From: Frederic Weisbecker <frederic@kernel.org>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Dmitry Safonov <dima@arista.com>,
Eric Dumazet <edumazet@google.com>,
LKML <linux-kernel@vger.kernel.org>,
Dmitry Safonov <0x7f454c46@gmail.com>,
Andrew Morton <akpm@linux-foundation.org>,
David Miller <davem@davemloft.net>,
Frederic Weisbecker <fweisbec@gmail.com>,
Hannes Frederic Sowa <hannes@stressinduktion.org>,
Ingo Molnar <mingo@kernel.org>,
"Levin, Alexander (Sasha Levin)" <alexander.levin@verizon.com>,
Paolo Abeni <pabeni@redhat.com>,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
Peter Zijlstra <peterz@infradead.org>,
Radu Rendec <rrendec@arista.com>, Rik van Riel <riel@redhat.com>,
Stanislaw Gruszka <sgruszka@redhat.com>,
Thomas Gleixner <tglx@linutronix.de>,
Wanpeng Li <wanpeng.li@hotmail.com>
Subject: Re: [RFC 1/2] softirq: Defer net rx/tx processing to ksoftirqd context
Date: Thu, 11 Jan 2018 05:44:57 +0100 [thread overview]
Message-ID: <20180111044456.GC11633@lerouge> (raw)
In-Reply-To: <CA+55aFx_3zwQJ0YbDCL4YxpWEWhcEZfJnn42LzWBWDi3h1VdGA@mail.gmail.com>
On Wed, Jan 10, 2018 at 08:19:49PM -0800, Linus Torvalds wrote:
> On Wed, Jan 10, 2018 at 7:22 PM, Frederic Weisbecker
> <frederic@kernel.org> wrote:
> >
> > Makes sense, but I think you need to keep the TASK_RUNNING check.
>
> Yes, good point.
>
> > So perhaps it should be:
> >
> > - return tsk && (tsk->state == TASK_RUNNING);
> > + return (tsk == current) && (tsk->state == TASK_RUNNING);
>
> Looks good to me - definitely worth trying.
>
> Maybe that weakens the thing so much that it doesn't actually help the
> UDP packet storm case?
>
> And maybe it's not sufficient for the dvb issue.
>
> But I think it's worth at least testing. Maybe it makes neither side
> entirely happy, but maybe it might be a good halfway point?
Yes I believe Dmitry is facing a different problem where he would rather
see ksoftirqd scheduled more often to handle the queue as a deferred batch
instead of having it served one by one on the tails of IRQ storms.
(Dmitry correct me if I misunderstood).
But your patch still seems to make sense for the case you described: when
ksoftirqd is voluntarily preempted off and the current IRQ could handle the
queue.
next prev parent reply other threads:[~2018-01-11 4:45 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-09 13:36 [RFC 0/2] Net softirq deferring to ksoftirqd Dmitry Safonov
2018-01-09 13:36 ` [RFC 1/2] softirq: Defer net rx/tx processing to ksoftirqd context Dmitry Safonov
2018-01-09 16:03 ` Frederic Weisbecker
2018-01-10 21:20 ` Dmitry Safonov
2018-01-09 18:02 ` Eric Dumazet
2018-01-10 21:48 ` Dmitry Safonov
2018-01-11 2:13 ` Linus Torvalds
2018-01-11 3:22 ` Frederic Weisbecker
2018-01-11 4:19 ` Linus Torvalds
2018-01-11 4:44 ` Frederic Weisbecker [this message]
2018-01-11 14:31 ` Dmitry Safonov
2018-01-11 16:20 ` Eric Dumazet
2018-01-11 16:32 ` Peter Zijlstra
2018-01-11 16:38 ` David Miller
2018-01-11 16:43 ` Peter Zijlstra
2018-01-11 18:48 ` Linus Torvalds
2018-01-11 19:15 ` Eric Dumazet
2018-01-11 19:43 ` Linus Torvalds
2018-01-11 19:48 ` Eric Dumazet
2018-01-11 20:03 ` Linus Torvalds
2018-01-11 20:16 ` Eric Dumazet
2018-01-11 20:22 ` Linus Torvalds
2018-01-11 20:34 ` Dmitry Safonov
2018-01-11 20:37 ` Eric Dumazet
2018-01-11 20:40 ` Linus Torvalds
2018-01-11 20:46 ` Dmitry Safonov
2018-01-11 20:53 ` Eric Dumazet
2018-01-11 21:13 ` Dmitry Safonov
2018-01-12 5:41 ` Frederic Weisbecker
2018-01-12 5:23 ` Mike Galbraith
2018-01-12 10:13 ` Peter Zijlstra
2018-01-12 17:26 ` Linus Torvalds
2018-01-12 17:44 ` Mike Galbraith
2018-01-12 17:51 ` Linus Torvalds
2018-01-12 18:15 ` Mike Galbraith
2018-01-12 18:44 ` Mike Galbraith
2018-01-17 20:30 ` David Miller
2018-01-17 21:06 ` Linus Torvalds
2018-01-17 21:49 ` David Miller
2018-01-17 21:54 ` Thomas Gleixner
2018-01-17 21:58 ` Linus Torvalds
2018-01-17 22:00 ` Thomas Gleixner
2018-01-17 22:02 ` Eric Dumazet
2018-01-17 22:24 ` David Miller
2018-01-17 22:54 ` Thomas Gleixner
2018-02-06 16:56 ` Sebastian Andrzej Siewior
2018-02-13 16:36 ` Thomas Gleixner
2018-01-17 21:54 ` Linus Torvalds
2018-01-17 21:58 ` Thomas Gleixner
2018-01-12 19:28 ` Thomas Gleixner
2018-01-12 19:53 ` Frederic Weisbecker
2018-01-12 14:58 ` Frederic Weisbecker
2018-01-12 15:15 ` Mike Galbraith
2018-01-12 17:00 ` Frederic Weisbecker
2018-01-12 18:08 ` Mike Galbraith
2018-01-12 17:24 ` Linus Torvalds
2018-01-09 13:36 ` [RFC 2/2] softirq: Introduce mask for __do_softirq() Dmitry Safonov
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=20180111044456.GC11633@lerouge \
--to=frederic@kernel.org \
--cc=0x7f454c46@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=alexander.levin@verizon.com \
--cc=davem@davemloft.net \
--cc=dima@arista.com \
--cc=edumazet@google.com \
--cc=fweisbec@gmail.com \
--cc=hannes@stressinduktion.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=pabeni@redhat.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=peterz@infradead.org \
--cc=riel@redhat.com \
--cc=rrendec@arista.com \
--cc=sgruszka@redhat.com \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=wanpeng.li@hotmail.com \
/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