All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>, LKML <linux-kernel@vger.kernel.org>
Subject: Re: deadlock in scheduler enabling HRTICK feature
Date: Wed, 26 Jun 2013 09:05:34 +0200	[thread overview]
Message-ID: <20130626070533.GA3601@dyad.programming.kicks-ass.net> (raw)
In-Reply-To: <51CA0980.8010409@gmail.com>

On Tue, Jun 25, 2013 at 03:20:00PM -0600, David Ahern wrote:
> On 6/25/13 3:17 PM, Peter Zijlstra wrote:
> >On Tue, Jun 25, 2013 at 03:05:38PM -0600, David Ahern wrote:
> >>Peter/Ingo:
> >>
> >>I can reliably cause a deadlock in the scheduler by enabling the HRTICK
> >>feature. I first hit the problem with 2.6.27 but have been able to reproduce
> >>it with newer kernels. I have not tried top of Linus' tree, so perhaps this
> >>has been fixed in 3.10.
> >
> >Yeah, I know.. its been on the todo list forever but its never been
> >important. Its disabled by default and all sched debug features are for
> >those brave enough to keep the pieces ;-)
> >
> 
> Not a whole to of pieces to keep.
> 
> What is the expectation that the feature provides? not a whole lot of
> documentation on it. I walked down the path wondering if it solved an odd
> problem we are seeing with the CFS in 2.6.27 kernel.

Its supposed to use hrtimers for slice expiry instead of the regular tick.

IIRC it did work at some point but bitrotted a bit since. The good news is that
the deadline scheduler wants to use it and I'll probably have to fix it up
then.

But yes, I need to write more comments in sched/features.h

  reply	other threads:[~2013-06-26  7:06 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-06-25 21:05 David Ahern
2013-06-25 21:17 ` Peter Zijlstra
2013-06-25 21:20   ` David Ahern
2013-06-26  7:05     ` Peter Zijlstra [this message]
2013-06-26 16:46       ` David Ahern
2013-06-27 10:43         ` Peter Zijlstra
2013-06-27 10:53           ` Peter Zijlstra
2013-06-27 12:28             ` Mike Galbraith
2013-06-27 13:06             ` Ingo Molnar
2013-06-27 19:18             ` Andy Lutomirski
2013-06-27 20:37               ` Peter Zijlstra
2013-06-27 22:28           ` David Ahern
2013-06-28  9:00             ` Ingo Molnar
2013-06-28  9:18               ` Peter Zijlstra
2013-07-12 13:29                 ` [tip:sched/core] sched: Fix HRTICK tip-bot for Peter Zijlstra
2013-06-28  9:09             ` deadlock in scheduler enabling HRTICK feature Peter Zijlstra
2013-06-28 17:28               ` David Ahern

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=20130626070533.GA3601@dyad.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=dsahern@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --subject='Re: deadlock in scheduler enabling HRTICK feature' \
    /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 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.