RAS is a critical requirement for enterprise class servers, which includes high availability server platforms. System uptime is measured against the goal of “five nines,” which represents 99.999 percent availability. One of the key aims of manageability software is to help achieve this goal, by implementation functions like dynamic error detection, correction, hardware failure prediction, and the taking of corrective actions like replacing or turning off failing components before the failure actually happens. This article describes the enhanced Intel® architecture platform dynamic error handling framework, a system level error management infrastructure that is now an integral part of most industry standard server class operating systems.This article is based on material found in book Beyond BIOS: Developing with the Unified Extensible Firmware Interface, 2nd Edition by Vincent Zimmer, Michael Rothman, and Suresh Marisetty.
Manageability and the Intel Unified Extensible Firmware Interface
Download (257.99 KB)