Abstract

Continuous data protection, which logs every update to a file system, is an enabling technology to protect file systems against malicious attacks and/or user mistakes, because it allows each file update to be undoable. Existing implementations of continuous data protection work either at disk access interface or within the file system. Despite the implementation complexity, their performance overhead is significant when compared with file systems that do not support continuous data protection. Moreover, such kernel-level file update logging implementation is complex and cannot be easily ported to other operating systems. This paper describes the design and implementation of four user-level continuous data protection implementations for NFS servers, all of which work on top of the NFS protocol and thus can be easily ported to any operating systems that support NFS. The first implementation takes a naive update-in-place strategy and requires a separate logging server. The second implementation is based on the first implementation but takes a non-overwrite strategy to reduce the disk I/O overhead associated with writes. The third implementation improves upon the second implementation by eliminating the need of a separate logging server. The last implementation is derived from the third implementation but incorporates a kernel-level performance optimization module to reduce the context switching and memory copying overhead associated with user-level implementations. Measurements obtained from running standard benchmarks and real-world NFS traces on these user-level continuous data protection systems demonstrate a surprising result: Performance of NFS servers protected by pure user-level continuous data protection schemes could be comparable to that of unprotected vanilla NFS servers.

Citations