Measuring the Relationships between Internet Geography and RTT

Abstract

When designing distributed systems and Internet protocols, designers can benefit from statistical models of the Internet that can be used to estimate their performance. However, it is frequently impossible for these models to include every property of interest. In these cases, model builders have to select a reduced subset of network properties, and the rest will have to be estimated from those available. In this paper we present a technique for the analysis of Internet round trip times (RTT) and its relationship with other geographic and network properties. This technique is applied on a novel dataset comprising ∼19 million RTT measurements derived from ∼200 million RTT samples between ∼54 thousand DNS servers. Our main contribution is an information-theoretical analysis that allows us to determine the amount of information that a given subset of geographic or network variables (such as RTT or great circle distance between geolocated hosts) gives about other variables of interest. We then provide bounds on the error that can be expected when using statistical estimators for the variables of interest based on subsets of other variables.

Faces in the Clouds: Long-Duration, Multi-User, Cloud-Assisted Video Conferencing

“…Instead of using a population-related split, the number of DNS servers in the location was used as a proxy for Internet penetration in that area. A dataset of DNS servers was collected by the authors in [19] and this is used for the normalisation. Hence, demand is given in triples (x i , y i , l i ) with the following properties:…”

“…Our datasets are obtained from two measurement studies [4], [19] which look at a large scale dataset gathered using the domain name service (DNS) infrastructure, geolocation of DNS servers and measurement of the delays between them. This work is used in two different ways in this article: (1) to inform us on the likely density of the placement of Internet users within a country; and (2) to translate geographical locations to round-trip times.…”

Taxing the Queue: Hindering Middleboxes From Unauthorized Large-Scale Traffic Relaying

“…• Estimate an approximation to the average RTT from itself to a content recipient [12], [13]. Because wireless access networks have unique latency-estimation issues, they are beyond the scope of this letter.…”

CPV: Delay-Based Location Verification for the Internet

“…A common challenge faced by delay-based geolocation techniques is to find an accurate delay-to-distance mapping function, and thus factors affecting the correctness of this mapping have been well studied in the literature [18], [19]. CPV undertakes a set of measures to mitigate the effect of these factors.…”