On Fluctuation Resilience of Second Generation Distributed Hash Tables
Nis Ingvar Damm, Dietrich Fahrenholtz, Volker Turau · 2011
Abstract. Every Peer-to-Peer system destined for wide-spread use has to face the challenges imposed by peer population dynamics, which result from peers joining and leaving the system at their own discretion. So any Distributed Hash Table (DHT) design must take precautions against this peer population fluctuation (aka. churn) to sustain efficient lookup performance. Although important, an analysis of the influence of fluctuation on the performance of second generation DHTs in a unified attempt has not been done yet. An existing performance versus cost analysis by Li et al. aims at finding optimal parameters for DHTs being evaluated. However, their analysis focuses on one fluctuation scenario only. In this paper, we analyse second generation DHTs covering a wide range of topologies in a simulation framework under different fluctuation rates and evaluate their performance. Overall Kademlia attains the best lookup performance but its bandwidth consumption goes up significantly when increasing fluctuation rate. With a limited bandwidth budget and high fluctuation rate, Kelips lookup performance is the best among all examined DHTs. 1