IEEE/ACM Transactions on Networking (TON)
Holistic schedulability analysis for distributed hard real-time systems
Microprocessing and Microprogramming - Parallel processing in embedded real-time systems
Analysis of hard real-time communications
Real-Time Systems
Efficient network QoS provisioning based on per node traffic shaping
IEEE/ACM Transactions on Networking (TON)
A solution for a deterministic QoS in multimedia systems
ACIS International Journal of Computer & Information Science - Special issue on software engineering applied to networking & parallel/distributed computing
Network calculus: a theory of deterministic queuing systems for the internet
Network calculus: a theory of deterministic queuing systems for the internet
ISoLA'10 Proceedings of the 4th international conference on Leveraging applications of formal methods, verification, and validation - Volume Part I
Combining network calculus and scheduling theory to improve delay bounds
Proceedings of the 20th International Conference on Real-Time and Network Systems
Hi-index | 0.00 |
We focus on non-preemptive Fixed Priority (fp) scheduling. Unlike the classical approach, where flows sharing the same priority are assumed to be scheduled arbitrarily, we assume that these flows are scheduled Earliest Deadline First (edf), by considering their absolute deadline on their first visited node. The resulting scheduling is called fp/edf*. In this paper, we establish new results for fp/edf* in a distributed context, first when flows follow the same sequence of nodes (the same path). We then extend these results when flows follow different paths. We show how to compute an upper bound on the end-to-end response time of any flow when the packet priority is computed on the first node and left unchanged on any subsequent node. This alleviates the packet processing in core nodes. For that purpose, we use a worst case analysis based on the trajectory approach, that is less pessimistic than classical approaches. We compare our results with those provided by the holistic approach: the benefit can be very high.