Double Standard Method for Designing Adaptive Backup Systems

Abstract

Backup systems are vital for ensuring data life and usability. Most modern backup software is still laborious to configure, takes a lot of effort to continuously monitor and adjust, and is excessively prone to failure due to insufficient resources or due to hardware problems. This paper presents strategies driving an adaptive backup system that is able to auto-configure, self-monitor, and adapt itself to various conditions, with little human intervention and with very simple initial setup. The main discussion is around the hierarchical structure of the balancing problems that must be solved by the backup system, such that it can adapt to the changing work conditions. Authors propose the Dual Standard Model for automated balancing decisions, which has a striking similarity with human behavior. The software is used in production on a large network containing 1k+ Linux desktops, servers, and clusters at Carnegie Mellon University.