From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-yb1-xb2a.google.com (mail-yb1-xb2a.google.com [IPv6:2607:f8b0:4864:20::b2a]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 293113CB37 for ; Thu, 22 Feb 2024 19:03:19 -0500 (EST) Received: by mail-yb1-xb2a.google.com with SMTP id 3f1490d57ef6-dcc7cdb3a98so281802276.2 for ; Thu, 22 Feb 2024 16:03:19 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1708646598; x=1709251398; darn=lists.bufferbloat.net; h=to:in-reply-to:cc:references:message-id:date:subject:mime-version :from:content-transfer-encoding:from:to:cc:subject:date:message-id :reply-to; bh=waYwdGbMoluGesvbcUuQ2loGf6ss4KEsYT74iYTuow8=; b=JwTnhBKS6eIQVXUZhd3pITIZ7+BDMHmi/KDSdfeA6jFILjYM/M2pYtL+chxTDJS2xN 0rSmxS6JR6mygueh5U9pBpQWidSNNvpdEm8oJEw/R6lDigu3OYFoYsT1kxwXpL9vmxWV fenUC0JoJ7USeGAFFFZJYljiASGVXnxsuchtBxp+VnUB6AN2WvD9gxqKwInui9Sz+adu Cb3sCZEumFilvbNjZWnt3s69W9t1VLCpN8E7xnW15x6+RocKoaRFBoWO4oB1yQVZ+PMd q71LUWempwlC1HXwH/1iEU4dsKBl9PbM5XlBt9sQ+Wt5Xt7oVoJTlDzpMnr/CZrCp3/a AU4g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1708646598; x=1709251398; h=to:in-reply-to:cc:references:message-id:date:subject:mime-version :from:content-transfer-encoding:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=waYwdGbMoluGesvbcUuQ2loGf6ss4KEsYT74iYTuow8=; b=L0d6zygvDfr0v56lpSxy3fn7ewPteHGcXqcOGxMRZCovKazAi1U8fmWZL/HmsMCn9d gadRPxivum8CHIYSuGTKZhawoKiFwEC45CrC0E7Pv96Quh4NeSd8yjazHY6nPqmpBUyP rJh7UVLqgCIpqkA+Hh4VZN+NicFlGHFnmgvU8fKzT5Jprnnw9psOv3RResnVOTLTenoV qM7HYf7mVvKxsBUeF4ZiQZ5x5i2egWbvTSEimwdA2XI38q34/Pm26fSwSS4s/R+S29Gs g9xyNdWFHcORe3+dI9idpRpM0w7cfQ5Uhiqb5niJO7Wgl9y1hRLZHiUz7XGV/sWn96M8 C8mg== X-Gm-Message-State: AOJu0YxAcrnmLBIpd4x9GnPbpMTKf3Ka64PSLzKoLk3L79VCvV3N0FsJ ajicRq2AlElSoNtVbyI1Dao/iTWze07z+n+KTJWw5MpKfZpO7rd1 X-Google-Smtp-Source: AGHT+IFmAxcCEHUZVlO/gYMXkZGjUEdXSsczRZn7rTA5MX8LaZ/oCpnHLlQBHnf6s1U1Crviq3uhXA== X-Received: by 2002:a05:6902:302:b0:dc7:49a0:7f87 with SMTP id b2-20020a056902030200b00dc749a07f87mr658438ybs.63.1708646598424; Thu, 22 Feb 2024 16:03:18 -0800 (PST) Received: from smtpclient.apple ([2600:1700:2c58:d080:bdf9:8e90:fd4e:18bc]) by smtp.gmail.com with ESMTPSA id y23-20020a25ad17000000b00dcd512855d4sm3120744ybi.58.2024.02.22.16.03.17 (version=TLS1_3 cipher=TLS_AES_128_GCM_SHA256 bits=128/128); Thu, 22 Feb 2024 16:03:18 -0800 (PST) Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable From: Dave Cohen Mime-Version: 1.0 (1.0) Date: Thu, 22 Feb 2024 19:03:07 -0500 Message-Id: References: <71924C54-A1AA-421F-B9A3-738DC04E8412@pch.net> Cc: Bill Woodcock , Brent Legg In-Reply-To: <71924C54-A1AA-421F-B9A3-738DC04E8412@pch.net> To: =?utf-8?Q?Network_Neutrality_is_back!_Let=C2=B4s_make_the_techni?= =?utf-8?Q?cal_aspects_heard_this_time!?= X-Mailer: iPhone Mail (21D61) Subject: Re: [NNagain] The Whys of the Wichita IXP Project X-BeenThere: nnagain@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: =?utf-8?q?Network_Neutrality_is_back!_Let=C2=B4s_make_the_technical_aspects_heard_this_time!?= List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Feb 2024 00:03:19 -0000 I think this landscape is changing. These days I=E2=80=99m only focused on a= couple of specific markets, but in those markets we are seeing both 1) a pr= oliferation of IXs either adding nodes in new facilities or getting connecti= vity out to them to provide at least some capability and 2) datacenter provi= ders, particularly more large-deployment-oriented facilities, seeking to att= ract IXPs in their sites or drive connectivity out to them as part of their o= wn connectivity offerings. I believe that some of this dynamic is driven by t= ransit simply being so cheap that it=E2=80=99s hard for carriers to justify r= apidly expanding their footprints at the rate that datacenters themselves ar= e expanding and some of it that larger enterprises are more willing to add I= X connectivity to their Internet mix than they were in the days of everyone b= eing extremely ratio-sensitive. Dave Cohen craetdave@gmail.com > On Feb 22, 2024, at 6:31=E2=80=AFPM, Bill Woodcock via Nnagain wrote: >=20 > =EF=BB=BF >=20 >> On Feb 22, 2024, at 19:58, rjmcmahon via Nnagain wrote: >> Boston University spent $305M on this and it doesn't have an IXP. >> https://www.bu.edu/articles/2022/center-for-computing-and-data-sciences-p= hoto-essay/ >> It's like building a magnificent train station w/o any tracks to/fro the s= tation. >=20 > Most datacenters don=E2=80=99t contain IXPs, and most IXPs aren=E2=80=99t l= ocated in datacenters. It=E2=80=99s very financially advantageous for a neu= tral multi-tenant datacenter to contain an IXP, but generally much less adva= ntageous for an IXP to be located in a datacenter. Datacenters tend to conc= entrate content, but that content can be transported to an IXP over just a f= ew strands of fiber. Whereas eyeballs have to be physically aggregated, and= that=E2=80=99s over thousands of strands, so the average distance to eyebal= ls matters, whereas the average distance to content just doesn=E2=80=99t hav= e a significant multiplier on it, and the content is portable anyway. The o= ptimum location for an IXP is in a city center, whereas the optimum location= for a datacenter (all political, zoning, and real-estate factors considered= ) is typically in an industrial park well outside the city core. >=20 > Lots of organizations need a datacenter for their own use, and universitie= s are typical in that. It doesn=E2=80=99t mean that they=E2=80=99d make sen= se as locations for an IXP, unless they=E2=80=99re also aggregating a lot of= eyeball fiber for some reason. >=20 > -Bill >=20 > _______________________________________________ > Nnagain mailing list > Nnagain@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/nnagain