By Topic

A Comparative Analysis of Server Selection in Content Replication Networks

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Tao Wu ; Nokia Res. Center, Cambridge, MA ; David Starobinski

Server selection plays an essential role in content replication networks, such as peer-to-peer (P2P) and content delivery networks (CDNs). In this paper, we perform an analytical investigation of the strengths and weaknesses of existing server selection policies, based initially on an M/G/1 processor sharing (PS) queueing-theoretic model. We develop a theoretical benchmark to evaluate the performance of two general server selection policies, referred to as EQ_DELAY and EQ_LOAD, which characterize a wide range of existing server selection algorithms. We find that EQ_LOAD achieves an average delay always higher than or equal to that of EQ_DELAY. A key theoretical result of this paper is that in an N-server system, the worst case ratio between the average delay of EQ_DELAY or EQ_LOAD and the minimal average delay (obtained from the benchmark) is precisely N. We constructively show how this worst case scenario can arise in highly heterogeneous systems. This result, when interpreted in the context of selfish routing, means that the price of anarchy in unbounded delay networks depends on the topology, and can potentially be very large. Our analytical findings are extended in asymptotic regimes to the G/G/1 first-come first-serve and multi-class M/G/1-PS models and supported by simulations run for various arrival and service processes, scheduling disciplines, and workload exhibiting temporal locality. These results indicate that our analysis is applicable to realistic scenarios.

Published in:

IEEE/ACM Transactions on Networking  (Volume:16 ,  Issue: 6 )