
+			 * memcg_set_shrinker_bit():
+			 *
+			 * list_lru_add()     shrink_slab_memcg()
+			 *   list_add_tail()    clear_bit()
+			 *   <MB>               <MB>
+			 *   set_bit()          do_shrink_slab()
+			 */
+			smp_mb__after_atomic();
+			ret = do_shrink_slab(&sc, shrinker, priority);
+			if (ret == SHRINK_EMPTY)
+				ret = 0;
+			else
+				memcg_set_shrinker_bit(memcg, nid, i);
+		}
 		freed += ret;
 
 		if (rwsem_is_contended(&shrinker_rwsem)) {


  parent reply index

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 ` [PATCH v9 14/17] mm: Iterate only over charged shrinkers during memcg shrink_slab() Kirill Tkhai
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 ` Kirill Tkhai [this message]
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=153112561772.4097.11011071937553113003.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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git
	git clone --mirror https://lore.kernel.org/lkml/10 lkml/git/10.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git