System architecture for a large scale video on demand service
Computer Networks and ISDN Systems - Driving applications for future networks
A file system for continuous media
ACM Transactions on Computer Systems (TOCS)
Design of a large scale multimedia storage server
JENC5 Selected papers of the annual conference on Internet Society/5th joint European networking conference
Efficient Storage Techniques for Digital Continuous Multimedia
IEEE Transactions on Knowledge and Data Engineering
Continuous Retrieval of Multimedia Data Using Parallelism
IEEE Transactions on Knowledge and Data Engineering
NOSSDAV '95 Proceedings of the 5th International Workshop on Network and Operating System Support for Digital Audio and Video
The Design and Implementation of a RAID-3 Multimedia File Server
NOSSDAV '95 Proceedings of the 5th International Workshop on Network and Operating System Support for Digital Audio and Video
Efficient Data Layout, Scheduling and Playout Control in MARS
NOSSDAV '95 Proceedings of the 5th International Workshop on Network and Operating System Support for Digital Audio and Video
The VLDB Journal — The International Journal on Very Large Data Bases
| Hi-index | 0.00 |
With the increasing processing speeds, there is a shift away from the paradigm of centralized, sequential storage systems towards distributed and network based storage systems. Further, with the new imaging and real time multimedia applications, it is becoming more than ever important to design powerful, efficient and scaleable I/O systems. In this paper, the requirements of storage subsystems in multimedia environment were presented. The storage system components relating to those requirements were analyzed. Current solutions were surveyed and classified. Then we proposed approaches to improve storage subsystem performance for multimedia. The first approach applies constrained layout currently used for single disk model to multi-disk system. The second calls for using a striping unit that meets both media and storage system optimization criteria. The third uses a pool of buffers instead of single buffer per stream.