[Bloat] [Starlink] [Rpm] [LibreQoS] On FiWi

[Brandon Butterworth]

On Mon Mar 20, 2023 at 10:21:10PM -0700, Frantisek Borsik wrote:
> Even at Friday evening Netflix time, there?s hardly more than 25/5 Mbps
> consumed.

Today. Today has never been a good target when planning builds that
need to last the next decade. Fibre affords us the luxury of sufficient
capacity to reduce the infrastructure churn where we choose to.

> Also, the real improvements that will be really felt by the people are on
> the bufferbloat front (enterprise as well as residential)

That's a separate matter and needs addressing whatever the delivery
technology and speed.

> If there?s just single one talk that everyone should watch from that
> Understanding Latency webinar series I have shared, it?s this one, with
> Gino Dion (Nokia Bell Labs), Magnus Olden (Domos - Latency Management) and
> Angus Laurie-Pile (GameBench):
> https://m.youtube.com/watch?v=MRmcWyIVXvg&t=1358s
> It?s all about the 1-25Gbps misconception, what we did to put it out there
> as techies, and what can be done to show the customers to change that?40
> minutes, but it?s WORTHWHILE.

TL;DL

I got "how can we monetise latency", says it all, nothing gets fixed
without a premium and the way they were talking that means most do
not get the fix as it becomes an incentive to increase latency to force
more payment. The speed is immaterial in that.

> Now, I hope to really piss You off with the following statement  :-P but:
> 
> even sub 5/1 Mbps ?broadband? in Africa with bufferbloat fixed on as many
> hops along the internet journey from a data center to the customers mobile
> device (or with just LibreQoS middle box in the ISP?s network) is feeling
> way better than 25Gbps XG-PON. The only time the XG-PON guy could really
> feel like a king of the world would be during his speedtest.

So? Some companies will find ways to do things badly regardless, others
make best of what they have. Nothing to get annoyed at nor an argument
to not build faster networks.

I think I may mave missed your point. What are you suggesting, we don't
build faster networks? A new (faster) network build is a great opportunity
to fix bufferbloat.

brandon