Proactive data management is necessary if data centre managers want to achieve increased efficiency, better planning cycles and higher levels of service.
This is according to Mark van Heerden from Perpetual Power Systems, an Emerson Network Power reseller, who says that data centres have entered a new stage of maturity and required to react to rapid, continuous changes dictated by capacity and availability requirements.
“The data centre is now seen as a significant corporate asset, which plays a vital role in business management and customer service. Over the past decade, it has undergone an evolution that has seen computing and data storage capacities increase significantly. The approach to managing the data centre has also shifted,” says Van Heerden.
According to IDC, global server shipments increased 15.3% year over year to $15-billion in the fourth quarter of 2010 (4Q10). This was the highest quarterly revenue in three years and the fourth consecutive quarter with improving year-over-year revenue growth as the market continued to accelerate throughout the calendar year.
He says there are two trends that emerged in the second half of the decade which has impacted the evolution of data centres. The first is the increased focus on data centre energy consumption, with both the density and quantity of servers rising. Data centre energy consumption became a significant factor in terms of IT cost management and concerns about global warming.
“Early efforts to reduce data centre energy consumption focused on reducing costs around data centre cooling, which accounts for approximately 37% of data centre energy consumption. Efforts should be focused on reducing this consumption spend to 11%, which will allow clients to increase power usage effectiveness.
"Subsequent efforts take a more holistic approach that recognises the interdependency of data centre systems and shifted the focus to the IT systems that create the need for cooling,” says Van Heerden.
The second trend was the adoption of virtualisation technologies. In its annual survey of data centre managers, the Data Centre Users’ Group saw virtualisation adoption rates of 81% in 2009.
This has created a dynamically changing application environment layered on an essentially static physical environment, which increases data centre complexity and introduces new challenges to physical infrastructure management.
Evolving from a reactive to proactive approach to data centre management requires a new type of system. “It needs to provide visibility into the data centre’s physical infrastructure within IT and facilities as well as across these two domains. It is what we like to call data centre infrastructure management (DCIM).”
There are 10 DCIM steps, he says, that will assist to increase data centre efficiency and availability. “This is done by deploying and leveraging measurement, intelligent controls and centralised monitoring and management.”
This infrastructure monitoring provides a systematic approach to building the foundation for data centre infrastructure management. By employing these prescribed 10 points, data centres stand to gain operational, strategic and transformative advantage for their enterprise or business.
* Sensing temperatures.
* Monitoring power.
* Monitoring rack conditions.
* Detecting fluid leaks.
* Intelligent control of precision cooling.
* Intelligent control of critical power.
* Managing alerts and alarms.
* Monitoring energy efficiency.
* Monitoring batteries.
* Monitoring and managing remotely.
Van Heerden says that by using these steps, data centre managers can automatically collect data from infrastructure systems and sensors placed strategically within the physical space. The data can be utilised to gain higher availability, increase efficiency, enhance the value of virtualisation, consolidate efforts and improve planning.
“By enabling management across the board, data centre operators will gain a true understanding of the true capacity of their IT and infrastructure systems, allowing them to manage closer to the actual capacity of the system, rather than the conservative estimates that leave some percentage of capacity unused as a buffer.”
Although sophisticated data centre management tools have emerged in recent years, many facilities still lack the ability to comprehensively monitor their physical infrastructure systems.
Van Heerden says this is partly due to the disparate systems that make up the data centre infrastructure, partly the result of the rapid changes transpiring in the data centre, and partly the lack of a clear and simple roadmap for bringing together these disparate systems into a common network.
“The 10 step approach provides data centre managers with a logical process to move towards comprehensive data centre infrastructure monitoring.”