Savage, Stefan
Collins, Andy
Hoffman, Eric
Abstract
The path taken by a packet traveling across the Internet dependson
a large number of factors, including routing protocols and pernetwork
routing policies. The impact of these factors on the end-to-end
performance experienced by users is poorly understood. In this
paper, we conduct a measurement-based study comparing theperformance
seen using the "default" path taken in the Internet with the potential
performance available using some alternate path. Our study uses
five distinct datasets containing measurements of "path quality",
such as round-trip time, loss rate, and bandwidth, takenbetween
pairs of geographically diverse Internet hosts. We construct the
set of potential alternate paths by composing these mea-surements
to form new synthetic paths. We find that in 30-80% of the cases,
there is an alternate path with significantly superior qual-ity.
We argue that the overall result is robust and we explore two
hypotheses for explaining it.
|
Keywords
route
path
length
inflation
Notes
More concerned with delay, latency, packet loss than just length.
|
Related Papers
Bibtex
@inproceedings{ savage.collins_better99,
author = "Stefan Savage and Andy Collins and Eric Hoffman and John Snell and Thomas E. Anderson",
title = "The End-to-End Effects of Internet Path Selection",
booktitle = "ACM SIGCOMM Computer Communication Review",
pages = "289-299",
year = "1999",
volume="29",
month = "Oct.",
url = "citeseer.nj.nec.com/savage99endtoend.html" }