[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1518120895.2849.14.camel@arista.com>
Date: Thu, 08 Feb 2018 20:14:55 +0000
From: Dmitry Safonov <dima@...sta.com>
To: David Miller <davem@...emloft.net>, bigeasy@...utronix.de
Cc: frederic@...nel.org, linux-kernel@...r.kernel.org,
alexander.levin@...izon.com, peterz@...radead.org,
mchehab@...pensource.com, torvalds@...ux-foundation.org,
hannes@...essinduktion.org, paulmck@...ux.vnet.ibm.com,
wanpeng.li@...mail.com, tglx@...utronix.de,
akpm@...ux-foundation.org, pabeni@...hat.com, rrendec@...sta.com,
mingo@...nel.org, sgruszka@...hat.com, riel@...hat.com,
edumazet@...gle.com
Subject: Re: [RFC PATCH 2/4] softirq: Per vector deferment to workqueue
On Thu, 2018-02-08 at 13:45 -0500, David Miller wrote:
> From: Sebastian Andrzej Siewior <bigeasy@...utronix.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.
--
Thanks,
Dmitry
Powered by blists - more mailing lists