Best Practices from the Green Grid Drive eBay’s New Data Center
By: eBay Inc. Staff
eBay breaks new ground in data center efficiency, leveraging the Green Grid’s Power Usage Effectiveness and Data Center Maturity Model.
Editor's Note: The following press release was published on PRNewswire on Feb. 27, 2012.
The Green Grid, the global IT industry’s leading voice for advancing resource efficiency in data centers and business computing ecosystems, today released a case study detailing its industry best practices as they helped drive member company eBay to achieve new levels of energy efficiency in its recently completed data center in Phoenix, Ariz. eBay relied on The Green Grid’s Power Usage Effectiveness (PUETM) metric and Data Center Maturity Model (DCMM) to guide the design and construction, request-for-proposal (RFP) process, and server optimization for its desert-located facility named “Project Mercury.”
Faced with the challenge of consolidating its data centers and deploying tens of thousands of new servers in less than six months, eBay turned to The Green Grid to help achieve maximum energy efficiency for a brand new facility. eBay used The Green Grid’s best practices to take a holistic, end-to-end view of the space it was using, the servers it was deploying, and how its data centers were designed and operated.
Project Mercury was made possible through a metrics-based approach to guide data center design and server procurement. PUE was a driving tool in eBay’s vendor RFP process and the company leveraged PUE in its design criteria to achieve maximum efficiency from the beginning. Project Mercury has reported promising initial results in efficiency with a site average PUEL3,WC of 1.35 during one week in January 2012 and a best case PUEL3,HC of 1.26. In addition, a partial PUE (pPUEL3,HC) of 1.018 was measured in a rooftop container during the same period. eBay reported the same 20-rack rooftop container achieved pPUEL3,HC as low as 1.046 with outdoor conditions of 46oC (115°F) measured one day in August 2011. eBay also relied on total cost of ownership (TCO) to assess its servers in terms of the total lifetime kilowatt hours (kWh) used while running the company’s workload.
To achieve maximum efficiency, eBay leveraged several best practices from The Green Grid’s DCMM, highlighting the value of the Model and how it can impact bottom line results. Aligned with the DCMM, eBay’s approach further testifies to the benefits of using metrics to guide design and purchase decisions in data centers. eBay’s metrics-based approach optimized the company’s data center supply chain for lower PUE and TCO, due in large part to higher server density within the data center and a “hot water” cooling system that requires traditional chiller operation only a few days per year.
Other results include an innovative server rollout to support rapid scaling, dense rack deployments, and a consolidated set of server designs that balance space, power, cooling, cabling, and weight configurations for maximum speed, workload agility and efficiency. The modular, scalable design is ready to handle up to five generations of future technologies and provides a data center space that places servers in the appropriately resilient space, slashing cost in half for hosting 80 percent of eBay’s applications.
“We needed to meet an organizational demand to consolidate data centers and deploy tens of thousands of new servers in under six months,” said Dean Nelson, Senior Director, Global Foundational Services (GFS), eBay. “As part of that process, we wanted to push the envelope in terms of what had been achieved in data center efficiency to date. eBay was able to achieve both goals because we took a metrics-based approach to the process, which included ensuring that our server and data center RFP processes used PUE and TCO to optimize our supply chain, taking a modular, scalable, and forward-thinking data center design, and aligning ourselves with The Green Grid’s DCMM from the beginning.”
“By all accounts, eBay’s Project Mercury is an advanced data center designed to optimize performance and energy use for eBay's specific workload profile, and one that also meets the five-year horizons defined by The Green Grid’s DCMM,” said Brad Brech, IBM representative and board member of The Green Grid. “This facility is an example of what is possible by establishing and relying on industry best practices for achieving maximum energy efficiency and low environmental impact in data centers. The Green Grid is at the heart of this mission and the organization will continue to look for new and innovative ways to promote resource efficiency and sustainability within the business computing ecosystem.”
To view the full case study, please visit: www.thegreengrid.org/en/Global/Content/white-papers/WP45-CaseStudyBreakingNewGroundonDataCenterEfficiency
Project Mercury Presented: The Green Grid Forum 2012
The Green Grid’s Fifth Annual Forum and Members Meeting, titled “Moving to Resource Efficient IT: Achieving Greater Productivity and Environmental Sustainability,” will feature a session led by Dean Nelson of eBay discussing the design and construction of Project Mercury and the resulting case study. The session will take place on day two of the event, Wednesday, March 7, from 3:35-4:45 p.m.
The Green Grid Forum 2012 will be held March 6-7, 2012 at the DoubleTree Hotel in San Jose, Calif. For more information or to register, please visit: http://www.thegreengrid.org/events/TGGforum-2012.aspx.
You can also find information about Forum 2012 on LinkedIn (http://linkd.in/roI3cu), Facebook (https://www.facebook.com/pages/The-Green-Grid/112345132111805) or join the conversation on Twitter by using the hashtag #TGGForum12.
About The Green Grid
The Green Grid is a global consortium of companies, government agencies and educational institutions dedicated to advancing resource efficiency in data centers and business computing ecosystems.
The Green Grid does not endorse vendor-specific products or solutions, and instead seeks to provide industry-wide recommendations on best practices, metrics and technologies that will improve overall data center resource efficiencies. Membership is open to organizations interested in data center operational efficiency at the Contributor, General or Associate member level and individuals at the Individual level.