[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <aRIRR0hWpd5PKUGk@slm.duckdns.org>
Date: Mon, 10 Nov 2025 06:22:31 -1000
From: Tejun Heo <tj@...nel.org>
To: Andrea Righi <arighi@...dia.com>
Cc: David Vernet <void@...ifault.com>, Changwoo Min <changwoo@...lia.com>,
Dan Schatzberg <schatzberg.dan@...il.com>,
Emil Tsalapatis <etsal@...a.com>, sched-ext@...ts.linux.dev,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH 02/13] sched_ext: Make slice values tunable and use
shorter slice in bypass mode
On Mon, Nov 10, 2025 at 06:21:10AM -1000, Tejun Heo wrote:
> Hello,
>
> On Mon, Nov 10, 2025 at 08:03:37AM +0100, Andrea Righi wrote:
> > I agree that slice_bypass_us can be a tunable in sysfs, but I think it'd be
> > nicer if the default time slice would be a property of sched_ext_ops, is
> > there any reason to not do that?
>
> My thinking was that a scheduler should always be able to avoid using the
> default slice. Even if we allow the default slice to be overridden by the
> scheduler, it's still very crude as it will apply the same slice to all
> tasks. I'm not necessarily against moving it into ops but a bit unsure how
> useful it is.
Hmm... for now, let me drop slice_dfl knob from this patch. We can address
this separately.
Thanks.
--
tejun
Powered by blists - more mailing lists