LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
To: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: LKML <linux-kernel@vger.kernel.org>, Ingo Molnar <mingo@elte.hu>,
	Dmitry Adamushko <dmitry.adamushko@gmail.com>,
	Mike Galbraith <efault@gmx.de>,
	Dhaval Giani <dhaval@linux.vnet.ibm.com>
Subject: Re: [RFC/PATCH 01/17] sched: mix tasks and groups
Date: Tue, 1 Apr 2008 17:42:38 +0530	[thread overview]
Message-ID: <20080401121238.GA3341@linux.vnet.ibm.com> (raw)
In-Reply-To: <20080309170925.857156000@chello.nl>

On Sun, Mar 09, 2008 at 06:08:51PM +0100, Peter Zijlstra wrote:
> This patch allows tasks and groups to exist in the same cfs_rq. With this
> change the CFS group scheduling follows a 1/(M+N) model from a 1/(1+N)
> fairness model where M tasks and N groups exist at the cfs_rq level.
> 
> [a.p.zijlstra@chello.nl: rt bits]
> Signed-off-by: Dhaval Giani <dhaval@linux.vnet.ibm.com>
> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
> ---
>  kernel/sched.c      |   54 ++++++++++++++++++++++++++++++++++++++++++++++++++--
>  kernel/sched_fair.c |   48 +++++++++++++++++++++++++++++++++++++++++++---
>  kernel/sched_rt.c   |   15 ++++++++------
>  3 files changed, 106 insertions(+), 11 deletions(-)
> 
> Index: linux-2.6-2/kernel/sched.c
> ===================================================================
> --- linux-2.6-2.orig/kernel/sched.c
> +++ linux-2.6-2/kernel/sched.c
> @@ -273,18 +273,23 @@ struct task_group {
>  };
> 
>  #ifdef CONFIG_FAIR_GROUP_SCHED
> +
> +#ifdef CONFIG_USER_SCHED
>  /* Default task group's sched entity on each cpu */
>  static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
>  /* Default task group's cfs_rq on each cpu */
>  static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;
> +#endif


I am trying to understand the change this brings for semantics of RT-scheduling.

With this change, /cgroup will be seen as the parent group of all other
groups (say: /cgroup/A, /cgroup/B etc). Is that correct?

If so, the check in __rt_schedulable() needs a change as well, which assumes 
that all task groups form a flat hierarchy.

For example: lets say that init_task_group (/cgroup in this case) had the
default rt_bandwidth of 95% (global_rt_runtime()). A child group under it 
(/cgroup/A) is created. If user tries to assign it a rt-bandwidth of
50%, then AFAICS, it will fail with current code, whereas it shouldn't
(because by giving /cgroup/A 50% bandwidth, we are not really exceeding
the globally allowed RT bandwidth of 95%, since /cgroup/A is a child of
/cgroup).

-- 
Regards,
vatsa

  reply	other threads:[~2008-04-01 12:03 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-03-09 17:08 [RFC/PATCH 00/17] Current sched patch stack Peter Zijlstra
2008-03-09 17:08 ` [RFC/PATCH 01/17] sched: mix tasks and groups Peter Zijlstra
2008-04-01 12:12   ` Srivatsa Vaddagiri [this message]
2008-04-01 12:05     ` Peter Zijlstra
2008-03-09 17:08 ` [RFC/PATCH 02/17] sched: allow the CFS group scheduler to have multiple levels Peter Zijlstra
2008-03-12 14:47   ` Dhaval Giani
2008-03-09 17:08 ` [RFC/PATCH 03/17] sched: rt-group: full hierarchy support for the rt groups Peter Zijlstra
2008-03-12  8:25   ` Dhaval Giani
     [not found]     ` <661de9470803120129l66497656o948c13c6c0c26766@mail.gmail.com>
2008-03-12  9:29       ` Peter Zijlstra
2008-03-12 13:34         ` Balbir Singh
2008-03-12 13:39           ` Dhaval Giani
2008-03-12 14:08         ` Balbir Singh
2008-03-09 17:08 ` [RFC/PATCH 04/17] sched: fair-group: SMP-nice for group scheduling Peter Zijlstra
2008-03-09 17:08 ` [RFC/PATCH 05/17] sched: rt-group: optimize dequeue_rt_stack Peter Zijlstra
2008-03-09 17:08 ` [RFC/PATCH 06/17] sched: fair-group scheduling vs latency Peter Zijlstra
2008-03-09 17:08 ` [RFC/PATCH 07/17] sched: fair-group: de-couple load-balancing from the rb-trees Peter Zijlstra
2008-03-09 17:08 ` [RFC/PATCH 08/17] sched: fair-group: single RQ approach Peter Zijlstra
2008-03-09 17:08 ` [RFC/PATCH 09/17] sched: fair: remove moved_group() Peter Zijlstra
2008-03-09 17:09 ` [RFC/PATCH 10/17] sched: remove sysctl_sched_batch_wakeup_granularity Peter Zijlstra
2008-03-09 17:09 ` [RFC/PATCH 11/17] sched: fair: optimize sched_slice() Peter Zijlstra
2008-03-09 17:09 ` [RFC/PATCH 12/17] sched: fair: cfs_root_rq Peter Zijlstra
2008-03-09 17:09 ` [RFC/PATCH 13/17] sched: fair: calc_delta_weight() Peter Zijlstra
2008-03-09 17:09 ` [RFC/PATCH 14/17] sched: fair: avg_vruntime Peter Zijlstra
2008-03-09 17:09 ` [RFC/PATCH 15/17] sched: fair-group: EEVDF scheduling Peter Zijlstra
2008-03-09 17:09 ` [RFC/PATCH 16/17] sched: fair: bound tardiness Peter Zijlstra
2008-03-09 17:09 ` [RFC/PATCH 17/17] sched: fair: optimize the elegebility test Peter Zijlstra

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=20080401121238.GA3341@linux.vnet.ibm.com \
    --to=vatsa@linux.vnet.ibm.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=dhaval@linux.vnet.ibm.com \
    --cc=dmitry.adamushko@gmail.com \
    --cc=efault@gmx.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --subject='Re: [RFC/PATCH 01/17] sched: mix tasks and groups' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).