mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Qais Yousef <qais.yousef@arm.com>
To: Hillf Danton <hdanton@sina.com>
Cc: John Stultz <jstultz@google.com>,
	LKML <linux-kernel@vger.kernel.org>,
	linux-mm@kvack.org, Connor O'Brien <connoro@google.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Steven Rostedt <rostedt@goodmis.org>
Subject: Re: [RFC PATCH v4 2/3] sched: Avoid placing RT threads on cores handling long softirqs
Date: Mon, 10 Oct 2022 16:42:16 +0100	[thread overview]
Message-ID: <20221010154216.6mw7fszdaoajurvm@wubuntu> (raw)
In-Reply-To: <20221005060155.1571-1-hdanton@sina.com>

On 10/05/22 14:01, Hillf Danton wrote:
> On 4 Oct 2022 18:13:52 -0700 John Stultz <jstultz@google.com>
> > On Tue, Oct 4, 2022 at 5:22 PM Hillf Danton <hdanton@sina.com> wrote:
> > > On 3 Oct 2022 19:29:36 -0700 John Stultz <jstultz@google.com>
> > > >
> > > > Why would ksoftirqd preempt the rt task?
> > > >
> > > For example the kthread becomes sensitive to latency.
> > 
> > Is it the case where
> > the ksoftirqd thread is configured to run at higher rtprio?
> > 
> Yes, you are right.

I don't see a problem here. If a sys-admin configures their ksoftirqds to be
a higher priority RT tasks than the audio threads, then they better know what
they're doing :-)

The issue at hand here is that the softirqs boundedness is hard to control. And
the scheduling delays ensued are hard to deal with by any sys-admin.

Networking has actually introduced some knobs to help control that - but the
tricky bit of still being able to deliver high throughput networking while
keeping the softirq bounded to minimize scheduling delays/latencies. I think
even for PREEMPT_RT, high performance networking could be impacted to achieve
the required low latency.

See this paper which explores this duality:

	https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.702.7571&rep=rep1&type=pdf


With WiFi 6 and 5G mobile networks, phones are actually expected to deliver
multi-gigabit network throughputs.


Cheers

--
Qais Yousef

  parent reply	other threads:[~2022-10-10 15:42 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-10-03 23:20 [RFC PATCH v4 0/3] Softirq -rt Optimizations John Stultz
2022-10-03 23:20 ` [RFC PATCH v4 1/3] softirq: Add generic accessor to percpu softirq_pending data John Stultz
2022-10-03 23:20 ` [RFC PATCH v4 2/3] sched: Avoid placing RT threads on cores handling long softirqs John Stultz
     [not found]   ` <20221004013611.1822-1-hdanton@sina.com>
2022-10-04  2:29     ` John Stultz
     [not found]       ` <20221005002149.1876-1-hdanton@sina.com>
2022-10-05  1:13         ` John Stultz
     [not found]         ` <20221005060155.1571-1-hdanton@sina.com>
2022-10-10 15:42           ` Qais Yousef [this message]
     [not found]             ` <20221011111846.284-1-hdanton@sina.com>
2022-10-12 14:10               ` Qais Yousef
2022-10-17 12:40   ` [PATCH RFC " Alexander Gordeev
2022-10-18  3:42     ` John Stultz
2022-10-18  3:59       ` John Stultz
2022-10-18  5:32       ` John Stultz
2022-10-19  9:11       ` Alexander Gordeev
2022-10-19 22:09         ` John Stultz
2022-10-20  0:15           ` Qais Yousef
2022-10-20 12:47           ` Alexander Gordeev
2022-10-22 18:34             ` Joel Fernandes
2022-10-23  7:45               ` Alexander Gordeev
2022-11-15  7:08                 ` John Stultz
2022-11-15 12:55                   ` Alexander Gordeev
2022-10-19 11:23       ` Qais Yousef
2022-10-22 18:28   ` [RFC PATCH " Joel Fernandes
2022-11-15 21:36     ` John Stultz
2022-10-03 23:20 ` [RFC PATCH v4 3/3] softirq: defer softirq processing to ksoftirqd if CPU is busy with RT John Stultz
2022-10-04 10:45   ` David Laight
2022-10-04 19:19     ` John Stultz
2022-10-10 16:09   ` Qais Yousef
2022-10-17 14:44     ` Qais Yousef
2022-10-18  0:04       ` John Stultz
2022-10-19 11:01         ` Qais Yousef

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=20221010154216.6mw7fszdaoajurvm@wubuntu \
    --to=qais.yousef@arm.com \
    --cc=connoro@google.com \
    --cc=hdanton@sina.com \
    --cc=jstultz@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.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

all inboxes | Powered by JetHome®