Quantifying the Impact of Frame Preemption on Combined TSN Shapers

TL;DR

This work tackles the problem of achieving deterministic QoS in TSN by integrating Frame Preemption (FP) with Credit-Based Shaper (CBS) and Gate Control List (GCL). It implements the combined FP-CBS-GCL framework in OMNeT++/INET and evaluates multiple integration modes (nonfrozen, frozen, return-to-zero; with/without Hold/Release) across synthetic and Orion networks, using Simulated Maximum Delay (SMD) and Simulated Maximum Jitter (SMJ) as KPIs. The key contributions include the first comprehensive FP-on-CBS-with-GCL analysis, showing AVB end-to-end delay reductions up to 40% when AVB is Preemptable, and zero TT jitter in the with Hold/Release mode, along with guardband-based improvements for without Hold/Release. The findings provide actionable guidance for configuring FP with CBS and GCL to optimize AVB latency while maintaining TT performance, and the authors release an open-source implementation for further study.

Abstract

Different scheduling mechanisms in Time Sensitive Networking (TSN) can be integrated together to design and support complex architectures with enhanced capabilities for mixed critical networks. Integrating Frame Preemption (FP) with Credit-Based Shaper (CBS) and Gate Control List (GCL) opens up different modes and configuration choices resulting in a complex evaluation of several possibilities and their impact on the Quality of Service (QoS). In this paper, we implement and quantify the integration of preemptive CBS with GCL by incorporating FP into the architecture. Our experiments show that the end-to-end delay of Audio Video Bridging (AVB) flows shaped by CBS reduces significantly (up to 40\%) when AVB flows are set to preemptable class. We further show that the jitter of Time Triggered (TT) traffic remains unaffected in "with Hold/Release" mode. Furthermore, we propose to introduce Guardband (GB) in the "without Hold/Release" to reduce the jitter of the TT flow. We compare all the different integration modes, starting with CBS with GCL, extending it further to FP. We evaluate all feasible combinations in both synthetic and realistic scenarios and offer recommendations for practical configuration methods.

Figures (23)

• Figure 1: Motivational example of the benefits of using Frame Preemption in a complex TSN network.
• Figure 2: Basic Working Mechanism of (a) no FP (b) with FP.
• Figure 3: CBS with GCL Credit Integration Modes: Credit evolution (a) nonfrozen (b) frozen and (c) return-to-zero during GB.
• Figure 4: Simulation of the Nonfrozen mode showcasing the credit behavior while the GB is active.
• Figure 5: Simulation of the Frozen mode showcasing the credit behavior.