Modeling End-to-End Response Times in Multi-Tier Internet Applications

Many Internet applications and workflow systems employ multi-tier software architectures. The performance of such multi-tier Internet applications is typically measured by the end-to-end response times. Most of the earlier works in modeling the response times of such systems have limited their study to modeling the mean. However, since the user-perceived performance is highly influenced by the variability in response times, the variance of the response times is important as well. In this paper, we derive expressions for estimating the mean end-to-end latency of more general applications and provide approximations to its variance. We validate our model by testing on two Web applications. We find that the model has a very good accuracy in estimating the mean endto-end response time and its variance with margins of error less than 10 percent. We believe this model is useful for capacity planning, resource provisioning, and performance prediction of Internet applications and services.

[1]  Hans van den Berg,et al.  TheM/G/1 queue with processor sharing and its relation to a feedback queue , 1991, Queueing Syst. Theory Appl..

[2]  Dan Rubenstein,et al.  Provisioning servers in the application tier for e-commerce systems , 2004, Twelfth IEEE International Workshop on Quality of Service, 2004. IWQOS 2004..

[3]  K. Shin,et al.  Performance Guarantees for Web Server End-Systems: A Control-Theoretical Approach , 2002, IEEE Trans. Parallel Distributed Syst..

[4]  J. R. Jackson.  Networks of Waiting Lines , 1957 .

[5]  Asser N. Tantawi,et al.  An analytical model for multi-tier internet services and its applications , 2005, SIGMETRICS '05.

[6]  Daniel A. Menascé,et al.  Resource Allocation for Autonomic Data Centers using Analytic Performance Models , 2005, Second International Conference on Autonomic Computing (ICAC'05).

[7]  J. Morrison.  Response-Time Distribution for a Processor-Sharing System , 1985 .

[8]  Onno Boxma,et al.  Sojourn times in queueing networks , 1989 .

[9]  Edward G. Coffman,et al.  Waiting Time Distributions for Processor-Sharing Systems , 1970, JACM.

[10]  Onno Boxma,et al.  Sojourn-time approximations in a two-node queueing network , 2005 .

[11]  Ben Shneiderman,et al.  Response time and display rate in human performance with computers , 1984, CSUR.

[12]  Jin Chen,et al.  Autonomic Provisioning of Backend Databases in Dynamic Content Web Servers , 2006, 2006 IEEE International Conference on Autonomic Computing.

[13]  Robert D. van der Mei,et al.  Modelling End-to-end Quality-of-Service for Transaction-Based Services in Multi-Domain Environments , 2006, 2006 IEEE International Conference on Web Services (ICWS'06).

[14]  B. Urgaonkar,et al.  Cataclysm: policing extreme overloads in internet applications , 2005, WWW '05.

[15]  Teunis J. Ott,et al.  The sojourn-time distribution in the M/G/1 queue by processor sharing , 1984, Journal of Applied Probability.

[16]  Daniel A. Menascé.  Web Server Software Architectures , 2003, IEEE Internet Comput..