원문정보
초록
영어
An effective decentralized metadata management schema is critical to a reliable and scal-able large-scale distributed storage system. With regard to the defects of huge expansion cost and high sensitivity to cluster alteration borne in both the hash-based and subtree-based metadata management schemas, a metadata server (MDS) clustering schema based on con-sistent hash structure, named DSVL, is proposed. By introducing virtual MDS into the con-sistent MDS cluster, it can effectively balance MDS cluster load. Besides, the standby mecha-nism and the lazy update policy are merged and applied to the MDS cluster to accomplish rapid MDS failover as well as zero data migration in case of cluster alteration. The results of prototype system and simulation test prove that DSVL, with the features of balanced metadata distribution, rapid failover, flexible scalability and zero data migration amount in case of node alteration, can meet the demands for flexible and effective management of large-scale data storage systems with ever increasing data amount.
목차
1. Introduction
2. Related Work
3. Architecture of DSVL
3.1. The MDS Layout Structure
3.2. Balanced Metadata Distribution
4. MDS Failover
5. Experimentation
5.1. Lookup
5.2. Metadata Distribution Balance
5.3. Migration Overhead
6. Discussions
7. Conclusion
Acknowledgement
References
저자정보
참고문헌
- 1Coda: a highly available file system for a distributed workstation environment네이버 원문 이동
- 2Study on the P2P Cloud Storage System네이버 원문 이동
- 3Scalable and Adaptive Metadata Management in Ultra Large-Scale File Systems네이버 원문 이동
- 4Consistent hashing and random trees: distributed caching protocols for relieving hot spots on the World Wide Web네이버 원문 이동
- 5Cloud Database-as-a-Service (DaaS) - ROI네이버 원문 이동
- 6(Reference title not available)
- 7(Reference title not available)
- 8Apache hadoop goes realtime at Facebook네이버 원문 이동
- 9The Hadoop Distributed File System네이버 원문 이동
- 10(Reference title not available)
- 11(Reference title not available)
- 12A nine year study of file system and storage benchmarking네이버 원문 이동
- 13(Reference title not available)
- 14NFS Version 3 Design and Implementation네이버 원문 이동
- 15(Reference title not available)
- 16(Reference title not available)
- 17(Reference title not available)
- 18(Reference title not available)