Towards Omnia: A Monitoring Factory for Quality-Aware DevOps

Abstract

Modern DevOps pipelines entail extreme automation and speed as paramount assets for continuous application improvement. Likewise, monitoring is required to assess the quality of service and user-experience such that applications can continuously evolve towards use-centric excellence. In this scenario however, it is increasingly difficult to pull up and maintain efficient monitoring infrastructures which are frictionless, i.e., they do not introduce any slowdown neither in the DevOps pipeline nor in the DevOps organizational and social structure comprising multiple roles and responsibilities. Using an experimental prototype, this paper elaborates Omnia an approach for structured monitoring configuration and rollout based around a monitoring factory, i.e., a re-interpretation of the factory design-pattern for building and managing ad-hoc monitoring platforms. Comparing with practitioner surveys and the state of the art, we observed that Omnia shows the promise of delivering an effective solution that tackles the steep learning curve and entry costs needed to embrace cloud monitoring and monitoring-based DevOps continuous improvement.