King: estimating latency between arbitrary internet end hosts
ACM SIGCOMM Computer Communication Review
Chord: a scalable peer-to-peer lookup protocol for internet applications
IEEE/ACM Transactions on Networking (TON)
On lifetime-based node failure and stochastic resilience of decentralized peer-to-peer networks
SIGMETRICS '05 Proceedings of the 2005 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
ASAP: an AS-Aware Peer-Relay Protocol for High Quality VoIP
ICDCS '06 Proceedings of the 26th IEEE International Conference on Distributed Computing Systems
Minimizing churn in distributed systems
Proceedings of the 2006 conference on Applications, technologies, architectures, and protocols for computer communications
Opendht: a public dht service
Peer-to-peer communication across network address translators
ATEC '05 Proceedings of the annual conference on USENIX Annual Technical Conference
ATEC '04 Proceedings of the annual conference on USENIX Annual Technical Conference
Characterizing residential broadband networks
Proceedings of the 7th ACM SIGCOMM conference on Internet measurement
Residual-based estimation of peer and link lifetimes in P2P networks
IEEE/ACM Transactions on Networking (TON)
| Hi-index | 0.00 |
The presence of restrictive network address translators (NATs) and firewalls prevent nodes from directly exchanging packets and thereby pose a problem for peer-to-peer (p2p) communication systems. Skype, a popular p2p VoIP application, addresses this problem by using another Skype client (relay) with unrestricted connectivity to relay the signaling and media traffic between session endpoints. This distributed technique for addressing connectivity issues raises challenging questions about the reliability and latency of relayed calls, relay selection techniques, and the interference of relayed calls with the applications running on relays -- a phenomena we refer to as user annoyance. We devise a framework to analyze reliability in peer-to-peer communication systems and present a simple model to estimate the number of relays needed for maintaining the desired reliability for the media sessions. We then analyze two techniques for improving the reliability of relayed calls. We present a distributed relay selection technique that leverages a two level hierarchical p2p network to find a relay in O(1) hop. We augment our distributed relay selection technique to find a relay that minimizes call latency and user annoyance. Our results indicate that for Skype node lifetimes, at least three relays are needed to achieve a 99.9% success rate for call duration of 60 mins (95th percentile of Skype call durations).