A popularity-based data allocation scheme for a VOD server

Chang, Carl K.; Shih, Chiao-Chuan; Nguyen, Theresa; Mongkolwat, P.

doi:10.1109/cmpsac.1996.542427

Cited by 3 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In other words, if data unit i is being retrieved, then its successive unit (i + 1) will be accessed next. Compared to traditional computing, data retrieval for on-demand services is more predictable [5]. Therefore, a careful data placement scheme will improve the spatial locality of data retrieval.…”

Section: Data Localitymentioning

confidence: 98%

A circular skip-cluster scheme to support video-on-demand services

Chang

Shih

1999

Multimedia Systems

View full text Add to dashboard Cite

The major drawback of the existing cluster placement scheme is the long response time caused by admission control if the number of clusters and the number of users are large. A circular skip-cluster placement scheme is proposed to reduce the size of the data buffer as well as the system response time. Furthermore, the popularity of each video is different in the real world. We propose a new popularitybased data allocation scheme to allocate data units within a cluster such that the corresponding data units of these popular videos are stored in those cylinders at one end of each cluster. Due to a higher spatial locality within these hot cylinders, some data units requested by the users are stored in the same cylinder such that one seek operation, one rotation, and one transfer operation are required to retrieve these data units. Therefore, the time required to retrieve data for these requests can be reduced, thus also reducing the system response time. Based on our results, the buffer size and the system response time can be reduced by half or more. These findings are essential for constructing video-on-demand systems that provide satisfactory performance.

show abstract

Section: Data Localitymentioning

confidence: 98%

A circular skip-cluster scheme to support video-on-demand services

Chang

Shih

1999

Multimedia Systems

View full text Add to dashboard Cite

show abstract

“…The load balancing issue stems from different object popularities among the movie library, which is a nontrivial issue when modeling and designing large-scale multimedia servers. Because some media objects are more popular than others, the retrieval of media objects is highly skewed in many multimedia applications such as video-on-demand [16][41][57] [62]. A multimedia server with large amount of video objects has to take video popularity into account.…”

Section: Load Balancingmentioning

confidence: 99%

Clustered Multimedia Servers: Architectures and Storage Systems

Tan

Jin

2003

Annual Review of Scalable Computing

View full text Add to dashboard Cite

This paper presents an overview of the recent advances on the design of clustered multimedia servers. It is focused on the following aspects: server architecture, media data organization, real-time stream scheduling and admission control algorithms. For the architecture, we give a taxonomy regarding the various structures of cluster components, and survey over 20 existing server systems, either from the laboratories or the industry. We then examine the data organization methods employed in multimedia servers, which shape the system behavior in many aspects. To reveal the essentials of multimedia service, we take a closer look at the real-time scheduling techniques for streaming data. The admission control issue is finally discussed as an indispensable component for both efficient resource utilization and guaranteed QoS for clients.

show abstract

“…It maintains a root directory in the form of a B + -tree. Each entry in the root directory points to a [16], [24] Interleave Separate Analyze [4], [6] Simulate [35], [39] Sync Cluster Same Analyze [29] Implement [43] Async Cluster Same Simulate [36], [10], [11], [3] Implement [17], [18], [9] Interleave subdirectory that records the physical block locations of an object. The subdirectory is also implemented as a B + -tree.…”

Section: Directory Managermentioning

confidence: 99%

Resource scheduling in a high-performance multimedia server

Pang

Bryan²,

Krishnan³

1999

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Supporting continuous media (CM) data£such as video and audio£imposes stringent demands on the retrieval performance of a multimedia server. In this paper, we propose and evaluate a set of data-placement and retrieval algorithms to exploit the full capacity of the disks in a multimedia server. The data-placement algorithm declusters every object over all of the disks in the server£using a time-based declustering unit£with the aim of balancing the disk load. As for runtime retrieval, the quintessence of the algorithm is to give each disk advance notification of the blocks that have to be fetched in the impending time periods, so that the disk can optimize its service schedule accordingly. Moreover, in processing a block request for a replicated object, the server will dynamically channel the retrieval operation to the most lightly loaded disk that holds a copy of the required block. We have implemented a multimedia server based on these algorithms. Performance tests reveal that the server achieves very high disk efficiency. Specifically, each disk is able to support up to 25 MPEG-1 streams. Moreover, experiments suggest that the aggregate retrieval capacity of the server scales almost linearly with the number of disks.

show abstract

A popularity-based data allocation scheme for a VOD server

Cited by 3 publications

References 4 publications

A circular skip-cluster scheme to support video-on-demand services

A circular skip-cluster scheme to support video-on-demand services

Clustered Multimedia Servers: Architectures and Storage Systems

Resource scheduling in a high-performance multimedia server

Contact Info

Product

Resources

About