GPFS: A Shared-Disk File System for Large Computing Clusters
FAST '02 Proceedings of the Conference on File and Storage Technologies
Large files, small writes, and pNFS
Proceedings of the 20th annual international conference on Supercomputing
A comparison of file system workloads
ATEC '00 Proceedings of the annual conference on USENIX Annual Technical Conference
Scalable performance of the Panasas parallel file system
FAST'08 Proceedings of the 6th USENIX Conference on File and Storage Technologies
A nine year study of file system and storage benchmarking
ACM Transactions on Storage (TOS)
Hi-index | 0.00 |
Nowadays many cluster file systems achieve high I/O throughput by parallel I/O from all nodes in the cluster. As concurrent applications usually share the system resources e.g. inode, block bitmap, it's important to coordinate these parallel accesses to preserve file system consistency and POSIX file system semantics. Consequently, a serialization management is required in the cluster file system, which can be realized in the distributed lock management (DLM) scheme. We have implemented DLM for BWFS (Blue Whale File System). The paper introduced the design of BWFS DLM. The strategies for BWFS DLM have also been discussed, which improve existing approaches by effectively reducing additional overhead incurred by the lock management. Theoretical analysis is given to prove the correctness of our novel scheme, and experiments with our prototype implementation are described to show significant benefits from BWFS DLM. In the realistic scenario that need accesses to data and metadata in both of sharing and exclusive modes, our proposed scheme can help BWFS scale up to support a larger cluster installation with high performance and high availability.