Quantitative system performance: computer system analysis using queueing network models
Quantitative system performance: computer system analysis using queueing network models
IEEE Transactions on Computers
Asymptotic analysis of multiclass closed queueing networks: common bottleneck
Performance Evaluation
COBRA fundamentals and programming
COBRA fundamentals and programming
Asymptotic analysis of multiclass closed queueing networks: multiple bottlenecks
Performance Evaluation
Mean-Value Analysis of Closed Multichain Queuing Networks
Journal of the ACM (JACM)
IEEE Transactions on Software Engineering
Performance of Client/Server Systems
Performance Evaluation: Origins and Directions
Software Performance Evaluation by Models
Performance Evaluation: Origins and Directions
Hi-index | 0.00 |
When designing and deploying distributed systems it is necessary to determine process activation policy. A process's activation policy determines whether it is persistent or should be created and terminated with each call. For persistent processes the replication or threading levels must be decided. Inappropriate replication/threading levels can lead to unnecessary queuing delays for callers or an unnecessarily high consumption of memory resources. The purpose of this paper is to present quantitative techniques that determine appropriate process replication/threading levels. The results also provide information that can be used to guide the choice of process activation policy. Chosen replication levels are sensitive to the total number of customers using the system and the portion of customers belonging to each class. The algorithms presented consider all workload conditions, are iterative in nature, and are hybrid mathematical programming and analytic performance evaluation methods.