Optimizing Network Calculus for Switched Ethernet Network with Deficit Round Robin

Abstract

Avionics Full Duplex switched Ethernet (AFDX) is the de facto standard for the transmission of critical avionics flows. It is a specific switched Ethernet solution based on First-in First-out (FIFO) scheduling. Worst-case traversal time (WCTT) analysis is mandatory for such flows, since timing constraints have to be guaranteed. A classical approach in this context is Network Calculus (NC). However, NC introduces some pessimism in the WCTT computation. Moreover, the worst-case often corresponds to very rare scenarios. Thus, the network architecture is most of the time lightly loaded. Typically, less than 10 % of the available bandwidth is used for the transmission of avionics flows on an AFDX network embedded in an aircraft. One solution to improve the utilization of the network is to introduce Quality of Service (QoS) mechanisms. Deficit Round Robin (DRR) is such a mechanism and it is envisioned for future avionics networks. A WCTT analysis has been proposed for DRR. It is based on NC. It doesn't make any assumption on the scheduling of flows by end systems. The first contribution of this paper is to identify sources of pessimism of this approach and to propose an improved solution which removes part of this pessimism. The second contribution is to show how the scheduling of flows can be integrated in this optimized DRR approach, thanks to offsets. An evaluation on a realistic case study shows that both contributions bring significantly tighter bounds on worst-case latencies. Index Terms-Deficit Round Robin, Network Calculus, worstcase traversal time, switched Ethernet network, offsets

Quantum assignment for QoS-aware AFDX network with deficit round robin

“…The NC approach for WCTT analysis used in this paper (from [5]) can be very pessimistic as it assumes that the competing classes are always active and the traffic from each class is maximum. This The problem of pessimism in [5] was addressed in [11] by quantifying the maximum amount of traffic of each competing class within the delay bound computed by [5]. However, the optimised NC approach in [11] cannot be used with the quantum assignment algorithm presented in this paper as it does not respect Lemma 3.1.…”

“…A WCTT analysis is mandatory in order to guarantee that critical flows never exceed their deadline. Such a WCTT analysis has been proposed for DRR in [5] and optimised for AFDX in [11]. Both approaches are based on network calculus (NC).…”

“…It might not be the case. Thus the approach in [11] optimises the one in [5] by quantifying the maximum amount of traffic of each competing class within the delay bound computed by [5].…”

“…We consider an industrial-size configuration. It includes 96 endsystems, 8 switches, 984 flows, and 6276 paths (multi-cast VL) [11]. We arbitrarily distribute flows between 2 critical classes: a class C 1 for flows with small BAGs (up to 16 ms) and a class C 2 for flows with larger BAGs.…”

“…[5] generalises the analysis to network with heterogeneous flows. An optimised WCTT analysis for DRR on AFDX is proposed in [11].…”