Abstract | ||
---|---|---|
One of the most challenging problems in P2P computing is the difficulty of locating content in an efficient and scalable way. The structured P2P overlay is unsuitable for dynamic environments because users come from non-cooperating organizations with highly dynamic joining and leaving. Unstructured systems are designed more specifically for the heterogeneous Internet environment, where the nodes’ persistence and availability are not guaranteed. In this paper, a detailed measurement study of three popular unstructured P2P overlays and our overlay called MPO is performed. Our method is to analyze performances of classical searching algorithms in various overlays. Key factors in content locations including scalability, query success rate, query messages, cost, disturbed times and fault tolerance are considered carefully. The simulation results show some characteristics in unstructured P2P overlay and prove that MPO is a highly efficient, low cost and fault tolerant overlay. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/CSSE.2008.887 | CSSE (3) |
Keywords | Field | DocType |
topology,p2p,fault tolerance,network topology,search algorithm,overlay,measurement,fault tolerant,searching algorithm | Search algorithm,Computer science,Computer network,Peer to peer computing,Network topology,Fault tolerance,Overlay,Database,The Internet,Scalability,Distributed computing | Conference |
Volume | Issue | Citations |
3 | null | 0 |
PageRank | References | Authors |
0.34 | 5 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiaqi Liu | 1 | 0 | 1.35 |
Zhigang Chen | 2 | 274 | 44.15 |
Deng Li | 3 | 3 | 1.40 |
Athanasios V. Vasilakos | 4 | 12735 | 523.55 |