Cluster delegation: high-performance, fault-tolerant data sharing in NFS

Abstract

We present cluster delegation, an enhancement to the NFSv4 file system, that improves both performance and recoverability in computing clusters. Cluster delegation allows data sharing among clients by extending the NFSv4 delegation model so that multiple clients manage a single file without interacting with the server. Based on cluster delegation, we implement a fast commit primitive, cooperative caching, and the ability to recover the uncommitted updates of a failed computer. Cluster delegation supports both read and write operations in the cooperative cache, while preserving the consistency guarantees of NFSv4. We have implemented cluster delegation by modifying the Linux NFSv4 client and show that it improves client performance and reduces server load by more than half.