From: Mike Galbraith <efault@gmx.de>
To: Dmitry Safonov <dima@arista.com>, David Miller <davem@davemloft.net>
Cc: bigeasy@linutronix.de, frederic@kernel.org,
linux-kernel@vger.kernel.org, alexander.levin@verizon.com,
peterz@infradead.org, mchehab@s-opensource.com,
torvalds@linux-foundation.org, hannes@stressinduktion.org,
paulmck@linux.vnet.ibm.com, wanpeng.li@hotmail.com,
tglx@linutronix.de, akpm@linux-foundation.org, pabeni@redhat.com,
rrendec@arista.com, mingo@kernel.org, sgruszka@redhat.com,
riel@redhat.com, edumazet@google.com
Subject: Re: [RFC PATCH 2/4] softirq: Per vector deferment to workqueue
Date: Fri, 09 Feb 2018 05:11:08 +0100 [thread overview]
Message-ID: <1518149468.24350.40.camel@gmx.de> (raw)
In-Reply-To: <1518121820.2849.17.camel@arista.com>
On Thu, 2018-02-08 at 20:30 +0000, Dmitry Safonov wrote:
> On Thu, 2018-02-08 at 15:22 -0500, David Miller wrote:
> > From: Dmitry Safonov <dima@arista.com>
> > Date: Thu, 08 Feb 2018 20:14:55 +0000
> >
> > > On Thu, 2018-02-08 at 13:45 -0500, David Miller wrote:
> > >> From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> > >> Date: Thu, 8 Feb 2018 18:44:52 +0100
> > >>
> > >> > May I instead suggest to stick to ksoftirqd? So you run in
> > softirq
> > >> > context (after return from IRQ) and if takes too long, you
> > offload
> > >> the
> > >> > vector to ksoftirqd instead. You may want to play with the
> > metric
> > >> on
> > >> > which you decide when you want switch to ksoftirqd / account how
> > >> long a
> > >> > vector runs.
> > >>
> > >> Having read over this stuff for the past few weeks this is how I
> > feel
> > >> as well. Just make ksofbitrq do what we want (only execute the
> > >> overloaded softirq vectors).
> > >>
> > >> The more I look at the workqueue stuff, the more complications and
> > >> weird behavioral artifacts we are getting for questionable gain.
> > >
> > > What about creating several ksoftirqd threads per-cpu?
> > > Like I did with boot parameter to specify how many threads and
> > which
> > > softirqs to serve.
> >
> > Why do we need more than one per cpu?
>
> Ugh, yeah, I remember why I did it - I tried to reuse scheduler for
> each ksoftirqd thread to decide if it need to run now or later.
> That would give an admin a way to prioritise softirqs with nice.
> Not sure if it's a nice idea at all..
For RT that can be handy, but for the general case it's a waste of
cycles, so would want to be opt-in.
-Mike
next prev parent reply other threads:[~2018-02-09 4:12 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-19 15:46 [RFC PATCH 0/4] softirq: Per vector threading v3 Frederic Weisbecker
2018-01-19 15:46 ` [RFC PATCH 1/4] softirq: Limit vector to a single iteration on IRQ tail Frederic Weisbecker
2018-01-19 16:16 ` David Miller
2018-01-19 18:25 ` Linus Torvalds
2018-01-19 18:47 ` David Miller
2018-01-21 16:30 ` Frederic Weisbecker
2018-01-21 16:57 ` David Miller
2018-01-19 15:46 ` [RFC PATCH 2/4] softirq: Per vector deferment to workqueue Frederic Weisbecker
2018-01-20 8:41 ` Pavan Kondeti
2018-01-21 16:11 ` Frederic Weisbecker
2018-01-21 17:50 ` Pavan Kondeti
2018-01-21 20:48 ` Frederic Weisbecker
2018-02-08 17:44 ` Sebastian Andrzej Siewior
2018-02-08 18:45 ` David Miller
2018-02-08 20:14 ` Dmitry Safonov
2018-02-08 20:22 ` David Miller
2018-02-08 20:30 ` Dmitry Safonov
2018-02-09 4:11 ` Mike Galbraith [this message]
2018-02-09 12:35 ` Sebastian Andrzej Siewior
2018-02-15 16:13 ` Frederic Weisbecker
2018-02-15 16:58 ` Sebastian Andrzej Siewior
2018-01-19 15:46 ` [RFC PATCH 3/4] softirq: Defer to workqueue when rescheduling is needed Frederic Weisbecker
2018-01-19 15:46 ` [RFC PATCH 4/4] softirq: Replace ksoftirqd with workqueues entirely Frederic Weisbecker
2018-01-22 19:58 ` [RFC PATCH 0/4] softirq: Per vector threading v3 Mauro Carvalho Chehab
2018-01-23 10:13 ` Paolo Abeni
2018-01-23 12:32 ` Dmitry Safonov
2018-01-24 2:12 ` Frederic Weisbecker
2018-01-23 16:22 ` David Miller
2018-01-23 16:57 ` Paolo Abeni
2018-01-23 17:42 ` Linus Torvalds
2018-01-23 18:01 ` Mike Galbraith
2018-01-23 18:24 ` David Miller
2018-01-24 1:57 ` Frederic Weisbecker
2018-01-24 2:01 ` Frederic Weisbecker
2018-01-24 14:54 ` Paolo Abeni
2018-01-24 15:05 ` David Miller
2018-01-24 16:11 ` Paolo Abeni
2018-02-07 14:18 ` Mauro Carvalho Chehab
2018-03-01 15:21 ` Frederic Weisbecker
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=1518149468.24350.40.camel@gmx.de \
--to=efault@gmx.de \
--cc=akpm@linux-foundation.org \
--cc=alexander.levin@verizon.com \
--cc=bigeasy@linutronix.de \
--cc=davem@davemloft.net \
--cc=dima@arista.com \
--cc=edumazet@google.com \
--cc=frederic@kernel.org \
--cc=hannes@stressinduktion.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mchehab@s-opensource.com \
--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;
as well as URLs for NNTP newsgroup(s).