this paper, we describe an approach in which analytic performance models are combined with combinatorial search techniques to design controllers that run periodically (e.g., every few minutes) to determine the best possible configuration for the system given its workload. We first illustrate and motivate the ideas using a simulated multithreaded server. Then, we provide experimental results, obtained by using the techniques described here, to an actual Web server subject to a workload generated by SURG
Deriving analytical performance models requires intimate knowledge of the architecture and behavior ...
A widely used approach to achieving service level objectives for a software system (e.g., an email s...
Queueing models are routinely used to analyze the performance of software systems. However, contrary...
This paper addresses the problem of managing computing systems using an integration of model-based c...
Computer systems hosting critical e-commerce applications must typically satisfy stringent quality-o...
Computer systems are becoming extremely complex due to the large number and heterogeneity of their h...
Methods for automatically managing the performance of computing services must estimate a performance...
Analytic modelling has proven to be cost-effective in the performance evaluation of computer systems...
Computer systems hosting critical e-commerce applications must typically satisfy stringent quality-o...
High performance is always a desired objective in computing systems. Managing performance through ma...
This dissertation presents on-line solutions to the challenge of scheduling large numbers of web ser...
Abstract—Applying control-theoretic approaches to capacity provisioning and performance management o...
Modern distributed systems are characterized by a growing complexity of their architecture, function...
Time-triggered periodic control implementations are over provisioned for many execution scenarios in...
Queueing models are routinely used to analyze the per-formance of software systems. However, contrar...
Deriving analytical performance models requires intimate knowledge of the architecture and behavior ...
A widely used approach to achieving service level objectives for a software system (e.g., an email s...
Queueing models are routinely used to analyze the performance of software systems. However, contrary...
This paper addresses the problem of managing computing systems using an integration of model-based c...
Computer systems hosting critical e-commerce applications must typically satisfy stringent quality-o...
Computer systems are becoming extremely complex due to the large number and heterogeneity of their h...
Methods for automatically managing the performance of computing services must estimate a performance...
Analytic modelling has proven to be cost-effective in the performance evaluation of computer systems...
Computer systems hosting critical e-commerce applications must typically satisfy stringent quality-o...
High performance is always a desired objective in computing systems. Managing performance through ma...
This dissertation presents on-line solutions to the challenge of scheduling large numbers of web ser...
Abstract—Applying control-theoretic approaches to capacity provisioning and performance management o...
Modern distributed systems are characterized by a growing complexity of their architecture, function...
Time-triggered periodic control implementations are over provisioned for many execution scenarios in...
Queueing models are routinely used to analyze the per-formance of software systems. However, contrar...
Deriving analytical performance models requires intimate knowledge of the architecture and behavior ...
A widely used approach to achieving service level objectives for a software system (e.g., an email s...
Queueing models are routinely used to analyze the performance of software systems. However, contrary...