KHAUNTE,S.U.,AND LIMB, J. O. Statistical Characterization of a World Wide Web Browsing Session. Tech. rep., Georgia Institute of Technology, 1997.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....to what is available in the real world. The effort made to change the traffic models consisted of surveying the current literature on that topic, and then incorporating the new parameters and distributions into OPNET. The traffic source models used in this study are based on the ones given in [2][3]. 4 Results 4.1 Simulation Cases For the purposes of this study, the following parameters were made adjustable : 1. Minislot size 4 2. Number of terminals 3. The return link bit rate 4. The forward link bit rate, and The outputs of the simulation were chosen to be: 1. Web page delay 2. ....

Sunil Khaunte, John Limb "Statistical Characterization of a World Wide Web Browsing Session", Georgia Institute of Technology technical report.

....tools are useful for certain kinds of server testing, our approach is to measure server performance under loads which are scalable, parameterizable and as realistic as possible. Prior to our study, some attempts were made to tie different aspects of Web use together into a single model [61, 71] but none has presented a scalable model which accurately mimics actual users accessing a Web server. In addition, previous work has not created tools based on models that could be used to generate workloads at a Web server (although the model presented in [71] has recently been incorporated in ....

S. Khaunte and J. Limb. Statistical characterization of a World Wide Web browsing session. Technical Report GIT-CC-97-17, College of Computing, Georgia Institute of Technology, 1997. 107

....during which Web objects are transferred to client from a single 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 ....

....Page 16 OFF Times ffl These are the idle, think time periods between Web object requests during a browsing session. ffl Accurate modeling of OFF times is necessary in order to generate realistic network traffic [35] ffl Empirical measurements of OFF times has been shown to exhibit heavy tails [10, 22, 32] Time URL 1 URL 2 URL 3 OFF Client Requests Web Object OFF Time ON Time Base URI Embedded files Requested Object Received Client Requests Next Web Object # Web Server Performance Analysis Paul Barford Page 17 Network Characteristics ffl Bandwidth Utilization The number of bits second ....

Sunil Khaunte and John Limb. Statistical characterization of a world wide web browsing session. Technical Report GIT-CC-97-17, College of Computing, Georgia Institute of Technology, 1997.

....2.1 User workload model ON multiple files page page request OFF ( think ) OFF ( think ) ON . Figure 3: User workload model. The workload model shown in Fig. 3 is used to generate traffic for each individual user in our system. The model was derived from studies on WWW traffic [3, 10], but may also be applied to most of the other popular Internet applications, such as email, ftp, etc. In a typical web access environment, upon a user request for a new page, one or more files are transmitted back to the user, which corresponds to an ON period of the model. Once the burst of ....

S. Khaunte, J. Limb, "Statistical characterization of a World Wide Web browsing session," Georgia Institute of Technology, College of Computing Technical Report, GIT-CC-97-17, 1997.

....local loads on our server. Surge is a synthetic workload generator which is unlike previous workload generators because it incorporates a wide range or workload characteristics that are important to many different aspects of server performance. Studies of the network effects of Web traffic include [7, 8, 21, 30, 38, 43, 54, 56]. These studies show the performance effects of both HTTP protocol interaction and TCP packet level interactions. The shortfall of these studies when it comes to analyzing latency is that they only take measurements in one place (somewhere near an end point of an HTTP transaction) and, thus, ....

S. Khaunte and J. Limb. Statistical characterization of a world wide web browsing session. Technical Report GIT-CC-97-17, College of Computing, Georgia Institute of Technology, 1997.

....local loads on our server. Surge is a synthetic workload generator which is unlike previous workload generators because it incorporates a wide range or workload characteristics that are important to many different aspects of server performance. Studies of the network effects of Web traffic include [7, 8, 21, 29, 53, 37, 42, 52]. These studies show the performance effects of both HTTP protocol interaction and TCP packet level interactions. The shortfall of these studies when it comes to analyzing latency is that they only take measurements in one place (somewhere near an end point of an HTTP transaction) and, thus, ....

Sunil Khaunte and John Limb. Statistical characterization of a world wide web browsing session. Technical Report GIT-CC-97-17, College of Computing, Georgia Institute of Technology, 1997.

.... [15, 9] Each thread requests a document set which is then transfered by the server (ON time) After receiving the document set, a thread sleeps for some amount of time (OFF time) This ON OFF characteristic is an important difference between SURGE and other benchmarks such as [1, 2, 3, 4, 5] [14] also includes OFF times) Web Server SURGE Client SURGE Client SURGE Client ON OFF Thread ON OFF Thread ON OFF Thread ON OFF Thread System System System System LAN Figure 1: SURGE Architecture When SURGE is started on a client system, it begins by populating a number of arrays with data ....

Sunil U. Khaunte and John O. Limb. Statistical characterization of a world wide web browsing session. Technical report, College of Computing, Georgia Institute of Technology, 1997.

No context found.

KHAUNTE,S.U.,AND LIMB, J. O. Statistical Characterization of a World Wide Web Browsing Session. Tech. rep., Georgia Institute of Technology, 1997.

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