Characterizing IPv4 anycast adoption and deployment

Cicalese, Danilo; Augé, Jordan; Joumblatt, Diana; Friedman, Timur; Rossi, Dario

doi:10.1145/2716281.2836101

Cited by 34 publications

(24 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fan et al [20] used a combination of DNS queries and traceroute measurements to identify and characterize anycast nodes and, among their findings, they showed that up to 72% of all TLDs use anycast. Cicalese et al [17] proposed enumeration and city-level geolocation of anycast services using latency measurements, then used it to characterize IPv4 anycast adoption [16]. In later work [21], Fan et alcombined ECS with open DNS resolvers to measure front-ends in Google and Akamai's CDNs.…”

Section: Related Workmentioning

confidence: 99%

Anycast Latency: How Many Sites Are Enough?

Schmidt

Heidemann²,

Kuipers

2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Anycast is widely used today to provide important services including naming and content, with DNS and Content Delivery Networks (CDNs). An anycast service uses multiple sites to provide high availability, capacity and redundancy, with BGP routing associating users to nearby anycast sites. Routing defines the catchment of the users that each site serves. Although prior work has studied how users associate with anycast services informally, in this paper we examine the key question how many anycast sites are needed to provide good latency, and the worst case latencies that specific deployments see. To answer this question, we must first define the optimal performance that is possible, then explore how routing, specific anycast policies, and site location affect performance. We develop a new method capable of determining optimal performance and use it to study four real-world anycast services operated by different organizations: C-, F-, K-, and L-Root, each part of the Root DNS service. We measure their performance from more than 7,900 worldwide vantage points (VPs) in RIPE Atlas. (Given the VPs uneven geographic distribution, we evaluate and control for potential bias.) Key results of our study are to show that a few sites can provide performance nearly as good as many, and that geographic location and good connectivity have a far stronger effect on latency than having many nodes. We show how often users see the closest anycast site, and how strongly routing policy affects site selection.

show abstract

Section: Related Workmentioning

confidence: 99%

Anycast Latency: How Many Sites Are Enough?

Schmidt

Heidemann²,

Kuipers

2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…We depict in Fig. 8(b) the current state of our ongoing effort to perform full IPv4 anycast censuses from PlanetLab [2]. Shortly, for each IP/24 subnet, we first find a responsive target IP address, toward which we perform ICMP latency measurement from all PlanetLab hosts, running iGreedy on the resulting dataset.…”

Section: Applicationsmentioning

confidence: 99%

“…Anycast is an appealing solution as it is very simple to deploy (i.e., avoiding the need to manage some custom and complex application-layer solution), provides users with enhanced quality of experience (e.g., for services where we want to cache content close to the user), while also providing several advantages for the service provider (i.e., load balancing among replicas, robust to DDoS attacks in reason of geographic traffic confinement, etc.). Therefore, many important Internet services [2] use anycast nowadays, to reduce response times and mitigate the effects of server failure and denial of service attacks. While historically IP anycast has been mostly relegated to DNS, we observe an increasing tendency of anycast CDN services: e.g., EdgeCast [3] and CloudFlare [4], that advertise to serve respectively 1.5 billion objects per hour representing the 4% of the whole Internet traffic 1 and over 2 million Web sites 2 , are good examples well testifying this trend.…”

Section: Introductionmentioning

confidence: 99%

Latency-Based Anycast Geolocation: Algorithms, Software, and Data Sets

Cicalese

Joumblatt

Rossi

et al. 2016

IEEE J. Select. Areas Commun.

Self Cite

View full text Add to dashboard Cite

Use of IP-layer anycast has increased in the last few years beyond the DNS realm. Existing measurement techniques to identify and enumerate anycast replicas exploit specifics of the DNS protocol, which limits their applicability to this particular service. In this paper, we propose and thoroughly validate a protocol-agnostic technique for anycast replicas discovery and geolocation, further we also provide the community with open source software and datasets allowing others to replicate our experimental results, potentially facilitating the development of new techniques such as ours.In particular, our proposed method achieves thorough enumeration and city-level geolocalization of anycast instances from a set of known vantage points. The algorithm features an iterative workflow, pipelining enumeration (an optimization problem using latency as input) and geolocalization (a classification problem using side channel information such as city population) of anycast replicas. Results of a thorough validation campaign show our algorithm to be robust to measurement noise, and very lightweight as it requires only a handful of latency measurements.

show abstract

“…Several studies, both by others and us, have used measurement platforms to study anycast [3], [62], [66], [167], [101], [102], [179], [180]. As pre-deployed measurement platforms these systems are available and can measure anycast services externally (without requiring support from the service operator).…”

Section: Related Workmentioning

confidence: 99%

“…Current approaches to manage anycast catchments use one-off active measurements [62], platforms for active measurement such as RIPE Atlas [65], [101], [102], commercial services (for example, [177]), and analysis of anycast service logs [4]. While these approaches have provided insight, and RIPE Atlas and commercial services are in wide use, even the largest services have relatively small numbers of vantage points (from hundreds to 10.000 or so), and it is unclear how these measurement systems relate to actual operational traffic.…”

Section: Introductionmentioning

confidence: 99%

Improving Anycast with Measurements

Vries¹,

Bastiaan²

View full text Add to dashboard Cite

show abstract

Characterizing IPv4 anycast adoption and deployment

Cited by 34 publications

References 25 publications

Anycast Latency: How Many Sites Are Enough?

Anycast Latency: How Many Sites Are Enough?

Latency-Based Anycast Geolocation: Algorithms, Software, and Data Sets

Improving Anycast with Measurements

Contact Info

Product

Resources

About