Seer: predictive file hoarding for disconnected mobile operation
Seer: predictive file hoarding for disconnected mobile operation
Heavy-tailed probability distributions in the World Wide Web
A practical guide to heavy tails
A large-scale study of file-system contents
SIGMETRICS '99 Proceedings of the 1999 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Simplifying automated hoarding methods
MSWiM '02 Proceedings of the 5th ACM international workshop on Modeling analysis and simulation of wireless and mobile systems
PeerStore: Better Performance by Relaxing in Peer-to-Peer Backup
P2P '04 Proceedings of the Fourth International Conference on Peer-to-Peer Computing
Understanding churn in peer-to-peer networks
Proceedings of the 6th ACM SIGCOMM conference on Internet measurement
A cooperative internet backup scheme
ATEC '03 Proceedings of the annual conference on USENIX Annual Technical Conference
Hi-index | 0.00 |
The high churn and low bandwidth characteristics of peer-to-peer (P2P) backup systems make recovery a time-consuming activity that increases the system's outage. This is especially disturbing from the user's perspective, because during outage the user is prevented from carrying out useful work. Nevertheless, at any given time, a user typically requires only a small number of her files to continue working. If the backup system is able to quickly recover these files, then the system's outage can be greatly reduced, even if a large portion of the data lost is still being recovered. In this paper, we evaluate the use of a file system working set model to support efficient recovery of a P2P backup system. By exploiting a simple LRU-like working set model, we have designed a recovery mechanism that substantially reduces outage and allows the user to return to work more quickly. The simulations we have performed show that even this simple model is able to reduce the outage by as much as 80%, when compared to the state-of-practice in P2P backup recovery.