Messages in this thread | | | Date | Thu, 11 May 2023 22:03:36 +0200 | From | luca abeni <> | Subject | Re: [PATCH 1/2] sched/deadline: accurate reclaim bandwidth for GRUB |
| |
Hi,
first of all, thanks for your patience with my comments :)
On Thu, 11 May 2023 14:34:38 -0400 Vineeth Remanan Pillai <vineeth@bitbyteword.org> wrote: [...] > SMP GRUB paper has the equation for depreciating runtime as: > dq_i = -max{u_i, 1 - (extra_bw + Uinact)} dt > > Since we are caping at Umax, the equation would be > dq_i = -(max{u_i, Umax - (extra_bw + Uinact)} / Umax) dt (1) > > But existing implementation is: > dq_i = -max{u_i/Umax, 1 - (extra_bw + Uinact)} dt (2) > > Here in (2), we factored Umax only to the first term "u_i" and the > second term in max{} was as left as it is. What do you think?
I agree with you, (1) looks more correct. I do not know why I implemented (2), but I agree with (1) now.
> Now with normal DL and SCHED_FLAG_RECLAIM tasks, equation (1) can be > re-written as: > dq_i = > -(max{u_i, Ureclaim_max - (extra_bw + Uinact)}/Ureclaim_max)dt (3) > > I tested this equation (3) and it works as expected. What do you think > about the correctness of equation (3)?
I agree with this too.
> > I felt that, since we are using sequential reclaim mentioned in the > paper and we isolate all parameters per-cpu(except for extra_bw) we > could use the "-dq = -(U/Umax) dt" equation as it was simpler than > equation (3).
This is the part I am not sure about...
Maybe the best way to go is to split the patch: first you implement (1) (and use div64 to remove the approximation I used), then you implement (3) in a second patch.
Finally, if removing the max{} is really needed you can do it in a third patch (but I would try to go with Equation 3 before removing the max{})
Thanks, Luca
| |