Non-intrusive autonomic approach with self-management policies applied to legacy infrastructures for performance improvements - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles International Journal of Adaptive, Resilient and Autonomic Systems Year : 2010

Non-intrusive autonomic approach with self-management policies applied to legacy infrastructures for performance improvements

Abstract

The growing complexity of large IT facilities involves important time and effort costs to operate and maintain. Autonomic computing gives a new approach in designing distributed architectures that manage themselves in accordance with high-level objectives. The main issue is that existing architectures do not necessarily follow this new approach. The motivation is to implement a system that can interface heterogeneous components and platforms supplied by different vendors in a non-intrusive and generic manner. The goal is to increase the intelligence of the system by actively monitoring its state and autonomously taking corrective actions without the need to modify the managed system. In this paper, the authors focus on modeling software and hardware architectures as well as describing administration policies using a graphical language inspired from UML. The paper demonstrates that this language is powerful enough to describe complex scenarios and evaluates some self-management policies for performance improvement on a distributed computational jobs load balancer over a grid.
No file

Dates and versions

hal-00656972 , version 1 (05-01-2012)

Identifiers

Cite

Remi Sharrock, Thierry Monteil, Patricia Stolf, Daniel Hagimont, Laurent Broto. Non-intrusive autonomic approach with self-management policies applied to legacy infrastructures for performance improvements. International Journal of Adaptive, Resilient and Autonomic Systems , 2010, 2 (1), p. 58-76. ⟨10.4018/jaras.2011010104⟩. ⟨hal-00656972⟩
84 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More