<html><head></head><body><div dir="auto">This is pretty impressive... and also is a decent counter against the common argument that at BNG/backbone information rates flow queuing would be completely infeasible... or it might show that big iron silicon is just inferior to general purpose CPUs</div><br><br><div class="gmail_quote"><div dir="auto">On 7 June 2024 04:28:18 CEST, Dave Taht via Starlink <starlink@lists.bufferbloat.net> wrote:</div><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">
<div dir="auto">I occasionally am happy to point out the 150+ isps now running libreqos and cake... the several hundred running preseem and paraqum and bequant...<div dir="auto"><br></div><div dir="auto">As a rule of thumb about 10k wisp subscribers eat around 25gbit. This we (libreqos anyway) can do easily on a 1500 dollar whitebox (and we have pushed it past 60gbit in the v1.5 release entering beta shortly). This is usually way more capability than any given isp network segment needs... </div><div dir="auto"><br></div><div dir="auto">The wisps have got fq codel available native in much of their gear too, and of course starlink on their wifi... </div><div dir="auto"><br></div><div dir="auto">There are probably 60k isps left to go though. There are isps still on docsis 3.0. I tend to regard these issues nowadays as being demand side as these solutions are so widely available now... </div><div dir="auto"><br></div><div dir="auto">But with billions being spent to just upgrade to fiber... a dark cloud ahead is above 50mbit most of the bloat moves to the wifi... and despite eero, openwrt, Google fiber etc that have been getting it right... sigh.</div><div dir="auto"><br></div><div dir="auto">A bright light at the moment there is all the wifi products coming out with a mt79 chip.</div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Thu, Jun 6, 2024, 10:51 AM Stuart Cheshire <<a href="mailto:cheshire@apple.com">cheshire@apple.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">On Jun 4, 2024, at 16:03, Rich Brown <<a href="mailto:richb.hanover@gmail.com" target="_blank" rel="noreferrer">richb.hanover@gmail.com</a>> wrote:<br>
<br>
> Yeah... I didn't write that as carefully as I could have. I was switching between "user voice" (who'll say 'speed') and "expert" voice (I know the difference). Check it now: <a href="https://randomneuronsfiring.com/all-the-reasons-that-bufferbloat-isnt-a-problem/" rel="noreferrer noreferrer" target="_blank">https://randomneuronsfiring.com/all-the-reasons-that-bufferbloat-isnt-a-problem/</a><br>
<br>
Thanks for doing that.<br>
<br>
How about also changing “new faster ISP plan” to “new bigger ISP plan”? I know that may sound like a slightly weird phrase, but getting people’s attention by surprising them a little can be beneficial. If it looks weird to them and that makes them pause and think, then that’s good.<br>
<br>
If the hypothetical ISP imagined here were actually willing to offer a plan that truly provided consistently *faster* connectivity instead of just more of the same, we’d be very happy. The truth today is that most IPs offer *bigger*, not *better*. They are selling quantity, not quality.<br>
<br>
(I am intentionally not lumping *all* ISPs into the same bucket here. Some, like Comcast, are actually making big efforts to improve quality as well as quantity. Comcast dramatically reduced the working latency of my cable modem during the work-from-home pandemic, and they continue to work on improving that even more. I want to be sure to give credit where it is deserved.)<br>
<br>
Stuart Cheshire<br>
<br>
</blockquote></div>
</blockquote></div><div dir="auto"><div class='k9mail-signature'>-- <br>Sent from my Android device with K-9 Mail. Please excuse my brevity.</div></div></body></html>