* Budgeting approaches reflect views of data center function As we continue interviewing IT executives for Nemertes Research’s upcoming benchmark on data centers, we are finding two quite different approaches to budgeting and cost allocation around the data center.In some cases, data center operational costs are calculated “up to the OS,” with anything related to operating system configuration, patching and the applications running above the operating system considered outside the data center budget. Other IT executives take an “end-to-end” view. All activities related to the delivery of business services from the data center, including operational costs around the operating system and applications, are included in the data center costs.There are advantages and disadvantages to both approaches, and we can’t consider either “correct.” In fact, each approach will be appropriate for different companies.At the core of the budgeting question is each company’s IT culture. Is IT viewed as a service or a cost center? If IT and the data center are tasked with delivering infrastructure for business units to deliver services, they will account for the infrastructure without the cost of the operating system and application management. If the data center delivers business services to the end user, not infrastructure, then all the costs for delivering an application from the data center are included. Outsourcers face a similar conundrum. Traditionally, outsourcers would provide infrastructure for a business to use in the delivery of services. But, with increased adoption of application service providers and utility computing, the line between the underlying infrastructure and the business service is being blurred.So many outsourcers now see themselves as delivering business services, not infrastructure. This also changes the types of SLAs they will offer: instead of guaranteeing the uptime of the server, you will see more SLAs on the uptime of the service. Which type of approach is best? Again, it depends on the needs and culture of the business.One thing is certain, however. It is becoming increasingly difficult to keep a clean separation between infrastructure and business service. As data centers have changed to accommodate new computing and storage paradigms, the one-to-one correspondence between service and server is broken. Virtualization, clustering, on-demand computing and other such developments have made the infrastructure flexible and dynamic. Now a server may serve multiple applications, or several servers may provide a single service.Clearly, many of today’s applications are composites that involve interactions between many servers. A complex set of interdependencies between servers makes it very hard to manage them “in a vacuum” without looking at the business services for which they are responsible.A systemic approach to managing business service requires different management tools, but also different accounting practices. If your company’s IT culture is changing, you may need to adjust your accounting practices to allocate IT costs in alignment with your business goals. The different operational and organizational approaches to data center management are among many topics covered in our interviews with IT executives. Stay tuned for more trends and analysis. Related content news Cisco CCNA and AWS cloud networking rank among highest paying IT certifications Cloud expertise and security know-how remain critical in building today’s networks, and these skills pay top dollar, according to Skillsoft’s annual ranking of the most valuable IT certifications. Demand for talent continues to outweigh s By Denise Dubie Nov 30, 2023 7 mins Certifications Certifications Certifications news Mainframe modernization gets a boost from Kyndryl, AWS collaboration Kyndryl and AWS have expanded their partnership to help enterprise customers simplify and accelerate their mainframe modernization initiatives. By Michael Cooney Nov 30, 2023 4 mins Mainframes Cloud Computing Data Center news AWS and Nvidia partner on Project Ceiba, a GPU-powered AI supercomputer The companies are extending their AI partnership, and one key initiative is a supercomputer that will be integrated with AWS services and used by Nvidia’s own R&D teams. By Andy Patrizio Nov 30, 2023 3 mins CPUs and Processors Generative AI Supercomputers news VMware stung by defections and layoffs after Broadcom close Layoffs and executive departures are expected after an acquisition, but there's also concern about VMware customer retention. By Andy Patrizio Nov 30, 2023 3 mins Virtualization Data Center Industry Podcasts Videos Resources Events NEWSLETTERS Newsletter Promo Module Test Description for newsletter promo module. Please enter a valid email address Subscribe