Re: [Cake] diffserv3 vs diffserv4

[Sebastian Moeller <moeller0@gmx.de>]

Hi Kevin,


> On Jul 25, 2020, at 12:12, Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk> wrote:
> 
> 
> 
>> On 24 Jul 2020, at 18:42, Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk> wrote:
>> 
>> 
>> The move from diffserv4 to diffserv5 WAS about de-prioritization.
> 
> It was also about minimum bandwidth allocations:
> 
> LE: 1/64th

That is 6 binary orders of magnitude, on a slow link, LE is effectively starved and there will be no real forward progress. For real scavenger services this might well be a sane policy, but this requires the very selective with assigning flows to this tin ;)

> BK: 1/16th
> BE: 1/1
> VI: 1/2
> VO: 1/4

So I see 1/64 + 1/16 + 1/1 + 1/2 + 1/4 = 1.828125 which seems excessive for actually guaranteed minimums. I was under the naive? impression the minima should add up to <= 1, no?


> 
> So worst case, best effort should get 11/64ths in the extreme case of all other tins in use.

	This seems only true, if on overload the lowest prioritiers tiers get their allotment first, no?

I am confused... but I am also confused by cake's output:
"

                   Bulk  Best Effort        Voice
  thresh       3062Kbit       49Mbit    12250Kbit"

as far as I can tell, Bulk's 3062Kbit must be the minimum, while BE and Voice give their maxima... That, or I am missing something important...
(I wonder whether it would not be clearer to give both min and max for each tin, then again I probably missing all the deyails of the actual implementation...)

Best Regards
	Sebastian

> 
> Cheers,
> 
> Kevin D-B
> 
> gpg: 012C ACB2 28C6 C53E 9775  9123 B3A2 389B 9DE2 334A
> 
> _______________________________________________
> Cake mailing list
> Cake@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/cake