Re: [PATCH] softirq: let the userside tune the SOFTIRQ_NOW_MASK with sysctl

[Jason Xing]

On Tue, May 9, 2023 at 9:05 PM Thomas Gleixner <tglx@xxxxxxxxxxxxx> wrote:
>
> On Mon, Apr 10 2023 at 10:30, Jason Xing wrote:
> > From: Jason Xing <kernelxing@xxxxxxxxxxx>
> >
> > Currently we have two exceptions which could avoid ksoftirqd when
> > invoking softirqs: HI_SOFTIRQ and TASKLET_SOFTIRQ. They were introduced
> > in the commit 3c53776e29f8 ("Mark HI and TASKLET softirq synchronous")
> > which says if we don't mask them, it will cause excessive latencies in
> > some cases.
>
> As we are ripping this out, I'll ignore this patch.

Sure, please ignore this heuristic patch. Paolo and I have already
tested that revert patch in the production environment before and
verified its usefulness, please take that one if you could.

Thanks,
Jason