The mathematics of nonlinear programming
The mathematics of nonlinear programming
Business-oriented resource management policies for e-commerce servers
Performance Evaluation - Special issue on internet performance modelling
On maximizing service-level-agreement profits
Proceedings of the 3rd ACM conference on Electronic Commerce
Inferring client response time at the web server
SIGMETRICS '02 Proceedings of the 2002 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Computer Performance Modeling Handbook
Computer Performance Modeling Handbook
Fuzzy Control
Optimizing Quality of Service Using Fuzzy Control
DSOM '02 Proceedings of the 13th IFIP/IEEE International Workshop on Distributed Systems: Operations and Management: Management Technologies for E-Commerce and E-Business Applications
Queueing Model Based Network Server Performance Control
RTSS '02 Proceedings of the 23rd IEEE Real-Time Systems Symposium
A Feedback Control Approach for Guaranteeing Relative Delays in Web Servers
RTAS '01 Proceedings of the Seventh Real-Time Technology and Applications Symposium (RTAS '01)
A smart hill-climbing algorithm for application server configuration
Proceedings of the 13th international conference on World Wide Web
Hierarchical model-based autonomic control of software systems
DEAS '05 Proceedings of the 2005 workshop on Design and evolution of autonomic application software
Tracking time-varying parameters in software systems with extended Kalman filters
CASCON '05 Proceedings of the 2005 conference of the Centre for Advanced Studies on Collaborative research
Triage: Performance differentiation for storage systems using adaptive control
ACM Transactions on Storage (TOS)
Effective web service load balancing through statistical monitoring
Communications of the ACM - Self managed systems
Using Policies to Drive Autonomic Management
WOWMOM '06 Proceedings of the 2006 International Symposium on on World of Wireless, Mobile and Multimedia Networks
Understanding the management of client perceived response time
SIGMETRICS '06/Performance '06 Proceedings of the joint international conference on Measurement and modeling of computer systems
Auto-tune design and evaluation on staged event-driven architecture
Proceedings of the 1st workshop on MOdel Driven Development for Middleware (MODDM '06)
eQoS: Provisioning of Client-Perceived End-to-End QoS Guarantees in Web Servers
IEEE Transactions on Computers
Optimizing system configurations quickly by guessing at the performance
Proceedings of the 2007 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Self-optimizing block transfer in web service grids
Proceedings of the 9th annual ACM international workshop on Web information and data management
A control theoretical approach to self-optimizing block transfer in Web service grids
ACM Transactions on Autonomous and Adaptive Systems (TAAS)
BI batch manager: a system for managing batch workloads on enterprise data-warehouses
EDBT '08 Proceedings of the 11th international conference on Extending database technology: Advances in database technology
Fuzzy control for guaranteeing absolute delays in web servers
International Journal of High Performance Computing and Networking
Scalable adaptive web services
Proceedings of the 2nd international workshop on Systems development in SOA environments
Tuning mechanisms for two major parameters of Apache web servers
Software—Practice & Experience
Design of a Fuzzy PI Controller to Guarantee Proportional Delay Differentiation on Web Servers
AAIM '07 Proceedings of the 3rd international conference on Algorithmic Aspects in Information and Management
Non-intrusive performance management for computer services
Proceedings of the ACM/IFIP/USENIX 2006 International Conference on Middleware
VCONF: a reinforcement learning approach to virtual machines auto-configuration
ICAC '09 Proceedings of the 6th international conference on Autonomic computing
Towards runtime optimization of software quality based on feedback control theory
Proceedings of the First Asia-Pacific Symposium on Internetware
Dynamic adaptation of response-time models for QoS management in autonomic systems
Journal of Systems and Software
HTCPNs: based tool for web-server clusters development
CEE-SET'08 Proceedings of the Third IFIP TC 2 Central and East European conference on Software engineering techniques
Non-intrusive performance management for computer services
Middleware'06 Proceedings of the 7th ACM/IFIP/USENIX international conference on Middleware
Research on resource allocation for multi-tier web applications in a virtualization environment
Frontiers of Computer Science in China
URL: A unified reinforcement learning approach for autonomic cloud management
Journal of Parallel and Distributed Computing
Performance evaluation of fuzzy-neural HTTP request distribution for web clusters
ICAISC'06 Proceedings of the 8th international conference on Artificial Intelligence and Soft Computing
HTCPNs---Based modelling and evaluation of dynamic computer cluster reconfiguration
CEE-SET'09 Proceedings of the 4th IFIP TC 2 Central and East European conference on Advances in Software Engineering Techniques
Autonomic Provisioning with Self-Adaptive Neural Fuzzy Control for Percentile-Based Delay Guarantee
ACM Transactions on Autonomous and Adaptive Systems (TAAS)
| Hi-index | 0.00 |
Properly optimizing the setting of configuration parameters can greatly improve performance, especially in the presence of changing workloads. This paper explores approaches to online optimization of the Apache web server, focusing on the MaxClients parameter (which controls the maximum number of workers). Using both empirical and analytic techniques, we show that MaxClients has a concave upward effect on response time and hence hill climbing techniques can be used to find the optimal value of MaxClients. We investigate two optimizers that employ hill climbing--one based on Newton's Method and the second based on fuzzy control. A third technique is a heuristic that exploits relationships between bottleneck utilizations and response time minimization. In all cases, online optimization reduces response times by a factor of 10 or more compared to using a static, default value. The trade-offs between the online schemes are as follows. Newton's method is well known but does not produce consistent results for highly variable data such as response times. Fuzzy control is more robust, but converges slowly. The heuristic works well in our prototype system, but it may be difficult to generalize because it requires knowledge of bottleneck resources and an ability to measure their utilizations.