&lt;title&gt;Disk scheduling for multimedia data streams&lt;/title&gt;

Daigle, Steve J.; Strosnider, J.K.

doi:10.1117/12.171701

Cited by 24 publications

(20 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This can be done either ment. Unlike previous studies [9][10][11][12][13], the proposed algoby external helper applications, by plug-ins, or by having rithm does not need real-time hardware and operating the functionality integrated within the browser [1]. Second, system support, and hence can be implemented and dethe TCP transport protocol employed in today's WWW ployed in today's server platforms.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Design and Performance Evaluation of a Multimedia Web Server

Lee

Wong

1998

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

With rapid advances in audio and video technologies, more and more content will be encoded and delivered Today, vast amounts of text, images, graphics, animation, and even Java applets are being hosted and delivered by the by means of audio/video in addition to texts and images. WWW. With rapid advances in audio and video technologies, However, conventional Web servers are designed for data more and more contents will be encoded and delivered by services and hence have no provisions for delivering conmeans of audio/video in addition to texts and images. However, tinuous media (CM) such as audio and video. While a few conventional Web servers are designed for data services and commercial products allow streaming video directly from hence have no provisions for delivering continuous media such standard Web servers using the standard hypertext transfer as audio and video. While one can still provide continuousprotocol (HTTP), the video quality is usually limited and media services by a separate server in addition to the Web subject to the workload of the web server.server, extra hardware cost and management complexity are Another approach is to use a separate server to stream incurred. Moreover, unused capacity in the Web server cannot continuous media. Many commercial products are availbe utilized even if the continuous-media server is overloaded, and vice versa. This paper presents a design and implementa-able in this category. Clearly this approach requires extra tion of a server which integrates continuous-media services hardware and increases management complexity as multiwith traditional Web services. To resolve disk and network ple servers have to be maintained. Moreover, unused cacontentions, a simple yet effective fixed-priority scheduler is pacity in the Web server cannot be utilized even if the CM employed. Experimental results show that the proposed sched-server is overloaded, and vice versa.uler performs well with non-real-time hardware and operating Unlike existing systems, this paper presents a design and system platforms. © 1998 Academic Press implementation for a multimedia server where CM services are integrated with traditional Web services. In other words, the multimedia server software runs on a single server hardware and delivers both Web and CM services.

show abstract

Section: Related Workmentioning

confidence: 99%

“…The Integrated Disk Scheduler is an implementation of Multimedia scheduling has been studied extensively in the integrated scheduler for scheduling requests in the disk the literature, such as in [9][10][11][12][13]. While the proposed algosubsystem.…”

Section: I/o Schedulingmentioning

confidence: 99%

Design and Performance Evaluation of a Multimedia Web Server

Lee

Wong

1998

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

show abstract

“…In case there are quasi-backlogged applications, but no one is eligible (lines [19][20][21][22], V (t) is pushed-up to the minimum virtual start time among all the quasi-backlogged applications (the latter coincide with the applications enqueued in B-WF 2 Q+ when b-wf2q+ get next application is invoked). Since an application is eligible if and only if its virtual start time is not higher than the system virtual time, this jump guarantees B-WF 2 Q+ to be work-conserving [14].…”

Section: The B-wfmentioning

confidence: 99%

“…Existing algorithms for providing a predictable disk service can be broadly divided into three groups: 1) real-time disk schedulers [19], ; 2) proportional share or bandwidth reservation timestampbased disk schedulers (also known as fair-queueing schedulers); and 3) proportional share round robin disk schedulers. In addition, examples of frameworks for providing QoS guarantees are Cello [20], APEX [21], PRISM [22] and Argon [23].…”

Section: Related Workmentioning

confidence: 99%

High Throughput Disk Scheduling with Fair Bandwidth Distribution

Valente

Checconi

2010

IEEE Trans. Comput.

View full text Add to dashboard Cite

Abstract-Mainstream applications-such as file copy/transfer, Web, DBMS, or video streaming-typically issue synchronous disk requests. As shown in this paper, this fact may cause workconserving schedulers to fail both to enforce guarantees and to provide a high disk throughput. A high throughput can be however recovered by just idling the disk for a short time interval after the completion of each request. In contrast, guarantees may still be violated by existing timestamp-based schedulers, because of the rules they use to tag requests.Budget Fair Queueing (BFQ), the new disk scheduler presented in this paper, is an example of how disk idling, combined with proper back-shifting of request timestamps, may allow a timestamp-based disk scheduler to preserve both guarantees and a high throughput. Under BFQ each application is always guaranteed-over any time interval and independently of whether it issues synchronous requests-a bounded lag with respect to its reserved fraction of the total number of bytes transferred by the disk device.We show the single-disk performance of our implementation of BFQ in the Linux kernel through experiments with real and emulated mainstream applications.Index Terms-Scheduling, secondary storage, quality of service.

show abstract

“…In attempting to satisfy multiple concurrent and conflicting requirements (e.g., disk bandwidth, deadline, and priority), scheduler designers and algorithm developers depend mainly on heuristics to code the schedulers (e.g., see [1,2,3,5,6,9,12,14,17,20,21]). It is not always clear that these schedulers are equitable to all aspects of the system, or are controllable in a measurable way to favor one aspect of the system over the other.…”

Section: Introductionmentioning

confidence: 99%