| E. Cohen, B. Krishnamurthy, and J. Rexford, "Improving end-to-end performance of the Web using server volumes and proxy filters", Proceedings of the ACM SIGCOMM 1998. |
....Wills studied site wide volumes and volumes based on the first level prefix of object s path name [11] They report that for sites with frequently changing resources the latter type of volume is more appropriate because site wide volumes can generate a large number of invalidations. Cohen et al. [5] studied volumes based on access patterns and directory structure and proposed heuristics for thinning volumes. In our approach to volume construction, only objects composing a page are included in a volume, which results in tighter volumes, meaning that clients receive few invalidations that are ....
Edith Cohen, Balachander Krishnamurthy, and Jennifer Rexford. Improving end-to-end performance of the Web using server volumes and proxy filters. In ACM SIGCOMM'98 Conference, September 1998.
....done in data clustering, such as K means [4] HAC [5] CLANRNS [6] etc. In the Web research community, there have been many interesting research studies on clustering Web content or identifying related Web pages for pre fetching, information retrieval, and Web page organization, etc. Cohen et al. [7] investigated the effect of content clustering based on temporal access patterns, and found it effective in reducing latency, but they considered a single server environment, and didn t study the more accurate spatial frequency clustering. Su et al. proposed a recursive density based clustering ....
E. Cohen, B. Krishnamurthy, and J. Rexford, "Improving end-to-end performance of the Web using server volumes and proxy filters," in Proc. of ACM SIGCOMM, 1998.
....Wills studied site wide volumes and volumes based on the rst level pre x of object s path name [11] They report that for sites with frequently changing resources the latter type of volume is more appropriate because site wide volumes can generate a large number of invalidations. Cohen et al. [5] studied volumes based on access patterns and directory structure and proposed heuristics for thinning volumes. In our approach to volume construction, only objects composing a page are included in a volume, which results in tighter volumes, meaning that clients receive few invalidations that are ....
Edith Cohen, Balachander Krishnamurthy, and Jennifer Rexford. Improving end-to-end performance of the Web using server volumes and proxy lters. In ACM SIGCOMM'98 Conference, September 1998.
....which eliminates the issue of waiting for slow or unreachable clients. MONARCH can be deployed using the HTTP protocol and without any extra support from the network, such as multicast. Cohen et al. investigated approaches for grouping related Web objects into volumes and reducing volume size [1]. They explored directory structure and client access patterns as indicators of relationships between objects. In our work we construct volumes based on known relationships between objects instead of using heuristics to infer relationships. Shi et al. also download pages from a set of Web sites ....
E. Cohen, B. Krishnamurthy, and J. Rexford. Improving end-to-end performance of the Web using server volumes and proxy filters. In ACM SIGCOMM'98 Conference, September 1998.
....as K means [7] HAC [8] CLANRNS [9] etc. In the Web research community, there have been many interesting research studies on clustering Web content or identifying related Web pages for various purposes, such as pre fetching, information retrieval, and Web page organization, etc. Cohen et al. [10] investigated the effect of content clustering based on temporal access patterns and found it effective in reducing latency, but they considered a single server environment and didn t study the more accurate spatial clustering. Padmanabhan and Mogul [11] proposed a pre fetching algorithm using a ....
E. Cohen, B. Krishnamurthy, and J. Rexford, "Improving end-to-end performance of the web using server volumes and proxy filters," in Proceedings of ACM SIGCOMM, Sep 1998.
.... can be implemented by either the dissemination of predicted resources to the client [7] or exchange of messages between server and clients, having the server piggybacking information about the predicted resources onto regular response messages, avoiding establishment of any new TCP connections [11]. Such a mechanism has been implemented in [11] 18] and seems the most appropriate since it requires relatively few enhancements to the current request response protocol and no changes to the HTTP 1.1 protocol. In what follows in this article, we assume that there is a system implementing a ....
.... of predicted resources to the client [7] or exchange of messages between server and clients, having the server piggybacking information about the predicted resources onto regular response messages, avoiding establishment of any new TCP connections [11] Such a mechanism has been implemented in [11], 18] and seems the most appropriate since it requires relatively few enhancements to the current request response protocol and no changes to the HTTP 1.1 protocol. In what follows in this article, we assume that there is a system implementing a server based predictive prefetcher, which ....
E. Cohen, B. Krishnamurthy, and J. Rexford, "Improving End-toEnd Performance of the Web Using Server Volumes and Proxy Filters," Proc. ACM Conf. Applications, Technologies, Architectures and Protocols for Computer Comm. (ACM SIGCOMM '98), pp. 241253, Aug. 1998.
No context found.
Edith Cohen, Balachander Krishnamurthy, and Jennifer Rexford. Improving End-to-End Performance of the Web Using Server Volumes and Proxy Filters. Proc. SIGCOMM '98, September, 1998, pp. 241253.
....hints via headers so that proxies between poorly connected clients and the origin server can increase the freshness interval for resources. By providing information to caches along the path, the origin server can help guide caching policies at the intermediaries. As discussed in earlier work [15, 16, 10], hints can be provided by the server about request patterns of resources. Grouping resources into volumes and tailoring them to suit the client s interests can e ectively provide useful information. Now, an additional factor can be used by the server in deciding the set of hints to be delivered ....
Edith Cohen, Balachander Krishnamurthy, and Jennifer Rexford. Improving End-to-End Performance of the Web Using Server Volumes and Proxy Filters. In ########### ## ### ### ####### ### ##########, September 1998. http://www.acm.org/sigcomm/sigcomm98/tp/abs_20.html.
.... non standard ones (such as DNS based content distribution) or again via protocol extensions (such as compression, deltaencoding [11] and HTTP range requests) Piggybacking, which dates back to pre TCP days, has been exploited for obviating unnecessary cache validations [7] and for sending hints [3]. Piggybacking techniques that exploit existing protocols, have low overhead, reduced deployment costs, are easier to test and hopefully be adopted. In this paper, we explore ways to speed up Web delivery by piggybacking some or all of a HTTP resource in DNS responses. Most HTTP transactions are ....
Edith Cohen, Balachander Krishnamurthy, and Jennifer Rexford. Improving End-to-End Performance of the Web Using Server Volumes and Proxy Filters. In Proc. ACM SIGCOMM, September 1998. http://www.acm.org/sigcomm/sigcomm98/ tp/abs_20.html.
....Hence, the resource based policy that was very effective for server side management is not likely to be effective at the proxy s end, client based policies, however, may be effective. Another avenue is to bridge the server client information gap using piggybacking techniques as proposed in [13]. In principle, the two sided control of each persistent connection could lead to global underutilization. Accommodating a new connection may cause the closing of two existing connections, one at each end. Moreover, a connection closed by one end may be a priority at the other end. Such ....
E. Cohen, B. Krishnamurthy, and J. Rexford. Improving end-to-end performance of the Web using server volumes and proxy filters. In Proceedings of the ACM SIGCOMM'98 Conference, September 1998.
No context found.
E. Cohen, B. Krishnamurthy, and J. Rexford, "Improving end-to-end performance of the Web using server volumes and proxy filters", Proceedings of the ACM SIGCOMM 1998.
No context found.
E. Cohen, B. Krishnamurthy, and J. Rexford. Improving End-to-End Performance of the Web Using Server Volumes and Proxy Filters. In Proc. ACM SIGCOMM 98, pages 241--253. ACM, September 1998. http://www.research.att.com/edith/ Papers/sigcomm98.ps.Z
No context found.
E. Cohen, B. Krishnamurthy, and J. Rexford, "Improving end-to-end performance of the Web using server volumes and proxy filters," in Proc. of SIGCOMM'98, Vancouver, BC, 1998, pp. 241--253.
No context found.
E. Cohen, B. Krishnamurthy, and J. Rexford, "Improving End-to-End Performance of the Web Using Server Volumes and Proxy Filters," Proceedings of ACM SIGCOMM, pp. 241-253, Vancouver, British Columbia, September 1998.
No context found.
E. Cohen, B. Krishnamurthy, and J. Rexford, "Improving End-to-End Performance of the Web Using Server Volumes and Proxy Filters," in SIGCOMM, 1998, pp. 241--253.
No context found.
Edith Cohen, Balachander Krishnamurthy, and Jennifer Rexford. Improving end-to-end performance of the Web using server volumes and proxy filters. In ACM SIGCOMM'98 Conference, September 1998.
No context found.
E. Cohen, B. Krishnamurthy, and J. Rexford, "Improving end-to-end performance of the Web using server volumes and proxy filters," in ACM SIGCOMM, Sept. 1998, pp. 241--253.
No context found.
E. Cohen, B. Krishnamurthy, and J. Rexford, "Improving End-to-End Performance of the Web Using Server Volumes and Proxy Filters," In Proceedings of ACM SIGCOMM, pp. 241-253, Vancouver, British Columbia, September 1998.
No context found.
E. Cohen, B. Krishnamurthy, et al. Improving End-to-End Performance of the Web Using Server Volumes and Proxy Filters. In ACM SIGCOMM Conference. 1998.
No context found.
E. Cohen, B. Krishnamurthy, and J. Rexford. Improving end-to-end performance of the Web using server volumes and proxy filters. In Proceedings of the ACM Conference on Applications, Technologies, Architectures and Protocols for Computer Communication (ACM SIGCOMM'98), pages 241--253, 1998.
No context found.
E. Cohen, B. Krishnamurthy, and J. Rexford. Improving end-to-end performance of the web using server volumes and proxy lters. In SIGCOMM '98, 1998.
No context found.
E. Cohen, B. Krishnamurthy, and J. Rexford. Improving end-to-end performance of the web using server volumes and proxy lters. In SIGCOMM '98, 1998.
No context found.
E. Cohen, B. Krishnamurthy, and J. Rexford, "Improving End-toEnd Performance of the Web Using Server Volumes and Proxy Filters," Proc. ACM SIGCOMM '98, Sept. 1998.
No context found.
E. Cohen, B. Krishnamurthy, and J. Rexford. Improving End-to-End Performance of the Web Using Server Volumes and Proxy Filters. 1998.
No context found.
E. Cohen, B. Krishnamurthy, and J. Rexford, "Improving End-to-End Performance of the Web Using Server Volumes and Proxy Filters", Proceedings of ACM SIGCOMM'98 Conference, pp. 241-253, Vancouver, BC, September 1998.
First 50 documents Next 50
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