Sec 5.9

[larseggert]

Markku Kojo said:

Sec 5.9

The statement made here is not convincing and is likely to be incorrect. E.g., CUBIC with larger decrease factor would most likely release capacity notably slower than AIMD TCP if there is sudden congestion.

[bbriscoe]

I agree with Markku that the claim in the draft seems incorrect. Even with fast convergence, each reduction is a little less than Reno. It just needs to admit the difference, rather than saying there is no difference.

[larseggert]

@bbriscoe @markkukojo: would one of you want to propose a PR?

[larseggert]

Or @lisongxu, since he self-assigned this issue?

[goelvidhi]

Is it better to just remove congestion from this statement? We already covered congestion events in the rest of the draft.
Suggestion,

If there is a sudden routing change or a mobility event, CUBIC behaves the same as AIMD TCP.

[lisongxu]

Fine with me. Thank, @goelvidhi

[bbriscoe]

A section on sudden and transient events is meant to discuss
transient events such as sudden congestion, a routing change, or a mobility event.
These are all still about congestion (after all its a congestion control algorithm), so it cannot not discuss congestion. The difference here is the suddenness.

I'll post a PR, as Lars suggests, and see what you think. I'll briefly the difference after a sudden increase and a sudden decrease in capacity, relative to Reno.