Andreas Bieswanger

Hardware configuration framework for the IBM eServer z900

This paper describes the concept, architecture, and implementation of the hardware configuration module within the support element of the IBM eServer z900. For the z900 project, this base system firmware component has been redesigned to obtain a software structure with a clear, simple, and scalable architecture that is suitable for future extensions to the z900. To achieve the desired flexibility, an object-oriented framework has been developed which supports the autosensing and configuration of hardware components as well as their status representation and management. The new configuration concept is based on a rule approach in which, for each sensed physical part in the system, a configuration rule specifies the object hierarchy to be instantiated upon it, including attributes and interconnections to other system parts. Furthermore, the concept and architecture of the framework are built upon a hardware object model (HOM) that has been designed to allow for further integration of key business logic of the z900 service subsystem and hardware support code.

IBM zEnterprise energy management

Data centers are facing serious energy challenges. Increasing energy costs make the operation and cooling of servers more significant cost factors. Furthermore, improvements in technology have led to processor chips and systems with rapidly increasing power density. The resulting power consumption and cooling requirements of these systems are pushing many existing data centers to the limits of their power distribution capability and cooling capacity. Improvements in energy efficiency and management are needed at the chip and the system level to counteract this trend. This paper provides a comprehensive description of the hardware and firmware improvements implemented with IBM zEnterprise® 196 to stop the growth of and even reduce its energy footprint compared with previous IBM System z® servers. These include more power-efficient chips; power conversion and distribution; new sensors; cooling control firmware; new energy management functions; integrated hybrid energy management for power saving and power capping across the whole hybrid system; and data center energy-efficiency improvements resulting from options for water cooling, high-voltage DC (HVDC) power, and overhead cabling.

Energy Efficient Data Center

Abstract In this article we describe the application of physical analytics to manage optimally energy consumption of a data center (DC). In its core the solution leverages the intelligent co-management of IT workloads and the physical infrastructure of the DC. Specifically, we demonstrate workload dependent control using real-time data such as temperature, pressure, humidity and power consumption. The data is used to build specific and comprehensive models, which enables operators to either control the cooling resources or alternatively to place the IT workloads for optimum energy usage. Zusammenfassung Dieser Artikel beschreibt, wie der Energieverbrauch von Rechenzentren unter Anwendung von physikalischer Analytik optimiert werden kann. Es kommt dabei ein intelligentes Zusammenspiel von Management-Komponenten zum Einsatz, die sich von der Rechenzentrumsinfrastruktur bis zum IT Workload Management erstrecken. Wir demonstrieren dabei eine lastabhängige, automatisierte Steuerung auf Basis von Echtzeitdaten wie Temperatur, Luftdruck, Stromverbrauch und Luftfeuchtigkeit. Diese Daten werden zur Erstellung von spezifischen Modellen verwendet, mit deren Hilfe die Verantwortlichen im Rechenzentrum in die Lage versetzen werden, sowohl die Kühlungsinfrastruktur wie auch die Platzierung von IT Workload zu steuern für eine optimale Energieverwertung.

Power and thermal monitoring for the IBM system z10

In May 2007, IBM announced Project Big Green, an initiative M. R. Vanderwiel designed to accelerate the adoption of green technologies and services in order to make data centers more energy efficient. An integral part of this strategy is to enable power and thermal monitoring on all IBM server platforms. The IBM System z10e server delivers these capabilities and is the first system in its class on the market to provide this functionality. This paper introduces the z10e power and thermal monitoring architecture and provides an end-to-end view of the underlying technology, from reading voltage and current to visualizing trending information in the Active Energy Manager extension to IBM Director.