Last week I attended (and presented at) Data Centres Europe 2010 that was held at 24-25 June 2010 in the surroundings of the famous scientific/business park Sophia Antipolis near Nice, France and organized by Broadgroup. In its sixth edition, this European summit is for senior IT executives, analysts and vendors to network, discuss and learn about the latest developments in data centers. A great event, although battered by the icelandic volcano and strikes, attended by hundredths Senior IT Executives from all sorts of organizations.
In the presentations and the panel discussions there was much emphasis on the following topics:
– Sustainability and Green in the Data Center
– Cloud computing and the impact on Data Centers
– Raising finance – options, opportunities and structure
– Increasing Efficiency
– Reducing Data Centre Power Costs
– Legislative action over energy usage and carbon emissions
From my observation there were also three other recurring theme’s in the presentations and the discussions:
- The need for better designs, based on modular building blocks to get a flexible infrastructure
- That there is still a gap between the world of the site infrastructure and the IT infrastructure
- The need for monitoring, tools and performance indicators for the data center environment
Although it looks like we still are in a phase of IT infrastructure consolidation (virtualization), the rise of energy usage because of the demand of the growing digital economy, the likelihood of legislative action over carbon emissions and cloud computing ask for well thought, integral but modular designs to meet these new demands. Right provisioning is about right sizing and requires agility of the infrastructure. Some speakers of the financial industry were telling about the usage of an IT stack and modular approach of the site and IT infrastructure. Interxion told even about a statistical design approach, where the availability of different modular site infrastructure architectures are calculated and compared by means of monte carlo simulations to make choose the right infrastructure. They even claimed they discovered simpler architectures with better results than those proposed by the Uptime institute.
To get the right results on the business level there should be an integral approach in designing and managing the IT stack or IT value chain. But a lot of speakers make a note or remark in the site line that there are still gaps between the business and the IT and the Data Center (site) groups that makes it different to get commitment and agreements to take proper actions in terms of needed quality and energy usage. APC explicitly talked about the gap between IT and Site infrastructure and made some bold statements about a needed “energy revolution” to get things changed.
Also the spirit of Deming (plan, do, check, act) was ‘haunting’ around. Especially for energy usage and carbon footprint there is a need to know and therefore a need for figures and performance indicators. At this moment it looks like there is still not a shared understanding and agreement which are the proper performance indicators and therefore it is difficult to choose (if they are available) the right tools to do measurements. Because the proper order of things must be:
-The goals describe the purpose or the desired state to achieve.
-The goal is normally described as a state of the system.
-The means describe how the goals can be achieved.
-The means describe functions or activities that will achieve the goals.
With siloed decision-making, the measurement and accountability issues and the absence of true usage and cost analysis, inefficiency become the rule. Some of the observed issues are already picked up in the market by initiatives like the Stack of DatacenterPulse and OpenDCME.
There is still a lot of work needed and to do in the data center arena a work field and a market that is very dynamic at the moment.