Many organizations are currently performing significant data center infrastructure upgrades and replacements to support the growing demands of higher performance and higher availability requirements in conjunction with data center consolidation activities. Unfortunately, data center managers are becoming painfully aware of a new set of hurdles associated with these projects -- the emerging environmental deficiencies (data center power and cooling, in particular) of existing data centers. Driven primarily by the growth of new blade servers designed to minimize space use, but require at minimum twice the amount of power as traditional rack-mounted servers, and therefore more cooling, data center managers must quickly address the current and future data center power and cooling infrastructure, or face serious disruptions to service.
Organizations must analyze their data center facility design to ensure they can handle the concentrated power densities and deliver the data center cooling that modern equipment may require. Facility upgrades and/or new designs that match the new data center power and cooling demands should be considered. In addition, monitoring the planned changes and new server acquisitions must also occur so that the necessary changes to the data center physical infrastructure (space, power and cooling) can be accomplished prior to implementation.
Specifically, designs must ensure the total data center power delivered is adequate to supply the floor space at high energy densities. In addition, the data center cooling capacity necessary to remove the total heat output must be present. Detailed designs and equipment selections should reduce hot spots and provide adequate cooling to every part of the data center.
Liebert, a provider of data center power and cooling equipment, offers five various alternatives for deployment of high-density enclosures and blade servers to prevent exhaustion of the data center power/cooling infrastructure:
1. Provide the data center with the capability to power and cool any and every rack to the peak enclosure density.
2. Provide the data center with the capability to power and cool to an average value below the peak enclosure value, and use supplemental cooling equipment as needed to cool racks with a density greater than the design average value.
3. Provide the data center with the capability to power and cool to an average value below the peak enclosure value, and use rules to allow high density racks to borrow adjacent underutilized cooling capacity.
4. Provide the data center with the capability to power and cool to an average value below the peak potential enclosure value, and spread out the load of any proposed enclosures whose load exceeds the design average value by splitting the equipment among multiple rack enclosures.
5. Provide the data center with the capability to power and cool to an average value below the peak enclosure value, provide a special limited area within the room that has high cooling capacity, and limit the location of high density enclosures to that area.
Each of these alternatives has its set of advantages and disadvantages. However, the bottom line is that data center managers must plan and seriously rethink the design of the data center power and cooling infrastructure to meet the growing demands of the new computing equipment. For more information on using Aperture to manage power and cooling in today's high density data center, click here.