public inbox for cgroups@vger.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Tejun Heo <tj@kernel.org>
Cc: Zefan Li <lizefan@huawei.com>,
	Mike Galbraith <umgwanakikbuti@gmail.com>,
	Ingo Molnar <mingo@kernel.org>,
	LKML <linux-kernel@vger.kernel.org>,
	Cgroups <cgroups@vger.kernel.org>
Subject: Re: [PATCH] sched: Relax a restriction in sched_rt_can_attach()
Date: Tue, 5 May 2015 17:19:49 +0200	[thread overview]
Message-ID: <20150505151949.GQ21418@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <20150505141838.GR1971@htj.duckdns.org>

On Tue, May 05, 2015 at 10:18:38AM -0400, Tejun Heo wrote:
> > Now you can kludge around some of this, for example you can make the
> > default depend on the parent setting etc.. But that's horribly
> > inconsistent.
> 
> I don't think we can kludge this.  For all other resources, we're
> defining the limits that can't be crossed so nesting them w/ -1 by
> default is fine.  RR slices are different it that we're really slicing
> up and guaranteeing a portion of something finite, so unlimited by
> default thing doesn't really work here.

Note that you _could_ do the same thing with IO bandwidth; esp. with
these modern no-seek-penalty devices this could make sense.


> > So I really prefer not to go that way; if people use RR/FIFO they had
> > better bloody know what they're doing; which includes setting up the
> > system.
> 
> The problem is that this is tied to the normal cpu controller.  Users
> who don't have any intention of mucking with RT scheduling end up
> being dragged into it.  Given the strict nature of RR slicing, I'm
> don't even think it's actually useful to make the slicing
> hierarchical.  From cgroup's POV, it'd be best if RR slicing can be
> detached.

Like in the other mail; hierarchy still makes perfect sense for the
container case.

> > The whole RR/FIFO thing is so enormously broken (by definition; this
> > truly is unfixable) that you simply _cannot_ automate it.
> 
> Yeah, exactly.

I don't think you're quite agreeing to the same reasons I am. My main
objection to the whole SCHED_RR/FIFO thing as defined by POSIX is that
it does not in fact allow the OS to do what an OS _should_ do, namely
resource arbitration and control.

The whole rt-cgroup controller tries to somewhat contain that, but
fundamentally once you use RR/FIFO you've given up your system to
userspace control -- which btw is why its usually limited to root.

SCHED_DEADLINE avoids all these problems, at the cost of a more complex
setup.

But the fact that both need fixed portions of a limited total does not
in fact mean they're broken.

  reply	other threads:[~2015-05-05 15:19 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-05-04  0:54 [PATCH] sched: Relax a restriction in sched_rt_can_attach() Zefan Li
     [not found] ` <5546C34C.7050202-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2015-05-04  3:13   ` Mike Galbraith
     [not found]     ` <1430709236.3129.42.camel-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2015-05-04  4:39       ` Zefan Li
     [not found]         ` <5546F80B.3070802-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2015-05-04  5:10           ` Mike Galbraith
     [not found]             ` <1430716247.3129.44.camel-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2015-05-04  5:39               ` Mike Galbraith
     [not found]                 ` <1430717964.3129.62.camel-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2015-05-04  9:11                   ` Zefan Li
     [not found]                     ` <554737AE.5040402-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2015-05-04 12:08                       ` Mike Galbraith
2015-05-04 12:37                       ` Peter Zijlstra
2015-05-04 14:09                         ` Mike Galbraith
     [not found]                           ` <1430748582.3166.16.camel-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2015-05-05  3:46                             ` Zefan Li
     [not found]                               ` <55483CF8.8030908-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2015-05-05  6:02                                 ` Mike Galbraith
     [not found]                         ` <20150504123738.GZ21418-ndre7Fmf5hadTX5a5knrm8zTDFooKrT+cvkQGrU6aU0@public.gmane.org>
2015-05-05  3:54                           ` Zefan Li
2015-05-05 14:10                             ` Peter Zijlstra
2015-05-05 14:18                               ` Tejun Heo
2015-05-05 15:19                                 ` Peter Zijlstra [this message]
2015-05-05 16:31                                   ` Tejun Heo
2015-05-05 19:00                                     ` Peter Zijlstra
     [not found]                                       ` <20150505190057.GR23123-ndre7Fmf5hadTX5a5knrm8zTDFooKrT+cvkQGrU6aU0@public.gmane.org>
2015-05-05 19:06                                         ` Tejun Heo
     [not found]                                           ` <20150505190603.GZ1971-piEFEHQLUPpN0TnZuCh8vA@public.gmane.org>
2015-05-06  8:49                                             ` Peter Zijlstra
2015-05-05 14:41                         ` Tejun Heo
2015-05-05 15:11                           ` Peter Zijlstra
2015-05-05 16:13                             ` Tejun Heo
2015-05-05 16:50                               ` Peter Zijlstra
2015-05-05 18:29                                 ` Thomas Gleixner
2015-05-05 19:00                                   ` Tejun Heo
2015-05-06  9:12                                     ` Thomas Gleixner
2015-05-05 18:31                                 ` Tejun Heo
2015-05-05 14:09                   ` Tejun Heo

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=20150505151949.GQ21418@twins.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=cgroups@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lizefan@huawei.com \
    --cc=mingo@kernel.org \
    --cc=tj@kernel.org \
    --cc=umgwanakikbuti@gmail.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