S.S.Rao, H.M.Vin, and A. Tarafdar. Comparative Evaluation of Server-push and Client-pull Architectures for Multimedia Servers. In Proceedings of NOSSDAV'96, pages 45--48, April 1996.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....overheads are still incurred as the embedded proxy module will still have to receive video data from all other servers and then forward to the clients. not required, as there are no periodic requests traveling from a client back to the servers. Interested readers are referred to Rao et al. [15] for qualitative and simulation comparisons of the two service models in single server multimedia systems. Finally, the studies by Biersack et al. 16] 17] Bolosky et al. 18] Lee [6] and Reddy [19] are more closely related to the architecture proposed in this paper. In particular, the ....

S. S. Rao, H. M. Vin, and A. Tarafdar, "Comparative evaluation of server-push and client-pull architectures for multimedia servers," in Proc. 6th NOSSDAV, Zushi, Japan, Apr. 1996, pp. 45--48.

....is based on the server push service model where the servers continuously transmit data to a client. Briefly speaking, the two service models result in different designs for server and client, as well as different system requirements. Interested readers are referred to Lee [9] and Rao et al. [24] for comparisons between the two service models. Second, while RAIS employed block striping with distributed parity placement, we show that similar placement policy is not scalable for concurrent push. To solve this problem, we propose in Section IX a redundant server scheme that can be scaled up ....

S. S. Rao, H. M. Vin, and A. Tarafdar, "Comparative evaluation of server-push and client-pull architectures for multimedia servers," in Proc. 6th NOSSDAV, Zushi, Japan, Apr. 1996, pp. 45--48.

....playback instant. To do so, applications must estimate the response time of the server and issue requests appropriately. Since the response time varies dynamically depending on the server and the network load, client pull based applications that access image sequences are non trivial to develop [37]. Alternatively, rather than estimating the response 1 Several techniques have been proposed which scramble media streams prior to network transmission to enable approximate reconstruction in case of packet losses [6, 29] Storage Architectures for Digital Imagery 13 Request Response Server ....

S.S.Rao, H.M.Vin, and A. Tarafdar. Comparative Evaluation of Server-push and Client-pull Architectures for Multimedia Servers. In Proceedings of NOSSDAV'96, pages 45--48, April 1996.

....scheduling of requests independently at each disk in the system provides the dynamic storage system needed for full client interactivity. 7.2 Server push vs Client pull This section tries to compare two possible architectures for multimedia servers. The contents of this section are based on [12]. In the client pull architecture, the client requests for each block of data it wants to read and the server transmits it only after receiving the request from the client. While in server push architecture, once a request for a stream has been made by the client, the server automatically keeps on ....

Rao, S. & Vin, H. et al., \Comparative Evaluation of Server-push and Client-pull Architecture for Multimedia Servers".

No context found.

S.S.Rao, H.M.Vin, and A. Tarafdar. Comparative Evaluation of Server-push and Client-pull Architectures for Multimedia Servers. In Proceedings of NOSSDAV'96, pages 45--48, April 1996.

....interface. In addition to these novel features, Symphony synthesizes a number of recent innovations into the file system. These features include: 1) resource reservation (i.e. admission control) algorithms to provide QoS guarantees [32] 2) support for client pull and serverpush architectures [27], 3) support for fixed size and variable size blocks [34] and (4) support for data type specific caching techniques [3, 9] Integrating these diverse techniques into the file system is a key challenge, since it can significantly complicate the file system architecture. For simplicity and ....

....Typically textual applications are serviced using the client pull architecture, whereas, due to their periodic and sequential nature, the server push architecture is better suited for continuous media applications. Adapting continuous media applications to the client pull architecture is difficult [27]. Also, the server push architecture is inappropriate for supporting textual requests due to their aperiodic nature. Hence, to efficiently support multiple data types, an integrated file system will need to support both the client pull architecture and the server push architecture. Placement ....

S.S.Rao, H.M.Vin, and A. Tarafdar. Comparative Evaluation of Server-push and Client-pull Architectures for Multimedia Servers. In Proceedings of NOSSDAV'96, pages 45--48, April 1996.

No context found.

S.S.Rao, H.M.Vin, and A. Tarafdar, "Comparative evaluation of server-push and client-pull architectures for multimedia servers," in Proceedings of NOSSDAV'96, pp. 45--48, April 1996.

.... as SCAN EDF [6] However, our experiments have demonstrated that, even in such a scenario, the number of clients that can be supported by the clientpull architecture were 5 to 20 (for block sizes of 256KB and 32KB, respectively) lower as compared to the corresponding server push architecture [7]. ffl Initiation latency: We define initiation latency to be the difference between the time at which playback is initiated and the time at which the request is transmitted by the client. Since a server push architecture schedules the retrieval of blocks for a client only at round boundaries ....

....serviced as soon as possible and (2) the QoS requirements of the clients already in service are not violated. In fact, our experiments have demonstrated that, by employing such a scheme, the initiation latency of a server push architecture can be brought within 10ms of the client pull architecture [7]. ffl Buffer space requirement: Since round based scheduling synchronizes the accesses of blocks from each disk, and hence requires simultaneous buffer allocations, the server push architecture imposes higher buffer space requirements at the server as compared to its client pull counterpart. ....

[Article contains additional citation context not shown here]

S.S.Rao, H.M.Vin, and A. Tarafdar. Comparative Evaluation of Server-push and Client-pull Architectures for Multimedia Servers. Technical report, Department of Computer Sciences, University of Texas, Austin, 1996.

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