| R. Keller, W. Eelsberg, and B. Lamparter. Performance Bottlenecks in Digital Movie Systems. In D. Shepherd, G. Blair, G. Coulson, N. Davies, and F. Garcia, editors, Network and Operating System Support for Digital Audio and Video(NOSSDAV'93), Lecture Notes in Computer Science 846, pages 161{ 172. Springer-Verlag, Berlin Heidelberg, 1994. |
....in a class of active accumulation strategies. Simulation studies are used to validate analytical results presented here. 1. 2 Relation to Previous Work The problem of designing a scheduling strategy for CM data has been previously addressed in [RV93] CL93] LS92] AOG92] RVG 93] KEL94] Gem93] GC92] CKY94] TPBG93] Servicing strategies like [CKY93] RW93] and [Gem93] use single buffers while allowing head scheduling algorithms like C SCAN to decide the servicing order. Using single buffers can restrict the subscribers consumption sequence thereby disallowing ....
R. Keller, W. Effelsberg, and B. Lamparter. Performance bottlenecks in digital movie systems. In Proc. of 4 rd Intl. Workshop on Network and Operating Systems, 1994.
....other bottlenecks that are normally associated with actual applications such as the presentation of information (e.g. video display in a window) or the effect of running multiple applications concurrently. Related work undertaken by other researchers in similar areas include: Keller et al. [14] showed the effectiveness of shared memory in the delivery of digital video to user applications. However, no optimization was attempted at either operating system or network layers, which led to poor overall application performance due to various protocol and system overheads (e.g. data copying) ....
R. Keller, W. Effelsberg, and B. Lamparter. "Performance Bottlenecks in Digital Movie Systems", in Proc. of the 4th International Workshop on Network and Operating System Support for Digital Audio and Video, Lancaster House, Lancaster, UK, pp. 163-174, 1993.
.... G large G opt G small x T min transition Figure 9: Optimizing the Phase Switch for 2 phase Active Accumulation Algorithms 7 Related Work The problem of designing a scheduling strategy for continuous media has been addressed by many researchers [RV93] LS92] CL93] AOG92] RVG 93] KEL94] and [TPBG93] Each of them have used a cyclical model similar to the one discussed in this paper. RV93] discuss their approach to designing a multi user high definition TV (HDTV) system. They use a similar scheduling model to the one described here and had realized the non linearity of the ....
R. Keller, W. Effelsberg, and B. Lamparter. Performance bottlenecks in digital movie systems. In Proc. of 4 rd Intl. Workshop on Network and Operating Systems, 1994.
....or other functions cannot be completely eliminated. Neither jitter nor MTU parameters of the transport QoS can be directly in uenced by the MCAM user. MCAM keeps jitter as low as it can to provide an isochronous service. The key mechanism to eliminate jitter is to use queues in shared memory [13]. The MTU size parameter o ered by the transport service is used by MCAM to realize an optimal mapping of CM stream parts to transport data units. The algorithm is simple: If only video has to be transmitted, ll each network packet completely (user data size = MTU) otherwise compute the user ....
....Therefore only the mapping of quality to shared memory bu ers could be realized at this time. A requested high quality implies both high throughput and minimal delay jitter. If this cannot be mapped to operating system and transport guarantees, MCAM uses queues in shared memory to eliminate jitter [13]. Optimal mapping tables for combinations of QoS parameter and available system resources are still experimental. 4.4 Monitoring QoS There are at least two options in QoS handling: either you trust your system components to ful ll the QoS requirements, or you monitor them. Since each system ....
R. Keller, W. Eelsberg, and B. Lamparter. Performance Bottlenecks in Digital Movie Systems. In D. Shepherd, G. Blair, G. Coulson, N. Davies, and F. Garcia, editors, Network and Operating System Support for Digital Audio and Video(NOSSDAV'93), Lecture Notes in Computer Science 846, pages 161{ 172. Springer-Verlag, Berlin Heidelberg, 1994.
....[20] we have gained experience in implementing CM streams (continuous media streams, e.g. video) in a network. We have learned from XMovie and other projects that while low level stream services can be implemented on today s computers successfully, they are currently limited by severe bottlenecks [19]. For the realization of a practical multimedia service in a distributed environment, two additional support services are absolutely necessary: movie directory and CM equipment control. The movie directory is used as a repository for movie information, such as digital image format and storage ....
R. Keller, W. Eelsberg, and B. Lamparter. Performance Bottlenecks in Digital Movie Systems. In Proc. NOSSDAV'93, pages 163-174, Lancaster, U.K., Nov. 1993.
....we have gained experience in implementing CM streams (continuous media streams, e.g. video) in a network. We have learned from XMovie and other projects that while low level stream services can be implemented on today s computers successfully, they are currently limited by severe bottlenecks [20]. For the realization of a practical multimedia service in a distributed environment, two additional support services are absolutely necessary: movie directory and CM equipment control. The movie directory is used as a repository for movie information, such as digital image format and storage ....
R. Keller, W. Effelsberg, and B. Lamparter. Performance Bottlenecks in Digital Movie Systems. In Proc. NOSSDAV'93, pages 163--174, Lancaster, U.K., Nov. 1993.
No context found.
Keller, R., W. Effelsberg, and B. Lamparter. "Performance Bottlenecks in Digital Movie Systems." Proc. 4th International Workshop On Network and Operating System Support for Digital Audio and Video, Lancaster House, Lancaster, U.K., Pages 163-174.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC