Inferring client response time at the web server

ABSTRACT

As businesses continue to grow their World Wide Web presence, it is becoming increasingly vital for them to have quantitative measures of the client perceived response times of their web services. We present Certes (CliEnt Response Time Estimated by the Server), an online server-based mechanism for web servers to measure client perceived response time, as if measured at the client. Certes is based on a model of TCP that quantifies the effect that connection drops have on perceived client response time, by using three simple server-side measurements: connection drop rate, connection accept rate and connection completion rate. The mechanism does not require modifications to http servers or web pages, does not rely on probing or third party sampling, and does not require client-side modifications or scripting. Certes can be used to measure response times for any web content, not just HTML. We have implemented Certes and compared its response time measurements with those obtained with detailed client instrumentation. Our results demonstrate that Certes provides accurate server-based measurements of client response times in HTTP 1.0/1.1 [14] environments, even with rapidly changing workloads. Certes runs online in constant time with very low overhead. It can be used at web sites and server farms to verify compliance with service level objectives.

REFERENCES

• 1: Mark Allman, A web server's view of the transport layer, ACM SIGCOMM Computer Communication Review, v.30 n.5, October 2000 [doi>10.1145/505672.505674]
• 2: J. Almeida, M. Dabu, A. Manikutty, and P. Cao. Providing Differentiated Levels of Service in Web Content Hosting. In Workshop on Internet Server Performance Conference Proceedings, June 1998.
• 3: Hari Balakrishnan , Hariharan S. Rahul , Srinivasan Seshan, An integrated congestion management architecture for Internet hosts, ACM SIGCOMM Computer Communication Review, v.29 n.4, p.175-187, Oct. 1999
• 4: Paul Barford , Mark Crovella, A performance evaluation of hyper text transfer protocols, ACM SIGMETRICS Performance Evaluation Review, v.27 n.1, p.188-197, June 1999
• 5: N. Bhatti and R. Friedrich. Web Server Support for Tiered Services. IEEE Network, 13(5):6764-71, Sept.-Oct. 1999.
• 6: R. Braden. Requirements for Internet Hosts - communication layers. RFC 1122, October 1989.
• 7: N. Cardwell, S. Savage, and T. Anderson. Modeling TCP Latency. In IEEE INFOCOMM Conference Proceedings, volume 3, pages 1742-1751, 2000.
• 8: X. Chen and P. Mohapatra. Providing Differentiated Service from an Internet Server. In 8th Int. Conf. On Computer Communications and Networks Conference Proceedings, pages 214-217, 1999.
• 9: Xiangping Chen , Prasant Mohapatra , Huamin Chen, An admission control scheme for predictable server response time for web accesses, Proceedings of the 10th international conference on World Wide Web, p.545-554, May 01-05, 2001, Hong Kong, Hong Kong [doi>10.1145/371920.372156]
• 10: E. Cohen, B. Krishnamurthy, and J. Rexford. Efficient Algorithms for Predicting Requests to Web Servers. In IEEE INFOCOM Conference Proceedings, pages 284-293, 1999.
• 11: P. Danzig. Keynote talk presented at NOSSDAV. http://www.nossdav.org/2001/keynote_nossdav2001.ppt, 2001.
• 12: Lars Eggert , John Heidemann, Application-level differentiated services for Web servers, World Wide Web, v.2 n.3, p.133-142, 1999 [doi>10.1023/A:1019200806549]
• 13: Exodus. http://www.exodus.com/.
• 14: R. Fielding, J. Gettys, J. Mogul, H. Frystyk, and T. Berners-Lee. Hypertext Transfer Protocol- HTTP 1.1. RFC 2068, January 1997.
• 15: Yun Fu , Amin Vahdat , Ludmila Cherkasova , Wenting Tang, EtE: Passive End-to-End Internet Service Performance Monitoring, Proceedings of the General Track: 2002 USENIX Annual Technical Conference, p.115-130, June 10-15, 2002
• 16: E. J. Postel. Transmission Control Protocol. RFC 793, September 1981.
• 17: V. Kanodia and E. Knightly. Multi-Class Latency-Bounded Web Services. In IEEE/IFIP IWQoS Conference Proceedings, June 2000.
• 18: KeyNote. http://www.keynote.com/.
• 19: K. Li and S. Jamin. A Measurement-Based Admission-Controlled Web Server. In IEEE INFOCOMM Conference Proceedings, pages 651-659, 2000.
• 20: Chenyang Lu , Tarek F. Abdelzaher , John A. Stankovic , Sang H. Son, A Feedback Control Approach for Guaranteeing Relative Delays in Web Servers, Proceedings of the Seventh Real-Time Technology and Applications Symposium (RTAS '01), p.51, May 30-June 01, 2001
• 21: MercuryInteractive. http://www-heva.mercuryinteractive.com/.
• 22: Erich Nahum , Tsipora Barzilai , Dilip Kandlur, Performance issues in WWW servers, ACM SIGMETRICS Performance Evaluation Review, v.27 n.1, p.216-217, June 1999
• 23: NetQoS. http://www.netqos.com/.
• 24: Henrik Frystyk Nielsen , James Gettys , Anselm Baird-Smith , Eric Prud'hommeaux , Håkon Wium Lie , Chris Lilley, Network performance effects of HTTP/1.1, CSS1, and PNG, ACM SIGCOMM Computer Communication Review, v.27 n.4, p.155-166, Oct. 1997
• 25: Jitendra Padhye , Victor Firoiu , Don Towsley , Jim Kurose, Modeling TCP throughput: a simple model and its empirical validation, ACM SIGCOMM Computer Communication Review, v.28 n.4, p.303-314, Oct. 1998
• 26: Jitendra Pahdye , Sally Floyd, On inferring TCP behavior, Proceedings of the 2001 conference on Applications, technologies, architectures, and protocols for computer communications, p.287-298, August 2001, San Diego, California, United States
• 27: Raju Pandey , J. Fritz Barnes , Ronald Olsson, Supporting quality of service in HTTP servers, Proceedings of the seventeenth annual ACM symposium on Principles of distributed computing, p.247-256, June 28-July 02, 1998, Puerto Vallarta, Mexico [doi>10.1145/277697.277742]
• 28: S. Parekh, N. Gandhi, J. Hellerstein, D. Tilbury, T. Jayram, and J. Bigus. Using Control Theory to Achieve Service Level Objectives In Performance Management. In IFIP/IEEE International Symposium on Integrated Network Management Conference Proceedings, pages 841-854, 2001.
• 29: R. Rajamony and M. Elnozahy. Measuring Client-Perceived Response Times on the WWW. In 3rd USENIX Symposium on Internet Technologies and Systems (USITS) Conference Proceedings, March 2001.
• 30: Luigi Rizzo, Dummynet: a simple approach to the evaluation of network protocols, ACM SIGCOMM Computer Communication Review, v.27 n.1, p.31-41, Jan. 1997 [doi>10.1145/251007.251012]
• 31: F. Donelson Smith , Félix Hernández Campos , Kevin Jeffay , David Ott, What TCP/IP protocol headers can tell us about the web, ACM SIGMETRICS Performance Evaluation Review, v.29 n.1, p.245-256, June 2001
• 32: W. Richard Stevens, TCP/IP illustrated (vol. 1): the protocols, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1993
• 33: StreamCheck. http://www.streamcheck.com/.
• 34: Thiemo Voigt , Renu Tewari , Douglas Freimuth , Ashish Mehra, Kernel Mechanisms for Service Differentiation in Overloaded Web Servers, Proceedings of the General Track: 2002 USENIX Annual Technical Conference, p.189-202, June 25-30, 2001
• 35: WebStone. http://www.mindcraft.com/.
• 36: M. Yajnik, S. Moon, J. Kurose, and D. Towsley. Measurement and Modeling of the Temporal Dependence in Packet Loss. In IEEE INFOCOM Conference Proceedings, pages 345-352, 1999.
• 37: Y. Zhang, V. Paxson, and S. Shenker. The Stationarity of Internet Path Properties: Routing, Loss and Throughput. In Technical Report, ACIRI, May 2000.

INDEX TERMS

Primary Classification:
  D. Software
  D.4 OPERATING SYSTEMS
      D.4.8 Performance

General Terms:
Algorithms, Experimentation, Management, Measurement, Performance

Keywords:
client perceived response time, web server