Skip to content Skip to footer

Demand for HPC requires an open standards approach  

Image: Adobe Stock / Olga

Paul Mellon, Operations Director at Stellium Data Centres, delves into what it means to be ‘OCP-Ready’ and how the certification could help data centre managers and operators more effectively accommodate HPC environments.

Is your colocation data centre OCP-Ready? Ready for what you may ask, which is not unsurprising bearing in mind this certification is not yet particularly well known. However, out of sheer necessity, this is about to change with the market’s onward push for power-hungry HPC workloads and the data centre infrastructure that goes with it.

Launched by the OCP (Open Compute Foundation) five years ago, OCP-Ready certification reflects a colocation facility’s readiness to receive OCP community clients in terms of size of rack, power density per rack and efficiency. The goal of the programme is to identify colocation data centre providers and facilities where solutions architects can deploy OCP IT equipment without complications. Because the programme’s standards are open-source, operators will know what a given rack needs to do in terms of size, capability, and power before it arrives on-site, and ensure the design and layout is ready to support this class of equipment. The net result: faster speed to market, reduced costs and greater energy efficiency.

With the majority of Open Compute, hardware is deployed as a fully-populated rack. OCP-Ready data centre facilities must be able to easily accommodate racks of these weights and dimensions and be able to deploy multiple racks of such equipment at scale. As a minimum, the rack sizes can weigh 500kGs to 1500 kGs, and be 47U in height. The workloads can be anything from 6.6 kW to 36 kW and beyond. Additionally, cooling of these racks will require potentially a range of solutions – immersive, chilled water/air, chip cooling. For the higher densities, the expectation is for PUE to be sub 1.1.

Getting ready

Achieving OCP-Ready compliance is pretty intensive. While this is a self-certification process, it is definitely not a tick box exercise. It involves presenting your data centre technically and environmentally to your technical peers, including a Q&A session.

As part of the interview/Q&A session, we had to demonstrate that we lived their principles in our daily operations. It would just not work if these remained on the wall as a set of rules. We had to demonstrate our commitment to continuous development in terms of ISO14001 – Environmental Management, our CCA tariff relief programme and to lowering our PUE from its current level of 1.24.

It also entails working with the OCP to achieve compliance against their rigorous requirements across five functional areas within the data centre: power, cooling, IT technical space layout and design, facility management and control, and facility operations. Thereafter, demonstrating an ongoing commitment to continuous improvement and of course sharing.

Still not convinced? There are still hundreds of millions of highly inefficient IT environments throughout the world with PUE levels in-excess of two in the public sector, the commercial sector and industrial environments, all awaiting migration to the cloud. OCP is engaged in making this transition faster, more efficient and more robust. 

The roots to this go back to 2009 when Facebook and several other technology companies created a data centre design that would reduce cost and boost efficiency. The first Facebook facility built in Prineville, Oregon was a great success so the group decided to make the design information available to all through an open source format. These efforts ultimately led to the formation of the Open Compute Project Foundation (OCP) as a collaborative community focused on redesigning hardware technology which more efficiently supports the growing demands on compute infrastructure.

Added value

The real value that OCP brings is that these elements are researched at such scale as to short circuit the development and standardisation process from decades to years and sometimes months. As a result, high power density and cooling is now readily available at all levels in the data centre community. For example, a single rack can now accommodate 100 kW in normal chilled water cooling and this scales to 250 kW with immersive cooling.

These developments represent giant steps forward and are impossible to replicate in a normal business environment, hence the ongoing migration of workloads to the cloud and colocation data centres. In addition to lower power usage, there are substantial benefits in terms of flexibility of how organisations choose to manage their services and growth as well as robust SLA’s guaranteeing 99.98% service availability.

Furthermore, OCP-Ready fits neatly alongside other global standards within the industry such as BREAM, LEED, ISO and Uptime while complementing The European Code of Conduct for Data Centres (EU DC CoC).

With the drive towards HPC and the challenges this brings for colocation operators and their customers, an open standards-based hardware certification programme for colocation facilities is a necessity. It’s time to get OCP-Ready. 

Paul Mellon
Paul Mellon
Operations Director at Stellium Data Centres

You may also like

Stay In The Know

Get the Data Centre Review Newsletter direct to your inbox.