Fast Allocation of Processes in Distributed and Parallel Systems
IEEE Transactions on Parallel and Distributed Systems
Model-Based Performance Prediction in Software Development: A Survey
IEEE Transactions on Software Engineering
Performance Engineering with the UML Profile for Schedulability, Performance and Time: A Case Study
MASCOTS '04 Proceedings of the The IEEE Computer Society's 12th Annual International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems
Performance evaluation of UML software architectures with multiclass Queueing Network models
Proceedings of the 5th international workshop on Software and performance
Towards Autonomic Distribution of Existing Object Oriented Programs
ICAS '06 Proceedings of the International Conference on Autonomic and Autonomous Systems
An Automatic Framework for Efficient Software Performance Evaluation and Optimization
ANSS '07 Proceedings of the 40th Annual Simulation Symposium
The Future of Software Performance Engineering
FOSE '07 2007 Future of Software Engineering
Automated Deployment of Distributed Software Components with Fault Tolerance Guarantees
SERA '08 Proceedings of the 2008 Sixth International Conference on Software Engineering Research, Management and Applications
ArcheOpterix: An extendable tool for architecture optimization of AADL models
MOMPES '09 Proceedings of the 2009 ICSE Workshop on Model-Based Methodologies for Pervasive and Embedded Software
Proceedings of the first joint WOSP/SIPEW international conference on Performance engineering
Consolidation and replication of VMs matching performance objectives
ASMTA'12 Proceedings of the 19th international conference on Analytical and Stochastic Modeling Techniques and Applications
Deployment optimization of software objects by design-level delay estimation
The Journal of Supercomputing
Hi-index | 0.01 |
The correct deployment of software objects over the computational resources has a significant impact on the software performance. Achieving the optimal deployment manually is a tedious work as there are many different alternative solutions. In this paper a heuristic algorithm for optimizing the deployment of software objects is proposed which evaluates each deployment in the search space, considering its communicational and computational delays. In order to estimate these delays for an object deployment, our algorithm takes into account both the resource capacities and the execution load of the software for a given input-workload. The execution load of the software is measured by simulating the software use-case scenarios using the Finite State Process (FSP) models. From the simulation, the values of some metrics such as utilization, population and mean response times corresponding to the objects and threads participating in software use-case scenarios are recorded as the execution load indicators. These recorded simulation results are subsequently applied to estimate the goodness of a deployment in the search space.