The Descartes Modeling Language for Self-Aware Performance and Resource Management

The Descartes Modeling Language (DML) is a novel architecture-level language for modeling performance and resource management related aspects of modern dynamic software systems and IT infrastructures. Technically, DML is comprised of several sub-languages, each of them specified using OMG’s Meta-Object Facility (MOF) and referred to as meta-model in OMG’s terminology. The various sublanguages can be used both in offline and online settings for application scenarios like system sizing, capacity planning and trade-off analysis, as well as for self-aware resource management during operation. Modern software systems have increasingly distributed architectures composed of looselycoupled services that are typically deployed on virtualized infrastructures. Such system architectures provide increased flexibility by abstracting from the physical infrastructure, which can be leveraged to improve system efficiency. However, these benefits come at the cost of higher system complexity and dynamics. The inherent semantic gap between application-level metrics, on the one hand, and resource allocations at the physical and virtual layers, on the other hand, significantly increase the complexity of managing endto-end application performance. To address this challenge, techniques for online performance prediction are needed. Such techniques should make it possible to continuously predict at runtime: a) changes in the application workloads [HHKA14], b) the effect of such changes on the system performance, and c) the expected impact of system adaptation actions [BHK14]. Online performance prediction can be leveraged to design systems that proactively adapt to changing operating conditions, thus enabling what we refer to as self-aware1 performance and resource management [KBH14, HvHK14, KBHR10]. Existing approaches to performance and resource management in the research community are mostly based on coarsegrained performance models that typically abstract systems and applications at a high level, e.g., [JHJ10, ZCS07, CAAS07]. Such models do not explicitly model the software architecture and execution environment, distinguishing performance-relevant behavior at the virtualization level vs. at the level of applications hosted inside the running VMs. Thus, their online prediction capabilities are limited and do not support complex scenarios such as, for example, predicting how changes in application workloads propagate through the 1Self-awareness is understood as adopted for Dagstuhl Seminar 15041 (http://www.dagstuhl.de/15041) layers and tiers of the system architecture down to the physical resource layer, or predicting the effect on the response times of different services, if a VM in a given application tier is to be replicated or migrated to another host, possibly of a different type. To enable online performance prediction in scenarios such as the above, architecturelevel modeling techniques are needed, specifically designed for use in online settings. We present a new architecture-level language, called Descartes Modeling Language (DML)2, which provides appropriate modeling abstractions to describe the resource landscape, the application architecture, the adaptation space, and the adaptation processes of a software system and its IT infrastructure [BHK14, HvHK14]. We present an overview of the different constituent parts of DML and describe how they can be leveraged to enable online performance prediction and proactive model-based system adaptation. The complete DML specification is available as a technical report [KBH14]. A set of related tools and libraries are available from the DML website at http://descartes.tools/dml. Finally, we present some exemplary results from an industrial case study showing the applicability of our approach in a real-life setting [HvHK14].