Categories
Uncategorized

new conference paper “Anycast in Context: A Tale of Two Systems” at SIGCOMM 2021

We published a new paper “Anycast in Context: A Tale of Two Systems” by Thomas Koch, Ke Li, Calvin Ardi*, Ethan Katz-Bassett, Matt Calder**, and John Heidemann* (of Columbia, where not otherwise indicated, *USC/ISI, and **Microsoft and Columbia) at ACM SIGCOMM 2021.

From the abstract:

Anycast is used to serve content including web pages and DNS, and anycast deployments are growing. However, prior work examining root DNS suggests anycast deployments incur significant inflation, with users often routed to suboptimal sites. We reassess anycast performance, first extending prior analysis on inflation in the root DNS. We show that inflation is very common in root DNS, affecting more than 95% of users. However, we then show root DNS latency hardly matters to users because caching is so effective. These findings lead us to question: is inflation inherent to anycast, or can inflation be limited when it matters? To answer this question, we consider Microsoft’s anycast CDN serving latency-sensitive content. Here, latency matters orders of magnitude more than for root DNS. Perhaps because of this need, only 35% of CDN users experience any inflation, and the amount they experience is smaller than for root DNS. We show that CDN anycast latency has little inflation due to extensive peering and engineering. These results suggest prior claims of anycast inefficiency reflect experiments on a single application rather than anycast’s technical potential, and they demonstrate the importance of context when measuring system performance.

Categories
Papers Publications

new conference paper “Mapping the Expansion of Google’s Serving Infrastructure” in IMC 2013 and WSJ Blog

The paper “Mapping the Expansion of Google’s Serving Infrastructure” (by Matt Calder, Xun Fan, Zi Hu, Ethan Katz-Bassett, John Heidemann and Ramesh Govindan) will appear in the 2013 ACM Internet Measurements Conference (IMC) in Barcelona, Spain in Oct. 2013.

This work was also featured today in Digits, the technology news and analysis blog from the Wall Street Journal, and at USC’s press room.

A copy of the paper is available at http://www.isi.edu/~johnh/PAPERS/Calder13a, and data from the work is available at http://mappinggoogle.cs.usc.edu, from http://www.isi.edu/ant/traces/mapping_google/index.html, and from http://www.predict.org.

[Calder13a] figure 5a
Growth of Google’s infrastructure, measured in IP addresses [Calder13a] figure 5a
 

From the paper’s abstract:

Modern content-distribution networks both provide bulk content and act as “serving infrastructure” for web services in order to reduce user-perceived latency. Serving infrastructures such as Google’s are now critical to the online economy, making it imperative to understand their size, geographic distribution, and growth strategies. To this end, we develop techniques that enumerate IP addresses of servers in these infrastructures, find their geographic location, and identify the association between clients and clusters of servers. While general techniques for server enumeration and geolocation can exhibit large error, our techniques exploit the design and mechanisms of serving infrastructure to improve accuracy. We use the EDNS-client-subnet DNS extension to measure which clients a service maps to which of its serving sites. We devise a novel technique that uses this mapping to geolocate servers by combining noisy information about client locations with speed-of-light constraints. We demonstrate that this technique substantially improves geolocation accuracy relative to existing approaches. We also cluster server IP addresses into physical sites by measuring RTTs and adapting the cluster thresholds dynamically. Google’s serving infrastructure has grown dramatically in the ten months, and we use our methods to chart its growth and understand its content serving strategy. We find that the number of Google serving sites has increased more than sevenfold, and most of the growth has occurred by placing servers in large and small ISPs across the world, not by expanding Google’s backbone.

Categories
Publications Technical Report

new technical report “Mapping the Expansion of Google’s Serving Infrastructure”

We just released a new technical report “Mapping the Expansion of Google’s Serving Infrastructure”, available as https://www.isi.edu/~johnh/PAPERS/Calder13a.pdf

Growth of Google's serving network.
Growth of Google’s serving network (measured here in IP addresses).

From the abstract:

Modern content-distribution networks both provide bulk content and act as “serving infrastructure” for web services in order to reduce user-perceived latency. These serving infrastructures (such as Google’s) are now critical to the online economy, making it imperative to understand their size, geographic distribution, and growth strategies. To this end, we develop techniques that enumerate servers in these infrastructures, find their geographic location, and identify the association between clients and servers. While general techniques for server enumeration and geolocation can exhibit large error, our techniques exploit the design and mechanisms of serving infrastructure to improve accuracy. We use the EDNS-client-subnet extension to DNS to measure which clients a service maps to which of its servers. We devise a novel technique that uses this mapping to geolocate servers by combining noisy information about client locations with speed-of-light constraints. We demonstrate that this technique substantially improves geolocation accurate relative to existing approaches. We also cluster servers into physical sites by measuring RTTs and adapting the cluster thresholds dynamically. Google’s serving infrastructure has grown dramatically in the last six months, and we use our methods to chart its growth and understand its content serving strategy. We find that Google has almost doubled in size, and that most of the growth has occurred by placing servers in large and small ISPs across the world, not by expanding on Google’s backbone.

Datasets from this work will be available, please contact the authors at this time if you’re interested.