LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Thomas Gleixner <tglx@linutronix.de>
To: Julia Cartwright <julia@ni.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
	"x86@kernel.org" <x86@kernel.org>,
	Steven Rostedt <rostedt@goodmis.org>,
	Sebastian Siewior <bigeasy@linutronix.de>,
	Anna-Maria Gleixner <anna-maria@linutronix.de>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Jiri Olsa <jolsa@redhat.com>, Paolo Bonzini <pbonzini@redhat.com>,
	Juergen Gross <jgross@suse.com>
Subject: Re: [patch 10/12] hrtimer: Determine hard/soft expiry mode for hrtimer sleepers on RT
Date: Fri, 26 Jul 2019 23:35:00 +0200 (CEST)
Message-ID: <alpine.DEB.2.21.1907262327250.1791@nanos.tec.linutronix.de> (raw)
In-Reply-To: <20190726211623.GP29109@jcartwri.amer.corp.natinst.com>

Julia,

On Fri, 26 Jul 2019, Julia Cartwright wrote:
> On Fri, Jul 26, 2019 at 08:30:58PM +0200, Thomas Gleixner wrote:
> > +	 * OTOH, priviledged real-time user space applications rely on the
> > +	 * low latency of hard interrupt wakeups. If the current task is in
> > +	 * a real-time scheduling class, mark the mode for hard interrupt
> > +	 * expiry.
> > +	 */
> > +	if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
> > +		if (task_is_realtime(current) && !(mode & HRTIMER_MODE_SOFT))
> > +			mode |= HRTIMER_MODE_HARD;
> 
> Because this ends up sampling the tasks' scheduling parameters only at
> the time of enqueue, it doesn't take into consideration whether or not
> the task maybe holding a PI lock and later be boosted if contended by an
> RT thread.
>
> Am I correct in assuming there is an induced inversion here in this
> case, because the deferred wakeup mechanism isn't part of the PI chain?
>
> If so, is this just to be an accepted limitation at this point?  Is the
> intent to argue this away as bad RT application design? :)

This would bring us back to the point where we moved the hrtimers
which were not marked for hardirq expiry onto the separate softirq expiry
list. That caused horrible latencies in some scenarios.

The separation of the bases into hard and soft expiry mode solved that
nicely and I haven't heard a complaint since we changed that in 4.14-rt.

So yes I'd argue it's an application issue. Holding a lock while doing
e.g. a nanosleep is not the most brilliant idea.

Thanks,

	tglx

  parent reply index

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-26 18:30 [patch 00/12] (hr)timers: Prepare for PREEMPT_RT support Thomas Gleixner
2019-07-26 18:30 ` [patch 01/12] hrtimer: Remove task argument from hrtimer_init_sleeper() Thomas Gleixner
2019-07-26 19:57   ` Steven Rostedt
2019-07-26 20:01     ` Thomas Gleixner
2019-07-30 22:07   ` [tip:timers/core] " tip-bot for Thomas Gleixner
2019-07-26 18:30 ` [patch 02/12] hrtimer: Consolidate hrtimer_init() + hrtimer_init_sleeper() calls Thomas Gleixner
2019-07-30 22:08   ` [tip:timers/core] " tip-bot for Sebastian Andrzej Siewior
2019-08-01 15:49   ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 03/12] hrtimer: Introduce HARD expiry mode Thomas Gleixner
2019-07-30 22:10   ` [tip:timers/core] " tip-bot for Sebastian Andrzej Siewior
2019-08-01 15:52   ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 04/12] sched: Mark hrtimers to expire in hard interrupt context Thomas Gleixner
2019-07-30 22:11   ` [tip:timers/core] " tip-bot for Thomas Gleixner
2019-08-01 15:53   ` tip-bot for Sebastian Andrzej Siewior
2019-08-01 18:58   ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 05/12] perf/core: " Thomas Gleixner
2019-07-30 22:12   ` [tip:timers/core] " tip-bot for Thomas Gleixner
2019-08-01 15:54   ` tip-bot for Sebastian Andrzej Siewior
2019-08-01 18:59   ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 06/12] watchdog: Mark watchdog_hrtimer " Thomas Gleixner
2019-07-30 22:13   ` [tip:timers/core] " tip-bot for Sebastian Andrzej Siewior
2019-08-01 15:55   ` tip-bot for Sebastian Andrzej Siewior
2019-08-01 19:00   ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 07/12] KVM: LAPIC: Mark hrtimer " Thomas Gleixner
2019-07-26 19:41   ` Paolo Bonzini
2019-07-30 22:14   ` [tip:timers/core] " tip-bot for Sebastian Andrzej Siewior
2019-08-01 15:55   ` tip-bot for Sebastian Andrzej Siewior
2019-08-01 19:01   ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 08/12] tick: Mark tick related hrtimers to expiry " Thomas Gleixner
2019-07-30 22:14   ` [tip:timers/core] " tip-bot for Sebastian Andrzej Siewior
2019-08-01 15:56   ` tip-bot for Sebastian Andrzej Siewior
2019-08-01 19:01   ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 09/12] hrtimer: Move unmarked hrtimers to soft interrupt expiry on RT Thomas Gleixner
2019-07-30 22:15   ` [tip:timers/core] " tip-bot for Sebastian Andrzej Siewior
2019-08-01 15:57   ` tip-bot for Sebastian Andrzej Siewior
2019-08-01 19:02   ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 10/12] hrtimer: Determine hard/soft expiry mode for hrtimer sleepers " Thomas Gleixner
2019-07-26 20:44   ` Steven Rostedt
2019-07-26 20:52     ` Thomas Gleixner
2019-07-26 20:56       ` Steven Rostedt
2019-07-26 21:16   ` Julia Cartwright
2019-07-26 21:30     ` Steven Rostedt
2019-07-26 21:35     ` Thomas Gleixner [this message]
2019-07-30 22:16   ` [tip:timers/core] " tip-bot for Sebastian Andrzej Siewior
2019-08-01 15:58   ` tip-bot for Sebastian Andrzej Siewior
2019-08-01 19:03   ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 11/12] hrtimer: Prepare support for PREEMPT_RT Thomas Gleixner
2019-07-28  9:06   ` Juergen Gross
2019-07-29 15:08     ` Steven Rostedt
2019-07-29 17:30       ` Paolo Bonzini
2019-07-31  8:45         ` Juergen Gross
2019-07-30 22:17   ` [tip:timers/core] " tip-bot for Anna-Maria Gleixner
2019-08-01 15:58   ` tip-bot for Anna-Maria Gleixner
2019-08-01 19:04   ` tip-bot for Anna-Maria Gleixner
2019-08-20 13:26     ` Frederic Weisbecker
2019-08-23  2:12       ` [tip: timers/core] hrtimer: Improve comments on handling priority inversion against softirq kthread tip-bot2 for Frederic Weisbecker
2019-07-26 18:31 ` [patch 12/12] timers: Prepare support for PREEMPT_RT Thomas Gleixner
2019-07-30 22:17   ` [tip:timers/core] " tip-bot for Anna-Maria Gleixner
2019-08-01 15:59   ` tip-bot for Anna-Maria Gleixner
2019-08-01 19:04   ` tip-bot for Anna-Maria Gleixner
2019-07-29 19:45 ` [patch 00/12] (hr)timers: Prepare for PREEMPT_RT support 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=alpine.DEB.2.21.1907262327250.1791@nanos.tec.linutronix.de \
    --to=tglx@linutronix.de \
    --cc=acme@kernel.org \
    --cc=anna-maria@linutronix.de \
    --cc=bigeasy@linutronix.de \
    --cc=jgross@suse.com \
    --cc=jolsa@redhat.com \
    --cc=julia@ni.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=rostedt@goodmis.org \
    --cc=x86@kernel.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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git