Peer-to-Peer (P2P) computing has emerged as a popular model aiming at further utilizing Internet information and resources. Flooding is the basic method of searching in unstructured P2P networks, however, the blind flooding based search mechanism causes a large volume of unnecessary traffic, and greatly limits the performance of P2P systems. Our study shows that a large amount of these unwanted traffic is divinable and can be avoided while searching in P2P networks. Aiming at reducing the volume of unnecessary traffic, An Unnecessary Message Prediction based Searching mechanism (UMPS) is proposed. UMPS is a pure distributed scheme, it is based on the distributed neighbor list where neighbors within two hops are stored in. UMPS cuts down unwanted traffic by terminating unnecessary flooding that has been predicted in advance, and the techniques related to distributed neighbor list are also discussed. Simulation results show that more than 60% unnecessary messages can be reduced by UMPS, and the query coverage range is retained at the same time, and more unwanted messages can be reduced if a peer has larger degree, therefore load balancing is achieved also. Simulations also reveal that the effectiveness of UMPS is positive correlation with clustering coefficient of network Index Terms-Unstructured Peer-to-peer, flooding, unnecessary message, predict, search
Recovering from node failures is a critical issue in distributed database systems. In conventional log-based recovery protocols, the nodes providing recovery service may be overburdened, especially when the recovery is resource consuming. In this paper, an agent-based dynamic recovery protocol is presented. It divides the whole recovery process into three major steps: logrecovery, agent-recovery, and synchronization. The key idea of this protocol is to cache new database operations initiated during recovery into agents. All these cached operations are then replayed independently for further recovery. The analysis indicates that the new protocol can minimize internode's dependency and improve recovery speed. As a result, system failure rate is cut down and the overall performance gets improved.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.