Peer-to-peer network is attracting considerable interest from researchers because of its scalability and high performance relative to its cost. Because each node in the peer-to-peer network is autonomous, it is difficult to provide deterministic service on the network. Therefore, a new scheme providing fault tolerance for a streaming service is required. In this paper, we propose a framework for a fault tolerant streaming service on a peer-to-peer network. The proposed framework provides a service migration-based fault tolerance mechanism to cope with both node/link failures and link state changes. It maintains up-to-date node state information for rapid service migration when a fault occurs. Simulation results show that using a small-sized buffer, the proposed framework can provide hiccup-free streaming service and the overhead required to maintain the up-to-date node state information is negligible.
|Number of pages||11|
|Journal||Computer Systems Science and Engineering|
|Publication status||Published - Jul 2004|
- Peer-to-Peer network