A case for redundant arrays of inexpensive disks (RAID)
SIGMOD '88 Proceedings of the 1988 ACM SIGMOD international conference on Management of data
Designing file systems for digital video and audio
SOSP '91 Proceedings of the thirteenth ACM symposium on Operating systems principles
Staggered striping in multimedia information systems
SIGMOD '94 Proceedings of the 1994 ACM SIGMOD international conference on Management of data
Scheduling policies for an on-demand video server with batching
MULTIMEDIA '94 Proceedings of the second ACM international conference on Multimedia
Efficient Storage Techniques for Digital Continuous Multimedia
IEEE Transactions on Knowledge and Data Engineering
The Evaluation of Video Layout Strategies on a High-Bandwidth File Server
NOSSDAV '93 Proceedings of the 4th International Workshop on Network and Operating System Support for Digital Audio and Video
An Efficient Data Layout Scheme for Multi-Disks Continuous Media Servers
Multimedia Tools and Applications
Data Placement Scheme on Continuous Media Servers with ZBR Disks
ITCC '00 Proceedings of the The International Conference on Information Technology: Coding and Computing (ITCC'00)
Data migration in RAID based on stripe unit heat
ICMLC'05 Proceedings of the 4th international conference on Advances in Machine Learning and Cybernetics
Hi-index | 0.00 |
Rapid progress in high speed networking and mass storage technologies has made it possible to provide video-on-demand (VOD) services, that deliver movies to viewers' homes on request. In this paper, we study video data layout issues in the video server design. Specifically, we present a family of novel video data layout strategies, called Zone-Bit-Recording-Enhanced (ZBRE) layout schemes, which take into account the multiple-zone-recording feature of modern disk drives. The ZBRE layout schemes can be applied to either individual disks or disk arrays, such as RAID 3. Simulation results show that, by carefully laying out popular movies in the outer zones and aggregating "hot" movies together, disk performance can be improved significantly, with an up to 23% higher throughput than by randomly laying out data on disks. More importantly, these performance benefits are obtained without incurring any extra hardware cost.