From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: ARC-Seal: i=1; a=rsa-sha256; t=1526803206; cv=none; d=google.com; s=arc-20160816; b=i2MdUmVOe/SDncQoUV2rCl5K7MmIXSpLwUQUUmY8kjlieMw5uscTRx/lUJ+w3vhGbc nW/8+lKh2wxUPvlt9elNLTdxu8luZ+Y5tO2aHcqYKlsLCcZvNco4eQlPj3FkgFzEyA4A yyWNFdCJcVnP728iMiYPr7TEkHTGPk+25xL3m2oMk8s+mT8KGFVjNF7S8TU6xuvEmXD3 t900TvULBW8a32F5dkSddY3wMaelv8RugMT9sQp/lFeqTjabCZDevObck/8ay1aytvhu FRjZLMJJRNPbj+Xog5LKlC/4U3OXyVZNrYXxQYjN1NV/Y6pYVQqfkDXLh229eBnUyyyV MmPQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=in-reply-to:content-disposition:mime-version:references:message-id :subject:cc:to:from:date:dkim-signature:arc-authentication-results; bh=/AmKnO0W30rn1AiOxhXXC0Kq9Ocg80nYMSpjrPGywmM=; b=WvfZhzIkuymD5a4wf1IueZu1IV6Ne4T9XRZYissty3ojZO3DAGEfYq3K4p9kcFr4IS 7sfIDvZB/+5ZOzHsrMMtvuULZ5fgCV5m49r0MRr+s9YqvPSasLL62ZKtHRZ7LheAuVd0 Q2jv4Arc43KluaL4lZGhBfqbQ6pjjF29k+7QgwqArpKtgPlz/IIfrjpMhbRPSn56uZsj PEjMRge7T+zpNpGkMK7Oo4qGJJ8Ks2G6I7+LTUgriBtu1BQm7lAwwMHx8r2cABH7KVHF OrGecAriERX7l2H5NtGomjinm+zB5o/WHAZdS0XBphuj5o3n3rRQ8cqCs0IY5OOuJ6/8 ovWg== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@gmail.com header.s=20161025 header.b=B/f+IV3J; spf=pass (google.com: domain of vdavydov.dev@gmail.com designates 209.85.220.65 as permitted sender) smtp.mailfrom=vdavydov.dev@gmail.com; dmarc=pass (p=NONE sp=QUARANTINE dis=NONE) header.from=gmail.com Authentication-Results: mx.google.com; dkim=pass header.i=@gmail.com header.s=20161025 header.b=B/f+IV3J; spf=pass (google.com: domain of vdavydov.dev@gmail.com designates 209.85.220.65 as permitted sender) smtp.mailfrom=vdavydov.dev@gmail.com; dmarc=pass (p=NONE sp=QUARANTINE dis=NONE) header.from=gmail.com X-Google-Smtp-Source: AB8JxZrIlhztZpTVTk+jk2XG1vMp/o07+x+gmLe/hB+DuJsC0yrNULTXZHrPiMQWCAcQbxo673CfIA== Date: Sun, 20 May 2018 11:00:03 +0300 From: Vladimir Davydov To: Kirill Tkhai 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 v6 14/17] mm: Iterate only over charged shrinkers during memcg shrink_slab() Message-ID: <20180520080003.gfygtb6rloqpjaol@esperanza> References: <152663268383.5308.8660992135988724014.stgit@localhost.localdomain> <152663304128.5308.12840831728812876902.stgit@localhost.localdomain> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <152663304128.5308.12840831728812876902.stgit@localhost.localdomain> X-getmail-retrieved-from-mailbox: INBOX X-GMAIL-THRID: =?utf-8?q?1600790777328718772?= X-GMAIL-MSGID: =?utf-8?q?1600969199326873575?= X-Mailing-List: linux-kernel@vger.kernel.org List-ID: On Fri, May 18, 2018 at 11:44:01AM +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 > --- > mm/vmscan.c | 87 +++++++++++++++++++++++++++++++++++++++++++++++++++++------ > 1 file changed, 78 insertions(+), 9 deletions(-) > > diff --git a/mm/vmscan.c b/mm/vmscan.c > index f09ea20d7270..2fbf3b476601 100644 > --- a/mm/vmscan.c > +++ b/mm/vmscan.c > @@ -373,6 +373,20 @@ int prealloc_shrinker(struct shrinker *shrinker) > goto free_deferred; > } > > + /* > + * 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); > return 0; > > free_deferred: > @@ -544,6 +558,67 @@ 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; > + > + /* > + * 1) Caller passes only alive memcg, so map can't be NULL. > + * 2) shrinker_rwsem protects from maps expanding. > + */ > + map = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_map, > + 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 (unlikely(!shrinker)) { Nit: I don't think 'unlikely' is required here as this is definitely not a hot path. > + clear_bit(i, map->map); > + continue; > + } > + BUG_ON(!(shrinker->flags & SHRINKER_MEMCG_AWARE)); > + > + /* See comment in prealloc_shrinker() */ > + if (unlikely(list_empty(&shrinker->list))) Ditto. > + 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; > +} > +#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 > @@ -573,8 +648,8 @@ 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; > @@ -586,13 +661,7 @@ 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)) >