All of lore.kernel.org
 help / color / mirror / Atom feed
From: Thomas Gleixner <tglx@linutronix.de>
To: Christoph Hellwig <hch@infradead.org>
Cc: LKML <linux-kernel@vger.kernel.org>,
	Peter Zijlstra <peterz@infradead.org>, Tejun Heo <tj@kernel.org>,
	Jens Axboe <axboe@kernel.dk>, Ingo Molnar <mingo@elte.hu>,
	Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: [patch 1/4] sched: Separate the scheduler entry for preemption
Date: Wed, 22 Jun 2011 20:52:47 +0200 (CEST)	[thread overview]
Message-ID: <alpine.LFD.2.02.1106222047400.11814@ionos> (raw)
In-Reply-To: <20110622184328.GA6475@infradead.org>

On Wed, 22 Jun 2011, Christoph Hellwig wrote:

> On Wed, Jun 22, 2011 at 05:52:13PM -0000, Thomas Gleixner wrote:
> > Block-IO and workqueues call into notifier functions from the
> > scheduler core code with interrupts and preemption disabled. These
> > calls should be made before entering the scheduler core.
> > 
> > To simplify this, separate the scheduler core code into
> > __schedule(). __schedule() is directly called from the places which
> > set PREEMPT_ACTIVE and from schedule(). This allows us to add the work
> > checks into schedule(), so they are only called when a task voluntary
> > goes to sleep.
> 
> I don't think that works.  We'll need to flush the block requests even
> for an involuntary schedule.

We don't do that right now as that code conditional on:

    if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {

Also blk_flush_plug_list() when called from io_schedule() is
preemptible, so you might be preempted in the middle of the list
operations, so calling into it when preempted would result in an utter
disaster.

Thanks,

	tglx


  reply	other threads:[~2011-06-22 18:52 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-06-22 17:52 [patch 0/4] sched: Move work out of the scheduler core Thomas Gleixner
2011-06-22 17:52 ` [patch 1/4] sched: Separate the scheduler entry for preemption Thomas Gleixner
2011-06-22 18:43   ` Christoph Hellwig
2011-06-22 18:52     ` Thomas Gleixner [this message]
2011-06-22 19:42     ` Jens Axboe
2011-06-22 20:15       ` Thomas Gleixner
2011-06-23 11:41         ` Jens Axboe
2011-08-29 14:55   ` [tip:sched/urgent] " tip-bot for Thomas Gleixner
2011-06-22 17:52 ` [patch 3/4] block: Shorten interrupt disabled regions Thomas Gleixner
2011-06-22 17:52 ` [patch 2/4] sched: Move blk_schedule_flush_plug() out of __schedule() Thomas Gleixner
2011-06-22 17:52 ` [patch 4/4] sched: Distangle worker accounting from rq->lock Thomas Gleixner
2011-06-22 19:30   ` Thomas Gleixner
2011-06-23  8:37   ` Tejun Heo
2011-06-23  9:58     ` Thomas Gleixner
2011-06-23 10:15       ` Tejun Heo
2011-06-23 10:44         ` Ingo Molnar
2011-06-23 11:35           ` Tejun Heo
2011-06-23 12:51             ` Ingo Molnar
2011-06-24  9:01             ` Thomas Gleixner
2011-06-26 10:19               ` Tejun Heo
2011-06-23 15:07   ` Tejun Heo
2013-04-30 13:37   ` Steven Rostedt
2013-04-30 22:47     ` Steven Rostedt
2013-05-03  0:12       ` Tejun Heo
2013-05-03  0:57         ` Steven Rostedt
2013-07-24 10:04           ` Thomas Gleixner
2013-08-06 19:33             ` Steven Rostedt

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=alpine.LFD.2.02.1106222047400.11814@ionos \
    --to=tglx@linutronix.de \
    --cc=axboe@kernel.dk \
    --cc=hch@infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=peterz@infradead.org \
    --cc=tj@kernel.org \
    --cc=torvalds@linux-foundation.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.