[Cake] diffserv3 vs diffserv4

[Jonathan Morton]

> On 25 Jul, 2020, at 10:35 pm, David P. Reed <dpreed at deepplum.com> wrote:
> 
> And to be clear, AQM (cake, being an example) is not about bandwidth allocation. It does focus on latency/queueing-delay, for the most part.

Cake is not *just* an AQM, though I understand your point.  It is a qdisc with many interwoven functions.

Cake's Diffserv support is neither a pure priority scheme nor a pure bandwidth allocation.  By using a hybrid of the two for bandwidth allocation, I was hoping to avoid the main pitfalls that the simple Bell-headed approaches routinely encounter.  Each tin also has its own AQM parameters, which feed into the distinction between high-throughput and low-latency classes of traffic.

There are doubtless other approaches that could be tried, of course.  And there might be endless debate over exactly how many traffic classes are actually needed; I don't think five is the right number, and the symmetry argument is not persuasive.  But can we at least agree that Cake's attempt is a step in the right direction?

 - Jonathan Morton