Measurement, modeling, and analysis of a peer-to-peer file-sharing workload
SOSP '03 Proceedings of the nineteenth ACM symposium on Operating systems principles
Modeling and performance analysis of BitTorrent-like peer-to-peer networks
Proceedings of the 2004 conference on Applications, technologies, architectures, and protocols for computer communications
QoS-Aware Content Management in P2P Networks
HOT-P2P '04 Proceedings of the 2004 International Workshop on Hot Topics in Peer-to-Peer Systems
P2P contracts: a framework for resource and service exchange
Future Generation Computer Systems - Special issue: P2P computing and interaction with grids
Adaptive content management in structured P2P communities
InfoScale '06 Proceedings of the 1st international conference on Scalable information systems
Ensuring the performance and scalability of peer-to-peer distributed virtual environments
Future Generation Computer Systems
Caching video contents in IPTV systems with hierarchical architecture
ICC'09 Proceedings of the 2009 IEEE international conference on Communications
Editorial: Special Section: P2P and internet computing
Future Generation Computer Systems
Toward a Quality-of-Service Framework for Peer-to-Peer Applications
International Journal of Distributed Systems and Technologies
| Hi-index | 0.00 |
Peer-to-peer (P2P) file-sharing applications allow large communities of users to share multimedia contents. According to their willingness to participate in the P2P community, nodes can switch on and off. An active node participates in the community by downloading content from other nodes and by allowing others to download content which are stored in its own memory. In this paper, we focus on the design of content management at the nodes. Basically, whenever a node retrieves some new content, it may store it in the shared memory and make it available to other users, or it may ''consume'' it on the fly. The storing policy impacts the effectiveness of the application to provide content to users. Indeed, if only few copies of a given content are available, it may happen that, while the nodes storing those copies are off, the content is not available. Based on the probability that this content unavailability occurs, we define a notion of Quality-of-Service (QoS) and we propose criteria for the QoS design of content management policies. Moreover, we consider a simple policy based on these criteria and we evaluate its performance by an analytical model based on a Markovian approach.