Queueing Networks and Markov Chains
Queueing Networks and Markov Chains
A Synthetic Workload Generation Technique for Stress Testing Session-Based Systems
IEEE Transactions on Software Engineering
Performance impacts of autocorrelated flows in multi-tiered systems
Performance Evaluation
Burstiness in multi-tier applications: symptoms, causes, and new models
Proceedings of the 9th ACM/IFIP/USENIX International Conference on Middleware
Resource demand modeling for multi-tier services
Proceedings of the first joint WOSP/SIPEW international conference on Performance engineering
Automatic stress testing of multi-tier systems by dynamic bottleneck switch generation
Middleware'09 Proceedings of the ACM/IFIP/USENIX 10th international conference on Middleware
Hi-index | 0.00 |
Burstiness in resource consumption of requests has been recently observed to be a fundamental performance driver for multi-tier applications. This motivates the need for a methodology to create benchmarks with controlled burstiness that helps to improve the effectiveness of system sizing efforts and makes application testing more comprehensive. We tackle this problem using a model-based technique for the automatic and controlled generation of bursty benchmarks. Phase-type models are constructed in an automated manner to model the distribution of service demands placed by user sessions on various system resources. The models are then used to derive session submission policies that result in user-specified levels of service demand burstiness for resources at the different tiers in a system. A case study using a three-tier TPC-W testbed shows that our method is able to control and predict burstiness for session service demands and to cause dramatic latency and throughput degradations that are not visible with the same session mix and no burstiness.