An Approach to Autonomizing Legacy Systems

Abstract

Adding adaptation capabilities to existing distributed systems is a major concern. The question addressed here is how to retrofit existing systems with self-healing, adaptation and/or selfmanagement capabilities. The problem is obviously intensified for "systems of systems" composed of components, whether new or legacy, that may have been developed by d ifferent vendors, mixing and matching COTS and "open source" components. This system composition model is expected to be increasingly common in high performance computing. The usual approach is to train technicians to understand the complexities of these components and their connections, including performance tuning parameters, so that they can then manually monitor and reconfigure the system as needed. We envision instead attaching a "standard" feedbackloop infrastructure to existing distributed systems for the purposes of continual monitoring and dynamically adapting their activities and performance. (This approach can also be applied to "new" systems, as an alternative to "building in" adaptation facilities, but we do not address that here.) Our proposed infrastructure consists of multiple layers with the objectives of probing, measuring and reporting of activity and state within the execution of the legacy system among its components and connectors; gauging, analysis and interpretation of the reported events; and possible feedback to focus the probes and gauges to drill deeper, or -when necessarydirect but automatic reconfiguration of the running system.

Automatically generating adaptive logic to balance non-functional tradeoffs during reconfiguration

“…Developers often design and implement adaptation paths at design time to address specific reconfiguration scenarios that may arise at run time [2,3,9,23]. For example, Figure 1 illustrates an adaptation path for reconfiguring the underlying topology in a network of remote data mirrors.…”

“…Most traditional self-adaptive systems apply variants of rule-based [3,9,24] and utility-based [2,16,22] techniques to select applicable reconfiguration plans at run time. These reconfiguration plans encode sequences of reconfiguration instructions that define an adaptation path.…”

Autonomic Job Scheduling Policy for Grid Computing

“…There has been some work towards autonomic grid computing [8][11][6] [9]. Liu, and Parashar [11] present an environment that supports the development of self-managed autonomic components, dynamic and opportunistic composition of these components using high-level policies to realize autonomic applications, and provides runtime services for policy definition, deployment and execution.…”

Using Process Technology to Control and Coordinate Software Adaptation

“…As a consequence, within the DASADA program [3], under which we are conducting this research, a standard model, the Common DASADA Infrastructure (CDI) [25] has emerged, which organizes the design of the feedback loop according to multiple layers, as shown in Figure 1.…”

“…Our model for externalized dynamic adaptation is that of a layered architecture, which comprises layers for data collection, information analysis, decision / control, and actuation. In-depth discussion of the overall infrastructure model, and how its collection and analysis components have been fulfilled within our Kinesthetics eXtreme (KX) implementation can be found in [18] [23]. This paper focuses instead on the decision and control role, and how we have addressed it in KX with our Workflakes processbased engine.…”