In the circumstances in question IT infrastructure can be split into two parts: IT computing and communication equipment (servers, routers, storage, laptops and desktops) and the NCPI that this hardware supports. NCPI includes power, power distribution, cooling, cooling distribution, service and the physical infrastructure management systems that support the hardware and software platforms of mission-critical data centres and facilities.
Goal of standardisation
Experience shows that one-time engineering of an entire NCPI results in a distinctive system, with specific problems that require precise diagnosis and repair. These processes are not only expensive and time-consuming, but also provide little intelligence that can be applied to future problems or problems at other data centres in the organisation.
Standardisation eliminates the need for one-time engineering and eradicates the overhead of dealing with specific problems in the infrastructure, thereby freeing up resources for developing the data processing functionality of the IT layer supported by the infrastructure - the real mission of the data centre.
The goals of NCPI standardisation are to drive out the inefficiencies and error-prone complexity of one-time engineering, to transparently manage the routine business of IT physical infrastructure and create the same signature quality expected of any infrastructure.
Standardisation improves availability
Standardisation also impacts availability in several ways. The major factors affecting availability are the reliability of equipment, mean time to recover (MTTR) and human error.
In terms of the reliability of equipment, standardised modular components can be mass produced in greater volume than non-modularised systems, reducing production defects. Modular components can be returned to the manufacturer for factory service, which greatly improve s the quality of repairs. In addition, modular systems with standardised hook-ups can be configured at the factory in the same way they will be configured on site, allowing for factory pre-testing for defects.
In addition, standardised modular components facilitate internal redundancy (no downtime at the time of component failure) and hot-swap replacement (no downtime during swap-out of a failed component).
With MTTR, a failed modular component can be quickly swapped-out for replacement, so recovery is not delayed while waiting for repair. Standardisation results in systems that are easier to understand and operate, making diagnosis of problems faster and increasing the potential for diagnosis and correction by the user.
Of all the ways to increase availability, reducing human error offers by far the greatest opportunity. With standardised equipment and procedures, functionality is more transparent, routines are simplified and easier to learn and systems operate as expected. These factors reduce the likelihood of any human error ? from typing the wrong command to pulling the wrong plug.
Move to standardisation
It is clear, therefore, that adopting modular standardisation as a design strategy for data centre physical infrastructure can be beneficial on many fronts, not least in reducing unnecessary expense and avoiding downtime. In addition, standardisation and modularity of the data centre infrastructure streamlines and simplifies every process, from initial planning to daily operation, resulting in significant improvements in availability.