Abstract
Large-scale P2P systems typically have hundreds of thousands of peers that involve frequent dynamic activities. Current structured overlays do not identify well the rhythm in the dynamic activities, thus resulting in high maintenance overhead. In this paper, we present a new state cache system, called SCS, that solves the problem by exploiting the access patterns of dynamic activities in P2P systems. SCS partitions the whole P2P network into clusters and dynamically chooses a "super" node in each cluster to selectively record and maintain the routing information for departed nodes most likely to arrive back in the near future. The cached routing information enables SCS to simplify self-organization, reduce system maintenance overhead and provide high quality routing service. The experimental results show that SCS reduces the maintenance overhead by up to 66% while delivering much better routing performance, as compared to current structured P2P systems.
Original language | English (US) |
---|---|
Pages (from-to) | 154-168 |
Number of pages | 15 |
Journal | Journal of Parallel and Distributed Computing |
Volume | 65 |
Issue number | 2 |
DOIs | |
State | Published - Feb 2005 |
Keywords
- Maintenance overhead
- Peer-to-peer
- Routing performance
- SCS
- State cache
- Structured
ASJC Scopus subject areas
- Software
- Theoretical Computer Science
- Hardware and Architecture
- Computer Networks and Communications
- Artificial Intelligence