TY - GEN
T1 - An autonomic admission control policy for distributed web systems
AU - Bartolini, Novella
AU - Bongiovanni, Giancarlo
AU - Silvestri, Simone
N1 - Funding Information:
supported my work in this area. Special thanks are also due to my colleagues Dr. David Hough (University of Bath) and Professor Kenneth Stevenson (University of Calgary, Canada) with whom I enjoy close research collaborations, and to Miss Kathy Pratt (Calgary). Financial support for the work of the author from SERC (UK), NSERC (Canada), The Royal Society, The British Council and NATO (in the form of a Grant for International Collaboration in Research with Professor Stevenson) are gratefully acknowledged. Finally, I thank my wife, Janet, for the typing and proof reading of the entire manuscript.
PY - 2007
Y1 - 2007
N2 - This paper tackles the problem of autonomic admission control for web clusters. The main contribution of this work is the proposal of a new session admission algorithm that self-configures a dynamic constraint on the rate of incoming new sessions to guarantee the respect of Service Level Agreements (SLA). Unlike other approaches, our policy does not need any prior information on the incoming traffic, nor any assumption on the probability distribution of request inter-arrival or service time. Furthermore, it does not require any manual configuration or parameter tuning. We performed extensive simulations under a range of operating conditions and compared our algorithm to other previously proposed approaches. The simulations show that our policy rapidly adapts to the given traffic profile and improves service throughput while respecting the response time constraints imposed by the SLAs. It also improves service quality by reducing the oscillations of response time and number of active clients common to other policies.
AB - This paper tackles the problem of autonomic admission control for web clusters. The main contribution of this work is the proposal of a new session admission algorithm that self-configures a dynamic constraint on the rate of incoming new sessions to guarantee the respect of Service Level Agreements (SLA). Unlike other approaches, our policy does not need any prior information on the incoming traffic, nor any assumption on the probability distribution of request inter-arrival or service time. Furthermore, it does not require any manual configuration or parameter tuning. We performed extensive simulations under a range of operating conditions and compared our algorithm to other previously proposed approaches. The simulations show that our policy rapidly adapts to the given traffic profile and improves service throughput while respecting the response time constraints imposed by the SLAs. It also improves service quality by reducing the oscillations of response time and number of active clients common to other policies.
UR - http://www.scopus.com/inward/record.url?scp=57849155300&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=57849155300&partnerID=8YFLogxK
U2 - 10.1109/MASCOTS.2007.8
DO - 10.1109/MASCOTS.2007.8
M3 - Conference contribution
AN - SCOPUS:57849155300
SN - 9781424418541
T3 - IEEE International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems - Proceedings
SP - 138
EP - 144
BT - Proceedings of MASCOTS'07 15th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems
T2 - 15th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS'07
Y2 - 24 October 2007 through 26 October 2007
ER -