Fundamentals of a Novel Debugging Mechanism for Orchestrated Cloud Infrastructures with Macrosteps and Active Control

Abstract

In Infrastructure-as-a-Service (IaaS) clouds, the development process of a ready-to-use and reliable infrastructure might be a complex task due to the interconnected and dependent services that are deployed (and operated later on) in a concurrent way on virtual machines. Different timing conditions may change the overall initialisation method, which can lead to abnormal behaviour or failure in the non-deterministic environment. The overall motivation of our research is to improve the reliability of cloud-based infrastructures with minimal user interactions and significantly accelerate the time-consuming debugging process. This paper focuses on the behaviour of cloud-based infrastructures during their deployment phase and introduces the adaption of a replay, and active control enriched debugging technique, called macrostep, in the field of cloud orchestration in order to provide support for developers troubleshooting deployment-related errors. The fundamental macrostep mechanisms, including the generation of collective breakpoint sets as well as the traversal method for such consistent global states, have been combined with the Occopus cloud orchestrator and the Neo4J graph database. The paper describes the novel approach, the design choices as well as the implementation of the experimental debugger tool with a use case for validation purposes by providing some preliminary numerical results.

Experiences With Deep Learning Enhanced Steering Mechanisms for Debugging of Fundamental Cloud Services

“…Such simulation paths to suspicious situations can form an input (i.e. feed) a cloud debugger tool to make an attempt to reproduce the failure in the real cloud environment (see Section I-C) with active control (steering) [8].…”

“…Debugging reference architecture candidates (or their new versions) is a crucial but tedious and time-consuming task due to the deployment of services in a typically multitenant and non-deterministic environment. It poses several new challenges since software designers and testers must face (among others) the probe effect, the irreproducibility, the completeness problem, and also the large state-space that has to be handled somehow during the debugging/troubleshooting phases [8]. By modelling and verifying at least the most fundamental building blocks, we might achieve a higher level of coverage and thus a higher level of reliability, during the debugging, testing and later in the maintenance scenarios.…”

“…1) as well as the definition of metrics and features for deep learning are crucial in using formal modelling and verification methods, including Continuous Time Markov Chain modelling (CTMC) techniques and the PRISM modelchecker [9]. Later, the detected suspicious situations may steer our cloud debugger tool [8] towards the potential faults.…”

“…models reinforcement learning, CTMC network semi-automated Karn [25] service mesh automated testing rule based error detection network semi-automated Tomas [26] service mesh ML rand. forest, k-means, SVM, CNN security manual Wu [27] service We already proposed a novel cloud debugger method and a framework [8] for this purpose (see 'Debugging & steering engine' in Figure 1) that not only monitors but also actively controls the cloud-based processes leveraging on the socalled macrostep [29] based execution. The approach allows the rule-based evaluation by each macrostep, i.e.…”

“…The experimental integration of the presented results with a cloud debugger tool [8] is in progress that will provide significant help to cloud service and reference architecture developers.…”