From: Michal Hocko Subject: Re: [PATCH v2 0/5] Introduce memcg_stock_pcp remote draining Date: Fri, 27 Jan 2023 10:23:28 +0100 Message-ID: References: <20230125073502.743446-1-leobras@redhat.com> <9e61ab53e1419a144f774b95230b789244895424.camel@redhat.com> <52a0f1e593b1ec0ca7e417ba37680d65df22de82.camel@redhat.com> <601fc35a8cc2167e53e45c636fccb2d899fd7c50.camel@redhat.com> Mime-Version: 1.0 Content-Transfer-Encoding: quoted-printable Return-path: DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=suse.com; s=susede1; t=1674811409; h=from:from:reply-to:date:date:message-id:message-id:to:to:cc:cc: mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=2xvZjQHSmlkJ++xydcKZz/+IOLXbzOFKz6MRvf+IGoQ=; b=QYrMxh5iF8tEZkkIFQiaE0AmzYlUt1+vYWDsddn9lZSskr2jXsldh5NvFZbS6xqZHH9a8d uZwo40l3QwPpd4O9Ws+Lgz2Ss0yY/Rd4JXSO7AA1yqFZGpnGEFRWK8pc9UK4jbMEbt8qmu hNG0Yiin9IUP1Enty4F5i+/fAEiPJ2Y= Content-Disposition: inline In-Reply-To: <601fc35a8cc2167e53e45c636fccb2d899fd7c50.camel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> List-ID: Content-Type: text/plain; charset="iso-8859-1" To: Leonardo =?iso-8859-1?Q?Br=E1s?= Cc: Roman Gushchin , Marcelo Tosatti , Johannes Weiner , Shakeel Butt , Muchun Song , Andrew Morton , cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Frederic Weisbecker On Fri 27-01-23 05:12:13, Leonardo Br=E1s wrote: > On Fri, 2023-01-27 at 04:22 -0300, Leonardo Br=E1s wrote: > > On Fri, 2023-01-27 at 08:11 +0100, Michal Hocko wrote: > > > [Cc Frederic] > > >=20 > > > On Thu 26-01-23 15:12:35, Roman Gushchin wrote: > > > > On Thu, Jan 26, 2023 at 08:41:34AM +0100, Michal Hocko wrote: > > > [...] > > > > > > Essentially each cpu will try to grab the remains of the memory= quota > > > > > > and move it locally. I wonder in such circumstances if we need = to disable the pcp-caching > > > > > > on per-cgroup basis. > > > > >=20 > > > > > I think it would be more than sufficient to disable pcp charging = on an > > > > > isolated cpu. > > > >=20 > > > > It might have significant performance consequences. > > >=20 > > > Is it really significant? > > >=20 > > > > I'd rather opt out of stock draining for isolated cpus: it might sl= ightly reduce > > > > the accuracy of memory limits and slightly increase the memory foot= print (all > > > > those dying memcgs...), but the impact will be limited. Actually it= is limited > > > > by the number of cpus. > > >=20 > > > Hmm, OK, I have misunderstood your proposal. Yes, the overal pcp char= ges > > > potentially left behind should be small and that shouldn't really be a > > > concern for memcg oom situations (unless the limit is very small and > > > workloads on isolated cpus using small hard limits is way beyond my > > > imagination). > > >=20 > > > My first thought was that those charges could be left behind without = any > > > upper bound but in reality sooner or later something should be running > > > on those cpus and if the memcg is gone the pcp cache would get refill= ed > > > and old charges gone. > > >=20 > > > So yes, this is actually a better and even simpler solution. All we n= eed > > > is something like this > > > diff --git a/mm/memcontrol.c b/mm/memcontrol.c > > > index ab457f0394ab..13b84bbd70ba 100644 > > > --- a/mm/memcontrol.c > > > +++ b/mm/memcontrol.c > > > @@ -2344,6 +2344,9 @@ static void drain_all_stock(struct mem_cgroup *= root_memcg) > > > struct mem_cgroup *memcg; > > > bool flush =3D false; > > > =20 > > > + if (cpu_is_isolated(cpu)) > > > + continue; > > > + > > > rcu_read_lock(); > > > memcg =3D stock->cached; > > > if (memcg && stock->nr_pages && > > >=20 > > > There is no such cpu_is_isolated() AFAICS so we would need a help from > > > NOHZ and cpuisol people to create one for us. Frederic, would such an > > > abstraction make any sense from your POV? > >=20 > >=20 > > IIUC, 'if (cpu_is_isolated())' would be instead: > >=20 > > if (!housekeeping_cpu(smp_processor_id(), HK_TYPE_DOMAIN) || > > !housekeeping_cpu(smp_processor_id(), HK_TYPE_WQ) >=20 > oh, sorry 's/smp_processor_id()/cpu/' here: >=20 > if(!housekeeping_cpu(cpu, HK_TYPE_DOMAIN) || !housekeeping_cpu(cpu, HK_TY= PE_WQ)) Or maybe we can get a nice abstract API so that we do not have to really care about those low level details. I do not really know what those really mean and hopefully I shouldn't really need to know. --=20 Michal Hocko SUSE Labs