Ecotopia: An Ecological Framework for Change Management in Distributed Systems

TitleEcotopia: An Ecological Framework for Change Management in Distributed Systems
Publication TypeBook Chapters
Year of Publication2007
AuthorsDumitras T, Roşu D, Dan A, Narasimhan P
Editorde Lemos R, Gacek C, Romanovsky A
Book TitleArchitecting Dependable Systems IV
Series TitleLecture Notes in Computer Science
Pagination262 - 286
PublisherSpringer Berlin Heidelberg
ISBN Number978-3-540-74033-9, 978-3-540-74035-3
KeywordsAutonomic Computing, Dynamic Change Management, Fault-Tolerant Architecture, Operating systems, Performability, Service Orchestration, software engineering

Dynamic change management in an autonomic, service-oriented infrastructure is likely to disrupt the critical services delivered by the infrastructure. Furthermore, change management must accommodate complex real-world systems, where dependability and performance objectives are managed across multiple distributed service components and have specific criticality/value models. In this paper, we present Ecotopia, a framework for change management in complex service-oriented architectures (SOA) that is ecological in its intent: it schedules change operations with the goal of minimizing the service-delivery disruptions by accounting for their impact on the SOA environment. The change-planning functionality of Ecotopia is split between multiple objective-advisors and a system-level change-orchestrator component. The objective advisors assess the change-impact on service delivery by estimating the expected values of the Key Performance Indicators (KPIs), during and after change. The orchestrator uses the KPI estimations to assess the per-objective and overall business-value changes over a long time-horizon and to identify the scheduling plan that maximizes the overall business value. Ecotopia handles both external change requests, like software upgrades, and internal changes requests, like fault-recovery actions. We evaluate the Ecotopia framework using two realistic change-management scenarios in distributed enterprise systems.