Re: [PATCH 1/2] sched/deadline: accurate reclaim bandwidth for GRUB

[luca abeni]

On Tue, 9 May 2023 22:48:29 +0200
luca abeni <luca.abeni@xxxxxxxxxxxxxxx> wrote:

> Hi,
> 
> On Tue, 9 May 2023 15:29:21 -0400
> Vineeth Remanan Pillai <vineeth@xxxxxxxxxxxxxxx> wrote:
> [...]
> > > Is this understanding correct?    
> > Yes, the above two details are correct. In addition to that, I think
> > the existing equation had a small bug:
> > GRUB paper says, running time is depreciated as
> >    "dq = -U dt" where U is running_bw.
> > This is assuming that the whole cpu bandwidth could be reclaimed.
> > But in our case, we cap at Umax. So the equation should be
> >    "dq = -(U/Umax) dt"  
> 
> Yes, this is the approximation I was mentioning... Instead of using a
> division, I approximated it with a different equation using a sum.

Sorry, ignore this comment (and the following); I misinterpreted the
code (and my old notes).

I do not understand why the "max{}" doe not work well, I need to double
think about it.


			Luca