Figure 12 shows that, after CPU fault injection into the front-end container, the latency of thefront-end service of the target system changed markedly during the period from 2:50 p.m. to 2:55 p.m.Accordingly, the CPU injection fault in the experiment also occurred in this period. After collecting thesystem performance dataset of the chaotic experiment corresponding to Table 1, we obtained the causalrelation between the performance indicators by applying the causal inference graph constructionmethod in this study.Figure 12. Front-end latency after CPU fault injection.Because the complete graph is too large, a part of the complete graph is shown in Figure 13.Blue nodes are the KPIs of services, red nodes are the KPIs of the container, and green nodes are theKPIs of the working nodes for the Kubernetes cluster.Figure 13. Part of causality graph for all performance indicators.To diagnose the root cause of the front-end latency, we applied the causal search algorithm.The results show that the root cause chains in Figure 14 generated by the proposed algorithm arebasically consistent with the actual Sock Shop system architecture and do reflect the call relationsbetween services.