Re: [NNagain] FCC NOI due dec 1 on broadband speed standards

[Dave Taht <dave.taht@gmail.com>]

[-- Attachment #1.1: Type: text/plain, Size: 3034 bytes --]

On Tue, Nov 14, 2023 at 11:06 AM Dave Taht <dave.taht@gmail.com> wrote:

> As I noted also on the twitter thread for this, were I there, and
> dishonest, (particularly were gobs of money on the table) I could easily
> have permuted the bandwidth on both tests hugely upwards from a single
> laptop by running continuous speedtests. But speedtests are not what we do
> day in or out, and reflect normal usage not at all.
>
> The 83% of people (experts!!!) that were wrong is ... mindboggling.
>
> PS What wifi standard was at ietf? Is this still the old ciscos? The
> headline bandwidths claimed for any version of wifi drop dramatically at
> distance and with multiple users present.  So it might have taken a couple
> laptops out of the thousand there to move the stats in a perverse
> direction, now that I think about it.
>
> Thank you for doing this experiment! While there are certainly also cases
> were mass groupings of people totally saturate the underlying mac (more
> than the perceived bandwidth - I have seen congestion collapse and a sea of
> retransmits even in small wifi gatherings), the only number that seems a
> bit off  in your test from a typical residential/small office is the
> roughly 3.5x1 ratio between down and up. I am willing (for now) to put that
> down to engineers doing actual work, rather than netflix.
>

CORRECTION! 3x1. my fingers wanted it to be 5x1 (which is quite common in
many deployments), and then decided on their own to create 3.5x1... While
there is no ideal up/down ratio I firmly believe that 5x1 should be the
outside asymmetry, and there are compelling reasons.

I would be perfectly happy with a 10/10 connection (with bufferbloat
fixed), if only there was a way to pay for just that.


> I would so love to see more measurements like this at other wifi
> concentration points, in offices and coffee shops. Packet captures too!!!!
>
> On Tue, Nov 14, 2023 at 10:46 AM Livingood, Jason via Nnagain <
> nnagain@lists.bufferbloat.net> wrote:
>
>> On the subject of how much bandwidth does one household need, here's a
>> fun stat for you.
>>
>>
>>
>> At the IETF’s 118th meeting <https://www.ietf.org/how/meetings/118/> last
>> week (Nov 4 – 10, 2023), there were over 1,000 engineers in attendance. At
>> peak there were 870 devices connected to the WiFi network. Peak bandwidth
>> usage:
>>
>>    - Downstream peak ~750 Mbps
>>    - Upstream ~250 Mbps
>>
>>
>>
>> From my pre-meeting Twitter poll (
>> https://twitter.com/jlivingood/status/1720060429311901873):
>>
>> [image: A screenshot of a chat Description automatically generated]
>> _______________________________________________
>> Nnagain mailing list
>> Nnagain@lists.bufferbloat.net
>> https://lists.bufferbloat.net/listinfo/nnagain
>>
>
>
> --
> :( My old R&D campus is up for sale: https://tinyurl.com/yurtlab
> Dave Täht CSO, LibreQos
>


-- 
:( My old R&D campus is up for sale: https://tinyurl.com/yurtlab
Dave Täht CSO, LibreQos

[-- Attachment #1.2: Type: text/html, Size: 5512 bytes --]

[-- Attachment #2: image001.png --]
[-- Type: image/png, Size: 119956 bytes --]