All of lore.kernel.org
 help / color / mirror / Atom feed
From: Tejun Heo <tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
To: Mathieu Desnoyers
	<mathieu.desnoyers-vg+e7yoeK/dWk0Htik3J/w@public.gmane.org>
Cc: Li Zefan <lizefan-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>,
	cgroups <cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
	linux-kernel
	<linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
	Peter Zijlstra <peterz-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>,
	Ingo Molnar <mingo-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
	Valentin Schneider
	<valentin.schneider-5wv7dgnIgG8@public.gmane.org>,
	Thomas Gleixner <tglx-hfZtesqFncYOwBW4kG4KsQ@public.gmane.org>
Subject: Re: [regression] cpuset: offlined CPUs removed from affinity masks
Date: Wed, 19 Feb 2020 11:12:22 -0500	[thread overview]
Message-ID: <20200219161222.GF698990@mtj.thefacebook.com> (raw)
In-Reply-To: <1358308409.804.1582128519523.JavaMail.zimbra-vg+e7yoeK/dWk0Htik3J/w@public.gmane.org>

On Wed, Feb 19, 2020 at 11:08:39AM -0500, Mathieu Desnoyers wrote:
> I wonder if applying the online cpu masks to the per-thread affinity mask
> is the correct approach ? I suspect what we may be looking for here is to keep

Oh, the whole thing is wrong.

> the affinity mask independent of cpu hotplug, and look-up both the per-thread
> affinity mask and the online cpu mask whenever the scheduler needs to perform
> "is_cpu_allowed()" to check task placement.

Yes, that's what it should have done from the get-go. The way it's
implemented now, maybe we can avoid some specific cases like cpuset
not being used at all but it'll constantly get in the way if you're
expecting thread affinity to retain its value across offlines.

-- 
tejun

WARNING: multiple messages have this Message-ID (diff)
From: Tejun Heo <tj@kernel.org>
To: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Li Zefan <lizefan@huawei.com>, cgroups <cgroups@vger.kernel.org>,
	linux-kernel <linux-kernel@vger.kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@kernel.org>,
	Valentin Schneider <valentin.schneider@arm.com>,
	Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [regression] cpuset: offlined CPUs removed from affinity masks
Date: Wed, 19 Feb 2020 11:12:22 -0500	[thread overview]
Message-ID: <20200219161222.GF698990@mtj.thefacebook.com> (raw)
In-Reply-To: <1358308409.804.1582128519523.JavaMail.zimbra@efficios.com>

On Wed, Feb 19, 2020 at 11:08:39AM -0500, Mathieu Desnoyers wrote:
> I wonder if applying the online cpu masks to the per-thread affinity mask
> is the correct approach ? I suspect what we may be looking for here is to keep

Oh, the whole thing is wrong.

> the affinity mask independent of cpu hotplug, and look-up both the per-thread
> affinity mask and the online cpu mask whenever the scheduler needs to perform
> "is_cpu_allowed()" to check task placement.

Yes, that's what it should have done from the get-go. The way it's
implemented now, maybe we can avoid some specific cases like cpuset
not being used at all but it'll constantly get in the way if you're
expecting thread affinity to retain its value across offlines.

-- 
tejun

  parent reply	other threads:[~2020-02-19 16:12 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-01-16 17:41 [regression] cpuset: offlined CPUs removed from affinity masks Mathieu Desnoyers
2020-01-16 18:27 ` Valentin Schneider
     [not found] ` <1251528473.590671.1579196495905.JavaMail.zimbra-vg+e7yoeK/dWk0Htik3J/w@public.gmane.org>
2020-02-17 16:03   ` Mathieu Desnoyers
2020-02-17 16:03     ` Mathieu Desnoyers
2020-02-19 15:19     ` Tejun Heo
     [not found]       ` <20200219151922.GB698990-146+VewaZzwNjtGbbfXrCEEOCMrvLtNR@public.gmane.org>
2020-02-19 15:43         ` Mathieu Desnoyers
2020-02-19 15:43           ` Mathieu Desnoyers
2020-02-19 15:47           ` Tejun Heo
     [not found]             ` <20200219154740.GD698990-146+VewaZzwNjtGbbfXrCEEOCMrvLtNR@public.gmane.org>
2020-02-19 15:50               ` Mathieu Desnoyers
2020-02-19 15:50                 ` Mathieu Desnoyers
2020-02-19 15:52                 ` Tejun Heo
     [not found]                   ` <20200219155202.GE698990-146+VewaZzwNjtGbbfXrCEEOCMrvLtNR@public.gmane.org>
2020-02-19 16:08                     ` Mathieu Desnoyers
2020-02-19 16:08                       ` Mathieu Desnoyers
     [not found]                       ` <1358308409.804.1582128519523.JavaMail.zimbra-vg+e7yoeK/dWk0Htik3J/w@public.gmane.org>
2020-02-19 16:12                         ` Tejun Heo [this message]
2020-02-19 16:12                           ` Tejun Heo
     [not found]                           ` <20200219161222.GF698990-146+VewaZzwNjtGbbfXrCEEOCMrvLtNR@public.gmane.org>
2020-03-07 16:06                             ` Mathieu Desnoyers
2020-03-07 16:06                               ` Mathieu Desnoyers
     [not found]                               ` <316507033.21078.1583597207356.JavaMail.zimbra-vg+e7yoeK/dWk0Htik3J/w@public.gmane.org>
2020-03-12 18:26                                 ` Tejun Heo
2020-03-12 18:26                                   ` Tejun Heo
     [not found]                                   ` <20200312182618.GE79873-qYNAdHglDFBN0TnZuCh8vA@public.gmane.org>
2020-03-12 19:47                                     ` Mathieu Desnoyers
2020-03-12 19:47                                       ` Mathieu Desnoyers
     [not found]                                       ` <1289608777.27165.1584042470528.JavaMail.zimbra-vg+e7yoeK/dWk0Htik3J/w@public.gmane.org>
2020-03-24 18:01                                         ` Tejun Heo
2020-03-24 18:01                                           ` Tejun Heo
     [not found]                                           ` <20200324180139.GB162390-qYNAdHglDFBN0TnZuCh8vA@public.gmane.org>
2020-03-24 19:30                                             ` Mathieu Desnoyers
2020-03-24 19:30                                               ` Mathieu Desnoyers
     [not found]                                               ` <195391080.10219.1585078246788.JavaMail.zimbra-vg+e7yoeK/dWk0Htik3J/w@public.gmane.org>
2020-03-30 19:53                                                 ` Mathieu Desnoyers
2020-03-30 19:53                                                   ` Mathieu Desnoyers

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=20200219161222.GF698990@mtj.thefacebook.com \
    --to=tj-dgejt+ai2ygdnm+yrofe0a@public.gmane.org \
    --cc=cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=lizefan-hv44wF8Li93QT0dZR+AlfA@public.gmane.org \
    --cc=mathieu.desnoyers-vg+e7yoeK/dWk0Htik3J/w@public.gmane.org \
    --cc=mingo-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
    --cc=peterz-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org \
    --cc=tglx-hfZtesqFncYOwBW4kG4KsQ@public.gmane.org \
    --cc=valentin.schneider-5wv7dgnIgG8@public.gmane.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.