Re Berninger v. FCC: Cert petition filed with Supreme Court today

["Dave Farber" <farber () gmail com>]

Begin forwarded message:

> From: Dave Taht <dave.taht () gmail com>
> Date: October 2, 2017 at 12:50:40 AM EDT
> To: Dave Farber <dave () farber net>
> Cc: brett () lariat net, dcrocker () gmail com, ip <ip () listbox com>
> Subject: Re: [IP] Re Berninger v. FCC: Cert petition filed with Supreme Court today
>
> I should really stay out of this one, but one point got made along the way that bugs me, in that the current 
> workaround to all forms of wireless's interference and contention issues is often an extreme amount of bufferbloat 
> (seconds), which makes it behave much, much worse than wired.
>
> The core algorithms to fix that (codel, pie, fq_codel, fq_pie, cake) are either ietf standards or approaching them, 
> with readily available implementations on linux and bsd...
>
> And, last year, we landed a rather major fix for typical 802.11n latency, capacity, and jitter basd on fq_codel: 
>
> https://www.usenix.org/system/files/conference/atc17/atc17-hoiland-jorgensen.pdf
>
> which is basically proven and deployed in linux 4.11 (for, sadly, only three chipsets) 
>
> It would be nice if those 3000+ WISPs' vendors and the LTE providers *ran* to adopt these various forms of smart 
> queue management (SQM), cause it would make wireless behave much closer to wired under more circumstances.
>
> -- 
>
> Dave Täht
> CEO, TekLibre, LLC
> http://www.teklibre.com



-------------------------------------------
Archives: https://www.listbox.com/member/archive/247/=now
RSS Feed: https://www.listbox.com/member/archive/rss/247/18849915-ae8fa580
Modify Your Subscription: https://www.listbox.com/member/?member_id=18849915&id_secret=18849915-aa268125
Unsubscribe Now: 
https://www.listbox.com/unsubscribe/?member_id=18849915&id_secret=18849915-32545cb4&post_id=20171002210437:D1822EDE-A7D6-11E7-8136-B4795845A003
Powered by Listbox: http://www.listbox.com