Lucas Pardue

Agreed both are useful! I just think it helps to be upfront with the community that QUIC performance metrics don't directly infer real-world application mapping performance. Your proposal for "perf"...

HTTP header size limits are really a best effort hint, especially given the nature of HTTP intermediation and version translation. In a proxy chain, you've already had to advertise the...

Finished should fire if you've read all the data sent on the stream up until the Fin. Do you have a pcap or qlog of the case where you see...

Hmm, that does seem weird. Do you have any instructions for running this test setup that would allow us to try and repro?

I don't have many spare cycles to get anything complicated running, which is going to make investigating this hard. Maybe you can provide a curl trace log too just so...

I _think_ I might have emulated the sequence in https://github.com/cloudflare/quiche/pull/2278 but it would be great to see if curl client sees the same order of events.

Taking any automated action in response to a X_DATA_BLOCKED frame seems like a bad idea IMO. Thats an easy way to surprise users of the library and trigger DoS via...

> I am confused. Is FlowControl::autotune_window disabled on h3.speed.cloudflare.com? Or are you suggesting h3.speed.cloudflare.com should more agressively do auto tuning? Apologies, I misremembered how the flow control autotuning worked (I...

> I think this ratio (# STREAM / # BLOCKED) is misleading. E.g. say a client is blocked for 1 RTT, that would result in 1 STREAM_DATA_BLOCKED frame, but potentially...

Speaking as an individual: the opinion in https://github.com/httpwg/http-extensions/issues/3192#issue-3311909127 does not sufficiently reflect the variety of heterogenous networks that this document is designed for. For instance, a path with high throughput...