Re: [RFC][PATCH 1/2] sched: Avoid placing RT threads on cores handling long softirqs

[John Stultz]

On Wed, Aug 10, 2022 at 7:11 PM Randy Dunlap <rdunlap@xxxxxxxxxxxxx> wrote:
>
>
>
> On 8/10/22 18:57, John Stultz wrote:
> > diff --git a/init/Kconfig b/init/Kconfig
> > index c7900e8975f1..b0dde2771314 100644
> > --- a/init/Kconfig
> > +++ b/init/Kconfig
> > @@ -1278,6 +1278,17 @@ config SCHED_AUTOGROUP
> >         desktop applications.  Task group autogeneration is currently based
> >         upon task session.
> >
> > +config RT_SOFTIRQ_OPTIMIZATION
> > +       bool "Improve RT scheduling during long softirq execution"
> > +       depends on ARM64
> > +       depends on SMP
> > +       default n
> > +       help
> > +         Enable an optimization which tries to avoid placing RT tasks on CPUs
>
> Above line is indented with spaces only. :(
>
> > +      occupied by nonpreemptible tasks, such as a long softirq or CPUs
> > +      which may soon block preemptions, such as a CPU running a ksoftirq
> > +      thread which handles slow softirqs.
>
> All help text lines should be indented with one tab + 2 spaces,
> per Documentation/process/coding-style.rst.
> (The 3 lines above have one tab + one space.)

My apologies! I didn't notice (and checkpatch --strict didn't seem to complain).

I'll fix it up for the next revision.

Thanks for the quick feedback!
-john