Pei Cao. Characterization of Web Proxy Traffic and Wisconsin Proxy Benchmark 2.0, In World Wide Web Consortium Workshop on Web Characterization, Cambridge, MA, November 1998. Position paper.  Home/Search   Document Not in Database   Summary   Related Articles   Check

.... sources for characterizing web traffic patterns and trends (as in [12, 29, 28, 23] for building analytical models of same that can be used to generate artificial logs with the same patterns; and for testing, evaluating, and tuning systems such as proxy caches, switches, and web servers (as in [2, 1, 3, 11, 19]) Trace logs to be examined Log Type Software Date Number of Clients Number of Requests (HTML only all) Description Comments O1 Origin WebSite August 1997 April 1998 2968 48k 189k small software company approximately 9 of HTML requests from spiders O2 Origin Apache September 1998 October 1998 ....

Pei Cao. Characterization of Web Proxy Traffic and Wisconsin Proxy Benchmark 2.0, In World Wide Web Consortium Workshop on Web Characterization, Cambridge, MA, November 1998. Position paper.

.... As noted earlier, Gaurav Banga and Peter Druschel addressed the lack of realism in HTTP server benchmarks, and also developed an improved benchmark client [2] Similarly, Jussara Almeida and Pei Cao have been developing the Wisconsin Proxy Benchmark for measuring Web proxy server performance [6]. Proxy cache benchmarking is more difficult than simple server benchmarking, because one must emulate realistic serveraccess delays and realistic reference stream locality. 2.4. Statistics from recent conferences What do operating systems publications actually use for benchmarks I examined the ....

P. Cao. Characterization of Web Proxy Traffic and Wisconsin Proxy Benchmark 2.0. In Web Characterization Workshop. World Wide Web Consortium, Cambridge, MA, Nov., 1998. http://www.cs.wisc.edu/~cao/w3c-webchar-position/.

.... will be referenced k times after it was last referenced tends to be proportional to 1=k [104, 23] There is low correlation between the popularity of an object and its size, even though the average size of unpopular objects is larger than the average size of popular objects (see Chapter 4 20 and [22, 78]) The more popular an HTTP object is, the more likely it stays a popular object. The day to day membership variation of the top 1 most popular objects is much lower than the variation in the top 10 most popular objects (see Chapter 6 and [22, 79] This allows for relatively static working set ....

....size of popular objects (see Chapter 4 20 and [22, 78] The more popular an HTTP object is, the more likely it stays a popular object. The day to day membership variation of the top 1 most popular objects is much lower than the variation in the top 10 most popular objects (see Chapter 6 and [22, 79]) This allows for relatively static working set capture algorithms as is demonstrated by Rousskov et al. 110] In a study which explores rate of change, age, and inter modification time of Web objects, Douglis et al. 41] find that 22 of the resources referenced in their traces are accessed ....

Pei Cao. Characterization of Web Proxy Traffic and Wisconsin Proxy Benchmark 2.0. In W3C Web Characterization Workshop, Nov 5 1998.

....of documents, and reasons why documents are not cacheable. Finally, Section 7 summarizes our study and its results. 2 Previous Work Numerous recent studies of web traffic have been performed. These studies include analyses of web access traces from the perspective of browsers [10, 19] proxies [9, 2, 17, 12, 15, 11, 22, 5, 6, 4, 14], and servers [21, 1, 3] The earlier tracing studies were rather limited in request rate, number of requests, and diversity of population. The most recent tracing studies have been larger and generally more diverse. In addition to static analysis, some studies have also used trace driven cache ....

Pei Cao. Characterization of web proxy traffic and Wisconsin proxy benchmark 2.0, November 1998.

....5 then uses the model to compare cooperative caching schemes, and Section 6 summarizes and concludes. 2 Related work Web tracing and caching are highly active research areas. Recent studies of Web traffic include analyses of Web access traces from the perspective of browsers [11, 26] proxies [2, 5, 6, 7, 10, 13, 14, 18, 20, 23, 30], and servers [1, 4, 29] Earlier tracing studies were limited in request rate, number of requests, and diversity of population. The most recent tracing studies have been larger and more diverse. In addition to static analysis, some studies have also used trace driven cache simulation to ....

P. Cao. Characterization of Web proxy traffic and Wisconsin proxy benchmark 2.0. http://www.cs.wisc.edu/ cao/w3c-webchar-position, Nov. 1998. 30

....of documents, and reasons why documents are not cacheable. Finally, Section 7 summarizes our study and its results. 2 Previous Work Numerous recent studies of Web traffic have been performed. These studies include analyses of Web access traces from the perspective of browsers [11, 21] proxies [2, 4, 6, 10, 12, 15, 18, 19, 24], and servers [1, 3, 23] The earlier tracing studies were rather limited in request rate, number of requests, and diversity of population. The most recent tracing studies have been larger and generally more diverse. In addition to static analysis, some studies have also used trace driven cache ....

Pei Cao. Characterization of web proxy traffic and Wisconsin proxy benchmark 2.0, November 1998.

....model of Web behavior and presents results gained from that model. Section 5 summarizes and concludes. 2 Related Work Web tracing and caching are highly active research areas. Recent studies of Web traffic include analyses of Web access traces from the perspective of browsers [11, 25] proxies [10, 2, 23, 14, 20, 13, 28, 6, 7, 5, 17], and servers [27, 1, 4] The earlier tracing studies were rather limited in request rate, number of requests, and diversity of population. The most recent tracing studies have been larger and generally more diverse. In addition to static analysis, some studies have also used trace driven cache ....

Pei Cao. Characterization of web proxy traffic and Wisconsin proxy benchmark 2.0, November 1998.

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