ABSTRACT
Recent studies show that an end system's traffic may reach a distant anycast site within a global IP anycast system, resulting in high latency. To address this issue, some private and public CDNs have implemented regional IP anycast, a technique that involves dividing content-hosting sites into geographic regions, announcing a unique IP anycast prefix for each region, and utilizing DNS and IP-geolocation to direct clients to CDN sites in their corresponding geographic regions. In this work, we aim to understand how a regional anycast CDN partitions its sites and maps its customers' clients to its sites, and how a regional anycast CDN performs compared to its global anycast counterpart. We study the deployment strategies and the performance of two CDNs (Edgio and Imperva) that currently deploy regional IP anycast. We find that both Edgio and Imperva partition their sites and clients following continent or country borders. Furthermore, we compare the client latency distribution in Imperva's regional anycast CDN with its similar-scale DNS global anycast network, while accounting for and mitigating the relevant deployment differences between the two networks. We find that regional anycast can effectively alleviate the pathology in global IP anycast where BGP routes clients' traffic to distant CDN sites. However, DNS mapping inefficiencies, where DNS returns a sub-optimal regional IP anycast address that does not cover a client's low-latency CDN sites, can harm regional anycast's performance. Finally, we show what performance benefits regional IP anycast can achieve with a latency-based region partition method using the Tangled testbed. When compared to global anycast, regional anycast significantly reduces the 90th percentile client latency by 58.7% to 78.6% for clients across different geographic areas.
- Bernhard Ager, Nikolaos Chatzis, Anja Feldmann, Nadi Sarrar, Steve Uhlig, and Walter Willinger. Anatomy of a Large European IXP. In Proceedings of the Annual Conference of the Conference of the ACM Special Interest Group on Data Communication (SIGCOMM'12), 2012.Google ScholarDigital Library
- Akamai Technologies. Akamai Online Retail Performance Report: Milliseconds are Critical. Retrieved in Sep, 2022 from https://www.ir.akamai.com/news-releases/news-release-details/akamai-online-retail-performance-report-milliseconds-are.Google Scholar
- Amazon. Values Specific for Geolocation Records. Retrieved in Sep, 2022 from https://docs.aws.amazon.com/Route53/latest/DeveloperGuide/resource-record-sets-values-geo.html#rrsets-values-geo-location.Google Scholar
- Ruwaifa Anwar, Haseeb Niaz, David Choffnes, Ítalo Cunha, Phillipa Gill, and Ethan Katz-Bassett. Investigating Interdomain Routing Policies in the Wild. In Proceedings of the Annual Conference of the ACM Internet Measurement Conference (IMC'15), 2015.Google Scholar
- Todd Arnold, Ege Gürmeriçliler, Georgia Essig, Arpit Gupta, Matt Calder, Vasileios Giotsas, and Ethan Katz-Bassett. (How Much) Does a Private WAN Improve Cloud Performance? In Proceedings of the Annual Conference of the IEEE International Conference on Computer Communications (INFOCOM'20), 2020.Google Scholar
- Karthik Balakrishnan. Simplify Traffic Steering with Cloud DNS Routing Policies. Retrieved in Sep, 2022 from https://cloud.google.com/blog/products/networking/dns-routing-policies-for-geo-location-weighted-round-robin.Google Scholar
- Hitesh Ballani and Paul Francis. Towards a Global IP Anycast Service. In Proceedings of the Annual Conference of the Conference of the ACM Special Interest Group on Data Communication (SIGCOMM'05), 2005.Google ScholarDigital Library
- Hitesh Ballani, Paul Francis, and Sylvia Ratnasamy. A Measurement-Based Deployment Proposal for IP Anycast. In Proceedings of the Annual Conference of the ACM Internet Measurement Conference (IMC'06), 2006.Google Scholar
- Leandro M Bertholdo, Joao M Ceron, Wouter B de Vries, Ricardo de Oliveira Schmidt, Lisandro Zambenedetti Granville, Roland van Rijswijk-Deij, and Aiko Pras. Tangled: A Cooperative Anycast Testbed. In Proceedings of the IFIP/IEEE International Symposium on Integrated Network Management (IM'21), 2021.Google Scholar
- Matt Calder, Xun Fan, Zi Hu, Ethan Katz-Bassett, John Heidemann, and Ramesh Govindan. Mapping the Expansion of Google's Serving Infrastructure. In Proceedings of the Annual Conference of the ACM Internet Measurement Conference (IMC'13), 2013.Google ScholarDigital Library
- Matt Calder, Ashley Flavel, Ethan Katz-Bassett, Ratul Mahajan, and Jitu Padhye. Analyzing the Performance of an Anycast CDN. In Proceedings of the Annual Conference of the ACM Internet Measurement Conference (IMC'15), 2015.Google ScholarDigital Library
- Matt Calder, Manuel Schroder, Ryan Gao, Ryan Stewart, Jitu Padhye, Ratul Mahajan, Ganesh Ananthanarayanan, and Ethan Katz-Bassett. Odin: Microsoft's Scalable Fault-Tolerant CDN Measurement System. In Proceedings of 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI'18), 2018.Google Scholar
- Fangfei Chen, Ramesh K. Sitaraman, and Marcelo Torres. End-User Mapping: Next Generation Request Routing for Content Delivery. In Proceedings of the Annual Conference of the Conference of the ACM Special Interest Group on Data Communication (SIGCOMM'15), 2015.Google ScholarDigital Library
- Danilo Cicalese, Jordan Augé, Diana Joumblatt, Timur Friedman, and Dario Rossi. Characterizing IPv4 Anycast Adoption and Deployment. In Proceedings of the 11th ACM Conference on Emerging Networking Experiments and Technologies (CoNEXT '15), 2015.Google Scholar
- Danilo Cicalese, Diana Joumblatt, Dario Rossi, Marc-Olivier Buob, Jordan Augé, and Timur Friedman. A Fistful of Pings: Accurate and Lightweight Anycast Enumeration and Geolocation. In Proceedings of the Annual Conference of the IEEE International Conference on Computer Communications (INFOCOM'15), 2015.Google ScholarCross Ref
- Danilo Cicalese and Dario Rossi. A Longitudinal Study of IP Anycast. ACM SIGCOMM Computer Communication Review, 48(1):10--18, 2018.Google ScholarDigital Library
- Google Cloud. Cloud CDN. Retrieved in January, 2023 from https://cloud.google.com/cdn.Google Scholar
- Cloudflare. Cloudflare CDN Reference Architecture. https://cf-assets.www.cloudflare.com/slt3lc6tev37/18dA4NLfq8oXY8EVZxPlpY/b9cab82be79ebefa80f08c09eaa3d93e/Cloudflare_CDN_Reference_Architecture.pdf, 2022.Google Scholar
- Lorenzo Colitti, Erik Romijn, Henk Uijterwaal, and Andrei Robachevsky. Evaluating the Effects of Anycast on DNS Root Name Servers. Retrieved in Sep, 2022 from https://www.ripe.net/publications/docs/ripe-393.Google Scholar
- Carlo Contavalli, Wilmer van der Gaast, David C Lawrence, and Warren "Ace" Kumari. Client Subnet in DNS Queries. Technical report, RFC Editor, Dec 2016.Google Scholar
- DE-CIX. DE-CIX GlobePEER Looking Glass. Retrieved in Feb, 2023 from https://lg.de-cix.net/.Google Scholar
- Ricardo de O. Schmidt, John Heidemann, and Jan Kuipers. Anycast Latency: How Many Sites Are Enough? In Proceedings of Passive and Active Measurement (PAM'17), 2017.Google ScholarCross Ref
- Wouter B De Vries, Roland van Rijswijk-Deij, Pieter-Tjerk De Boer, and Aiko Pras. Passive Observations of a Large DNS Service: 2.5 Years in the Life of Google. IEEE transactions on network and service management, 17(1):190--200, 2019.Google Scholar
- EdgeCast. EdgeCast POPs. Retrieved in Sep, 2022 from https://docs.edgecast.com/cdn/Content/Reference/POP_Listing.htm.Google Scholar
- Xun Fan, John Heidemann, and Ramesh Govindan. Evaluating Anycast in the Domain Name System. In Proceedings of the Annual Conference of the IEEE International Conference on Computer Communications (INFOCOM'13), 2013.Google Scholar
- Ashley Flavel, Pradeepkumar Mani, David Maltz, Nick Holt, Jie Liu, Yingying Chen, and Oleg Surmachev. FastRoute: A Scalable Load-Aware Anycast Routing Architecture for Modern CDNs. In Proceedings of 4th USENIX Symposium on Networked Systems Design & Implementation (NSDI'15), 2015.Google Scholar
- Center for Applied Internet Data Analysis (CAIDA). CAIDA Data Server-PeeringDB Archive Aug,30,2022 Data. Retrieved in Feb, 2023 from https://publicdata.caida.org/datasets/peeringdb/2022/08/peeringdb_2_dump_2022_08_30.json.Google Scholar
- Center for Applied Internet Data Analysis (CAIDA). The CAIDA AS Relationships Dataset, Aug,30,2022 Data. Retrieved in Feb, 2023 from https://www.caida.org/catalog/datasets/as-relationships/.Google Scholar
- Manaf Gharaibeh, Anant Shah, Bradley Huffaker, Han Zhang, Roya Ensafi, and Christos Papadopoulos. A Look at Router Geolocation in Public and Commercial Databases. In Proceedings of the Annual Conference of the ACM Internet Measurement Conference (IMC'17), 2017.Google ScholarDigital Library
- Hadi Asghari. Pyasn · PyPI. Retrieved in Feb, 2023 from https://pypi.org/project/pyasn/.Google Scholar
- Shuai Hao, Yubao Zhang, Haining Wang, and Angelos Stavrou. End-Users Get Maneuvered: Empirical Analysis of Redirection Hijacking in Content Delivery Networks. In Proceedings of 27th USENIX Security Symposium (USENIX Security'18), 2018.Google Scholar
- Paul Hoffman, Andrew Sullivan, and Kazunori Fujiwara. DNS Terminology. RFC 8499, RFC Editor, Jan 2019.Google Scholar
- Bradley Huffaker, Marina Fomenkov, and Kc Claffy. Geocompare: A Comparison of Public and Commercial Geolocation Databases. Technical report, Cooperative Association For Internet Data Analysis (CAIDA), 2011.Google Scholar
- The International Air Transport Association (IATA). IATA Airport Code. Retrieved in Sep, 2022 from https://www.iata.org/en/publications/directories/code-search/.Google Scholar
- iconectiv. CLLI code. Retrieved in Sep, 2022 from https://www.commonlanguage.com/resources/commonlang/productshowroom/product/clli/.Google Scholar
- Imperva. Imperva PoPs. Retrieved in Sep, 2022 from https://status.imperva.com/?_ga=2.95445268.988020403.1637323716-57897548.1602317115.Google Scholar
- IPInfo. IPinfo. Retrieved in Sep, 2022 from https://ipinfo.io/.Google Scholar
- Weifan Jiang, Tao Luo, Thomas Koch, Yunfan Zhang, Ethan Katz-Bassett, and Matt Calder. Towards Identifying Networks with Internet Clients Using Public Data. In Proceedings of the Annual Conference of the ACM Internet Measurement Conference (IMC'21), 2021.Google Scholar
- Thomas Koch, Ke Li, Calvin Ardi, Ethan Katz-Bassett, Matt Calder, and John Heidemann. Anycast in Context: A Tale of Two Systems. In Proceedings of the Annual Conference of the Conference of the ACM Special Interest Group on Data Communication (SIGCOMM'21), 2021.Google Scholar
- JH Kuipers. Analysing the K-root Anycast Infrastructure. Retrieved in Sep, 2022 from https://labs.ripe.net/Members/jh_kuipers/analyzing-the-k-root-anycast-infrastructure.Google Scholar
- Victor Le Pochat, Tom Van Goethem, Samaneh Tajalizadehkhoob, Maciej Korczyński, and Wouter Joosen. Tranco: A Research-Oriented Top Sites Ranking Hardened Against Manipulation. In Proceedings of the 26th Annual Network and Distributed System Security Symposium (NDSS), 2019.Google Scholar
- Zhihao Li, Dave Levin, Neil Spring, and Bobby Bhattacharjee. Internet Anycast: Performance, Problems, & Potential. In Proceedings of the Annual Conference of the Conference of the ACM Special Interest Group on Data Communication (SIGCOMM'18), 2018.Google Scholar
- Ziqian Liu, Bradley Huffaker, Marina Fomenkov, Nevil Brownlee, and Kimberly Claffy. Two Days in the Life of the DNS Anycast Root Servers. In Proceedings of Passive and Active Measurement (PAM'07), 2007.Google Scholar
- Matthew Luckie, Bradley Huffaker, and K Claffy. Learning Regexes to Extract Router Names from Hostnames. In Proceedings of the Annual Conference of the ACM Internet Measurement Conference (IMC'19), 2019.Google ScholarDigital Library
- Matthew Luckie, Bradley Huffaker, Alexander Marder, Zachary Bischof, Marianne Fletcher, and K Claffy. Learning to Extract Geographic Information from Internet Router Hostnames. In Proceedings of the 17th International Conference on Emerging Networking EXperiments and Technologies (CoNEXT'21), 2021.Google ScholarDigital Library
- J MacQueen. Classification and Analysis of Multivariate Observations. In Proceedings of the 5th Berkeley Symp. Math. Statist. Probability, 1967.Google Scholar
- Ritesh Maheshwari. TCP over IP Anycast - Pipe Dream or Reality? Retrieved in Sep, 2022 from https://engineering.linkedin.com/network-performance/tcp-over-ip-anycast-pipe-dream-or-reality, 2015.Google Scholar
- MaxMind Inc. MaxMind. Retrieved in Sep, 2022 from https://www.maxmind.com/en/home.Google Scholar
- Stephen McQuistin, Sree Priyanka Uppu, and Marcel Flores. Taming Anycast in the Wild Internet. In Proceedings of the Annual Conference of the ACM Internet Measurement Conference (IMC'19), 2019.Google Scholar
- Trevor Mendez, Walter Milliken, and Dr. Craig Partridge. Host Anycasting Service. RFC, RFC Editor, Nov 1993.Google Scholar
- Microsoft. What is a Content Delivery Network on Azure? Retrieved in January, 2023 from https://docs.microsoft.com/en-us/azure/cdn/cdn-overview.Google Scholar
- Nitinder Mohan, Lorenzo Corneo, Aleksandr Zavodovski, Suzan Bayhan, Walter Wong, and Jussi Kangasharju. Pruning Edge Research with Latency Shears. In Proceedings of the 19th ACM Workshop on Hot Topics in Networks, 2020.Google Scholar
- Aaron Peters. CDN Finder (CDN Lookup Made Easy). Retrieved in Sep, 2022 from https://www.cdnplanet.com/tools/cdnfinder/.Google Scholar
- Aaron Peters. CDNPlanet - EDNS Client Subnet Checker. Retrieved in Sep, 2022 from https://www.cdnplanet.com/tools/edns-client-subnet-checker/.Google Scholar
- I. Poese, S. Uhlig, M. A. Kaafar, B. Donnet, and B. Gueye. IP Geolocation Databases: Unreliable? ACM SIGCOMM Comput. Commun. Rev., 41(2):53--56, 2011.Google ScholarDigital Library
- Yakov Rekhter and Tony Li. A Border Gateway Protocol 4 (BGP-4). RFC 4271, RFC Editor, Jan 1994.Google Scholar
- RouteView. BGP RIB Archive Aug,30,2022 Data. Retrieved in Feb, 2023 from ftp://archive.routeviews.org//bgpdata/2022.08/RIBS/rib.20220830. 0000.bz2.Google Scholar
- Sandeep Sarat, Vasileios Pappas, and Andreas Terzis. On the Use of Anycast in DNS. In Proceedings of the 2005 ACM International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS'06), 2006.Google Scholar
- Brandon Schlinker, Todd Arnold, Italo Cunha, and Ethan Katz-Bassett. PEERING: Virtualizing BGP at the Edge for Research. In Proceedings of the 15th ACM Conference on Emerging Networking Experiments and Technologies (CoNEXT '19), 2019.Google ScholarDigital Library
- Brandon Schlinker, Hyojeong Kim, Timothy Cui, Ethan Katz-Bassett, Harsha V. Madhyastha, Italo Cunha, James Quinn, Saif Hasan, Petr Lapukhov, and Hongyi Zeng. Engineering Egress with Edge Fabric: Steering Oceans of Content to the World. In Proceedings of the Annual Conference of the Conference of the ACM Special Interest Group on Data Communication (SIGCOMM'17), 2017.Google ScholarDigital Library
- Kyle Schomp and Rami Al-Dalky. Partitioning the Internet Using Anycast Catchments. ACM SIGCOMM Comput. Commun. Rev., 50(4):3--9, 2020.Google ScholarDigital Library
- Kyle Schomp, Onkar Bhardwaj, Eymen Kurdoglu, Mashooq Muhaimen, and Ramesh K. Sitaraman. Akamai DNS: Providing Authoritative Answers to the World's Queries. In Proceedings of the Annual Conference of the Conference of the ACM Special Interest Group on Data Communication (SIGCOMM'20), 2020.Google ScholarDigital Library
- Yuval Shavitt and Noa Zilberman. A Geolocation Databases Study. IEEE Journal on Selected Areas in Communications, 29(10):2044--2056, 2011.Google ScholarCross Ref
- Neil Spring, Ratul Mahajan, and Thomas Anderson. The Causes of Path Inflation. In Proceedings of the Annual Conference of the Conference of the ACM Special Interest Group on Data Communication (SIGCOMM'03), 2003.Google Scholar
- Neil Spring, Ratul Mahajan, and David Wetherall. Measuring ISP Topologies with Rocketfuel. In Proceedings of the Annual Conference of the Conference of the ACM Special Interest Group on Data Communication (SIGCOMM'02), 2002.Google Scholar
- RIPE NCC Staff. RIPE Atlas: A Global Internet Measurement Network. Internet Protocol Journal, 18, 2015.Google Scholar
- Akamai Technologies. EdgeScape. Retrieved in Sep, 2022 from https://developer.akamai.com/edgescape.Google Scholar
- Lan Wei and John Heidemann. Does Anycast Hang Up on You? In Proceedings of the Network Traffic Measurement and Analysis Conference (TMA'17), 2017.Google ScholarCross Ref
- Xiao Zhang, Tanmoy Sen, Zheyuan Zhang, Tim April, Balakrishnan Chandrasekaran, David Choffnes, Bruce M. Maggs, Haiying Shen, Ramesh K. Sitaraman, and Xiaowei Yang. AnyOpt: Predicting and Optimizing IP Anycast Performance. In Proceedings of the Annual Conference of the Conference of the ACM Special Interest Group on Data Communication (SIGCOMM'21), 2021.Google Scholar
Index Terms
- Regional IP Anycast: Deployments, Performance, and Potentials
Recommendations
A measurement-based deployment proposal for IP anycast
IMC '06: Proceedings of the 6th ACM SIGCOMM conference on Internet measurementDespite its growing use in critical infrastructure services, the performance of IP(v4) Anycast and its interaction with IP routing practices is not well understood. In this paper, we present the results of a detailed measurement study of IP Anycast. Our ...
Towards a global IP anycast service
SIGCOMM '05: Proceedings of the 2005 conference on Applications, technologies, architectures, and protocols for computer communicationsIP anycast, with its innate ability to find nearby resources in a robust and efficient fashion, has long been considered an important means of service discovery. The growth of P2P applications presents appealing new uses for IP anycast. Unfortunately, ...
Towards a global IP anycast service
Proceedings of the 2005 conference on Applications, technologies, architectures, and protocols for computer communicationsIP anycast, with its innate ability to find nearby resources in a robust and efficient fashion, has long been considered an important means of service discovery. The growth of P2P applications presents appealing new uses for IP anycast. Unfortunately, ...
Comments