Engineering of Self-aware IT Systems and Services: State-of-the-Art and Research Challenges

Modern IT systems have highly distributed and dynamic architectures composed of loosely-coupled services typically deployed on virtualized infrastructures. Managing system resources in such environments to ensure acceptable endto-end application Quality-of-Service (QoS) while at the same time optimizing resource utilization and energy efficiency is a challenge. The adoption of Cloud Computing technologies, including Software-as-a-Service (SaaS), Platform-asa-Service (PaaS) and Infrastructure-as-a-Service (IaaS), comes at the cost of increased system complexity and dynamicity. This makes it hard to provide QoS guarantees in terms of performance and availability, as well as resilience to attacks and operational failures [8]. Moreover, the consolidation of workloads translates into higher utilization of physical resources which makes the system much more vulnerable to threats resulting from unforeseen load fluctuations, hardware failures and network attacks. We present an overview of our work-in-progress and long-term research agenda focusing on the development of novel methods, techniques and tools for the engineering of so-called self-aware IT systems and services [6, 4, 7]. The latter are designed with built-in online QoS prediction and self-adaptation capabilities used to enforce QoS requirements in a costand energy-efficient manner. The current focus is on performance, availability and efficiency aspects, however, long-term we are planning to consider further QoS properties such as reliability and faulttolerance. Self-awareness, in this context, is defined by the combination of three properties that IT systems and services should possess: 1. Self-reflective: i) aware of their software architecture, execution environment and the hardware infrastructure on which they are running, ii) aware of their operational goals in terms of QoS requirements, service-level agreements (SLAs) and costand energy-efficiency targets, iii) aware of dynamic changes in the above during operation, 2. Self-predictive: able to predict the effect of dynamic changes (e.g., changing service workloads or QoS requirements) as well as predict the effect of possible adaptation actions (e.g., changing service deployment and/or resource allocations),