From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtp75.iad3a.emailsrvr.com (smtp75.iad3a.emailsrvr.com [173.203.187.75]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 540233B2A4; Mon, 20 Sep 2021 17:44:08 -0400 (EDT) Received: from app2.wa-webapps.iad3a (relay-webapps.rsapps.net [172.27.255.140]) by smtp18.relay.iad3a.emailsrvr.com (SMTP Server) with ESMTP id C3FE423A2D; Mon, 20 Sep 2021 17:44:07 -0400 (EDT) Received: from deepplum.com (localhost.localdomain [127.0.0.1]) by app2.wa-webapps.iad3a (Postfix) with ESMTP id AFD41A17E6; Mon, 20 Sep 2021 17:44:07 -0400 (EDT) Received: by apps.rackspace.com (Authenticated sender: dpreed@deepplum.com, from: dpreed@deepplum.com) with HTTP; Mon, 20 Sep 2021 17:44:07 -0400 (EDT) X-Auth-ID: dpreed@deepplum.com Date: Mon, 20 Sep 2021 17:44:07 -0400 (EDT) From: "David P. Reed" To: "David P. Reed" Cc: "David Lang" , starlink@lists.bufferbloat.net, "=?utf-8?Q?Valdis_Kl=C4=93tnieks?=" , "Make-Wifi-fast" , "Leonard Kleinrock" , "Bob McMahon" , "Cake List" , codel@lists.bufferbloat.net, "cerowrt-devel" , "bloat" , "Ben Greear" MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="----=_20210920174407000000_14326" Importance: Normal X-Priority: 3 (Normal) X-Type: html In-Reply-To: <1632173429.589822691@apps.rackspace.com> References: <1625188609.32718319@apps.rackspace.com> <989de0c1-e06c-cda9-ebe6-1f33df8a4c24@candelatech.com> <1625773080.94974089@apps.rackspace.com> <1625859083.09751240@apps.rackspace.com> <257851.1632110422@turing-police> <2760o61s-408q-4613-r840-3sq96s8q1s1@ynat.uz> <1632173429.589822691@apps.rackspace.com> X-Client-IP: 209.6.168.128 Message-ID: <1632174247.7178061@apps.rackspace.com> X-Mailer: webmail/19.0.12-RC X-Classification-ID: 140fe02b-b848-4f4e-9ea4-3cd9682b92c1-1-1 X-Mailman-Approved-At: Tue, 21 Sep 2021 13:50:10 -0400 Subject: Re: [Starlink] [Cake] [Bloat] [Cerowrt-devel] Little's Law mea culpa, but not invalidating my main point X-BeenThere: starlink@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: "Starlink has bufferbloat. Bad." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 20 Sep 2021 21:44:08 -0000 ------=_20210920174407000000_14326 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable =0AThe top posting may be confusing, but "the example" here is the example = of the > 100 TCP destinations and dozens of DNS queries that are needed (un= less cached) to display the front page of CNN today.=0AThat's "one website"= home page. If you look at the JavaScript resource loading code, and now th= e "service worker" javascript code, the idea that it is like fetching a fil= e using FTP is just wrong. Do NANOG members understand this? I doubt it.=0A= =0AOn Monday, September 20, 2021 5:30pm, "David P. Reed" said:=0A=0A=0A=0AI use the example all the time, but not for interview= ing. What's sad is that the answers seem to be quoting from some set of tex= tbooks or popular explanations of the Internet that really have got it all = wrong, but which many professionals seem to believe is true.=0A =0AThe same= phenomenon appears in the various subfields of the design of radio communi= cations at the physical and front end electronics level. The examples of me= ntal models that are truly broken that are repeated by "experts" are truly = incredible, and cover all fields. Two or three:=0A =0A1. why do the AM comm= ercial broadcast band (540-1600 kHz) signals you receive in your home trave= l farther than VHF band TV signals and UHF band TV signals? How does this = explanation relate to the fact that we can see stars a million light-years = away using receivers that respond to 500 Terahertz radio (visible light ant= ennas)?=0A =0A2. What is the "aperture" of an antenna system? Does it depen= d on frequency of the radiation? How does this relate to the idea of the si= ze of an RF photon, and the mass of an RF photon? How big must a cellphone = be to contain the antenna needed to receive and transmit signals in the 3G = phone frequencies?=0A =0A3. We can digitize the entire FM broadcast frequen= cy band into a sequence of 14-bit digital samples at the Nyquist sampling r= ate of about 40 Mega-samples per second, which covers the 20 Mhz bandwidth = of the FM band. Does this allow a receiver to use a digital receiver to tun= e into any FM station that can be received with an "analog FM radio" using = the same antenna? Why or why not?=0A =0AI'm sure Dick Roy understands all t= hree of these questions, and what is going on. But I'm equally sure that th= e designers of WiFi radios or broadcast radios or even the base stations of= cellular data systems include few who understand.=0A =0AAnd literally no o= ne at the FCC or CTIA understand how to answer these questions. But the pr= oblem is that they are *confident* that they know the answers, and that the= y are right.=0A =0AThe same is true about the packet layers and routing lay= ers of the Internet. Very few engineers, much less lay people realize that = what they have been told by "experts" is like how Einstein explained how ra= dio works to a teenaged kid:=0A =0A "Imagine a cat whose tail is in New Yo= rk and his head is in Los Angeles. If you pinch his tail in NY, he howls in= Los Angeles. Except there is no cat."=0A =0AThough others have missed it, = Einstein was not making a joke. The non-cat is the laws of quantum electrod= ynamics (or classically, the laws of Maxwell's Equations). The "cat" would = be all the stories people talk about how radio works - beams of energy (or = puffs of energy), modulated by some analog waveform, bouncing off of hard m= aterials, going through less dense materials, "hugging the ground", "far fi= eld" and "near field" effects, etc.=0A =0AEinstein's point was that there i= s no cat - that is, all the metaphors and models aren't accurate or equival= ent to how radio actually works. But the underlying physical phenomenon sup= porting radio is real, and scientists do understand it pretty deeply.=0A = =0ASame with how packet networks work. There are no "streams" that behave l= ike water in pipes, the connection you have to a shared network has no "spe= ed" in megabits per second built in to it, A "website" isn't coming from on= e place in the world, and bits don't have inherent meaning.=0A =0AThere is = NO CAT (not even a metaphorical one that behaves like the Internet actually= works).=0A =0ABut in the case of the Internet, unlike radio communications= , there is no deep mystery that requires new discoveries to understand it, = because it's been built by humans. We don't need metaphors like "streams of= water" or "sites in a place". We do it a disservice by making up these met= aphors, which are only apt in a narrow context.=0A =0AFor example, congesti= on in a shared network is just unnecessary queuing delay caused by multiple= xing the capacity of a particular link among different users. It can be cur= ed by slowing down all the different packet sources in some more or less fa= ir way. The simplest approach is just to discard from the queue excess pack= ets that make that queue longer than can fit through the link Then there ca= n't be any congestion. However, telling the sources to slow down somehow wo= uld be an improvement, hopefully before any discards are needed.=0A =0ATher= e is no "back pressure", because there is no "pressure" at all in a packet = network. There are just queues and links that empty queues of packets at a = certain rate. Thinking about back pressure comes from thinking about sessio= ns and pipes. But 90% of the Internet has no sessions and no pipes. Just as= there is "no cat" in real radio systems.=0A =0AOn Monday, September 20, 20= 21 12:09am, "David Lang" said:=0A=0A=0A=0A> On Mon, 20 Sep = 2021, Valdis Kl=C4=93tnieks wrote:=0A> =0A> > On Sun, 19 Sep 2021 18:21:56 = -0700, Dave Taht said:=0A> >> what actually happens during a web page load,= =0A> >=0A> > I'm pretty sure that nobody actually understands that anymore,= in any=0A> > more than handwaving levels.=0A> =0A> This is my favorite int= erview question, it's amazing and saddning at the answers=0A> that I get, e= ven from supposedly senior security and networking people.=0A> =0A> David L= ang_______________________________________________=0A> Bloat mailing list= =0A> Bloat@lists.bufferbloat.net=0A> https://lists.bufferbloat.net/listinfo= /bloat=0A> ------=_20210920174407000000_14326 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable

The top posting may be= confusing, but "the example" here is the example of the > 100 TCP desti= nations and dozens of DNS queries that are needed (unless cached) to displa= y the front page of CNN today.

=0A

That's "one websi= te" home page. If you look at the JavaScript resource loading code, and now= the "service worker" javascript code, the idea that it is like fetching a = file using FTP is just wrong. Do NANOG members understand this? I doubt it.=

=0A

 

=0A

On Monday, Se= ptember 20, 2021 5:30pm, "David P. Reed" <dpreed@deepplum.com> said:<= br />

=0A
=0A

I use the example all the time, but not for intervie= wing. What's sad is that the answers seem to be quoting from some set of te= xtbooks or popular explanations of the Internet that really have got it all= wrong, but which many professionals seem to believe is true.

=0A

 

=0A

The same phenomenon appears in the various subfields of = the design of radio communications at the physical and front end electronic= s level. The examples of mental models that are truly broken that are repea= ted by "experts" are truly incredible, and cover all fields. Two or three:<= /p>=0A

 

=0A

1. why do the AM commercial broadcast band = (540-1600 kHz) signals you receive in your home travel farther than VHF ban= d TV signals and UHF band TV signals?  How does this explanation relat= e to the fact that we can see stars a million light-years away using receiv= ers that respond to 500 Terahertz radio (visible light antennas)?

=0A

 

=0A

2. What is the "aperture" of an antenna system? Does= it depend on frequency of the radiation? How does this relate to the idea = of the size of an RF photon, and the mass of an RF photon? How big must a c= ellphone be to contain the antenna needed to receive and transmit signals i= n the 3G phone frequencies?

=0A

 

=0A

3. We can digit= ize the entire FM broadcast frequency band into a sequence of 14-bit digita= l samples at the Nyquist sampling rate of about 40 Mega-samples per second,= which covers the 20 Mhz bandwidth of the FM band. Does this allow a receiv= er to use a digital receiver to tune into any FM station that can be receiv= ed with an "analog FM radio" using the same antenna? Why or why not?

=0A=

 

=0A

I'm sure Dick Roy understands all three of these = questions, and what is going on. But I'm equally sure that the designers of= WiFi radios or broadcast radios or even the base stations of cellular data= systems include few who understand.

=0A

 

=0A

And li= terally no one at the FCC or CTIA understand how to answer these questions.=   But the problem is that they are *confident* that they know the answ= ers, and that they are right.

=0A

 

=0A

The same is t= rue about the packet layers and routing layers of the Internet. Very few en= gineers, much less lay people realize that what they have been told by "exp= erts" is like how Einstein explained how radio works to a teenaged kid:

= =0A

 

=0A

  "Imagine a cat whose tail is in New Yor= k and his head is in Los Angeles. If you pinch his tail in NY, he howls in = Los Angeles. Except there is no cat."

=0A

 

=0A

Thoug= h others have missed it, Einstein was not making a joke. The non-cat is the= laws of quantum electrodynamics (or classically, the laws of Maxwell's Equ= ations). The "cat" would be all the stories people talk about how radio wor= ks - beams of energy (or puffs of energy), modulated by some analog wavefor= m, bouncing off of hard materials, going through less dense materials, "hug= ging the ground", "far field" and "near field" effects, etc.

=0A

 

=0A

Einstein's point was that there is no cat - that is, all = the metaphors and models aren't accurate or equivalent to how radio actuall= y works. But the underlying physical phenomenon supporting radio is real, a= nd scientists do understand it pretty deeply.

=0A

 

=0A

Same with how packet networks work. There are no "streams" that behave l= ike water in pipes, the connection you have to a shared network has no "spe= ed" in megabits per second built in to it, A "website" isn't coming from on= e place in the world, and bits don't have inherent meaning.

=0A

 

=0A

There is NO CAT (not even a metaphorical one that behaves= like the Internet actually works).

=0A

 

=0A

But in = the case of the Internet, unlike radio communications, there is no deep mys= tery that requires new discoveries to understand it, because it's been buil= t by humans. We don't need metaphors like "streams of water" or "sites in a= place". We do it a disservice by making up these metaphors, which are only= apt in a narrow context.

=0A

 

=0A

For example, cong= estion in a shared network is just unnecessary queuing delay caused by mult= iplexing the capacity of a particular link among different users. It can be= cured by slowing down all the different packet sources in some more or les= s fair way. The simplest approach is just to discard from the queue excess = packets that make that queue longer than can fit through the link Then ther= e can't be any congestion. However, telling the sources to slow down someho= w would be an improvement, hopefully before any discards are needed.

=0A=

 

=0A

There is no "back pressure", because there is no = "pressure" at all in a packet network. There are just queues and links that= empty queues of packets at a certain rate. Thinking about back pressure co= mes from thinking about sessions and pipes. But 90% of the Internet has no = sessions and no pipes. Just as there is "no cat" in real radio systems.

= =0A

 

=0A

On Monday, September 20, 2021 12:09am, "David = Lang" <david@lang.hm> said:

=0A
=0A

> On Mon, 20 Se= p 2021, Valdis Kl=C4=93tnieks wrote:
>
> > On Sun, 19 S= ep 2021 18:21:56 -0700, Dave Taht said:
> >> what actually ha= ppens during a web page load,
> >
> > I'm pretty sure= that nobody actually understands that anymore, in any
> > more = than handwaving levels.
>
> This is my favorite interview = question, it's amazing and saddning at the answers
> that I get, ev= en from supposedly senior security and networking people.
>
&= gt; David Lang_______________________________________________
> Blo= at mailing list
> Bloat@lists.bufferbloat.net
> https://lis= ts.bufferbloat.net/listinfo/bloat
>

=0A
=0A
 ------=_20210920174407000000_14326--