IEEE Internet Computing
Solving layered queueing networks of large client-server systems with symmetric replication
Proceedings of the 5th international workshop on Software and performance
The Journal of Supercomputing
Deriving distribution of thread service time in layered queueing networks
WOSP '07 Proceedings of the 6th international workshop on Software and performance
Journal of Systems and Software
QoS management in service-oriented architectures
Performance Evaluation
Queueing analysis of a server node in transaction processing middleware systems
Computers and Operations Research
Activity routing in a distributed supply chain: Performance evaluation with two inputs
Journal of Network and Computer Applications
Predictive modelling of SAP ERP applications: challenges and solutions
Proceedings of the Fourth International ICST Conference on Performance Evaluation Methodologies and Tools
A performance experiment system supporting fast mapping of system issues
Proceedings of the Fourth International ICST Conference on Performance Evaluation Methodologies and Tools
D-factor: a quantitative model of application slow-down in multi-resource shared systems
Proceedings of the 12th ACM SIGMETRICS/PERFORMANCE joint international conference on Measurement and Modeling of Computer Systems
Software contention aware queueing network model of three-tier web systems
Proceedings of the 5th ACM/SPEC international conference on Performance engineering
Hi-index | 0.00 |
Being able to model contention for software resources(e.g., a critical section or database lock) is paramount tobuilding performance models that capture all aspects of thedelay encountered by a process as it executes. Several methodshave been offered for dealing with software contentionand with message blocking in client-server systems. Thispaper presents a general, straightforward, easy to understandand implement, approach to modeling software con-tentionusing queuing networks. The approach, called SQN-HQN,consists of a two-level iterative process. Two queuingnetworks are considered: one represents software resources(SQN) and the other hardware resources (HQN). Multiclassmodels are allowed and any solution technique-exact orapproximate-can be used at any of the levels. This techniquefalls in the general category of fixed-point approxi-matemodels and is similar in nature to other approaches.The main difference lies in its simplicity. The process convergesvery fast in the examples examined. The results werevalidated against global balance equation solutions and arevery accurate.