From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtp161.iad.emailsrvr.com (smtp161.iad.emailsrvr.com [207.97.245.161]) (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 323E321F196; Sat, 10 Nov 2012 06:18:07 -0800 (PST) Received: from localhost (localhost.localdomain [127.0.0.1]) by smtp56.relay.iad1a.emailsrvr.com (SMTP Server) with ESMTP id 7106A3D84D8; Sat, 10 Nov 2012 09:18:05 -0500 (EST) X-Virus-Scanned: OK Received: from legacy2.wa-web.iad1a (legacy2.wa-web.iad1a.rsapps.net [192.168.2.218]) by smtp56.relay.iad1a.emailsrvr.com (SMTP Server) with ESMTP id 445913D84BC; Sat, 10 Nov 2012 09:18:05 -0500 (EST) Received: from reed.com (localhost [127.0.0.1]) by legacy2.wa-web.iad1a (Postfix) with ESMTP id 30866E00B5; Sat, 10 Nov 2012 09:18:05 -0500 (EST) Received: by apps.rackspace.com (Authenticated sender: dpreed@reed.com, from: dpreed@reed.com) with HTTP; Sat, 10 Nov 2012 09:18:05 -0500 (EST) Date: Sat, 10 Nov 2012 09:18:05 -0500 (EST) From: dpreed@reed.com To: "Dave Taht" MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="----=_20121110091805000000_23154" Importance: Normal X-Priority: 3 (Normal) X-Type: html In-Reply-To: References: Message-ID: <1352557085.195910150@apps.rackspace.com> X-Mailer: webmail7.0 Cc: bloat-devel , cerowrt-devel@lists.bufferbloat.net, bloat Subject: Re: [Cerowrt-devel] Network tests as discussed in Washington, DC 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, 10 Nov 2012 14:18:07 -0000 ------=_20121110091805000000_23154 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable =0AI follow this pretty closely. The person you want to talk to is Sascha = Meinrath, about M-Lab - and if you have a good proposal, he has money to fu= nd a measurement project.=0A =0AM-Lab has been a partial failure politicall= y. The reason is this: the FCC does not want to do anything that would ann= oy incumbents running current Internet access systems. Direct measurement= s of latency are too dangerous. If you speak to the only Commissioner who = ever tried to get unbiased measurements (Copps) you will find that his atte= mpts were sabotaged on every side.=0A =0AThe same thing happened in the CRT= C inquiry regarding Net Neutrality, where I testified as an "expert witness= " on the argument that prioritization was necessary to reduce congestion. = My testimony pointed out that congestion was best measured by direct latenc= y measurements. The incumbent operators *refused* to provide latency data,= claiming a) they never measured it, and b) latency can be calculated from = average traffic volume measurements by "Little's Lemma", so it was unnecess= ary. (this last is categorically false, but it was "one expert vs. another= ").=0A =0AI wish you godspeed in getting direct latency measurements public= ized. The dataset collected by Netalyzr has been attacked by the incumbent= operators pretty strongly as "biased". (of course the measurements the FC= C commissioned to a contractor recommended by a Congressional staffer are "= unbiased").=0A =0A-----Original Message-----=0AFrom: "Dave Taht" =0ASent: Saturday, November 10, 2012 5:54am=0ATo: "bloat" , cerowrt-devel@lists.bufferbloat.net, "bloat-devel"= =0ASubject: [Cerowrt-devel] Network tes= ts as discussed in Washington, DC=0A=0A=0A=0AThe RRUL test idea presented e= arlier this week would do best with many=0Aunderlying servers, instrumented= with TCP stats collection, and a=0Alarge backend for analysis, and thus I = got interested in the current=0Astate of affairs in the internet as to how = to pull that together in=0Aconjunction with larger labs and universities.= =0A=0ASo, I started sorting through the debates at the FCC about network=0A= testing. A wide range of opinion is presented, AND represented - I=0Arandom= ly clicked on the names I recognised (like isc, verizon, karl=0Aauerbach, m= easurement labs, new horizon foundation, and many, many=0Aothers. I'm prett= y sure to get a balanced view I need to click on the=0Anames I don't recogn= ise!)=0A=0Asee position papers here:=0A=0Ahttp://apps.fcc.gov/ecfs/proceedi= ng/view.action?name=3D04-36=0A=0AAfter reading a dozen, I sighed, and went = back to coding.=0A=0AI'm just this guy, trying to fix bufferbloat, by all t= echnical means=0Anecessary. Additionally we're working on fixing ipv6, home= routers,=0Ahome gateways, naming, etc - and I rarely pay attention to poli= tics!=0A=0AIf anyone can provide a summary here of the debate as it stands = now=0Aand who the players are, it would be enlightening.=0A=0AIn other news= :=0A=0AI was very pleased to hear that Srikanth Sundaresan of the Bismark= =0Aproject ( http://projectbismark.net/ ) won the "Applied Networking=0ARes= earch Prize" at this past week's ietf ( http://irtf.org/anrp ),=0Afor:=0A= =0A"Broadband Internet Performance: A View From the Gateway"=0A=0Ahttp://co= nferences.sigcomm.org/sigcomm/2011/papers/sigcomm/p134.pdf=0A=0AAn early ve= rsion of cerowrt was used in some versions of bismark (they=0Alater went to= openwrt stable). I continue to build their repos for=0Apossible use in cer= owrt (or vice versa), and I'm contemplating=0Aextending their open sourced = backend database schema to include data=0Afrom the rrul tests....=0A=0Ahttp= s://github.com/dtaht/dashboard-db=0A=0A=0A-- =0ADave T=C3=A4ht=0A=0AFixing = bufferbloat with cerowrt: http://www.teklibre.com/cerowrt/subscribe.html=0A= _______________________________________________=0ACerowrt-devel mailing lis= t=0ACerowrt-devel@lists.bufferbloat.net=0Ahttps://lists.bufferbloat.net/lis= tinfo/cerowrt-devel ------=_20121110091805000000_23154 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable

= I follow this pretty closely.  The person you want to talk to is Sasch= a Meinrath, about M-Lab - and if you have a good proposal, he has money to = fund a measurement project.

=0A

 =0A

M-Lab has been a partial failure poli= tically.  The reason is this: the FCC does not want to do anything tha= t would annoy incumbents running current Internet access systems. &nbs= p; Direct measurements of latency are too dangerous.  If you speak to = the only Commissioner who ever tried to get unbiased measurements (Copps) y= ou will find that his attempts were sabotaged on every side.

=0A

 

=0A

The = same thing happened in the CRTC inquiry regarding Net Neutrality, where I t= estified as an "expert witness" on the argument that prioritization was nec= essary to reduce congestion.  My testimony pointed out that congestion= was best measured by direct latency measurements.  The incumbent oper= ators *refused* to provide latency data, claiming a) they never measured it= , and b) latency can be calculated from average traffic volume measurements= by "Little's Lemma", so it was unnecessary.  (this last is categorica= lly false, but it was "one expert vs. another").

=0A

 

=0A

I wish you godsp= eed in getting direct latency measurements publicized.  The dataset co= llected by Netalyzr has been attacked by the incumbent operators pretty str= ongly as "biased".  (of course the measurements the FCC commissioned t= o a contractor recommended by a Congressional staffer are "unbiased").

= =0A

 

=0A

-----Original Message-----
From: "Dave Taht" <dave.taht@gmai= l.com>
Sent: Saturday, November 10, 2012 5:54am
To: "bloat" &l= t;bloat@lists.bufferbloat.net>, cerowrt-devel@lists.bufferbloat.net, "bl= oat-devel" <bloat-devel@lists.bufferbloat.net>
Subject: [Cerowrt= -devel] Network tests as discussed in Washington, DC

=0A=0A

The RRUL t= est idea presented earlier this week would do best with many
underlyin= g servers, instrumented with TCP stats collection, and a
large backend= for analysis, and thus I got interested in the current
state of affai= rs in the internet as to how to pull that together in
conjunction with= larger labs and universities.

So, I started sorting through the= debates at the FCC about network
testing. A wide range of opinion is = presented, AND represented - I
randomly clicked on the names I recogni= sed (like isc, verizon, karl
auerbach, measurement labs, new horizon f= oundation, and many, many
others. I'm pretty sure to get a balanced vi= ew I need to click on the
names I don't recognise!)

see pos= ition papers here:

http://apps.fcc.gov/ecfs/proceeding/view.acti= on?name=3D04-36

After reading a dozen, I sighed, and went back t= o coding.

I'm just this guy, trying to fix bufferbloat, by all t= echnical means
necessary. Additionally we're working on fixing ipv6, h= ome routers,
home gateways, naming, etc - and I rarely pay attention t= o politics!

If anyone can provide a summary here of the debate a= s it stands now
and who the players are, it would be enlightening.

In other news:

I was very pleased to hear that Srikanth = Sundaresan of the Bismark
project ( http://projectbismark.net/ ) won = the "Applied Networking
Research Prize" at this past week's ietf ( htt= p://irtf.org/anrp ),
for:

"Broadband Internet Performance: = A View From the Gateway"

http://conferences.sigcomm.org/sigcomm/= 2011/papers/sigcomm/p134.pdf

An early version of cerowrt was use= d in some versions of bismark (they
later went to openwrt stable). I c= ontinue to build their repos for
possible use in cerowrt (or vice vers= a), and I'm contemplating
extending their open sourced backend databas= e schema to include data
from the rrul tests....

https://gi= thub.com/dtaht/dashboard-db


--
Dave T=C3=A4ht
<= br />Fixing bufferbloat with cerowrt: http://www.teklibre.com/cerowrt/subsc= ribe.html
_______________________________________________
Cerowrt= -devel mailing list
Cerowrt-devel@lists.bufferbloat.net
https://l= ists.bufferbloat.net/listinfo/cerowrt-devel

=0A ------=_20121110091805000000_23154--