Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Roman Gushchin <guro@fb.com>
To:     Greg Thelen <gthelen@google.com>
CC:     Andrew Morton <akpm@linux-foundation.org>,
        Johannes Weiner <hannes@cmpxchg.org>,
        Michal Hocko <mhocko@kernel.org>,
        Vladimir Davydov <vdavydov.dev@gmail.com>,
        Tejun Heo <tj@kernel.org>,
        "linux-mm@kvack.org" <linux-mm@kvack.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] writeback: sum memcg dirty counters as needed
Thread-Topic: [PATCH] writeback: sum memcg dirty counters as needed
Thread-Index: AQHU1Qb/Wv6KWk71Ak24H1OecVDKlaYYDFmA
Date:   Fri, 22 Mar 2019 18:15:20 +0000
Message-ID: <20190322181517.GA12378@tower.DHCP.thefacebook.com>
References: <20190307165632.35810-1-gthelen@google.com>
In-Reply-To: <20190307165632.35810-1-gthelen@google.com>
Accept-Language: en-US
Content-Language: en-US
x-ms-exchange-messagesentrepresentingtype: 1
x-originating-ip: [2620:10d:c090:200::1:d234]
x-ms-publictraffictype: Email
x-ms-office365-filtering-correlation-id: 80e70a92-90be-4304-4006-08d6aef25831
x-microsoft-antispam: BCL:0;PCL:0;RULEID:(2390118)(7020095)(4652040)(8989299)(5600127)(711020)(4605104)(4534185)(4627221)(201703031133081)(201702281549075)(8990200)(2017052603328)(7153060)(7193020);SRVR:BYAPR15MB3080;
x-ms-traffictypediagnostic: BYAPR15MB3080:
x-microsoft-antispam-prvs: <BYAPR15MB3080FA634CE1B4393FE41544BE430@BYAPR15MB3080.namprd15.prod.outlook.com>
x-forefront-prvs: 09840A4839
x-forefront-antispam-report: SFV:NSPM;SFS:(10019020)(346002)(376002)(136003)(396003)(39860400002)(366004)(189003)(199004)(99286004)(5660300002)(186003)(53936002)(68736007)(81166006)(256004)(1076003)(2906002)(229853002)(8936002)(54906003)(105586002)(86362001)(14444005)(106356001)(81156014)(4326008)(8676002)(52116002)(76176011)(14454004)(71200400001)(9686003)(305945005)(486006)(6512007)(316002)(71190400001)(6506007)(386003)(6116002)(97736004)(6916009)(6436002)(7736002)(46003)(6246003)(478600001)(476003)(33656002)(446003)(25786009)(6486002)(102836004)(11346002)(14143004);DIR:OUT;SFP:1102;SCL:1;SRVR:BYAPR15MB3080;H:BYAPR15MB2631.namprd15.prod.outlook.com;FPR:;SPF:None;LANG:en;PTR:InfoNoRecords;MX:1;A:1;
received-spf: None (protection.outlook.com: fb.com does not designate
 permitted sender hosts)
x-ms-exchange-senderadcheck: 1
x-microsoft-antispam-message-info: lqB4ST1t53ncLK3SaDVdUH4PvsU0qrsP6jfI5Hl9zjk0ztU/2Q2ZXIEbwTgGP50uj/W1TWuSinF82NgBnCsMLo0skGbJXzIoWOad8TEpwcjwDAjsVnEOWGimn7guBhmqU9Cg0miLGqvIqEL0hfyMJbSMArPAoFqUBQFYhwzKxMiL7vnwp/qpvkqIA+f4MrxJTHSBCYCdvG0RPjYafPvtmUWGExe6dyMWsLRRcBIlNIId6xiv3iIY4vSQqZL1eVn7RdfjKhPxR/v2G3CrnWCsRuSqmXvCvy/b6aScGVD9mr6BJgoVM8pu/gbSMY+qJR2IcziYrrKelGFcZwauyZO2GZOWrwjbr+MMC7wYt/5sQ+m0hk6n6JDGpTeRYdDpa6zv1G25FpSI5FPWZC11VdL2XRXVCGHMuugCQU+FgQEz7kY=
Content-Type: text/plain; charset="us-ascii"
Content-ID: <D5E78308D7D15849AB79E1E40C462DEF@namprd15.prod.outlook.com>
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-Network-Message-Id: 80e70a92-90be-4304-4006-08d6aef25831
X-MS-Exchange-CrossTenant-originalarrivaltime: 22 Mar 2019 18:15:20.8307
 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: 8ae927fe-1255-47a7-a2af-5f3a069daaa2
X-MS-Exchange-CrossTenant-mailboxtype: HOSTED
X-MS-Exchange-Transport-CrossTenantHeadersStamped: BYAPR15MB3080
X-OriginatorOrg: fb.com
X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:,, definitions=2019-03-22_10:,,
 signatures=0
X-Proofpoint-Spam-Reason: safe
X-FB-Internal: Safe
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Thu, Mar 07, 2019 at 08:56:32AM -0800, Greg Thelen wrote:
> Since commit a983b5ebee57 ("mm: memcontrol: fix excessive complexity in
> memory.stat reporting") memcg dirty and writeback counters are managed
> as:
> 1) per-memcg per-cpu values in range of [-32..32]
> 2) per-memcg atomic counter
> When a per-cpu counter cannot fit in [-32..32] it's flushed to the
> atomic.  Stat readers only check the atomic.
> Thus readers such as balance_dirty_pages() may see a nontrivial error
> margin: 32 pages per cpu.
> Assuming 100 cpus:
>    4k x86 page_size:  13 MiB error per memcg
>   64k ppc page_size: 200 MiB error per memcg
> Considering that dirty+writeback are used together for some decisions
> the errors double.
>=20
> This inaccuracy can lead to undeserved oom kills.  One nasty case is
> when all per-cpu counters hold positive values offsetting an atomic
> negative value (i.e. per_cpu[*]=3D32, atomic=3Dn_cpu*-32).
> balance_dirty_pages() only consults the atomic and does not consider
> throttling the next n_cpu*32 dirty pages.  If the file_lru is in the
> 13..200 MiB range then there's absolutely no dirty throttling, which
> burdens vmscan with only dirty+writeback pages thus resorting to oom
> kill.
>=20
> It could be argued that tiny containers are not supported, but it's more
> subtle.  It's the amount the space available for file lru that matters.
> If a container has memory.max-200MiB of non reclaimable memory, then it
> will also suffer such oom kills on a 100 cpu machine.
>=20
> The following test reliably ooms without this patch.  This patch avoids
> oom kills.
>
> ...
>=20
> Make balance_dirty_pages() and wb_over_bg_thresh() work harder to
> collect exact per memcg counters when a memcg is close to the
> throttling/writeback threshold.  This avoids the aforementioned oom
> kills.
>=20
> This does not affect the overhead of memory.stat, which still reads the
> single atomic counter.
>=20
> Why not use percpu_counter?  memcg already handles cpus going offline,
> so no need for that overhead from percpu_counter.  And the
> percpu_counter spinlocks are more heavyweight than is required.
>=20
> It probably also makes sense to include exact dirty and writeback
> counters in memcg oom reports.  But that is saved for later.
>=20
> Signed-off-by: Greg Thelen <gthelen@google.com>
> ---
>  include/linux/memcontrol.h | 33 +++++++++++++++++++++++++--------
>  mm/memcontrol.c            | 26 ++++++++++++++++++++------
>  mm/page-writeback.c        | 27 +++++++++++++++++++++------
>  3 files changed, 66 insertions(+), 20 deletions(-)
>=20
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 83ae11cbd12c..6a133c90138c 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -573,6 +573,22 @@ static inline unsigned long memcg_page_state(struct =
mem_cgroup *memcg,
>  	return x;
>  }

Hi Greg!

Thank you for the patch, definitely a good problem to be fixed!

> =20
> +/* idx can be of type enum memcg_stat_item or node_stat_item */
> +static inline unsigned long
> +memcg_exact_page_state(struct mem_cgroup *memcg, int idx)
> +{
> +	long x =3D atomic_long_read(&memcg->stat[idx]);
> +#ifdef CONFIG_SMP

I doubt that this #ifdef is correct without corresponding changes
in __mod_memcg_state(). As now, we do use per-cpu buffer which spills
to an atomic value event if !CONFIG_SMP. It's probably something
that we want to change, but as now, #ifdef CONFIG_SMP should protect
only "if (x < 0)" part.


> +	int cpu;
> +
> +	for_each_online_cpu(cpu)
> +		x +=3D per_cpu_ptr(memcg->stat_cpu, cpu)->count[idx];
> +	if (x < 0)
> +		x =3D 0;
> +#endif
> +	return x;
> +}

Also, isn't it worth it to generalize memcg_page_state() instead?
By adding an bool exact argument? I believe dirty balance is not
the only place, where we need a better accuracy.

Thanks!