From: Vladimir Davydov <vdavydov.dev@gmail.com>
To: Roman Gushchin <guro@fb.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
kernel-team@fb.com, Johannes Weiner <hannes@cmpxchg.org>,
Shakeel Butt <shakeelb@google.com>,
Waiman Long <longman@redhat.com>
Subject: Re: [PATCH v6 08/10] mm: rework non-root kmem_cache lifecycle management
Date: Sun, 9 Jun 2019 20:09:04 +0300 [thread overview]
Message-ID: <20190609170904.nxa2rb6inkvx3geg@esperanza> (raw)
In-Reply-To: <20190605024454.1393507-9-guro@fb.com>
On Tue, Jun 04, 2019 at 07:44:52PM -0700, Roman Gushchin wrote:
> Currently each charged slab page holds a reference to the cgroup to
> which it's charged. Kmem_caches are held by the memcg and are released
> all together with the memory cgroup. It means that none of kmem_caches
> are released unless at least one reference to the memcg exists, which
> is very far from optimal.
>
> Let's rework it in a way that allows releasing individual kmem_caches
> as soon as the cgroup is offline, the kmem_cache is empty and there
> are no pending allocations.
>
> To make it possible, let's introduce a new percpu refcounter for
> non-root kmem caches. The counter is initialized to the percpu mode,
> and is switched to the atomic mode during kmem_cache deactivation. The
> counter is bumped for every charged page and also for every running
> allocation. So the kmem_cache can't be released unless all allocations
> complete.
>
> To shutdown non-active empty kmem_caches, let's reuse the work queue,
> previously used for the kmem_cache deactivation. Once the reference
> counter reaches 0, let's schedule an asynchronous kmem_cache release.
>
> * I used the following simple approach to test the performance
> (stolen from another patchset by T. Harding):
>
> time find / -name fname-no-exist
> echo 2 > /proc/sys/vm/drop_caches
> repeat 10 times
>
> Results:
>
> orig patched
>
> real 0m1.455s real 0m1.355s
> user 0m0.206s user 0m0.219s
> sys 0m0.855s sys 0m0.807s
>
> real 0m1.487s real 0m1.699s
> user 0m0.221s user 0m0.256s
> sys 0m0.806s sys 0m0.948s
>
> real 0m1.515s real 0m1.505s
> user 0m0.183s user 0m0.215s
> sys 0m0.876s sys 0m0.858s
>
> real 0m1.291s real 0m1.380s
> user 0m0.193s user 0m0.198s
> sys 0m0.843s sys 0m0.786s
>
> real 0m1.364s real 0m1.374s
> user 0m0.180s user 0m0.182s
> sys 0m0.868s sys 0m0.806s
>
> real 0m1.352s real 0m1.312s
> user 0m0.201s user 0m0.212s
> sys 0m0.820s sys 0m0.761s
>
> real 0m1.302s real 0m1.349s
> user 0m0.205s user 0m0.203s
> sys 0m0.803s sys 0m0.792s
>
> real 0m1.334s real 0m1.301s
> user 0m0.194s user 0m0.201s
> sys 0m0.806s sys 0m0.779s
>
> real 0m1.426s real 0m1.434s
> user 0m0.216s user 0m0.181s
> sys 0m0.824s sys 0m0.864s
>
> real 0m1.350s real 0m1.295s
> user 0m0.200s user 0m0.190s
> sys 0m0.842s sys 0m0.811s
>
> So it looks like the difference is not noticeable in this test.
>
> Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
next prev parent reply other threads:[~2019-06-09 17:09 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-05 2:44 [PATCH v6 00/10] mm: reparent slab memory on cgroup removal Roman Gushchin
2019-06-05 2:44 ` [PATCH v6 01/10] mm: add missing smp read barrier on getting memcg kmem_cache pointer Roman Gushchin
2019-06-05 4:35 ` Shakeel Butt
2019-06-05 17:14 ` Roman Gushchin
2019-06-05 19:51 ` Shakeel Butt
2019-06-05 16:42 ` Johannes Weiner
2019-06-09 12:10 ` Vladimir Davydov
2019-06-10 20:33 ` Johannes Weiner
2019-06-10 20:38 ` Roman Gushchin
2019-06-05 2:44 ` [PATCH v6 02/10] mm: postpone kmem_cache memcg pointer initialization to memcg_link_cache() Roman Gushchin
2019-06-05 2:44 ` [PATCH v6 03/10] mm: rename slab delayed deactivation functions and fields Roman Gushchin
2019-06-09 12:13 ` Vladimir Davydov
2019-06-05 2:44 ` [PATCH v6 04/10] mm: generalize postponed non-root kmem_cache deactivation Roman Gushchin
2019-06-09 12:23 ` Vladimir Davydov
2019-06-05 2:44 ` [PATCH v6 05/10] mm: introduce __memcg_kmem_uncharge_memcg() Roman Gushchin
2019-06-09 12:29 ` Vladimir Davydov
2019-06-05 2:44 ` [PATCH v6 06/10] mm: unify SLAB and SLUB page accounting Roman Gushchin
2019-06-05 2:44 ` [PATCH v6 07/10] mm: synchronize access to kmem_cache dying flag using a spinlock Roman Gushchin
2019-06-05 16:56 ` Johannes Weiner
2019-06-05 22:02 ` Roman Gushchin
2019-06-06 0:48 ` Roman Gushchin
2019-06-09 14:31 ` Vladimir Davydov
2019-06-10 20:46 ` Roman Gushchin
2019-06-05 2:44 ` [PATCH v6 08/10] mm: rework non-root kmem_cache lifecycle management Roman Gushchin
2019-06-09 17:09 ` Vladimir Davydov [this message]
2019-06-05 2:44 ` [PATCH v6 09/10] mm: stop setting page->mem_cgroup pointer for slab pages Roman Gushchin
2019-06-09 17:09 ` Vladimir Davydov
2019-06-05 2:44 ` [PATCH v6 10/10] mm: reparent slab memory on cgroup removal Roman Gushchin
2019-06-09 17:18 ` Vladimir Davydov
2019-06-05 4:14 ` [PATCH v6 00/10] " Andrew Morton
2019-06-05 20:45 ` Roman Gushchin
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=20190609170904.nxa2rb6inkvx3geg@esperanza \
--to=vdavydov.dev@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=guro@fb.com \
--cc=hannes@cmpxchg.org \
--cc=kernel-team@fb.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=longman@redhat.com \
--cc=shakeelb@google.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox