On overload control through queue length for web servers
(2002)- Abstract
- We investigate the performance of overload control through queue length for two different web server architectures. Both of them use finite queue lengths to prevent servers from being overloaded. One architecture prioritizes requests from established sessions while the other treats all requests equally. First, we introduce queueing models for these two systems. Then, we define and explain a new web server performance metric that is a function of session throughput, error rate for connection within sessions and average request response time. Finally, we use simulation to evaluate the performance of these two types of web servers. The result suggests that the benefit of request prioritization is noticeable only when the capacities of the... (More)
- We investigate the performance of overload control through queue length for two different web server architectures. Both of them use finite queue lengths to prevent servers from being overloaded. One architecture prioritizes requests from established sessions while the other treats all requests equally. First, we introduce queueing models for these two systems. Then, we define and explain a new web server performance metric that is a function of session throughput, error rate for connection within sessions and average request response time. Finally, we use simulation to evaluate the performance of these two types of web servers. The result suggests that the benefit of request prioritization is noticeable only when the capacities of the sub-systems match each other. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/532493
- author
- Jianhua, Cao and Nyberg, Christian LU
- organization
- publishing date
- 2002
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Sixteenth Nordic Teletraffic Seminar NTS 16 : Helsinki University of Technology, Espoo August 21-23, 2002 : proceedings (Report / Helsinki University of Technology, Networking Laboratory)
- editor
- Lassila, Pasi ; Nyberg, Eeva and Virtamo, Jorma
- publisher
- Helsinki University of Technology, Networking Laboratory
- ISSN
- 1458-0322
- language
- English
- LU publication?
- yes
- id
- 87935f36-e6c7-4163-8313-f4f738ad2ff3 (old id 532493)
- date added to LUP
- 2016-04-01 16:35:31
- date last changed
- 2018-11-21 20:42:36
@inproceedings{87935f36-e6c7-4163-8313-f4f738ad2ff3, abstract = {{We investigate the performance of overload control through queue length for two different web server architectures. Both of them use finite queue lengths to prevent servers from being overloaded. One architecture prioritizes requests from established sessions while the other treats all requests equally. First, we introduce queueing models for these two systems. Then, we define and explain a new web server performance metric that is a function of session throughput, error rate for connection within sessions and average request response time. Finally, we use simulation to evaluate the performance of these two types of web servers. The result suggests that the benefit of request prioritization is noticeable only when the capacities of the sub-systems match each other.}}, author = {{Jianhua, Cao and Nyberg, Christian}}, booktitle = {{Sixteenth Nordic Teletraffic Seminar NTS 16 : Helsinki University of Technology, Espoo August 21-23, 2002 : proceedings (Report / Helsinki University of Technology, Networking Laboratory)}}, editor = {{Lassila, Pasi and Nyberg, Eeva and Virtamo, Jorma}}, issn = {{1458-0322}}, language = {{eng}}, publisher = {{Helsinki University of Technology, Networking Laboratory}}, title = {{On overload control through queue length for web servers}}, url = {{https://lup.lub.lu.se/search/files/4718027/625319.pdf}}, year = {{2002}}, }