From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtp121.iad3a.emailsrvr.com (smtp121.iad3a.emailsrvr.com [173.203.187.121]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by huchra.bufferbloat.net (Postfix) with ESMTPS id 157FF21F1B0 for ; Sat, 19 Apr 2014 11:16:38 -0700 (PDT) Received: from localhost (localhost.localdomain [127.0.0.1]) by smtp32.relay.iad3a.emailsrvr.com (SMTP Server) with ESMTP id 31CCD70090; Sat, 19 Apr 2014 14:16:35 -0400 (EDT) X-Virus-Scanned: OK Received: from app25.wa-webapps.iad3a (relay.iad3a.rsapps.net [172.27.255.110]) by smtp32.relay.iad3a.emailsrvr.com (SMTP Server) with ESMTP id 146B170089; Sat, 19 Apr 2014 14:16:35 -0400 (EDT) Received: from reed.com (localhost.localdomain [127.0.0.1]) by app25.wa-webapps.iad3a (Postfix) with ESMTP id 04EAC180042; Sat, 19 Apr 2014 14:16:35 -0400 (EDT) Received: by apps.rackspace.com (Authenticated sender: dpreed@reed.com, from: dpreed@reed.com) with HTTP; Sat, 19 Apr 2014 14:16:35 -0400 (EDT) Date: Sat, 19 Apr 2014 14:16:35 -0400 (EDT) From: dpreed@reed.com To: "Dave Taht" MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="----=_20140419141635000000_42074" Importance: Normal X-Priority: 3 (Normal) X-Type: html In-Reply-To: References: <1397924468.489728228@apps.rackspace.com> Message-ID: <1397931395.018720381@apps.rackspace.com> X-Mailer: webmail7.0 Cc: cerowrt-devel Subject: Re: [Cerowrt-devel] =?utf-8?q?comcast_provisioned_rates=3F?= X-BeenThere: cerowrt-devel@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: Development issues regarding the cerowrt test router project List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 19 Apr 2014 18:16:38 -0000 ------=_20140419141635000000_42074 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable =0AVery good. So the idea, rather than Comcast implementing codel or some= thing proper in the DOCSIS 3.0 systems they have in the field, is to emulat= e power boost to "impedance match" the add-on router-based codel approach t= o some kind of knowledge of what the DOCSIS CMTS buffering state looks like= ....=0A =0AAnd of course nothing can be done about "downstream" bufferbloat= in the Comcast DOCSIS deployment.=0A =0ASo instead of fixing Comcast's stu= ff "correctly", we end up with a literal "half measure".=0A =0AWho does Com= cast buy its CMTS gear from, and if it has a Heartbleed bug, maybe some ben= evolent hacker should just fix it for them?=0A =0AIt's now been 2 years sin= ce Comcast said they were deploying a fix. Was that just them hoping the c= ritics would dissipate their time and effort? And is Comcast still using = its Sandvine DPI gear?=0A =0AI'm afraid that monopolists really don't care.= Even friendly-sounding ones. Especially when they can use their technica= l non-deployments to get paid more by Netflix.=0A=0AOn Saturday, April 19, = 2014 1:57pm, "Dave Taht" said:=0A=0A=0A=0A> The featu= res of the PowerBoost feature are well documented at this=0A> point. A prop= er=0A> emulation of them is in the ns2 code. It has been a persistent featu= re=0A> request, to=0A> add support to some Linux rate shaper to properly em= ulate PowerBoost,=0A> but no funding=0A> ever arrived.=0A> =0A> Basically = you get 10 extra megabytes above the base rate at whatever=0A> rate the lin= e=0A> can sustain before it settles back to the base rate.=0A> =0A> You can= also see that as presently implemented, at least on a short=0A> RTT path, = the feature=0A> does not prevent bufferbloat.=0A> =0A> http://snapon.lab.bu= fferbloat.net/~cero2/jimreisert/results.html=0A> =0A> I'd like a faster, le= ss cpu intense rate shaper than sch_htb in=0A> general, and powerboost emul= ation would be nice.=0A> =0A> =0A> On Sat, Apr 19, 2014 at 9:38 AM, Aaron W= ood wrote:=0A> > Based on these results:=0A> >=0A> > ht= tp://snapon.lab.bufferbloat.net/~cero2/jimreisert/results.html=0A> >=0A> > = And talking off-list with Jim, I think that the "PowerBoost" is above the= =0A> > quoted rate, as the 24/4 service hits >36Mbps TCP data rate. I'm=0A= > definitely=0A> > sad that using SQM in the router instead of the modem lo= ses features like=0A> > that. But I'll just be happy to have upload over 1= Mbps again.=0A> >=0A> > I do know that the FCC was cracking down on adverti= sed vs. actual rates, and=0A> > started a "measuring broadband in America" = project:=0A> >=0A> > http://www.fcc.gov/measuring-broadband-america=0A> >= =0A> > -Aaron=0A> >=0A> >=0A> > On Sat, Apr 19, 2014 at 6:21 PM, wrote:=0A> >>=0A> >> As a non-Comcast-customer, I am curious too. = I had thought their=0A> "boost"=0A> >> feature allowed temporary rates *lar= ger* than the quoted "up to" rates.=0A> >> (but I remember the old TV-diago= nal games and disk capacity games, where=0A> any=0A> >> way to get a larger= number was used in the advertising, since the FTC=0A> didn't=0A> >> have a= definition that could be applied).=0A> >>=0A> >>=0A> >>=0A> >> I wonder if= some enterprising lawyer might bring the necessary consumer=0A> >> fraud c= lass-action before the FTC to get clear definitions of the=0A> numbers?=0A>= >> It's probably too much to ask for Comcast to go on the record with a=0A= > precise=0A> >> definition.=0A> >>=0A> >>=0A> >>=0A> >>=0A> >>=0A> >> On S= aturday, April 19, 2014 8:55am, "Aaron Wood"=0A> said:= =0A> >>=0A> >> I'm setting up new service in the US, and I'm currently assu= ming that=0A> all=0A> >> of Comcast's rates are "boosted" rates, not the "p= rovisioned" rates.=0A> >> So if they quote 50/10Mbps, I assume that's not w= hat will need to be set=0A> >> in SQM with CeroWRT.=0A> >> Does anyone have= good info on the "provisioned" rates that go with each=0A> of=0A> >> the C= omcast tiers?=0A> >> Basically, I'm trying to get to an apples-to-apples co= mparison with=0A> >> Sonic.net DSL (I'll be close enough to the CO to run i= n Annex M "upload=0A> >> priority" mode and get ~18/2 service).=0A> >> Than= ks,=0A> >> Aaron=0A> >=0A> >=0A> >=0A> > __________________________________= _____________=0A> > Cerowrt-devel mailing list=0A> > Cerowrt-devel@lists.bu= fferbloat.net=0A> > https://lists.bufferbloat.net/listinfo/cerowrt-devel=0A= > >=0A> =0A> =0A> =0A> --=0A> Dave T=C3=A4ht=0A> =0A> NSFW:=0A> https://w2.= eff.org/Censorship/Internet_censorship_bills/russell_0296_indecent.article= =0A> ------=_20140419141635000000_42074 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable

Very good.=   So the idea, rather than Comcast implementing codel or something pr= oper in the DOCSIS 3.0 systems they have in the field, is to emulate power = boost to "impedance match" the add-on router-based codel approach to some k= ind of knowledge of what the DOCSIS CMTS buffering state looks like....

= =0A

 

=0A

And of course nothing can be done about "downstream" bufferbloat in = the Comcast DOCSIS deployment.

=0A

 = ;

=0A

So instead of fixing Comcast's stu= ff "correctly", we end up with a literal "half measure".

=0A

 

=0A

Who does= Comcast buy its CMTS gear from, and if it has a Heartbleed bug, maybe some= benevolent hacker should just fix it for them?

=0A

 

=0A=0A

It's now been 2 years sin= ce Comcast said they were deploying a fix.  Was that just them hoping = the critics would dissipate their time and effort?   And is Comcast st= ill using its Sandvine DPI gear?

=0A

&nb= sp;

=0A

I'm afraid that monopolists real= ly don't care.  Even friendly-sounding ones.  Especially when the= y can use their technical non-deployments to get paid more by Netflix.

On Saturday, April 19, 2014 1:57pm, "Dave Taht" <dave.taht@gmail.= com> said:

=0A
=0A

> The features of the PowerBoost feature are w= ell documented at this
> point. A proper
> emulation of the= m is in the ns2 code. It has been a persistent feature
> request, t= o
> add support to some Linux rate shaper to properly emulate Power= Boost,
> but no funding
> ever arrived.
>
>= ; Basically you get 10 extra megabytes above the base rate at whatever
> rate the line
> can sustain before it settles back to the ba= se rate.
>
> You can also see that as presently implemente= d, at least on a short
> RTT path, the feature
> does not p= revent bufferbloat.
>
> http://snapon.lab.bufferbloat.net/= ~cero2/jimreisert/results.html
>
> I'd like a faster, less= cpu intense rate shaper than sch_htb in
> general, and powerboost = emulation would be nice.
>
>
> On Sat, Apr 19, 20= 14 at 9:38 AM, Aaron Wood <woody77@gmail.com> wrote:
> > B= ased on these results:
> >
> > http://snapon.lab.buff= erbloat.net/~cero2/jimreisert/results.html
> >
> > An= d talking off-list with Jim, I think that the "PowerBoost" is above the
> > quoted rate, as the 24/4 service hits >36Mbps TCP data rate.= I'm
> definitely
> > sad that using SQM in the router = instead of the modem loses features like
> > that. But I'll jus= t be happy to have upload over 1Mbps again.
> >
> > I= do know that the FCC was cracking down on advertised vs. actual rates, and=
> > started a "measuring broadband in America" project:
&g= t; >
> > http://www.fcc.gov/measuring-broadband-america
= > >
> > -Aaron
> >
> >
> >= ; On Sat, Apr 19, 2014 at 6:21 PM, <dpreed@reed.com> wrote:
>= >>
> >> As a non-Comcast-customer, I am curious too. = I had thought their
> "boost"
> >> feature allowed te= mporary rates *larger* than the quoted "up to" rates.
> >> (b= ut I remember the old TV-diagonal games and disk capacity games, where
> any
> >> way to get a larger number was used in the adv= ertising, since the FTC
> didn't
> >> have a definiti= on that could be applied).
> >>
> >>
> = >>
> >> I wonder if some enterprising lawyer might brin= g the necessary consumer
> >> fraud class-action before the F= TC to get clear definitions of the
> numbers?
> >> It= 's probably too much to ask for Comcast to go on the record with a
>= ; precise
> >> definition.
> >>
> >&= gt;
> >>
> >>
> >>
> >= > On Saturday, April 19, 2014 8:55am, "Aaron Wood"
> <woody77= @gmail.com> said:
> >>
> >> I'm setting up n= ew service in the US, and I'm currently assuming that
> all
&g= t; >> of Comcast's rates are "boosted" rates, not the "provisioned" r= ates.
> >> So if they quote 50/10Mbps, I assume that's not wh= at will need to be set
> >> in SQM with CeroWRT.
> &g= t;> Does anyone have good info on the "provisioned" rates that go with e= ach
> of
> >> the Comcast tiers?
> >> B= asically, I'm trying to get to an apples-to-apples comparison with
>= ; >> Sonic.net DSL (I'll be close enough to the CO to run in Annex M = "upload
> >> priority" mode and get ~18/2 service).
>= >> Thanks,
> >> Aaron
> >
> >> >
> > _______________________________________________=
> > Cerowrt-devel mailing list
> > Cerowrt-devel@lis= ts.bufferbloat.net
> > https://lists.bufferbloat.net/listinfo/ce= rowrt-devel
> >
>
>
>
> --> Dave T=C3=A4ht
>
> NSFW:
> https://w2.eff.= org/Censorship/Internet_censorship_bills/russell_0296_indecent.article
>

=0A
 ------=_20140419141635000000_42074--