A physics-style approach to scalability of distributed systems
Number of Authors: 2
2004 (English)Report (Refereed)
BEGIN example. Is it possible to treat large scale distributed systems as physical systems? The importance of that question stems from the fact that the behavior of many P2P systems is very complex to analyze analytically, and simulation of scales of interest can be prohibitive. In Physics, however, one is accustomed to reasoning about large systems. The limit of very large systems may actually simplify the analysis. As a first step, we here analyze the effect of the density of populated nodes in an identifier space in a P2P system. We show that while the average path length is approximately given by a function of the number of populated nodes, there is a systematic correction which depends on the density. In other words, the dependence is both on the number of address nodes and the number of populated nodes, but only through their ratio. Interestingly, the correction is negative for finite densities, showing that an amount of randomness somewhat shortens average path length. END of example.
Place, publisher, year, edition, pages
Swedish Institute of Computer Science , 2004, 1. , 9 p.
SICS Technical Report, ISSN 1100-3154 ; 2004:01
peer-to-peer, complex systems, DHTs
Computer and Information Science
IdentifiersURN: urn:nbn:se:ri:diva-22067OAI: oai:DiVA.org:ri-22067DiVA: diva2:1041609