PERT-GNN: Latency Prediction for Microservice-based Cloud-Native Applications via Graph Neural Networks

Da Sun Handason Tam, Yang Liu, Huanle Xu, Siyue Xie, Wing Cheong Lau

Abstract:

Cloud-native applications using microservice architectures are rapidly replacing traditional monolithic applications. To meet end- to-end QoS guarantees and enhance user experience, each compo- nent microservice must be provisioned with sufficient resources to handle incoming API calls. Accurately predicting the latency of microservices-based applications is critical for optimizing re- source allocation, which turns out to be extremely challenging due to the complex dependencies between microservices and the inher- ent stochasticity. To tackle this problem, various predictors have been designed based on the Microservice Call Graph. However, Microservice Call Graphs do not take into account the API-specific information, cannot capture important temporal dependencies, and cannot scale to large-scale applications.
In this paper, we propose PERT-GNN, a generic graph neural network based framework to predict the end-to-end latency for mi- croservice applications. PERT-GNN characterizes the interactions or dependency of component microservices observed from prior execution traces of the application using the Program Evaluation and Review Technique (PERT). We then construct a graph neu- ral network based on the generated PERT Graphs, and formulate the latency prediction task as a supervised graph regression prob- lem using the graph transformer method. PERT-GNN can capture the complex temporal causality of different microservice traces, thereby producing more accurate latency predictions for various applications. Evaluations based on datasets generated from com- mon benchmarks and large-scale Alibaba microservice traces show that PERT-GNN can outperform other models by a large margin. In particular, PERT-GNN is able to predict the latency of microservice applications with less than 12% mean absolute percentage error.