[tsvwg] draft-white-tsvwg-nqb-02#page-7 correctness issue

[Sebastian Moeller <[e-mail]>]

https://datatracker.ietf.org/doc/html/draft-white-tsvwg-nqb-02#page-7 states about fq_codel:
"In effect, the network element is
   making a decision as to what constitutes a flow, and then forcing all
   such flows to take equal bandwidth at every instant."

That seems simply incorrect. Only flows with queued up packets will be served equally, flows with lower rates will a) only be served up to that rate, and b) the reminder to their "fair-share of the capacity" will be equitably shared among all flows with higher rates.
I wonder why the NQB draft needs such along section about "Comparison to Existing Approaches" at all, but if it carries such a section I would prefer that section to be factual correct.

"The Dual-queue approach defined in this document achieves the main
   benefit of fq_codel: latency improvement without value judgements,
   without the downsides."

That also seems counterfactual, as NQB works exactly by looking at the value of the DSCP and hence makes a value judgement, while fq_codel looks at the behavior of flows (dynamically in relation to available capacity).


Best Regards
	Sebastian