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

[Sebastian Moeller]

Hi Brandon,


> On Mar 21, 2023, at 01:10, Brandon Butterworth via Rpm <rpm at lists.bufferbloat.net> wrote:
> 
> On Mon Mar 20, 2023 at 03:28:57PM -0600, dan via Starlink wrote:
>> I more or less agree with you Frantisek.   There are throughput numbers
>> that are need for current gen and next gen services, but those are often
>> met with 50-100Mbps plans today that are enough to handle multiple 4K
>> streams plus browsing and so forth
> 
> It is for now, question is how busy will it get and will that be before
> the next upgrade round.

	I agree these are rates that can work pretty well (assuming the upload is wide enough). This is also orthogonal to the point that both copper access networks, have already or a close to reaching their reasonable end of life, so replacing copper with fiber seems a good idea to future proof the access network. But once you do that you realize that actual traffic (at least for big ISPs that do not need to buy much transit and get cost neural peerings) is not that costly, so offering a 1 Gbps plan instead of a 100 Mbps is a no brainer, the customer is unlikely to actually source/sink that much more traffic and you might get a few pound/EUR/$ more out of essentially the same load.

> 
> This is why there's a push to sell gigabit in the UK.

	I think this also holds for the EU.

> 
> It gives newcomer altnets something the consumers can understand - big
> number - to market against the incumbents sweatng old assets
> with incremental upgrades that will become a problem. From my personal
> point of view (doing active ethernet) it seems pointless making
> equipment more expensive to enable lower speeds to be sold.


One additional reason for the "push for the gigabit" is political in nature. The national level of fiber deployment is taken as sort of digital trump game in which different countries want to look good, taking available capacity (and more so the giga-prefix) as proxy for digitalization and modernity. So if there are politic "mandates/desires" to have a high average capacity, then ISPs will follow that mandate, especially since that is basically an extension of the existing marketing anyways...


>> yet no one talks about latency and packet loss and other useful metrics

	Fun fact, I am currently diagnosing issues with my ISP regarding packet-loss, one of their gateways produces ~1% packet loss in the download direction independent of load, wrecking havoc with speedtest results (Not even BBR will tolerate 1% random loss without a noticeable throghuput hit) and hence resulting in months of customer complaints the ISP did not manage to root-cause and fix... Realistically the packetloss rate without load should be really close to 0


> Gamers get it and rate ISPs on it, nobody else cares. Part of the
> reason for throwing bandwith at the home is to ensure the hard to
> replace distribution and house drop is never the problem. Backhaul
> becomes the limit and they can upgrade that more easily when market
> pressure with speedtests show there is a problem.
> 
>> We need a marketing/lobby group.  Not wispa or other individual industry
>> groups, but one specifically for *ISPs that will contribute as well as
>> implement policies and put that out on social media etc etc.  i don't know
>> how we get there without a big player (ie Netflix, hulu..) contributing.
> 
> Peak time congestion through average stream speed reduction is faily obvious
> in playback stats. Any large platform has lots of data on which ISPs
> are performing well.
> 
> We can share stats with the ISPs and tell A that they are performing
> worse than B,C,D if there is a problem. I did want to publish it so
> the public could choose the best but legal were not comfortable
> with that.
> 
> brandon
> _______________________________________________
> Rpm mailing list
> Rpm at lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/rpm