Braun, H., and Claffy, K. "Web Traffic Characterization: An Assessment of the Impact of Caching Documents from NCSA's Web Server", Proceedings of the 2 nd International WWW Conference, Chicago, 1994.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....on improving performance by reducing the load on the overloaded devices in the system. This is typically done in one of four ways: increasing the capacity of the system for example by using server farms or multiprocessor machines [20, 22] using caches either on the client or on the server side [26, 15, 13]; designing more efficient software both at the OS level [34, 7, 23, 29] and the application level [37] and admission control [17, 44] Other means of avoiding overload are content adaptation [1] and offloading work to the client [3] Our work differs significantly from all these approaches in ....

H. Braun and K. Claffy. Web traffic characterization: an assessment of the impact of caching documents from NCSA's Web server. In Proceedings of the Second International WWW Conference, 1994.

.... Since the initial World Wide Web prototype was developed in 1990, it grows rapidly and becomes the most popular system on the Internet in recentyears [2] According to the Internet Domain Survey conducted in January 1996 about76 systems now have the registered domain name www,upfromonly 6 in July, 1994 [9] Due to the increasing demands of web requests, it becomes a critical issue for a web server of a popular site to offer high performance and guarantee high availability. Aweb server must be able to servemultiple simultaneous requests promptly even in its peak time. Besides, from the ....

....a worldwide web server on top of a multicomputer machine designed and implemented in our laboratory.Themachine uses a multistage switching network to connect multiple clusters of multiprocessors. Each processor This work was partially supported by the National Science Council under grants NSC84 2221 E 002 004, and NSC85 2221E 002 029. can either be a simple CPU module, or with individual storage devices and or network adapters attached depending on the needs of applications. As a result, multiple I O devices can be accessed concurrently to provide higher I O bandwidth than single bus ....

[Article contains additional citation context not shown here]

H. Braun, and K. Claffy,"Web Traffic characterization: an assessment of the impact of caching documents from NCSA's web server," Second World Wide Web Conference, Oct. 1994.

....and to non static requests. We also discuss SRPT applied to web server farms and Internet routers. 2 Previous Work There has been much literature devoted to improving the response time of web requests. Some of this literature focuses on reducing network latency, e.g. by caching requests ( 21] [12], 11] or improving the HTTP protocol ( 19] 32] Other literature works on reducing the delays at a server, e.g. by building more efficient HTTP servers ( 20] 33] or improving the server s OS ( 18] 5] 26] 29] Recent studies show that delays at the server make up a significant ....

H. Braun and K. Claffy. Web traffic characterization: an assessment of the impact of caching documents from NCSA's Web server. In Proceedings of the Second International WWW Conference, 1994.

....way to reduce the experienced latencies, the server s load, and the network congestion is to store multiple copies of the same Web documents in geographically dispersed Web caches. As most of the Web content is rather static, the idea of Web caching is not new. The first WWW browsers, e.g. Mosaic [10], were able to cache Web objects for later reference, thus, reducing the bandwidth used for Web traffic and the latency to the users. Web caching rapidly extended from a local cache used by a single browser to a shared cache serving all the clients from a certain institution. Unfortunately, since ....

K. Claffy and H.-W. Braun, "Web traffic characterization: an assessment of the impact of caching documents from NCSA's web server", In Electronic Proceedings of the Second World Wide Web Conference'94: Mosaic and the Web, 1994.

....and to non static requests. We also discuss SRPT applied to web server farms and Internet routers. 2 Previous Work There has been much literature devoted to improving the response time of web requests. Some of this literature focuses on reducing network latency, e.g. by caching requests ( 21] [12], 11] or improving the HTTP protocol ( 19] 32] Other literature works on reducing the delays at a server, e.g. by building more efficient HTTP servers ( 20] 33] or improving the server s OS ( 18] 5] 26] 29] Recent studies show that delays at the server make up a significant ....

H. Braun and K. Claffy. Web traffic characterization: an assessment of the impact of caching documents from NCSA's Web server. In Proceedings of the Second International WWW Conference, 1994.

....packet latency. However, Myers et al. show that the ranking of download times of the same three sites from 47 different mirrors was stable [10] Caching has been widely studied as a means for enhancing performance in the Internet during the 1990 s. These studies include cache traffic evaluation [11], 12] replacement algorithm BARFORD, CAI, GAST 3 performance [13] 14] cache hierarchy architecture [15] 16] and cache appliance design [17] 18] A number of recent papers have addressed the issue of proxy placement based on assumptions about the underlying topological structure of the ....

H. Braun and K. Claffy, "Web traffic characterization: An assessment of the impact of caching documents from NCSA's Web server," in Proceedings of the Second International WWW Conference, Chicago, IL, October 1994.

.... This is often done by replacing the server by a server farm (e.g. 8, 6, 16] Another solution is to enhance the OS to better support server software: 20, 9, 1, 15, 19] Finally, people try to limit the load at a server, either via installing a proxy cache (at the client or server end) e.g. [10, 4]) or by admission control ( 13] Our approach to coping with transient overload is different from the above approaches. Our approach does not require buying more hardware or limiting the number of system users. We simply propose scheduling the jobs in a different order from that traditionally ....

H. Braun and K. Claffy. Web traffic characterization: an assessment of the impact of caching documents from NCSA's Web server. In Proceedings of the Second International WWW Conference, 1994.

....a Web server. For that purpose, we analyzed the HTTP log of a Web server at George Mason University to characterize its workload. The results of this characterization are described in the following section. 3. 0 Workload Characterization Many studies have characterized the workload of Web servers [AAY97,AFAW97,AW96,BC94,CB96,CJ97]. These studies have concluded that many of the relevant parameters of a Web server traffic, such as the size of files requested, have a power tail. By this we mean that the tail of the cumulative distribution function decreases with a power law. Our findings support this conclusion as shown in ....

Braun, H., and Claffy, K. "Web Traffic Characterization: An Assessment of the Impact of Caching Documents from NCSA's Web Server", Proc. of the 2 nd International WWW Conference, Chicago, 1994.

....server, including idle ( OFF time ) periods. ffl See http: www.w3c.org WCA # Web Server Performance Analysis Paul Barford Page 6 Starting Points ffl General Web Performance Studies [14, 40] ffl Web Client Behavior Studies [9, 16, 20, 28, 32, 34, 52, 22] ffl Web Server Behavior Studies [3, 4, 5, 6, 7, 12, 13, 26, 29, 45] ffl Web Proxy and Caching Studies [2, 15, 23, 25, 36, 38, 51, 56, 57] ffl Network Effects of Web Traffic [11, 17, 19, 37, 44, 43, 42, 24, 27] ffl Load Generators [1, 8, 10, 18, 39, 46, 54, 55] # Web Server Performance Analysis Paul Barford Page 7 Key Questions for Performance Analysis ....

H. Braun and K. Claffy. Web traffic characterization: An assessment of the impact of caching documents from ncsa's web server. In Proceedings of the Second International WWW Conference, Chicago, IL, October 1994.

....effect of reducing the bandwidth available for competing requests, and thus increasing latencies for other users. In order to reduce access latencies, it is desirable to store copies of popular objects closer to the user. Consequently, Web caching has become an increasingly important topic [1] [8], 14] 18] 19] 22] Caching can be implemented at various points in the network. On one end of the spectrum, there is typically a cache in the Web server itself. Further, it is increasingly common for a university or corporation to implement specialized servers in the network called caching ....

# H. Braun and K. Claffy, "Web Traffic Characterization: An Assessment of the Impact of Caching Documents from NCSA's Web Server," Proc. Second Int'l World Wide Web Conf., Chicago, 1994.

....so as to maximize the strength of the encryption [24] Compressed data already makes up a large part of Internet traffic. For example, World Wide Web traffic has grown to exceed all other Internet traffic sources combined, whether measured by number of packets, number of bytes, or number of flows [5], 37] and furthermore, 65 of World Wide Web traffic is compressed GIF or JPEG image data [12] We expect to see an increasing awareness of security issues on the Internet in the future, resulting in a similar increase in encrypted data. However, at the present time, not all traffic is ....

H. W. Braun and K. Claffy, "Web traffic characterization: An assessment of the impact of caching documents from NCSA's web server," in Proc. 2nd Int. World Wide Web (WWW) Conf. `94, Chicago, IL, Oct. 1994.

....results in increasing load on its constituent networks and servers, and stresses the protocols that the Web is based on. Improving the performance of the Web has been the subject of much recent research, addressing various aspects of the problem such as better Web caching [Bestavros et al. 1995; Braun and Claffy 1994; Chankhunthod et al. 1996; Seltzer and Gwertzman 1995; Williams et al. 1996] HTTP protocol enhancements [Fielding et al. 1997; Mogul et al. 1997; Padmanabhan and Mogul 1994; Banga et al. 1997; Spasojevic et al. 1994] better HTTP servers and proxies [Apache 1998; Chankhunthod et al. 1996; ACME ....

.... To date most work on measuring Web software performance has concentrated on accurately characterizing Web server workloads in terms of request file types, transfer sizes, locality of reference in URLs requested and other related statistics [Arlitt and Williamson 1996; Bestavros et al. 1995; Braun and Claffy 1994; Crovella and Bestavros 1996; Cunha et al. 1995; Kwan et al. 1995] Some researchers have tried to evaluate the performance of Web servers and proxies using real workloads directly [Maltzahn et al. 1997; Mogul 1995a; Banga and Mogul 1998] However, this approach suffers from the experimental ....

[Article contains additional citation context not shown here]

Braun, H. and K. Claffy (1994), "Web Traffic Characterization: An Assessment of the Impact of Caching Documents from NCSA's Web Server," In Proceedings of the Second International WWW Conference, Chicago, IL, pp. 1007--1027.

....way to reduce the experienced latencies, the server s load, and the network congestion is to store multiple copies of the same Web documents in geographically dispersed Web caches. As most of the Web content is rather static, the idea of Web caching is not new. The first WWW browsers, e.g. Mosaic [10], were able to cache Web objects for later reference, thus, reducing the bandwidth used for Web traffic and the latency to the users. Web caching rapidly extended Pablo Rodriguez, Christian Spanner, and Ernst W. Biersack are with Institut EURECOM, Sophia Antipolis, France. frodrigue, spanner, ....

K. Claffy and H.-W. Braun, "Web traffic characterization: an assessment of the impact of caching documents from NCSA's web server", In Electronic Proceedings of the Second World Wide Web Conference '94: Mosaic and the Web, 1994.

....to Transactions on Networking, May 99 network congestion is to store multiple copies of the same Web documents in geographically dispersed Web caches. As most of the Web content is rather static, the idea of Web caching at the application layer is not new. The first WWW browsers, e.g. Mosaic [7], were able to cache Web objects for later reference, thus, reducing the bandwidth used for Web traffic and the latency to the users. Web caching rapidly extended from a local cache used by a single browser to a shared cache serving all the clients from a certain institution. Unfortunately, since ....

K. Claffy and H.-W. Braun, "Web traffic characterization: an assessment of the impact of caching documents from NCSA's web server", In Electronic Proceedings of the Second World Wide Web Conference '94: Mosaic and the Web, 1994.

....approach, which is common practice for modeling of conventional workloads, has for example been followed in [11] but here the objective was to study user behavior from an HCI point of view. Characterizing System Oriented Parameters The timings related to GETs have been studied in various papers [3, 12, 4]. As most Web servers and proxy servers provide access log files, these data can serve as a basis for the evaluation. In addition, network sniffer programs can be used to obtain further information. Finally, the timings for opening starting and terminating of browsers and windows have to be ....

H.-W. Braun and K. Claffy, "Web traffic characterization: An assessment of the impact of caching documents from ncsa's web server", in Proc. of Second Int. WWW Conference, 1994, http://www.ncsa.uiuc.edu/SDG/IT94/Proc."/DDay/claffy.

.... time(r) the time to respond to the GET time(ffl) the time to terminate an activity time(fi) the time to start a browser time( the time to open a window The timings related to GETs and to TCP IP requests if all levels are considered have been studied in various papers [Alme 96, Arli 95, Brau 94] As most Web servers and proxy servers provide access log files, these data can serve as a basis for the evaluation. In addition, network sniffer programs can be used to obtain further information. Finally, the timings for opening starting and terminating of browsers and windows have to be ....

H.-W. Braun and K. Claffy. "Web Traffic Characterization: An Assessment of the Impact of Caching Documents from NCSA's Web Server". In: Proceedings of Second International WWW Conference, Chicago, IL, USA, October 1994. http://www.ncsa.uiuc.edu/SDG/IT94/Proceedings/DDay/claffy.

....backbones and to improve user response times [Gwertzman Seltzer 1996, Chankhunthod et al. 1996, Zhang et al. 1997] One early study [Danzig et al. 1993] found that strategically placed caches could reduce FTP file traffic by as much as 50 . Similar studies of Web traffic yielded similar results [Braun Claffy 1994, Duska et al. 1997, Gribble Brewer 1997] As already described in Chapter 3, any caching scheme will be limited, among other considerations, by the fraction of Web pages that are dynamically generated, and hence classified as uncacheable. For instance, a CGI bin program might be run to produce ....

H. Braun and K. Claffy. "Web Traffic Characterization: An Assessment of the Impact of Caching Documents From NCSA's Web Server". In Second International World Wide Web Conference, October 1994.

....as performance, security, and limited functionality of WWW based management applications that are currently becoming available. The problems of performance in the web are well known. Some measures to improve aspects such as HTTP latency, geographic distribution and caching have been suggested [29][30], and are being taken into use. WWW applications use a document driven model : meaning long lived text, images, icons, and hot links to other documents. Clients can typically launch new applications to display movies or real time video and audio. Network management applications often interact ....

H.W. Braun, K.C. Clark, Web traffic characterization: an assessment of the impact of caching documents from NCSA's web server, Computer Networks and ISDN Systems 28, Dec 1995, pp.37-51. NWPER'96

No context found.

Braun, H., and Claffy, K. "Web Traffic Characterization: An Assessment of the Impact of Caching Documents from NCSA's Web Server", Proceedings of the 2 nd International WWW Conference, Chicago, 1994.

No context found.

H.-W. Braun and K. Claffy. "Web Traffic Characterization: An Assessment of the Impact of Caching Documents From NCSA's Web Server". In Second International World Wide Web Conference, October 1994.

No context found.

K. Claffy and H.-W. Braun, "Web traffic characterization: An assessment of the impact of caching documents from NCSA's web server," in Electronic Proc. 2nd World Wide Web Conf.'94: Mosaic and the Web, 1994.

No context found.

K. C. Claffy and H. Braun. Web traffic characterization: an assessment of the impact of caching documents from NCSA's web server. http://www.ncsa.uiuc.edu/SDG/IT94/Proceedings/DDay/claffy/main.html, September 1994.

No context found.

H.-W. Braun and K. Claffy. Web traffic characterization: an assessment of the impact of caching documents from ncsa's web server. In Proceedings of the Second International World Wide Web Conference, Oct. 1994.

No context found.

H. Braun and K. Claffy. Web traffic characterization: an assessment of the impact of caching documents from NCSA's Web server. In Proceedings of the Second International WWW Conference, 1994.

No context found.

K. C. Claffy, "Web traffic characterization: an assessment of the impact of caching documents from NCSA's web server," in Proceedings of the Second International WWW Conference, 1994. http://www.ncsa.uiuc. edu/SDG/IT94/Proceedings/DDay/claffy/main.html.

First 50 documents

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