From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: mail.toke.dk; spf=pass smtp.mailfrom=; dkim=pass header.d=g001.emailsrvr.com; arc=none (Message is not ARC signed); dmarc=fail (Used From Domain Record) header.from=deepplum.com policy.dmarc=none Received: from smtp99.iad3a.emailsrvr.com (smtp99.iad3a.emailsrvr.com [173.203.187.99]) by mail.toke.dk (Postfix) with ESMTPS id 416DA796BDE for ; Tue, 14 Oct 2025 17:55:36 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=g001.emailsrvr.com; s=feedback; t=1760457335; bh=qz6MpomKzgk8a1Bya/GArvvq0S1GPBCIaHrT/z3zArA=; h=Date:Subject:From:To:From; b=lWO0zc2XVhgVYLyw+cMxNF4EWtnM5oiP5we2JdQZ2t1vrEMtLvCpma73ar06yZSp7 bN7mWnuO3xl6b3gUO3L/6HI7rM51zpTYncVYhpsbok0xCqmx1Hfqk6otGtwx2sCQL/ WH9rVsPsd8pPp34I1S2aopXGayYQm1BIGI8SmUh8= Received: from app18.wa-webapps.iad3a (relay-webapps.rsapps.net [172.27.255.140]) by smtp29.relay.iad3a.emailsrvr.com (SMTP Server) with ESMTP id D0BDC25124; Tue, 14 Oct 2025 11:55:34 -0400 (EDT) Received: from deepplum.com (localhost.localdomain [127.0.0.1]) by app18.wa-webapps.iad3a (Postfix) with ESMTP id 9F943211B6; Tue, 14 Oct 2025 11:55:34 -0400 (EDT) Received: by apps.rackspace.com (Authenticated sender: dpreed@deepplum.com, from: dpreed@deepplum.com) with HTTP; Tue, 14 Oct 2025 11:55:34 -0400 (EDT) X-Auth-ID: dpreed@deepplum.com Date: Tue, 14 Oct 2025 11:55:34 -0400 (EDT) From: "David P. Reed" To: "Frantisek Borsik" Cc: "Cake List" , codel@lists.bufferbloat.net, "bloat" , "Jeremy Austin via Rpm" , "libreqos" , "Dave Taht via Starlink" MIME-Version: 1.0 Content-Type: text/plain;charset=UTF-8 Content-Transfer-Encoding: quoted-printable Importance: Normal X-Priority: 3 (Normal) X-Type: plain In-Reply-To: References: X-Client-IP: 209.6.168.128 Message-ID: <1760457334.648412280@apps.rackspace.com> X-Mailer: webmail/19.0.28-RC X-Classification-ID: 9dc88b32-37c4-43ed-99fa-39b5d251f5ae-1-1 Message-ID-Hash: CP343KROW4PNPF5KKS7Q5DD5HGOCGRQZ X-Message-ID-Hash: CP343KROW4PNPF5KKS7Q5DD5HGOCGRQZ X-MailFrom: dpreed@deepplum.com X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; loop; banned-address; emergency; member-moderation; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; digests; suspicious-header X-Mailman-Version: 3.3.10 Precedence: list Subject: [Bloat] Re: [Cake] The Bust of the Bandwidth Bubble (from Bandwidth by Dan Caruso) List-Id: General list for discussing Bufferbloat Archived-At: List-Archive: List-Help: List-Owner: List-Post: List-Subscribe: List-Unsubscribe: Some comments below by me that point out that "bandwidth bubble" makes no s= ense as a concept economically.=0A=0AOn Tuesday, October 14, 2025 01:39, "F= rantisek Borsik" said:=0A=0A...=0A=0A> Years b= efore the Bandwidth Bubble had begun to take shape, data had=0A> surfaced t= hat indicated something major was amiss. In 1998 an AT&T Labs=0A> Internet = researcher named Andrew M. Odlyzko published a paper debunking the=0A> wide= ly held view that Internet traffic was doubling every three months.=0A> Odl= yzko explained that the implications of this rapid traffic doubling=0A> wou= ld imply that by 2001 Internet traffic would have grown by a factor of=0A> = seventeen million. The amount of Bandwidth, Odlyzko calculated, would=0A> r= equire every Internet user on Earth to stream video twenty-four hours a=0A>= day. Clearly, that wasn't the trajectory.=0A=0AAndrew Odlyzko was a good f= riend of mine at the time. Andrew's a mathematician, not an "Internet resea= rcher", and this paper was trenchant and brilliant. He was not speaking for= AT&T. He was just pointing out that the Emperor was naked, which many of u= s engineers and mathematicians were also pointing out. Naked, in the sense = that no data supported the claim. None at all. I tried to track the claim b= ack to the source, and found it was made up in a talk by an "industry analy= st", and then echoed over and over by Very Serious People who gave speeches= . (so often this is the case ... self-reproducing "facts" that have a life = of their own).=0A=0A> =0A> "[Doubling every three months] was an extremely = convenient myth," said=0A> Odlyzko. "Every entrepreneur who was getting fin= ancing could quote it." In=0A> contrast, Odlyzko's analysis suggested Inter= net usage was doubling only=0A> once a year.=0A> =0A> Odlyzko's inconvenien= t truth was either unnoticed or, more likely,=0A> =0A> ignored."=0A=0AAs no= ted, many people knew that the claim was not founded in data or reality at = the time. So Andrew wasn't unnoticed, nor was his paper ignored. It just wa= s never cited by journalists or industry analysts, along with those of us i= n the industry who knew the real story. I spoke to many reporters "on backg= round" about this at the time. But I, like Andrew, wasn't a "spokesman" for= VCs. =0A=0A...=0A> =0A> =0A> "In the intermediate run, there would be neit= her be a clear "bandwidth=0A> glut" nor a "bandwidth scarcity," but a more = balanced situation, with=0A> supply and demand growing at comparable rates.= =0A> My reaction after reading Odlyzko's paper that night was: "Holy crap. = UUnet=0A> is lying." What I said was similar to the reaction I had when I r= ead about=0A> a deal=0A> between Enron and Blockbuster for internet bandwid= th since I knew that=0A> Enron had no bandwidth to sell.=0A> Again, "Holy c= rap."=0A=0AThis is consonant with my brief experience advising consultants = to Enron at the time.=0AEnron was selling what amounted to "futures" (but n= ot regulated futures) as if they were products. Interestingly, in their acc= ounting (which was very creative), they valued these "future sales" of band= width as Real Options on those "futures". That is, they projected their fut= ure sales as a stream of payments, and then created accounting units to val= ue the volatility of those future sales using Black Scholes based on the pr= esumed volatility. Then they "sold" these options to a corporate entity tha= t "bought" them (actually it was structured as a collateralized loan). The = result was that they could say the options were "capital assets". [I've si= mplified this, but it is well documented in the Enron bankruptcy].=0A=0AWha= t was going on was a legal way to create "capital" from nothing. (the futur= e uncertainty of Enron's sales of bandwidth to Blockbuster is the "nothing"= , it was "unknowable").=0A=0AIt's very similar to how NVidia gains a capita= l asset by a letter of intent to provide OpenAI with GPUs as just announced= , and OpenAI gives Oracle a capital asset by promising to have Oracle resel= l a huge amount OpenAI's products.=0A=0AOn its face, this is all *legal*. B= ut it is openly a scam, too. Just not an illegal scam.=0A=0AEnron's "bandwi= dth trading" platform was real, even though they had no bandwidth to trade.= They were proposing to be a "two-sided market" and valuing the volatility = of the future trading.=0A=0ASo, things weren't so simple. Finance (modern f= inance) and financial accounting now operate on a plane of unreality.=0A=0A= Andrew Odlyzko was right - there was no bandwidth there at all. But to star= t a platform, you don't need bandwidth to start. You need a "trading networ= k", and just as Enron also was a platform for trading Oil Future Sales, it = was betting it could be such a platform for bandwidth trading too.=0A=0AThe= bug here was that (as I learned), Enron had no clue how "bandwidth trading= " might connect to the way the Internet worked - things like peering and ro= uting. They thought they could somehow sign up all the suppliers of bandwid= th to this big thing called "The Internet" and insert themselves as a middl= eman, a trading platform.=0A=0A[And that's what I noticed, as a network eng= ineer - they were clueless on the technology side of how the Internet worke= d. Utterly clueless. Just finance mathematicians. It's why I lost interest = in their platform entirely.]=0A=0AHowever, the value of a network isn't the= volume of traffic it carries. The value of the network is the diversity of= connections and groups it can support. That's what makes a network differe= nt from an optical fiber. It's the switching it can do.=0A=0AAnd this is my= view of why the "Bandwidth Bubble" was a bubble. The investors and analyst= s were clueless when they decided that the value of the Internet was measur= ed by capacity.=0A=0AThe value of Starlink, for example, would be near zero= , if it didn't connect to the entire Internet. The options it creates for u= sers (connections they can choose to make in the future) come entirely from= Internet access, not dishy-to-dishy packets.=0A=0AIt's worth noting that t= he value in POTS was never in the subscriber line capacities (copper), whic= h never carried many bits at all. The value in POTS was in the number of pl= aces each customer can call when they need to. That's "option value", not c= apacity.=0A=0A(PS: I'm the guy who Reed's Law is named after. Along with Me= tcalfe's Law, it explains the value of the Internet to users. The capacity = of the Internet cannot be measured, because so much of it is in LANs these = days. No one knows how much of all the WiFi nets are used or not. Most are = mostly idle most of the time.)=0A=0ASo the two things that fundamentally ma= tter in the Internet are:=0A=0A1. Latency=0A2. Reachability via switching= =0A=0ANeither is measured by "bandwidth".