Re: [PATCH] hrtimer: Update softirq_expires_next correctly after __hrtimer_get_next_event()

[Greg KH]

On Wed, Apr 21, 2021 at 11:40:54PM +0900, Lorenzo Colitti wrote:
> On Wed, Apr 21, 2021 at 11:08 PM Lorenzo Colitti <lorenzo@xxxxxxxxxx> wrote:
> > load the timer will almost never fire since there will always be
> > another packet coming. So the speed of adding/updating the timer is
> > much more important than the accuracy. We will try to move it to
> > timer_list.
> 
> ... but actually, that's not acceptable, because AFAICS timer_list
> counts in jiffies so its resolution might be as low as 10ms. It's not
> acceptable to delay network traffic by up to 10ms under load. Not sure
> if there is another timer API that can be used here.

What do other network drivers do?  This has to be a common problem, why
is this USB driver somehow unique here?

thanks,

greg k-h