public inbox for rcu@vger.kernel.org
 help / color / mirror / Atom feed
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
To: linux-kernel@vger.kernel.org, rcu@vger.kernel.org
Cc: "Paul E. McKenney" <paulmck@kernel.org>,
	Anna-Maria Behnsen <anna-maria@linutronix.de>,
	Davidlohr Bueso <dave@stgolabs.net>,
	Frederic Weisbecker <frederic@kernel.org>,
	Ingo Molnar <mingo@kernel.org>,
	Josh Triplett <josh@joshtriplett.org>,
	Thomas Gleixner <tglx@linutronix.de>
Subject: PATCH v3 0/3] softirq: Use a dedicated thread for timer wakeups with forced-threading.
Date: Wed,  6 Nov 2024 15:51:36 +0100	[thread overview]
Message-ID: <20241106150419.2593080-1-bigeasy@linutronix.de> (raw)

Hi,

the following was in the PREEMPT_RT queue since last softirq rework. The
result is that timer wake ups (hrtimer, timer_list) happens in hardirq
processing them requires to wake ksoftirqd. ksoftirqd runs at SCHED_OTHER so it
will compete for resources with all other tasks in the system, potentially
delayed the processing further.

The idea was to let the timers be processed by a dedicated thread
running at low SCHED_FIFO priority.
While looking at it again, it might make sense to have the
pending_softirq flag per-thread to avoid threads with higher priority
picking up softirqs from low-priority threads. This isn't yet a problem
because adding softirqs for processing happens only from threaded
interrupts. So the low-priority thread will wait until the high-priority
thread is done. And the high-priority thread will PI-boost the
low-priority thread until it is done. It would only make sense to make
the flags per-thread once the BH lock is gone.

The patch is limited to the forced threaded case.

v2…v3 https://lore.kernel.org/all/20241024150413.518862-1-bigeasy@linutronix.de/
 - Redo the comment in interrupt.h. Make it more verbose and add more
   details. Frederick asked for it.

 - After updating the comment I convinced myself that it also makes
   sense to use this in the forced threaded case.

 - Merged raise_hrtimer_softirq() and raise_timer_softirq() into a
   single function since both use __raise_softirq_irqoff() in the
   alternative case.
 
v1…v2 https://lore.kernel.org/all/20241004103842.131014-1-bigeasy@linutronix.de/
 Frederick's comments:
 - Use __raise_softirq_irqoff() to raise the softirq for !PREEMPT_RT. Also a
   lockdep test to ensure that this is always invoked from an IRQ.
 - Make raise_ktimers_thread() only OR the flag and nothing else to
   align with __raise_softirq_irqoff(). The wake happens on return from
   interrupt anyway.
 - A comment in timersd_setup() and interrupt.h
 - local_pending_timers() => local_timers_pending().

Sebastian


             reply	other threads:[~2024-11-06 15:04 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-11-06 14:51 Sebastian Andrzej Siewior [this message]
2024-11-06 14:51 ` [PATCH v3 1/3] hrtimer: Use __raise_softirq_irqoff() to raise the softirq Sebastian Andrzej Siewior
2024-11-06 14:51 ` [PATCH v3 2/3] timers: " Sebastian Andrzej Siewior
2024-11-06 14:51 ` [PATCH v3 3/3] softirq: Use a dedicated thread for timer wakeups on PREEMPT_RT Sebastian Andrzej Siewior
2025-12-01 21:51   ` Jan Kiszka
2025-12-01 23:49     ` Luis Claudio R. Goncalves
2025-12-02  6:57       ` Jan Kiszka
2025-12-02  8:22         ` Sebastian Andrzej Siewior
2025-12-02  8:24     ` Sebastian Andrzej Siewior
2025-12-02 12:39       ` Jan Kiszka
2025-12-02 13:22         ` Sebastian Andrzej Siewior

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=20241106150419.2593080-1-bigeasy@linutronix.de \
    --to=bigeasy@linutronix.de \
    --cc=anna-maria@linutronix.de \
    --cc=dave@stgolabs.net \
    --cc=frederic@kernel.org \
    --cc=josh@joshtriplett.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=paulmck@kernel.org \
    --cc=rcu@vger.kernel.org \
    --cc=tglx@linutronix.de \
    /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