Serverless network file systems
ACM Transactions on Computer Systems (TOCS) - Special issue on operating system principles
File server scaling with network-attached secure disks
SIGMETRICS '97 Proceedings of the 1997 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
ONE-IP: techniques for hosting a service on a cluster of machines
Selected papers from the sixth international conference on World Wide Web
A case for intelligent disks (IDISKs)
ACM SIGMOD Record
Efficient admission control algorithms for multimedia servers
Multimedia Systems
IEEE Concurrency
Parallel Video Servers: A Tutorial
IEEE MultiMedia
COMPCON '96 Proceedings of the 41st IEEE International Computer Conference
A Scalable Distributed Multimedia File System Using Network Attached Autonomous Disks
MASCOTS '00 Proceedings of the 8th International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems
Bandwidth Guarantee in a Distributed Multimedia File System Using Network Attached Autonomous Disks
RTAS '00 Proceedings of the Sixth IEEE Real Time Technology and Applications Symposium (RTAS 2000)
Active disks: remote execution for network-attached storage
Active disks: remote execution for network-attached storage
Concurrent push-A scheduling algorithm for push-based parallel video servers
IEEE Transactions on Circuits and Systems for Video Technology
Supporting server-level fault tolerance in concurrent-push-based parallel video servers
IEEE Transactions on Circuits and Systems for Video Technology
Admission control for statistical QoS: theory and practice
IEEE Network: The Magazine of Global Internetworking
Medusa: a novel stream-scheduling scheme for parallel video servers
EURASIP Journal on Applied Signal Processing
Hi-index | 0.00 |
This paper proposes a new architecture, called intelligent network attached storage, for building a distributed video server. In this architecture, the data intensive and high overhead processing tasks such as data packaging and transmitting are handled locally at the storage nodes instead of at special delivery nodes. Thus an unnecessary data trip from the storage nodes to the delivery nodes is avoided, and a large amount of resource consumption is saved. Moreover, these "intelligent" storage nodes work cooperatively to give a single system image to the clients. Based on the architecture, we design our admission control and stream scheduling strategies, and conduct some simulation experiments to optimize the system design. The simulation results exhibit a near linear scalability of system performance with our design. Some implementation issues are also discussed in this paper.