Performance modeling of an Apache web server with bursty arrival traffic

Mikael Andersson; Jianhua Cao; Maria Kihl; Christian Nyberg

Performance modeling of an Apache web server with bursty arrival traffic

Mikael Andersson, Jianhua Cao, Maria Kihl, Christian Nyberg

Institutionen för elektro- och informationsteknik

Forskningsoutput: Kapitel i bok/rapport/Conference proceeding › Konferenspaper i proceeding › Peer review

97 Nedladdningar (Pure)

Sammanfattning

Performance modeling is an important topic in
capacity planning and overload control for web servers. We
present a queueing model of an Apache web server that uses
bursty arrival traffic. The arrivals of HTTP requests is
assumed to be a Markov Modulated Poisson Process and
the service discipline of the server is processor sharing. The
total number of requests that can be processed at one time is
limited to K. We obtain web server performance metrics
such as average response time, throughput and blocking
probability by simulations. Compared to other models, our
model is conceptually simple. The model has been validated
through measurements and simulations in our lab. The performance
metrics predicted by the model fit well to the
experimental outcome.

Originalspråk	engelska
Titel på värdpublikation	IC'03 : proceedings of the international conference on internet computing
Redaktörer	H. R. Arabnia, Y. Mun
Förlag	CSREA Press
Sidor	508-511
ISBN (tryckt)	1-932415-02-5
Status	Published - 2003
Evenemang	4th International Conference on Internet Computing - Varaktighet: 0001 jan. 2 → …

Konferens

Konferens	4th International Conference on Internet Computing
Period	0001/01/02 → …

Ämnesklassifikation (UKÄ)

Elektroteknik och elektronik
Kommunikationssystem

Tillgång till dokument

andersson_ic2003

Citera det här

@inproceedings{f845b424a88c4aff94656e1bbcdd5de2,

title = "Performance modeling of an Apache web server with bursty arrival traffic",

abstract = "Performance modeling is an important topic in capacity planning and overload control for web servers. We present a queueing model of an Apache web server that uses bursty arrival traffic. The arrivals of HTTP requests is assumed to be a Markov Modulated Poisson Process and the service discipline of the server is processor sharing. The total number of requests that can be processed at one time is limited to K. We obtain web server performance metrics such as average response time, throughput and blocking probability by simulations. Compared to other models, our model is conceptually simple. The model has been validated through measurements and simulations in our lab. The performance metrics predicted by the model fit well to the experimental outcome.",

author = "Mikael Andersson and Jianhua Cao and Maria Kihl and Christian Nyberg",

year = "2003",

language = "English",

isbn = "1-932415-02-5",

pages = "508--511",

editor = "Arabnia, {H. R.} and Y. Mun",

booktitle = "IC'03 : proceedings of the international conference on internet computing",

publisher = "CSREA Press",

address = "United States",

note = "4th International Conference on Internet Computing ; Conference date: 02-01-0001",

}

Performance modeling of an Apache web server with bursty arrival traffic. / Andersson, Mikael; Cao, Jianhua; Kihl, Maria et al.
IC'03 : proceedings of the international conference on internet computing. red. / H. R. Arabnia; Y. Mun. CSREA Press, 2003. s. 508-511.

Forskningsoutput: Kapitel i bok/rapport/Conference proceeding › Konferenspaper i proceeding › Peer review

TY - GEN

T1 - Performance modeling of an Apache web server with bursty arrival traffic

AU - Andersson, Mikael

AU - Cao, Jianhua

AU - Kihl, Maria

AU - Nyberg, Christian

PY - 2003

Y1 - 2003

N2 - Performance modeling is an important topic in capacity planning and overload control for web servers. We present a queueing model of an Apache web server that uses bursty arrival traffic. The arrivals of HTTP requests is assumed to be a Markov Modulated Poisson Process and the service discipline of the server is processor sharing. The total number of requests that can be processed at one time is limited to K. We obtain web server performance metrics such as average response time, throughput and blocking probability by simulations. Compared to other models, our model is conceptually simple. The model has been validated through measurements and simulations in our lab. The performance metrics predicted by the model fit well to the experimental outcome.

AB - Performance modeling is an important topic in capacity planning and overload control for web servers. We present a queueing model of an Apache web server that uses bursty arrival traffic. The arrivals of HTTP requests is assumed to be a Markov Modulated Poisson Process and the service discipline of the server is processor sharing. The total number of requests that can be processed at one time is limited to K. We obtain web server performance metrics such as average response time, throughput and blocking probability by simulations. Compared to other models, our model is conceptually simple. The model has been validated through measurements and simulations in our lab. The performance metrics predicted by the model fit well to the experimental outcome.

M3 - Paper in conference proceeding

SN - 1-932415-02-5

SP - 508

EP - 511

BT - IC'03 : proceedings of the international conference on internet computing

A2 - Arabnia, H. R.

A2 - Mun, Y.

PB - CSREA Press

T2 - 4th International Conference on Internet Computing

Y2 - 2 January 0001

ER -

Performance modeling of an Apache web server with bursty arrival traffic

Sammanfattning

Konferens

Ämnesklassifikation (UKÄ)

Tillgång till dokument

Fingeravtryck

Citera det här