The small-world phenomenon: an algorithmic perspective
STOC '00 Proceedings of the thirty-second annual ACM symposium on Theory of computing
A scalable content-addressable network
Proceedings of the 2001 conference on Applications, technologies, architectures, and protocols for computer communications
Chord: a scalable peer-to-peer lookup protocol for internet applications
IEEE/ACM Transactions on Networking (TON)
Pastry: Scalable, Decentralized Object Location, and Routing for Large-Scale Peer-to-Peer Systems
Middleware '01 Proceedings of the IFIP/ACM International Conference on Distributed Systems Platforms Heidelberg
P-Grid: A Self-Organizing Access Structure for P2P Information Systems
CooplS '01 Proceedings of the 9th International Conference on Cooperative Information Systems
Graph-theoretic analysis of structured peer-to-peer systems: routing distances and fault resilience
Proceedings of the 2003 conference on Applications, technologies, architectures, and protocols for computer communications
Techniques for Efficient Routing and Load Balancing in Content-Addressable Networks
P2P '05 Proceedings of the Fifth IEEE International Conference on Peer-to-Peer Computing
SCAN: a small-world structured p2p overlay for multi-dimensional queries
Proceedings of the 16th international conference on World Wide Web
Symphony: distributed hashing in a small world
USITS'03 Proceedings of the 4th conference on USENIX Symposium on Internet Technologies and Systems - Volume 4
A survey and comparison of peer-to-peer overlay network schemes
IEEE Communications Surveys & Tutorials
| Hi-index | 0.00 |
We propose in this paper RCAN, a novel topology to improve the routing performance of CAN overlays while minimizing the maintenance overhead during frequent nodes join and departure in large size networks. The key idea for our design is to equip each node with a few long links towards some distant nodes in the systems. Long links are clockwise directed and wrap around to form small rings along each dimension (multi-ring ). Unlike other protocols, RCAN does not assume a priori fixed limits for the network size or the routing state per node. The number of rings and their sizes self-adjust as nodes join and leave. Nodes auto-adapt their routing states to cope with network changes. RCAN is a pure P2P design, where all nodes assume the same responsibility. Following a uniform greedy routing, RCAN uses O (logn ) routing state and achieves O (logn ) routing performance which is asymptotically optimal. Besides, the communication cost of join operation is reduced to O (logn ) messages, instead of O (log2 n ) in other existing protocols, such as: Chord, pastry, SCAN, etc. Our secondary aim is also to enhance nodes' connectivity to provide more routing flexibility and robustness against failures. Through simulation we demonstrate the full scalability and efficiency of our design and its advantages over other existing methods.