TY - JOUR
T1 - Fine-Grained Device Management in an Interactive Media Server
AU - Rangaswami, Raju
AU - Dimitrijevic, Zoran
AU - Chang, Edward
AU - Gary Chan, Shueng Han
PY - 2003/12
Y1 - 2003/12
N2 - The use of interactive media has already gained considerable popularity. Interactivity gives viewers VCR controls like slow-motion, pause, fast-forward, and instant replay. However, traditional server-based or client-based approaches for supporting interactivity either consume too much network bandwidth or require large client buffering; and hence they are economically unattractive. In this paper, we propose the architecture and design of an interactive media proxy (IMP) server that transforms noninteractive broadcast or multicast streams into interactive ones for servicing a large number of end users. For IMP to work cost-effectively, it must carefully manage its storage devices, which are needed for caching voluminous media data. In this regard, we propose a fine-grained device management strategy consisting of three complementary components: disk profiler, data placement, and IO scheduler. Through quantitative analysis and experiments, we show that these fine-grained strategies considerably improve device throughput under various workload scenarios.
AB - The use of interactive media has already gained considerable popularity. Interactivity gives viewers VCR controls like slow-motion, pause, fast-forward, and instant replay. However, traditional server-based or client-based approaches for supporting interactivity either consume too much network bandwidth or require large client buffering; and hence they are economically unattractive. In this paper, we propose the architecture and design of an interactive media proxy (IMP) server that transforms noninteractive broadcast or multicast streams into interactive ones for servicing a large number of end users. For IMP to work cost-effectively, it must carefully manage its storage devices, which are needed for caching voluminous media data. In this regard, we propose a fine-grained device management strategy consisting of three complementary components: disk profiler, data placement, and IO scheduler. Through quantitative analysis and experiments, we show that these fine-grained strategies considerably improve device throughput under various workload scenarios.
KW - Data placement
KW - Disk profiling
KW - IO scheduling
KW - Interactive
KW - Media server
KW - Streaming
KW - Video-on-demand
UR - https://openalex.org/W2114585791
UR - https://www.scopus.com/pages/publications/0344395624
U2 - 10.1109/tmm.2003.814722
DO - 10.1109/tmm.2003.814722
M3 - Journal Article
SN - 1520-9210
VL - 5
SP - 558
EP - 569
JO - IEEE Transactions on Multimedia
JF - IEEE Transactions on Multimedia
IS - 4
ER -