KubeKlone: A Digital Twin for Simulating Edge and Cloud Microservices.

Microservices are terraforming the computing landscape with web-scale infrastructures (e.g., Facebook, Google, Amazon) and telecom infrastructures (e.g., ATT, Ericsson) adopting them. At it’s core, the microservices paradigm promotes a decoupling of applications into multiple services – a decoupling that promotes better scalability, fault-tolerance, and deployability. Unfortunately, this decoupling significantly increases the space of configuration options and performance problems, rendering traditional approaches to management ineffective. Recent efforts to address this problem embrace Artificial Intelligence for IT Operations (AIOps). However, training effective AI models requires significant amounts of data and, in some instances, a framework for quickly exploring or analyzing model performance. Digital twins, or simulators, have effectively enabled AI-based management frameworks within other domains (e.g., manufacturing, industrial and automotive). In this paper, we propose the design of KubeKlone, the first comprehensive and opensource digital twin for modeling cloud-native microservices applications. KubeKlone is motivated by our need for accurate, efficient, and general model training. KubeKlone satisfies these goals by decoupling the simulation of microservices from the training of machine learning (ML) models while simultaneously ensuring efficiency and simplifying model design. In particular, KubeKlone introduces a queue-based simulator that abstracts infrastructure details and focuses on modeling, with queues, resource contentions across host and network components. To simplify model design, KubeKlone provides interfaces that hide simulator details and provides wrappers around popular ML packages. To illustrate the strengths of KubeKlone, we validate it against a deployment on Google Cloud Engine and implement several AIOps resource management algorithms (including PARTIES).