Time-sensitive networking (TSN) is a promising technology for local area applications that require ultra-low latency, such as industrial automation, audio and video bridging, and 5G fronthaul transport. TSN guarantees deterministic packet transport with low latency, low packet delay jitter, and low packet loss. Correct provisioning of end-to-end latency is crucial for achieving optimal network performance and satisfying flow latency constraints. As TSN increasingly supports cloud and fog computing, managing virtualization overhead becomes critical to preserving latency performance. This work analyzes and compares TSN simulated, bare metal, and virtualized network deployments. The study focuses on an important TSN mechanism, namely, the IEEE 802.1Qav credit-based shaper (CBS). It examines its impact on end-to-end latency. Experiments show that the conducted TSN simulations provide latency results close to those from real-world setups, validating simulation as a reliable tool for TSN prototyping. Meanwhile, deploying TSN networks in virtualization-based scenarios presents specific trade-offs. All configurations achieved an average latency of less than 1 ms across all tested scenarios when the TSN idle slope parameter was tuned correctly to prioritize CBS-regulated traffic. Notably, despite the processing overhead introduced by virtualization, optimized configurations, such as those using kernel bypassing, outperformed bare metal deployments in terms of latency. However, this improvement came at the cost of reduced throughput, as fewer packets were forwarded compared to other scenarios. These findings underscore the importance of CBS parameter tuning and highlight the balance between performance and stability in virtualized TSN environments.

The rise of interactive real-time applications has exposed the latency limitations that current networks experience. Recently, the Low Latency, Low Loss, and Scalable Throughput (L4S) architecture emerged to address this problem across the Internet. This paper is the first to systematically review existing L4S experimental development efforts. It synthesizes the current state of research and identifies and outlines several remaining challenges. This analysis maps the primary research themes, dominant algorithms, and common evaluation methodologies, confirming that L4S can deliver on its promise for low-latency in controlled settings. Concurrently, the review summarizes the critical challenges and limitations reported in the literature, particularly concerning partial deployment, real-world wireless performance, and implementation robustness. By providing a structured overview of the technology’s maturity and key open questions, it serves as a guide for future work toward a robust, at-scale deployment of low-latency internet services.