Joint scheduling and admission control for ATS-based switching nodes
SIGCOMM '92 Conference proceedings on Communications architectures & protocols
Web server workload characterization: the search for invariants
Proceedings of the 1996 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Preserving QoS of e-commerce sites through self-tuning: a performance model approach
Proceedings of the 3rd ACM conference on Electronic Commerce
Integrating Service Level Agreements: Optimizing Your OSS for SLA Delivery
Integrating Service Level Agreements: Optimizing Your OSS for SLA Delivery
A method for transparent admission control and request scheduling in e-commerce web sites
Proceedings of the 13th international conference on World Wide Web
An analytical model for multi-tier internet services and its applications
SIGMETRICS '05 Proceedings of the 2005 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
A simple approximation for modeling nonstationary queues
INFOCOM'96 Proceedings of the Fifteenth annual joint conference of the IEEE computer and communications societies conference on The conference on computer communications - Volume 1
QoS optimization for thermal-aware cyber-physical systems
Proceedings of the 2011 ACM Symposium on Research in Applied Computation
Hi-index | 0.00 |
Multi-tier architectures are widely used by internet applications. Guaranteeing the performance, and more generally the quality of service (QoS), of such applications remains a crucial issue. In this paper we propose a methodology to get the optimal admission control of multi-tier server systems under high loads for one QoS objective. First we present a model of multi-tier server systems using fluid approximations. Second, we state and solve an optimization problem which consists in finding the configuration that maximizes the availability of the system for a given performance constraint. Simulations of both model and control from this preliminary work are presented. They show that the optimal configuration of such systems is not always intuitive.