<div dir="ltr">Godspeed for your next project, Dave.<br></div><br><div class="gmail_quote"><div dir="ltr">On Fri, Aug 24, 2018 at 10:11 PM Dave Taht <<a href="mailto:dave.taht@gmail.com">dave.taht@gmail.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">All:<br>
<br>
It is with some regret that I am announcing the closing of my<br>
make-wifi-fast lab at the end of this month.<br>
<br>
Over the years we have relied on the donation of lab space from<br>
ISC.org, georgia tech, the LINCs, and the University of Karstadt and<br>
elsewhere - but my main base of operation has always been the<br>
"yurtlab", in a campground deep in the los gatos hills where I could<br>
both experiment and deploy wifi fixes[0] at scale. CeroWrt, in<br>
particular, was made here.<br>
<br>
During the peak of the make-wifi-fast effort I rented additional space<br>
on the same site, which at peak had over 30 routers in a crowded<br>
space, competing. Which I (foolishly) kept, despite the additional<br>
expense. Having heat in the winter and aircond in the summer was<br>
helpful.<br>
<br>
With ongoing donations running at $90/month[1] - which doesn't even<br>
cover <a href="http://bufferbloat.net" rel="noreferrer" target="_blank">bufferbloat.net</a>'s servers in the cloud - my biggest expense has<br>
been keeping the lab at lupin open at $1800/mo.<br>
<br>
I kept the lab going through the sch_cake and openwrt 18.06 release<br>
process, and I'm now several months behind on rent[3], and given how<br>
things have gone for the past 2 years I don't see much use for it in<br>
the future. Keeping it open, heated and dry in the winter has always<br>
been a problem also. I'm also aware of a few larger, much better<br>
equipped wifi labs that have thoroughly tested our "fq_codel for<br>
wifi"[4] work that finally ends the "wifi performance anomaly". it's<br>
in multiple commercial products now, we're seeing airtime fairness<br>
being actually *marketed* as a wifi feature, and I kind of expect<br>
deployment be universal across all mediatek mt76, and qualcomm ath9k<br>
and ath10k based products in the next year or two. We won, big, on<br>
wifi. Knocked it out of the park. Thanks all!<br>
<br>
Despite identifying all kinds of other work[5] that can be done to<br>
make wifi better, no major (or even minor) direct sponsor has ever<br>
emerged[2] for the make-wifi-fast project. We had a small grant from<br>
comcast, a bit of support from nlnet also, I subsidized what I did<br>
here from other work sources, toke had his PHD support, and all the<br>
wonderful volunteers here... and that's it.<br>
<br>
Without me being able, also, to hire someone to keep the lab going, as<br>
I freely admit to burnout and PTSD on perpetually reflashing and<br>
reconfiguring routers...<br>
<br>
I'm closing up shop here to gather enough energy, finances, and time<br>
for the next project, whatever it is.<br>
<br>
The make-wifi-fast mailing list and project will continue, efforts to<br>
make more generic the new API also, and hopefully there's enough users<br>
out there to<br>
keep it all going forward without the kind of comprehensive testing I<br>
used to do here.<br>
<br>
If anyone feels like reflashing, oh, 30 bricked routers of 8 different<br>
models, from serial ports (in multiple cases, like the 6 uap-ac-lites,<br>
via soldiering on headers), I'll gladly toss all the extra equipment<br>
in the lab in a big box and ship them to you. Suggestions for a<br>
suitable donation target are also of interest.<br>
<br>
The yurtlab has been an amazing, totally unique, unusual (and<br>
sometimes embarrassing [6]) place to work and think, but it's time to<br>
go.<br>
<br>
Perhaps I'll convince my amazingly supportive landlord to let me leave<br>
behind a plaque:<br>
<br>
"On this spot bufferbloat on the internet and in WiFi was fixed, 2011-2018".<br>
<br>
Sincerely,<br>
Dave Taht<br>
<br>
[0] <a href="https://lwn.net/Articles/705884/" rel="noreferrer" target="_blank">https://lwn.net/Articles/705884/</a> "How we made wifi fast again"<br>
[1] <a href="https://www.patreon.com/dtaht" rel="noreferrer" target="_blank">https://www.patreon.com/dtaht</a><br>
[2] Like adrian chadd's infamous flameout - I too, give up on wifi.<br>
There's gotta be some other tech worth working on. What we shipped is<br>
"good enough" to carry a few years though.<br>
[3] This is not a passive-aggressive request for help making rent next<br>
month, given all the other problems I have, it's best to close up shop<br>
while I look for a new gig.<br>
[4] <a href="https://arxiv.org/pdf/1703.00064.pdf" rel="noreferrer" target="_blank">https://arxiv.org/pdf/1703.00064.pdf</a> "ending the wifi anomaly"<br>
[5] <a href="https://docs.google.com/document/d/1Se36svYE1Uzpppe1HWnEyat_sAGghB3kE285LElJBW4/edit#" rel="noreferrer" target="_blank">https://docs.google.com/document/d/1Se36svYE1Uzpppe1HWnEyat_sAGghB3kE285LElJBW4/edit#</a><br>
[6] <a href="https://www.cringely.com/2012/10/01/clothing-may-be-optional-but-bufferbloat-isnt/" rel="noreferrer" target="_blank">https://www.cringely.com/2012/10/01/clothing-may-be-optional-but-bufferbloat-isnt/</a><br>
_______________________________________________<br>
Bloat mailing list<br>
<a href="mailto:Bloat@lists.bufferbloat.net" target="_blank">Bloat@lists.bufferbloat.net</a><br>
<a href="https://lists.bufferbloat.net/listinfo/bloat" rel="noreferrer" target="_blank">https://lists.bufferbloat.net/listinfo/bloat</a><br>
</blockquote></div>