Enabling Self-Managing Applications using Model-based Online Control Strategies

Abstract

Abstract-The increasing heterogeneity, dynamism, and uncertainty of emerging DCE (Distributed Computing Environment) systems imply that an application must be able to detect and adapt to changes in its state, its requirements, and the state of the system to meet its desired QoS constraints. As system and application scales increase, ad hoc heuristic-based approaches to application adaptation and self-management quickly become insufficient. This paper builds on the Accord programming system for rule-based self-management, and extends it with model-based control and optimization strategies. This paper also presents the development of a self-managing data streaming service based on online control using Accord. This service is part of a Grid-based fusion simulation workflow consisting of long-running simulations, executing on remote supercomputing sites and generating several terabytes of data, which must then be streamed over a wide-area network for live analysis and visualization. The self-managing data streaming service minimize data streaming overheads on the simulations, adapt to dynamic network bandwidth, and prevent data loss. An evaluation of the service demonstrating its feasibility is presented.

Using Filtered Cartesian Flattening and Microrebooting to Build Enterprise Applications with Self-adaptive Healing

“…Numerous MDE approaches for building self-healing service compositions (Joshi et al, 2005;Lapouchnian et al, 2005;Bhat et al, 2006;Barbier, 2006;Elkorobarrutia et al, 2006;Calinescu, 2007;Denaro et al, 2007) rely on developers modelling each potential error state and the recovery paths from each state. Regardless of the technique used, developers are always responsible for implementing the complex application-specific recovery actions.…”

“…There are a large number of other healing or adaptation approaches (Joshi et al, 2005;Lapouchnian et al, 2005;Bhat et al, 2006;Barbier, 2006;Elkorobarrutia et al, 2006;Calinescu, 2007;Denaro et al, 2007) that rely on identifying error states and then planning and executing some number of recovery actions. As shown in Section 3, modelling and implementing recovery actions is complex and costly.…”

“…A common approach (Joshi et al, 2005;Lapouchnian et al, 2005;Barbier, 2006;Bhat et al, 2006;Elkorobarrutia et al, 2006;Calinescu. 2007;Denaro et al, 2007) to modelling application healing is to model the individual error states that the application can enter and a recovery path (a sequence of recovery actions) to return the application to a correct state.…”

“…This approach allows MDE tools to generate much of the complex healing code and in many cases, remove the healing code if it does not function properly. Although, numerous approaches (Joshi et al, 2005;Bhat et al, 2006;Calinescu, 2007;Denaro et al, 2007) have been devised to build MDE models and platforms for enterprise applications, these approaches tend to suffer from one or more of the following problems:…”

“…For each potential error state that an application's service composition could enter, conventional MDE adaptation techniques (Joshi et al, 2005;Bhat et al, 2006;Calinescu, 2007, Denaro et al, 2007 require explicitly modelling both the error state and the numerous actions to transition from the error state to a correct state. For large enterprise applications, moreover, there are usually a significant number of potential error states and complex nuanced considerations, such as availability of other services, database locks held and transaction states.…”