1 / 16

Web Performance Metrics

Web Performance Metrics. Outline. Web Performance Metrics Architectures: Thin & Fat Clients Successful web applications? Scalability Performance Load balancing server Measuring Performance & Scalability Benchmarking, Throughput & Cost Course Summary. Web Performance.

aran
Download Presentation

Web Performance Metrics

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Web Performance Metrics

  2. Outline • Web Performance Metrics • Architectures: Thin & Fat Clients • Successful web applications? • Scalability • Performance • Load balancing server • Measuring Performance & Scalability • Benchmarking, Throughput & Cost • Course Summary

  3. Web Performance • What are people saying about Web performance… • “Tripod’s Web site is our business. If it’s not fast and reliable, there goes our business.”, Don Zereski, Tripod’s vice-president of Technology (Internet World) • “Sites have been concentrating on the right content. Now, more of them -- specially e-commerce sites -- realize that performance is crucial in attracting and retaining online customers.” Gene Shklar, Keynote The New York Times, 8/8/98

  4. Web Performance Metrics • Web Performance Metrics: • WWW user perception: • fast response time • no connection refused • Web administrators: • highthroughput • high availability Need for quantitative measurements: • Response time • Throughput

  5. Throughput Example: The Web site of a travel agency was monitored for 30 minutes and 9,000 HTTP requests were counted. We want to assess the server throughput. 3 types of Web objects • HTML pages: 30% and avg. size of 11,200 bytes • images: 65% and avg. size of 17,200 bytes • video clips: 5% and avg. size of 439,000 bytes

  6. Throughput • in terms of requests: • (No. of requests)/(period of time) = 9,000/(30 x 60) = 5 requests/sec • in terms of bits/sec per class: • (total requests x class % x avg. size) / (period of time) • HTML throughput (Kbps) • 9,000 x 0.30 x (11,200 x 8) / 1,800 = 131.25 • Image throughput (Kbps) • 9,000 x 0.65 x (17,200 x 8) / 1,800 = 436.72 • Video throughput (Kbps) • 9,000 x 0.05 x (439,000 x 8) / 1,800 = 857.42 • Total throughput • 131.25 + 436.72 + 857.42 = 1,425.39 Kbps

  7. Response Time • Example: Virtual car dealership • users search and submit purchase requests for new and used cars on the Web. • 1,300 affiliated car dealers provide info about vehicles on their parking lots. • new agreements will be phased in gradually, increasing the Web server’s traffic by 10%, then 20%, and finally 30% w.r.t. to current load.

  8. virtual car dealership clients Web server Internet • Database: • vehicle description • price • picture Response Time

  9. Response Time • Web server request types: • retrieve document and images • search the DB according to make, model, price range, and distance of dealer from buyer. • purchase request. • Critical request: search • 5% of searches generate a car sale • Average sale generates $18,000 in revenues. • Service Level Considerations:

  10. Current Current + 10% Current+20% Current+30% Searches per day 92,448 101,693 110,938 120,182 Response Time 2.86 3.80 5.67 11.28 Percent Sales Lost 0 0 60% 95% Sales per day 4622 5085 2219 300 Daily revenue ($1K) $ 83,203 $ 91,524 $ 39,938 $ 5,408 Potential daily revenue ($1K) $ 83,203 $ 91,524 $ 99,844 $ 108,164 Lost daily revenue ($1K) $ 59,906 $ 102,756 $ - $ 0 Response Time • Management questions: • will the Web server support the load increase while preserving the response time below 4 sec? • if not, at which point will its capacity be saturated? • how much money could be lost daily if the Web server saturates when the load increases?

  11. Fat Client & Thin Client • Interface • Users can access the web application via web browsers. • Different browser-dependent technologies • Business Logic • A set of operations required to provide the services for the client. E.g. transfer funds from one bank account to another one. • Data Management • Provide reliable, secure access to the data • E.g. the ticket of a ticket reservation system

  12. Fat Client & Thin Client Fat Client Interface Business Logic Data Management Thin Client Interface Business Logic Data Management

  13. Load Balancing Server Distribute requests over Multiple servers Requests

  14. Linux Virtual Server • Provides a high availability service to Internet hosts • Shares the same file system • Load balancer becomes the single failure point of the system • http://www.linuxvirtualserver.org/

  15. Performance Measures • Different stress test engines on the Web

  16. Course Summary • In this course, we have discussed many web programming techniques: • Markup language • HTML, XHTML, XML • Client side programming • JavaScript, how to use cookie, form validation • Advanced web design technologies • Scalability & Performance issues

More Related