Performance Analysis of Dynamic Priority Shifting

Authors:
Philipp Reinecke;Katinka Wolter;Johannes Zapotoczky
Affiliations:
Institut für Informatik, Humboldt-Universität zu Berlin, Berlin, Germany;Institut für Informatik, Humboldt-Universität zu Berlin, Berlin, Germany;Institut für Informatik, Humboldt-Universität zu Berlin, Berlin, Germany
Venue:
EPEW '08 Proceedings of the 5th European Performance Engineering Workshop on Computer Performance Engineering
Year:
2008

Citing 7
Cited 0

Real-Time Systems: Design Principles for Distributed Embedded Applications

Real-Time Systems: Design Principles for Distributed Embedded Applications
Petri Net Modelling and Performability Evaluation with TimeNET 3.0

TOOLS '00 Proceedings of the 11th International Conference on Computer Performance Evaluation: Modelling Techniques and Tools
Optimisation of downlink resource allocation algorithms for UMTS networks

EURASIP Journal on Wireless Communications and Networking
Providing Throughput Guarantees in 802.11e WLAN Through a Dynamic Priority Assignment Mechanism

Wireless Personal Communications: An International Journal
An analytic study of tuning systems parameters in IEEE 802.11e enhanced distributed channel access

Computer Networks: The International Journal of Computer and Telecommunications Networking
Analysis of bandwidth allocation algorithms for wireless personal area networks

Wireless Networks
Gnuplot in Action: Understanding Data with Graphs

Gnuplot in Action: Understanding Data with Graphs

Quantified Score

Hi-index	0.00

Visualization

Abstract

We investigate the benefit of priority shifting for resource allocation in systems with a shared resource, where higher priority implies better service. Priority schemes where priority levels are assigned fixed shares of the resource experience underutilisation if there are only low-priority tasks present. In these situations, lower priority tasks can be `shifted up' to higher priority. This increases overall system utilisation and improves the service experienced by low-priority tasks. We present a shifting framework, study its properties and develop a Petri net model for a shifting algorithm. We analyse the model in order to identify situations where shifting of priorities is beneficial.