Snooze: A Self-Organizing, Self-Healing and Self-Optimizing Cloud Management System

Demo and posterInternational audienceLarge-scale virtualized data centers enabling today's cloud services now require the cloud providers to implement easily configurable, fault-tolerant, and energy-efficient cloud management systems. In this demo we present the self-organization, self-healing, and self-optimization mechanisms of Snooze, a novel cloud management system based on a hierarchical architecture. Particularly, we focus on four key features: (1) dynamic hierarchy construction; (2) hierarchy failure recovery; (3) periodic and event-based (e.g. underload) virtual machine live migration for idle time creation; (4) power management to transition idle servers into a low-power state for energy savings