Power and Cooling Capacity Management for Data Centers

Powe r and Cooling
Capacity Management for Data Centers


By Neil Rasmussen
White Paper #150


Executive Summary
High density IT equipment stresses the power density capability of modern data centers.
Installation and unmanaged proliferation of this equipment can lead to unexpected
problems with power and cooling infrastructure including overheating, overloads, and loss
of redundancy. The ability to measure and predict power and cooling capability at the rack
enclosure level is required to ensure predictable performance and optimize use of the
physical infrastructure resource. This paper describes the principles for achieving power
and cooling capacity management.
©2007 American Power Conversion. All rights reserved. No part of this publication may be used, reproduced, photocopied, transmitted, or stored in any retrieval system of any nature, without the written permission of the copyright owner. www.apc.com WP #150 Rev 0 2 Introduction
According to Gartner Inc., most data center operators are unaware of the loading and current power and cooling capability of their data centers, even at a total bulk level. Installing equipment that exceeds the design density of the data center, and the resultant stresses on the power and cooling systems, are causing downtime from overloads, overheating, and loss of redundancy. The IT Infrastructure Library (ITIL) defines capacity management CAPACITY MANAGEMENT ITIL Definition as the discipline that ensures infrastructure is provided at the right time in the right volume at the right price, and that it is used in the Providing infrastructure... most efficient manner. The critical success factors are: At the RRIIGGHHTT TTIIMMEE In the RRIIGGHHTT AAMMOOUUNNTT . Providing accurate capacity forecasts At the RRIIGGHHTT PPRRIICCEE AND Æ UUSSEEDD EEFFFFIICCIIEENNTTLLYY . Providing appropriate capacity to meet business needs This involves input from many areas of the business to identify what IT systems are (or will be) required, what power and cooling infrastructure is required to support these IT loads, what level of contingency will be needed, and what the cost of this infrastructure will be. This paper applies the ITIL view of capacity management specifically to the problem of power, cooling, and space capacity of data centers. A model is described for the quantification of power and cooling supply, demand, and the different types of capacity that must be managed. This model can serve as a framework for describing a capacity management system, or for establishing service level management guidelines. Figure 1 - Capacity management is an ITIL service process
Incident Service Level Management Management IT Service Problem Availability Management Community Management Management
Change IT Financial Management Capacity ManagementManagement Release Management ITIL SSeerrvviiccee DDeelliivveerryy processes Focused on business ownersITIL SSeerrvviiccee SSuuppppoorrtt processes Configuration ManagementFocused on end users
©2007 American Power Conversion. All rights reserved. No part of this publication may be used, reproduced, photocopied, transmitted, or stored in any retrieval system of any nature, without the written permission of the copyright owner. www.apc.com WP #150 Rev 0 3 Background
The ability to establish the power and cooling capability at a specific rack is extremely rare. Data center operators typically do not have the information they need to effectively deploy new equipment at the rate required by the business, and are unable to answer simple questions such as: . Where in my data center should I deploy the next server so I don't impact the availability of existing equipment? . From a power and cooling availability standpoint, where is the best location to deploy the proposed IT equipment? . Will I be able to install new equipment without negatively impacting my safety margins such as redundancy and backup runtime? . Will I still have power or cooling redundancy under fault or maintenance conditions? . Can I deploy new hardware technology, such as blade servers, using my existing power and cooling infrastructure? . Do I need to spread out my blade servers to get reliable operation? ... [download for more]