BLADE SERVER TECHNOLOGY - HOT TOPIC - Energy Efficiency

Download PDF version

Using Blade Servers to Increase Energy Efficiency

One of the hottest topics in data center management is energy efficiency. But, what can a data center manager do to control runaway energy costs? There is a straightforward process:

Make a plan - start with assumptions, if necessary and then fine tune as you acquire more data about your consumption profile
Monitor and then analyze your energy consumption and factor those results back into your plan
Develop a timeline and forecast for future data center performance requirements
Explore which new technologies, blades, virtualization, infrastructure consolidation, power management programs are available to manage and reduce power consumption
Use that plan with expert assistance from energy and equipment vendors to map out a realistic program of data center floor planning, cooling planning and power management
Continue to monitor and analysis power usage and use that data to refine your data center planning

With the cost of energy skyrocketing at the same time as user demand for more performance is increasing, IT managers are facing a power, space and cost crunch. Some data center managers have already reported that the cost of electricity and cooling in the data center are exceeding the cost of the equipment itself. IDC estimates for every $1.00 spent on new data center hardware, an additional $0.50 is spent on power and cooling, more than double the amount of five years ago. According to Gartner, 70 percent of CIO's are reporting that power and/or cooling issues are now their single largest problem in the data center. Gartner estimates that 50 percent of data centers in 2008 will have insufficient power and cooling capacity to meet demand with 48 percent of the data center budget being spent on energy, up from 8 percent a few years ago.

IDC chart

It is clear that IT managers need new ways to reduce power as they increase data center performance. Blade servers are a key server consolidation and infrastructure management technology whose deployment can deliver the needed increase in performance while giving data center managers new ways to cut power consumption and costs.

It may seem counterintuitive. Blade servers pack more horsepower into smaller chassis and enable a greater concentration of compute power in the data center. With multiple, highly compact blade servers, a single blade server chassis can deliver more compute resources than racks of individual server towers or rows of server racks. But this increased density can translate into higher power consumption per square foot. How does one get around this physical limitation? Besides adopting blade server architectures in the data center, it takes smarter planning, superior power management tools and effective utilization of advanced new technologies such as virtualization.

1 - Plan for Efficient Cooling

A critical first step is to accurately plan for present and future power needs and design a power and cooling floorplan that optimizes power consumption. Many data center managers are shocked to learn that a very low percentage of power they purchase actually gets used in the data center. The majority goes out the window due to inefficient power distribution and cooling footprints. One common and power wasting mistake is oversizing the power and cooling capabilities by overbuilding the actual needs of the data center.

APC figure

Initial planning that anticipates future hotspots can help avoid costly floorplan alterations later. Installing smaller and lower cost cooling and power units closer to computational hotspots can avoid the situation where expensive edge-based cooling systems try to cool systems that are located across the data center. This is very inefficient and costly. IBM and other vendors offer services that include assessment of existing infrastructure, analysis of future computational requirements, workload estimates and factor in how to budget and place both cooling and power systems to provide the maximum cooling in the most efficient manner.

2 - Monitor and Manage Power Consumption to Tune for Efficiency

Of course, to manage power consumption, you must employ advanced power-monitoring software to understand and control power consumption. It is not uncommon for data center managers to lack information on how much power individual servers consume. Without an accurate way to measure power consumption, peak loading and the effects of virtualization, adding more servers, switches or storage subsystems, it is impossible for managers to control power consumption. New advanced tools such as IBM PowerExecutive automated tools needed to monitor and manage power consumption accurately. It can measure real-time power consumption and heat emission by individual server, server group or location. It allows the optimization of energy use and the lowering of power consumption when low utilization can provide cost savings. These power monitoring and management capabilities are an important tool in achieving energy efficiency in the data center.

IBM PowerExecutive

3 - Virtualization for Increased Server Utilization

The third tool is virtualization technology to achieve higher server utilization. By enabling more applications to run more efficiently on fewer servers, virtualization technology increases server utilization and in turn reduces the number of servers and subsequent power and cooling costs for a given infrastructure. Alternatively, it permits an increase in applications and server performance without a corresponding increase in power consumption and energy budgets. Today, many data center are using only 5 to 10 percent of their server capacity. Through the use of virtualization technologies, this percentage can climb to nearly 100 percent. Higher server utilization lowers overall power requirements.

So, to tackle the power challenges in the data center, turn to blade servers, plan accurately for right-sized power and cooling, monitor and manage power consumption on a server, rack and data center level, and apply virtualization technologies to increase performance and increase server utilization.

Additional Resources