public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: David Ahern <david.ahern@oracle.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: efault@gmx.de, mingo@kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [RFC PATCH] sched: Add cpu based entries to debugfs
Date: Mon, 30 Mar 2015 07:02:53 -0600	[thread overview]
Message-ID: <5519497D.5030909@oracle.com> (raw)
In-Reply-To: <20150330074452.GM23123@twins.programming.kicks-ass.net>

On 3/30/15 1:44 AM, Peter Zijlstra wrote:
> On Sun, Mar 29, 2015 at 10:13:33PM -0400, David Ahern wrote:
>> Before spending too much time formalizing this I wanted to see if you guys
>> would entertain the idea of making this info available via debugfs. It does
>> move the existing sched_features file to sched/features -- not sure how
>> acceptable it is to move files in debugfs.
>
> There also already is a /proc/sys/kernel/sched_domain/ sysctl thing that
> has much of the stuff in.
>
> I'm not opposed to a debugfs thing, but only if we can take the sysctl
> thing out.
>

Related files I aware of; perhaps there are others:

- /sys/devices/system/cpu entries. e.g., for cpu topology (physical 
package id, core id, sibling cores and threads)

- debufs file for sched_features

- /proc/sys/kernel/sched_domain for tweaking scheduling parameters

I could not find anything that shows the sched_domain information. The 
proposal here was to create read-only debugfs files to dump the same 
info (but with better readability for large systems) that comes with the 
sched_debug parameter. I chose debugfs because a) sched_features is 
there and b) it is debug information about the scheduler.

I could just as easily out it under /proc/sys/kernel/sched_domain or 
create a sched subdir under /sys/devices/system/cpu/cpu$n if one of 
those is preferred.

David

      parent reply	other threads:[~2015-03-30 13:03 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-03-30  2:13 [RFC PATCH] sched: Add cpu based entries to debugfs David Ahern
2015-03-30  2:32 ` Mike Galbraith
2015-03-30  2:48   ` David Ahern
2015-03-30  3:08     ` Mike Galbraith
2015-03-30 13:03       ` David Ahern
2015-03-30 14:45         ` Mike Galbraith
2015-03-30  7:44 ` Peter Zijlstra
2015-03-30  8:26   ` Mike Galbraith
2015-03-30  8:28     ` Peter Zijlstra
2015-03-30  8:43       ` Mike Galbraith
2015-03-30  9:18         ` Peter Zijlstra
2015-03-31  9:13           ` Ingo Molnar
2015-04-06  2:10             ` David Ahern
2015-04-06  4:04               ` Mike Galbraith
2015-03-30 13:02   ` David Ahern [this message]

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=5519497D.5030909@oracle.com \
    --to=david.ahern@oracle.com \
    --cc=efault@gmx.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox