Re:Re: [PATCH,RESEND] softirq: Introduce SOFTIRQ_FORCED_THREADING

[Thomas Gleixner]

Qing,

On Sat, Aug 28 2021 at 10:18, 王擎 wrote:
>> On Mon, Aug 23 2021 at 11:33, Wang Qing wrote:
>> What you are proposing here is completly different as you enforce
>> softirq execution in context of ksoftirqd only.
>
> Thank you for reply and explanation, I just provide a choice to balance
> the execution of softirq according to their own business scenarios.

That's not a choice. Forced interrupt threading is a boot-time option
and not a compile time boolean. So with your change you even changed the
behaviour of the kernel when your magic config switch is not selected by
the user.

>> What are you referring to? PREEMPT_RT does not modify the priority of
>> ksoftirqd. If system designers want to do that, then they can do so from
>> user space. 
>
> I refer to the kernel-3.14 RT Patches. I used it at that time and achieved 
> very good results.

There is a reason why RT does not use this anymore and switched to a
different model. As I said before. Just because it works for you, it's
not necessarily a solution which should be exposed for general
consumption.

> I remember where I saw that softirqd was split into the original process 
> and the RT process. This can partially solve my problem.

Your patch has absolutely nothing to do with that. You just picked some
random part out of those 7+ years old patches and then claim that it's
something RT does, which is just not true.

Thanks,

        tglx