Proceedings of the twentieth ACM symposium on Operating systems principles
Journal-guided resynchronization for software RAID
FAST'05 Proceedings of the 4th conference on USENIX Conference on File and Storage Technologies - Volume 4
Dynamo: amazon's highly available key-value store
Proceedings of twenty-first ACM SIGOPS symposium on Operating systems principles
An analysis of data corruption in the storage stack
FAST'08 Proceedings of the 6th USENIX Conference on File and Storage Technologies
End-to-end data integrity for file systems: a ZFS case study
FAST'10 Proceedings of the 8th USENIX conference on File and storage technologies
Inside dropbox: understanding personal cloud storage services
Proceedings of the 2012 ACM conference on Internet measurement conference
Proceedings of the Twenty-Fourth ACM Symposium on Operating Systems Principles
ACM SIGOPS 24th Symposium on Operating Systems Principles
Towards efficient, portable application-level consistency
Proceedings of the 9th Workshop on Hot Topics in Dependable Systems
ViewBox: integrating local file systems with cloud storage services
FAST'14 Proceedings of the 12th USENIX conference on File and Storage Technologies
Hi-index | 0.00 |
Cloud-based file synchronization services, such as Dropbox, have never been more popular. They provide excellent reliability and durability in their server-side storage, and can provide a consistent view of their synchronized files across multiple clients. However, the loose coupling of these services and the local file system may, in some cases, turn these benefits into drawbacks. In this paper, we show that these services can silently propagate both local data corruption and the results of inconsistent crash recovery, and cannot guarantee that the data they store reflects the actual state of the disk. We propose techniques to prevent and recover from these problems by reducing the separation between local file systems and synchronization clients, providing clients with deeper knowledge of file system activity and allowing the file system to take advantage of the correct data stored remotely.