From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752087AbeC1G55 (ORCPT ); Wed, 28 Mar 2018 02:57:57 -0400 Received: from mout.gmx.net ([212.227.15.19]:51617 "EHLO mout.gmx.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750735AbeC1G5z (ORCPT ); Wed, 28 Mar 2018 02:57:55 -0400 Message-ID: <1522220235.24311.1.camel@gmx.de> Subject: Re: [PATCH v6 2/2] cpuset: Add cpuset.sched_load_balance to v2 From: Mike Galbraith To: Waiman Long , Tejun Heo Cc: Juri Lelli , Li Zefan , Johannes Weiner , Peter Zijlstra , Ingo Molnar , cgroups@vger.kernel.org, linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org, kernel-team@fb.com, pjt@google.com, luto@amacapital.net, torvalds@linux-foundation.org, Roman Gushchin Date: Wed, 28 Mar 2018 08:57:15 +0200 In-Reply-To: References: <1521649309-26690-1-git-send-email-longman@redhat.com> <1521649309-26690-3-git-send-email-longman@redhat.com> <20180322084120.GE7231@localhost.localdomain> <20180323075952.GA4763@localhost.localdomain> <20180326124711.GE5942@localhost.localdomain> <20180327140259.GN1840639@devbig577.frc2.facebook.com> Content-Type: text/plain; charset="ISO-8859-15" X-Mailer: Evolution 3.22.6 Mime-Version: 1.0 Content-Transfer-Encoding: 7bit X-Provags-ID: V03:K0:NXgdVDtOt+x1WrZji20Xh8UPBc9TjfjC2h+YWRv1FhTcCMDmSDl 2AP1/83Vop9T65PumDT+dMwHSgbS8bl8bFhQHg37pOM3SXj5sHjnyfRj3og7dEP1pKhfrTQ o57D1MhoJUS+M+xAa2R8lkMqhMH6FW1+tFSsGxgEzeIDvBi1LY6WHHovHAPVqaP0wcz0rHt NNAV6XTj0moOFicbN35Ag== X-UI-Out-Filterresults: notjunk:1;V01:K0:YCoy1Hwqpv8=:Q8mHzXLTphMuAnm3Stz/an 1YxfCy2on/KaNs4kfvGZknROgu8K5lW22XrhhpsSxJZcR+Dj+Kqq/VzJqQLXN9/jz7yvsOtTK jFnBBMFFdNb3gaLFNSHKeahOkISpCJOBKOOt/YybWXpElCaVoVpbuquDwQ34lyqDtLDN9l9av e75iiTHDXEZLEj6bsrWTqc7l32RowsVMvH7mqKH9mFexjRZhpF73YCXjFtarK3YvegRH77/U+ 52UVh6+00LdaGGLEkvBSp3IypyTyLPHMpeSQ6zXr57IQp0BMXOoDb6d3TyMGoWgAKjtnkzO5C WhRD5EhJTNeW4ZCeCCELhlaY9rms4UeOBo7rkqm8crTCQyr9KZ0mwYoXbVDgWGIRsFZ93LOVA ZSNKIo2pVdrR4k8HIShWUFE8Lw4kMJXo7Tcjj5FWBE4GpBl87FEWsf32GypkxRciZNw2Afzkq TaMm7np+FlGoEoY56YpB3PRBykTiIdfeDtSQt5TzBm2KrxhLn0Fyz6rLdmpvA/nYAL20lqvTg RJly3+S1vfyjkoTHSHDc4WdGwkmXQuh5yJM7LjT377AQQI2OLlWosM6T+XXXwFQOEGFYBrj3v FTDLMqHpMMQNR3rzaNScnE/hZ2RlhKF3WCs7L9SfQajQaoHjNjzobCbrzUryZy0WOaCzwVHA5 /7/qNQQSDpJuzyf4+xfh9o63eO9trgDGBmhFuI3aP7QbHpFJNfUGJWj7UzG7i6lLhF+Ki1QBl amDOObVOpwGsgk4PXZpY/w+Dzs85Wav8q5m2pjxz6XM27mBnxcF8SKVz6jdK63ELqUY6NXCp3 +Ka039Y5RPTZAV9nRHUi52gTJP1QxFyhv28cpX9eLg5ZHtRg6U= Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 2018-03-27 at 10:23 -0400, Waiman Long wrote: > On 03/27/2018 10:02 AM, Tejun Heo wrote: > > Hello, > > > > On Mon, Mar 26, 2018 at 04:28:49PM -0400, Waiman Long wrote: > >> Maybe we can have a different root level flag, say, > >> sched_partition_domain that is equivalent to !sched_load_balnace. > >> However, I am still not sure if we should enforce that no task should be > >> in the root cgroup when the flag is set. > >> > >> Tejun and Peter, what are your thoughts on this? > > I haven't looked into the other issues too much but we for sure cannot > > empty the root cgroup. > > > > Thanks. > > > Now, I have a different idea. How about we add a special root-only knob, > say, "cpuset.cpus.isolated" that contains the list of CPUs that are > still owned by root, but not participated in load balancing. All the > tasks in the root are load-balanced among the remaining CPUs. > > A child can then be created that hold some or all the CPUs in the > isolated set. It will then have a separate root domain if load balancing > is on, or an isolated cpuset if load balancing is off. > > Will that idea work? Hrm. Sounds very much like the typical v1 setup today.. root /\ peons vips ...with v2 root effectively shrinking to become the v1 "peons" set *rd/sd/sd_llc wise only* when you poke /cpuset.cpus.isolated, but still actually spanning all CPUs. True? If so, a user would also still have to create a real "peons" subset as in v1 and migrate everything not nailed to the floor into it for containment, else any task can be placed or place itself anywhere in the box, or merely wake to find itself sitting on it's previous, but now vip turf CPU. -Mike