Performance modeling and control of web servers
(2004)- Abstract
- This thesis deals with the task of modeling a web server and designing a
mechanism that can prevent the web server from being overloaded. Four
papers are presented. The first paper gives an M/G/1/K processor sharing
model of a single web server. The model is validated against measurements
ands imulations on the commonly usedw eb server Apache. A description
is given on how to calculate the necessary parameters in the model. The
second paper introduces an admission control mechanism for the Apache
web server basedon a combination of queuing theory andcon trol theory.
The admission control mechanism is tested in the laboratory, implemented
as a stand-alone... (More) - This thesis deals with the task of modeling a web server and designing a
mechanism that can prevent the web server from being overloaded. Four
papers are presented. The first paper gives an M/G/1/K processor sharing
model of a single web server. The model is validated against measurements
ands imulations on the commonly usedw eb server Apache. A description
is given on how to calculate the necessary parameters in the model. The
second paper introduces an admission control mechanism for the Apache
web server basedon a combination of queuing theory andcon trol theory.
The admission control mechanism is tested in the laboratory, implemented
as a stand-alone application in front of the web server. The third paper
continues the work from the secondp aper by discussing stability. This
time, the admission control mechanism is implemented as a module within
the Apache source code. Experiments show the stability and settling time of
the controller. Finally, the fourth paper investigates the concept of service
level agreements for a web site. The agreements allow a maximum response
time anda minimal throughput to be set. The requests are sorted into
classes, where each class is assigneda weight (representing the income for
the web site owner). Then an optimization algorithm is appliedso that the
total profit for the web site during overload is maximized. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/532281
- author
- Andersson, Mikael LU
- supervisor
-
- Maria Kihl LU
- organization
- publishing date
- 2004
- type
- Thesis
- publication status
- published
- subject
- pages
- 96 pages
- publisher
- Lund Institute of Technology
- language
- English
- LU publication?
- yes
- additional info
- The information about affiliations in this record was updated in December 2015. The record was previously connected to the following departments: Department of Communication Systems (011020000)
- id
- 2fe20282-6abe-4678-a784-9a77ec6db0f7 (old id 532281)
- date added to LUP
- 2016-04-01 15:18:18
- date last changed
- 2018-11-21 20:33:46
@misc{2fe20282-6abe-4678-a784-9a77ec6db0f7,
abstract = {{This thesis deals with the task of modeling a web server and designing a<br/><br>
mechanism that can prevent the web server from being overloaded. Four<br/><br>
papers are presented. The first paper gives an M/G/1/K processor sharing<br/><br>
model of a single web server. The model is validated against measurements<br/><br>
ands imulations on the commonly usedw eb server Apache. A description<br/><br>
is given on how to calculate the necessary parameters in the model. The<br/><br>
second paper introduces an admission control mechanism for the Apache<br/><br>
web server basedon a combination of queuing theory andcon trol theory.<br/><br>
The admission control mechanism is tested in the laboratory, implemented<br/><br>
as a stand-alone application in front of the web server. The third paper<br/><br>
continues the work from the secondp aper by discussing stability. This<br/><br>
time, the admission control mechanism is implemented as a module within<br/><br>
the Apache source code. Experiments show the stability and settling time of<br/><br>
the controller. Finally, the fourth paper investigates the concept of service<br/><br>
level agreements for a web site. The agreements allow a maximum response<br/><br>
time anda minimal throughput to be set. The requests are sorted into<br/><br>
classes, where each class is assigneda weight (representing the income for<br/><br>
the web site owner). Then an optimization algorithm is appliedso that the<br/><br>
total profit for the web site during overload is maximized.}},
author = {{Andersson, Mikael}},
language = {{eng}},
note = {{Licentiate Thesis}},
publisher = {{Lund Institute of Technology}},
title = {{Performance modeling and control of web servers}},
url = {{https://lup.lub.lu.se/search/files/4363215/625298.pdf}},
year = {{2004}},
}