| Summary: | The routes used in the Internet's interdomain routing system are a rich
information source that could be exploited to answer a wide range of
questions. However, analyzing routes is difficult, because the fundamental
object of study is a set of paths. In this dissertation, we present new
analysis tools -- metrics and methods -- for analyzing paths, and apply them
to study interdomain routing in the Internet over long periods of time.
Our contributions are threefold. First, we build on an existing metric (Routing
State Distance) to define a new metric that allows us to measure the similarity
between two prefixes with respect to the state of the global routing system.
Applying this metric over time yields a measure of how the set of paths to each
prefix varies at a given timescale. Second, we present PathMiner, a system to
extract large scale routing events from background noise and identify the AS
(Autonomous System) or AS-link most likely responsible for the event. PathMiner
is distinguished from previous work in its ability to identify and analyze
large-scale events that may re-occur many times over long timescales. We show
that it is scalable, being able to extract significant events from multiple
years of routing data at a daily granularity. Finally, we equip Routing State
Distance with a new set of tools for identifying and characterizing
unusually-routed ASes. At the micro level, we use our tools to identify
clusters of ASes that have the most unusual routing at each time. We also show
that analysis of individual ASes can expose business and engineering strategies
of the organizations owning the ASes. These strategies are often related to
content delivery or service replication. At the macro level, we show that the
set of ASes with the most unusual routing defines discernible and interpretable
phases of the Internet's evolution. Furthermore, we show that our tools can be
used to provide a quantitative measure of the "flattening" of the Internet.
|
|---|
