Evolving technology in wireless telecommunication, such as 5G, provides opportunities to utilize wireless communication more in an industrial setting where reliability and predictability are of great concern. More capable Industrial Internet of Things devices (IIoT) are, indeed, a catalyst for Industry 4.0. Still, before the IIoT devices can be deemed capable enough, a method to evaluate the IIoT systems unobtrusively—so that the evaluation does not affect the performance of the systems—must be established. This thesis aims to answer how the performance of a distributed control system can be unobtrusively evaluated, and also determine what the state-of-the-art is in latency measurements in distributed control systems. To answer the question, a novel diagnostics method for time-critical control systems in cloud-fog automation is proposed and extensively evaluated on real-life testbeds that use 5G, WiFi 6, and Ethernet in an edge-computing topology with real control systems. The feasibility of the proposed method was verified by experiments conducted with a diagnostics framework prototype developed in this thesis. In the proposed diagnostics framework, the controller application is monitored by a computing probe based on an extended Berkeley Packet Filter program. Network communication between the controller and control target is evaluated with a multi-channel Ethernet probe and custom-made software that computes several metrics related to the performance of the distributed system. The data from the unobtrusive probes are sent to a time-series database that is used for further analysis and real-time visualization in a graphical interface created with Grafana. The proposed diagnostics method together with the developed prototype can be used as a research infrastructure for future evaluations of distributed control systems.