ms datacenters

A few weeks back we had the privilege of hosting a data centre visit and tour for the residential neighbours of the Dublin data centre. Given the long projected lifespan of our new facility, we’re going to be neighbours for a long time, and so we felt it was important for us to get reacquainted now that the major construction is completed. We were keen to demystify the very large complex that had been emerging right in their back yard over the past year. It was very pleasant to share some pizza, provide a little background presentation, and then show this very important audience the fruits of our innovation.   

When preparing to present a mega data centre to folks who are not generally familiar with data centres, and who in some cases are very new to computers and the Internet, you have to take a very different approach, and I have to admit to finding it an enjoyable challenge to present Microsoft’s Software plus Services strategy, the emergence of the Internet, and this particular data centre in an informative and entertaining manner. The audience ranged from people in their early 20’s who are just entering the workforce to some who have been retired for many years. A couple had engineering backgrounds and wanted to delve into the construction, mechanical and electrical systems, while others were far more interested in the creature comforts we have in place for our workforce and the impact that our arrival would have on the neighbourhood from an employment, environmental, and security perspective.  

It was fascinating to hear their questions and to listen to their feedback as we toured them through the facility showing everything from the air handling units on the roof, the server pods providing hot aisle containment in the colos, and the extensive electrical distribution systems. I never imagined how hard it would be to stay away from the many industry terms and acronyms that we treat as part of our everyday language today, and on a couple of occasions it was only those quizzical looks that alerted us to the fact that we had slipped back into Microspeak again.  

Based on their comments and questions during the visit, it was clear that the community very interested in learning about our approaches to protecting the environment, to guard customer information, and to be an asset to the neighbourhood, the county and Ireland. They asked great questions about how clean and efficient we are, how we manage physical and logical security, what financial investments we were making, and what the impact on local employment would be. They were quite vocal in their enthusiasm for the design that takes advantage of the Irish weather to dramatically improve our power efficiency, reduce our carbon emissions, and to almost completely overcome the need to consume water.  Overall, the visit was a great success, and I believe we were able to provide them with a sense of why we are here, and what makes this new facility such a unique asset to Microsoft and Ireland.  

Containers Increase IT Efficiency of Microsoft’s Cloud Computing Infrastructure  

Microsoft’s cloud computing infrastructure takes another big step forward this week with the grand opening of our Chicago data center. At more than 700,000 square feet, this facility significantly expands our ability to meet the demand generated from our Live, Online, and Cloud Computing services offerings for our customers. Combined with the grand opening of our Dublin, Ireland, data center last week to expand our capacity and network throughout EMEA, the opening in Chicago demonstrates how Microsoft is expanding capacity around the world to support its online businesses and customers.

Investing in turbulent economic times is always a tough choice – one that Microsoft is clearly making by investing in technology and innovation in a thoughtful and measured manner with an eye towards long-term growth for our customers, our shareholders, and our business. Microsoft’s data centers represent the infrastructure foundation of the company’s cloud services offerings and demonstrate how Microsoft is positioning itself to compete and succeed with an approach we call Software plus Services. Microsoft’s Software plus Services strategy is designed to create computing experiences that offer both the best of client technology and the best of the Web to connect people, data, devices, and applications.

One of many reasons we decided to hold a grand opening of the Chicago facility is to share our best practices. While in one sense our best practices are competitive advantages for Microsoft, we hope they will also help others in the industry make the cloud a safer and more reliable place that companies can trust for their operations.  Very few companies can make the infrastructure investment that Microsoft has, so we think it is important to share what we’ve learned with the industry.  

The first phase of the Chicago data center represents 30 megawatts of critical power. An additional 30 megawatts is pre-positioned for future growth. This incremental approach means customers today will enjoy top-notch performance and availability while we control costs for Microsoft and its shareholders.

One aspect of this data center that I’d like to talk about in some detail here involves our continued focus on environmental best practices.

Through the use of pre-manufactured, standard shipping containers, each of which house approximately 1,800 to 2,500 servers (as we’ve noted in previous blogs), we are able to realize greater conservation of energy and deliver new advancements in power efficiency. In addition, the isolated nature of containers enables Microsoft and its vendors to research new approaches around power and cooling alternatives to reduce energy consumption even more in the future.

Inside view of a container in the Chicago data center. 

The Chicago facility is one of the largest data centers in the world to use containers. The entire first floor is devoted to parking stalls for containers, which will eventually house more than two-thirds of all the servers in the data center. The containers plug into standard interfaces called “CBlox” that we have developed with our partners. This interface provides a kind of “plug and play” for data center containers (for those of you who have been around long enough to remember when Microsoft developed “Plug and Play” for Windows).

See the video of containers being installed in the new Chicago facility.

Containers provide further environmental benefits in that they don’t require additional packaging materials or external form factors for the thousands of servers that they house. They also require less cabling and other equipment that all add up to unnecessary waste in traditional data center designs. Containers are also a very efficient way to quickly deploy capacity.

Another best practice we are using in Chicago is water-side economization, which enables us to cool the facility without requiring the high levels of electricity typically needed to power large chillers.  Environmental sustainability is in Microsoft’s DNA and the Chicago data center serves as a great example.

I’d also like to talk about the incredible quality and amount of work that went into this data center, as well as the investments Microsoft has made in the local community throughout this project. Building this state-of-the-art facility generated approximately 3,000 construction-related jobs with a peak workforce of around 1,100 workers. More than 1.5 million man-hours of labor went into the project, and the total investment in the facility will top $500 million over time.

This week’s grand opening provides us the opportunity to thank those who helped turn our vision for the Chicago data center into reality. The facility actually began operations on July 20, delivering online services to our customers. It is gratifying to reflect on this achievement as we plan our next advances to move data center sustainability and efficiency forward for Microsoft, our customers, and the industry.

Arne

Arne Josefsberg,

General Manager of Infrastructure Services

Global Foundation Services

Microsoft

Environmental advances and expanded international computing delivered

This is a big week for Microsoft’s online, live, and cloud services as we celebrate the grand opening of our new data center in Dublin, Ireland. The Dublin facility delivers two key advances for Microsoft’s Software plus Services initiatives. One is expanded support for all our customers in the Europe, Middle East, and Africa region, thanks to Microsoft’s first mega data center built outside of the U.S.  The other is dramatically improved environmental sustainability, resulting from innovative technology that takes advantage of the naturally cool climate in Ireland.

Regarding expanded international support, the new data center is already playing an important role in helping meet growing customer demand for Microsoft services in Europe and beyond. The facility, which began operations on July 1, 2009, currently covers 303,000 square feet, with 5.4 mega watts of critical power available to deliver services to consumers and business customers. Over time, the data center can expand to a total of 22.2 mega watts of critical power to support our growing cloud services.  Combined with our other new mega data center in Chicago, Illinois—which we’ll celebrate the grand opening of next week on September 30—Microsoft is taking significant steps forward in our cloud computing capabilities.

It is important to note that at both facilities we will ramp up capacity incrementally to meet increases in customer demand.  We are making thoughtful, measured investments in order to contain costs at the same time that we build out our infrastructure to deliver a secure cloud foundation, with robust performance and availability for services around the world.

Regarding the environment and Green IT factors, Microsoft is leveraging a combination of natural environmental factors to dramatically improve the environmental sustainability of the Dublin data center as compared to traditionally-built data centers. The average temperature range year round in Dublin is between 23 to 80 degrees F (-5 to 27 degrees C) and that, combined with the use of air-side economization, results in “free cooling” (chiller-free) operations 100% year round under normal operating conditions. This in turn significantly reduces water consumption and the use of chemicals required to treat cooling towers, which are common throughout the data center industry but not required in our Dublin facility.

Air-handling units on the roof of the data center (see photos above and below) draw outside air down into the facility to cool the server rooms, and then return hot air back out to the roof. Traditional data centers, on the other hand, cool server rooms with chillers, which consume a great deal of power and water. No chillers are used in the Dublin data center. The outside air that cools the facility is usually lower than the 95 degree F limit for our server rooms. If it ever exceeds that temperature, or in the extremely rare event of external air quality issues such as a nearby fire, Direct eXpansion (DX) cooling will be used. DX is a simpler means of mechanical cooling that is normally used for residential, automotive, or light commercial applications.

As a result of these measures the Dublin facility will use less than 1% of the water that traditional data center facilities typically use on an annual basis, and will improve Power Usage Effectiveness (PUE) by approximately 50%.

These improvements are part of our continued corporate commitment to environmental sustainability. Microsoft is a proud participant and endorser of the European Union (EU) Code of Conduct for Data Centres, a voluntary program that encourages organizations responsible for the operations of data centers to utilize technologies, systems, and processes that maximize the efficient use of electricity. We are one of the largest online service providers to sign the EU’s Code of Conduct for Data Centres. Our participation includes a commitment to continuing to develop and employ innovative systems and processes that deliver computing scale to meet our evolving Software plus Services business initiatives with the lowest possible consumption of power and natural resources. We also work actively with The Green Grid and Climate Savers Computing industry consortiums and the U.S. Environmental Protection Agency to advance sustainability and reduce the carbon footprint of data centers globally.

On September 16 we were honored to be recognized as a Best Practice in the European Commission's Sustainable Energy Europe Campaign for innovative achievements in design and operational strategies that are driving greater sustainability and efficiency at the Dublin facility.

While our best practices are competitive advantages for Microsoft, we hope they will also help others in the industry make the cloud a safer and more reliable place that companies can trust for their operations.  Very few companies can make the infrastructure investment that Microsoft has, so we think it is important to share our best practices with the industry. This is one of many reasons we decided to hold a grand opening of the facility today.

I’d like to close by noting how this week’s grand opening helps celebrate and build upon Microsoft’s long-term investment in operations in the Republic of Ireland. Microsoft Ireland is now nearing the 25-year anniversary mark, and I believe the building of the Dublin data center will long be remembered as a key milestone of our relationship with this community. The $500 million facility is one of the largest construction projects in Ireland over last 12 months and has generated approximately 1 million man-hours of work with a peak workforce of around 2,100 workers. The data center will also provide approximately 35-50 jobs in the Dublin area for years to come.

It is exciting to unveil this marvellous facility and I’d like to extend my thanks to all the people inside and outside Microsoft who helped make it happen.

Arne

Arne Josefsberg,

General Manager of Infrastructure Services

Global Foundation Services

I recently participated in a Podcast for InsideHPC.com with a discussion on “the differences on going green in general IT and going green in HPC” which John West put so eloquently  (go to Episode 2: IT, HPC, and where the twain shall meet at http://tinyurl.com/m7ku4m).  I found this to be an interesting discussion for several reasons.

First, as many of you know, I have been saying for over a decade now that efficient computing will be a differentiator. I believe this is true now more than ever before.  In this economy, capital resources are constrained to levels organizations have never seen before.  As I stated in the Podcast: that is where the opportunity lies.  I incorrectly quoted my favorite inventor Thomas Edison as saying “Innovation only occurs with constraints.”  What he really said was “Discontent is the first necessity of progress” and it was actually Mike Heffernan (High Tech Visionary) that stated “The absence of constraints is the death of creativity.”  So what I said in the Podcast captures the intent for both of these visionaries.  The constraints the economy has place on IT budgets has driven innovation through necessity. For enterprises and cloud services businesses such as ours, we have to drive costs down since margins are tighter than ever before. Similarly, HPC is facing less funding but its computation needs are exploding -- resulting in focus on efficiency and innovation to meet needs with smaller budgets.  It’s really quite exciting to see businesses being more proactive in this climate.

Second, I have spoken about the fact that at Microsoft, as with our competitors, we are driving towards hyper-efficiency and moving away from acquiring general purpose servers. Clearly our business focus over the past couple of years for our business has been to reduce cost by right sizing to our needs.  Anything that is not needed is stripped to improve efficiency and reduce cost.  I did not think of this before, but Steve Cumings made the statement that HPC is requiring the same. 

Finally, Pat Tiernen said something which I believe is very important.  “If it will improve your business anyway, why not do it.”  He is absolutely right. It’s astounding to me that organizations aren’t naturally trying to become more efficient just for the simple reason that it will drive costs down.  Why is it that utility companies need to be giving incentives for people to save money?  Look at PG&E, I simply applaud Mark Bramfitt for leading the charge in this space.  He gives you money to save money.  What a concept. J 

So in the end, ultimately, the economic constraints put on us as an industry will finally provide the motivations to drive towards efficiency.  It’s not about differentiation any more, it’s about survival.  There is no stronger incentive than that.

cb

Christian Belady, Principal Infrastructure Architect

Global Foundation Services

I am really excited that our team is now reaching another key milestone in data center innovations. July marks the launch of our two newest mega data centers in Chicago and Dublin. Our Dublin facility will go live on July 1, followed by our Chicago facility on July 20 to support our growing Online, Live, and Cloud services.

Together these Generation 3 facilities demonstrate Microsoft’s continuing commitment to improving data center efficiency with a focus on environmental sustainability.

The Dublin, Ireland, data center is our first mega data center built outside of the United States. This building covers 303,000 square feet, with 5.4 mega watts of critical power available now. Over time, the data center can expand to a total of 22.2 mega watts of critical power, growing with our business and customer demand. The facility makes extensive use of outside air economization to cool the facility year round, resulting in greater power efficiency with a resultant reduction in carbon footprint.

                                           Dublin Data Center

The Chicago, Illinois facility covers over 700,000 square feet—approximately the size of 16 football fields—with critical power of 60 megawatts. Phase 1 represents 30 mega watts of critical power and the rest is pre-positioned for future growth. Two-thirds of the Chicago data center is optimized for housing containerized servers. Containers conserve energy and will help us realize new advancements in power efficiency with a PUE yearly average calculated at 1.22.  These prepackaged units (with up to 1,800 to 2,500 servers each) can be wheeled into the facility and made operational within hours, so they represent important advances in the ability to quickly and efficiently provision capacity. The density inside the containers can exceed 10 times that of traditional data centers.

It is truly exciting to bring these two data centers online. We take great pride in the innovations they deliver to move the data center industry forward and to extend Microsoft’s online services to customers globally.  As the company’s Software-plus-Services strategy progresses, these data centers will play a key supporting role.

I’d like to extend my congratulations and thanks to everyone at Microsoft who was involved in creating these state-of-the-art facilities and to all the local and regional trades people and organizations that helped make them possible. For more information on our cloud infrastructure strategy and services please visit our web site.

Arne

Arne Josefsberg,

General Manager of Infrastructure Services

Global Foundation Services

Building an organization around exceptional leaders with the deepest industry expertise is core to how we evolve our Global Foundation Services organization. One such leader is Kevin Timmons, who joined Microsoft Global Foundation Services (GFS) today to head up our Data Center Services organization. Kevin brings a wealth of knowledge and passion in this space, most recently serving as vice president of Operations at Yahoo!, where he led the build-out of their data centers and infrastructure. Before that he was a director of Operations at GeoCities, and prior to that he served as a senior software engineer at Marconi Dynamics.

Kevin is known as a hands-on leader with a great grasp on the issues in his field and a keen interest in increasing energy efficiency. One of the key ways he has approached that challenge was by closely measuring efficiency at each data center and using PUE (Power Usage Effectiveness) as a key metric—a strategy that helped build more efficient data centers. Kevin also brings valuable experience and know-how in the field of data center site selection. Anyone familiar with our areas of focus in Microsoft data centers, especially around environmental sustainability, will recognize the great fit Kevin’s experiences bring to the team. In sitting down with him and exploring these areas in depth, I’ve become increasingly excited about the industry experience Kevin brings to our team.

In addition to bringing Kevin on board, we’ve recently restructured our Infrastructure Services team within GFS. In mid May we aligned the organization around five teams: Shared Infrastructure, Programmable Infrastructure, Platform Hardware and Standards, Global Network Services, and the Data Center Services team that Kevin now heads up. These changes will help us align our teams with Microsoft’s evolving cloud computing business and position our infrastructure for the upcoming year and beyond. We look forward to sharing more about these teams in upcoming postings.

The release last week of our white paper on Securing Microsoft’s Cloud Infrastructure generated a lot of discussion in the industry, which was our intent. We wrote the paper in part to communicate our practices to customers concerned about security in the cloud environment and to generate a healthy dialogue within the industry in order to share best practices for creating more secure cloud-based services.

Pete Boden, general manager of our Online Services Security team, posted a blog today providing more detail in response to questions we've gotten since we released the paper. Give it a read to learn more about Microsoft's history in online services and security, and how that history led to our Information Security Program that has been independently certified by British Standards Institute (BSI) Management Systems America as being compliant with ISO/IEC 27001:2005.

Companies considering moving their IT operations to the cloud are understandably concerned about security, privacy, reliability, and operational controls. To address these concerns and help share best practices with the rest of the industry, the Online Services Security and Compliance (OSSC) team within the Global Foundation Services group that supports Microsoft’s cloud infrastructure has published a white paper titled: Securing Microsoft’s Cloud Infrastructure

Our Online Services Security team is led by Charlie McNerney, GM, Business & Risk Management, who has posted a blog today describing how our coordinated and strategic application of people, processes, technologies, and experience with consumer and enterprise security has resulted in continuous improvements to the security practices and policies of the Microsoft cloud infrastructure.

And you can find more information on our strategic vision for Microsoft’s infrastructure at our Global Foundation Services web site.

Part # 2

(A couple of years ago, when our Data Center Services’ Research & Engineering team within Microsoft’s  Global Foundation Services (GFS) group kicked off the Generation 4.0 Data Center design project,  we began with the question of:  What are the primary business challenges facing data center deployments today? )  Here’s the rest of the story….

Question Everything

Often the application of technology involves as much innovation as the technology itself.  Rather than reinvent the wheel we looked at our industry’s journey thus far.  We started by questioning everything up to and including the roof and the very definition of a data center. With a lot of prior art in modularization, some of which has already been applied to the IT industry, we saw a good fit. The military has been deploying portable ground stations with IT servers and communications equipment for decades. And for some time now telecom companies have deployed pre-manufactured buildings which are then assembled on site as central offices.

As part of our design project we met to discuss the modular solution space with a group of folks from our Infrastructure Services team within GFS , including members of our hardware, data center operations, development, engineering, risk management, and security teams, as well as our internal product groups. (The original Gen 4.0 team from the two-day session is 100 percent intact and still working at Microsoft, by the way.) We knew we could modularize the server room, which we now call Server PACs. The challenge became how to modularize the entire facility. So we created other PACs: Generator PACS, Medium Voltage Switchgear PACs, UPS PACs, etc. Next, we developed the system electrical one-line diagrams and mechanical schematics for our four data center classes.

Then we had to take these single lines and schematics and break them into logical modules for the components to reside in. This may seem easy but represents a shift in thinking from a building where, for instance, we would have a UPS room and associated equipment and switchgear manufactured by multiple vendors and put it physically in sometimes separate modules. The challenge became how to shift from a traditional construction mindset to the new, modularized manufacturing mindset. Maintainability is a large part of reliability in a facility, and became a key differentiator between the four classes. Our A Class infrastructure, which is not concurrently maintainable and is on basically street power and unconditioned air, will require scheduled downtime for maintenance. The cost, efficiency, and time-to-market targets for A Class are very aggressive and a fraction of what the industry has come to see as normal today.  We realized that standardization and reuse of components from one class to the next was a key to improving cost and efficiency.  Our premise was that the same kit of parts (or modules) should be usable from class to class. These modules (in this new mindset) can be added to other modules to transition within the data center from one class to the next.

 Standardize to Differentiate

With the standardization of a kit of modular parts it is possible to supply different types of facilities—large-scale, mega-data centers and edge or mini-data centers—from the same supply chain.  A pre-manufactured set of solutions can thus reduce costs through economy of scale. Traditionally, because of network and site service costs it has been more cost effective to deploy 40 megawatts of capacity in a single location than to build 40 individual 1-megawatt facilities. In a pre-manufactured model that isn’t necessarily the case.  The use of a production-line approach, while at the same time simplifying interconnections through the right modularization of the components, can drive costs down for mini- as well as mega-data center facilities. Of course the fixed costs of site development must be considered, but we are finding that the production-line approach is significantly narrowing the difference in cost per megawatt for mega- and mini-data centers.

We realize that innovation will come from many sources, and so we are partnering with technology leaders in the vendor community, as well as our customers, to help drive and deliver the benefits of this new approach. We believe it is crucially important to develop this technology now due to the many constraints on our environment and economy globally. However, we do not have unlimited resources to drive this alone. Through industry partnership and collaboration we will be able to accelerate the adoption of modular data centers and deliver the benefits of technology, software, and services to more people.

Imagine the possibilities of bringing affordable computing to corners of the world that have no power or IT grid to speak of today. This could be done using modular power plants such as fuel cells and modular data centers in partnership with wireless technology where there is a lack of existing infrastructure (for example). Applications could become virtual in the local modular data center, or the cloud, and the thousands of services and applications it holds could be provided via low-cost devices. Great opportunities like being able to provide a $100 or a lot less laptop (or new access devices not yet invented) per child could then be achieved sooner.  A modular data center could quickly be deployed to support millions of virtual applications and at the same time access the power of the Internet and cloud services for a large population that does not have that opportunity today. Personally, I am very excited about these possibilities and believe I am fortunate to be working on this technology at this time.

We look forward to continued collaboration with our industry participants.

You can read part 1 of this 2 part series in my earlier blog on April 29, 2009

/dc

Daniel Costello, director of Data Center Services 

Global Foundation Services

Daniel Costello is the director for Data Center Services at Microsoft, responsible for data center research and engineering, standards and technologies, data center technology roadmap, Generation 4 data center engineering, data center automation and integration with IT hardware, operating systems and applications.  Daniel works closely with Microsoft Research on proof of concepts in support of the data center of the future and manages a team of facility engineers and service architects.  

Part 1: 

A couple of years ago, when our Data Center Services’ Research & Engineering team within Microsoft’s Global Foundation Services (GFS) group kicked off the Generation 4.0 Data Center design project, we began with the question of: What are the primary business challenges facing data center deployments today?  

Challenge #1: Time to Market

We kept coming back to a couple of leading issues. The first focused on time to market and meeting a variable demand profile. The issue is simple: it takes months to years to build data centers, but sometimes businesses need to move faster.

This issue isn’t entirely new, of course. When we designed our Chicago facility we made significant gains in this area by devoting more than half the facility to housing containers that served as modularized server rooms, or Pre-Assembled Components (PACs).  Server PACs dramatically reduce time to market because they are assembled at the same time as the site infrastructure and building for the data center. When the site preparation is complete all we have to do is roll the containers into the new facility, connect a few cables, and we’re up and running.

This advance was the heart of our Generation 3 data center. While we saw it as a great step forward, it almost immediately led us to ask ourselves whether we could take the gains even further by modularizing the entire facility. That led us to the crux of Generation 4, where we created further PACs: Generator PACS, Medium Voltage Switchgear PACs, UPS PACs, etc. By moving to PACs for all these key data center systems, we created a design where almost everything we need to add new capacity can be pre-assembled in parallel and then brought together in a matter of weeks. The fact that the components all come in their own modular containers eliminated the need for much of the on-site construction—which can be the most time-consuming, expensive, and environmentally unfriendly element of building a data center.

Perhaps most importantly, with Generation 4 we can quickly add capacity incrementally in response to demand. Gone are the days when we had to wait 12-18 months for a large data center to be built, only to use a small portion of its capacity while we waited for demand to catch up to capacity. In short, our Generation 4 design delivers a revolution in terms of time to market that the data center industry has never seen before.

Challenge #2: Cost

The next business challenge (after time to market) is cost. We looked at several areas impacting cost, capital efficiency, and return on invested capital (ROIC), which affects cash flow and is calculated using Net Present Value (NPV). Capital outlay itself is now widely measured by our industry in dollar value ($) per watt, versus square foot.

Operational costs that impact Cost of Goods Sold (COGS) are measured in $ per kilowatt per month and are impacted largely by depreciation, energy costs, and operations staffing. A couple of years ago we moved to a chargeback model for power versus real estate, and as Christian Belady pointed out in his blog, that incentive-based approach proved effective in turning the corner on power usage and costs.

To tackle other costs in the data center, the use of server PACs is proving equally effective. Using this approach we project our Chicago facility will deliver cost savings of approximately 30 percent and enable a more efficient cash flow because we will not build out the modularized server PACS until they are required. That’s just the beginning of the cost benefits as we move to Generation 4 and fully modularize the data center. The traditional raised floor is not where the majority of the money or lead time is spent. Instead, it is in the electrical and mechanical systems. Moving to PACs in these areas will reduce costs and free large amounts of capital previously required to construct huge facilities that we might not fully utilize for several years.

Challenge #3: Efficiency

The discussion on the impact of energy costs led us to the next business challenge: efficiency. Efficiency has been called the “fifth fuel” and is regarded as a source of energy in itself. Today the industry is beginning to use Power Usage Effectiveness (PUE) as the recognized metric for data center efficiency.  If we take a look at the larger picture beyond just operational power consumption, the Total Cost of Energy (TCOE) also needs to be considered to address the full lifecycle of the data center–from component manufacturer to transportation to construction and on-site assembly, and even end of life. 

When we considered the goal of making our data centers more energy efficient, our team’s debate focused on the inefficiency of using redundant hardware systems to provide backup and failover capabilities. Previously many data centers have been built with the same level of reliability to the highest common denominator.  Our Generation 4 team no longer believes that hardware redundancy is the best way to ensure service reliability. Therefore, we began with a fresh approach to this industry problem by looking at the latest technology capabilities and then establishing multiple classes of service. Each class was assigned a differentiated chargeback model that would encourage our properties to move to the lowest cost and most efficient service level that meets their business needs. To support this we are developing software that moves reliability across all applications higher up the Open Systems Interconnect (OSI) model all the way to the operating system and application layer. The four classes of data center service we have created are still being researched and we may consolidate them over time. Regardless, our goal around software-based reliability matched to hardware levels of reliability is driving the right discussions.

Challenge #4: Flexibility and Density

The last major challenge we identified was to enable data centers to be flexible and host multiple form factors and levels of density. With traditionally built facilities, the density of the data center is normally set during design. That density then remains unchanged for 15 years or longer during the facility’s lifecycle. Measured in watts per square foot, density can lead to capacity planning challenges. Build with too low a density and the data center will be less energy efficient and take up more real estate than is necessary, which can have a big impact when land is expensive. Build too high a density and you can strand power and cooling, which is where the majority of the costs are.

The Goals our Engineering Team Set

·         Reduce time-to-market and deliver the facility at the same time as the computing infrastructure

·         Reduce capital cost per megawatt and reduce COGS per kilowatt per month by class

·         Increase ROIC and minimize the up-front investment for data centers

·         Differentiate reliability and redundancy by data center class and design the system to be flexible to accommodate any class of service in the same facility

·         Drive data center efficiency up while lowering PUE, water usage, and overall TCOE

·         Develop a solution to accept multiple levels of density and form factors, such as racks, skids, or containers

      Next week, I will talk about the process we used to develop these ideas.

      /dc

     Daniel Costello, director of Data Center Services

     Global Foundation Services

Daniel Costello is the director for Data Center Services at Microsoft, responsible for data center research and engineering, standards and technologies, data center technology roadmap, Generation 4 data center engineering, data center automation and integration with IT hardware, operating systems and applications.  Daniel also works closely with Microsoft Research on proof of concepts in support of the data center of the future and manages a team of facility engineers and service architects.  

Interested in learning more about Green IT? Check out Microsoft’s Webcast Series on TechNet!

How to Reduce Energy Consumption, Waste, and Costs while Increasing Efficiency and ROI

What does environmental sustainability mean to data centers, industry operators, and IT businesses? A lot of managers in these areas may barely notice the Earth Day global event on April 22 as they struggle to support their businesses in the face of budget cuts and uncertainty about the future. But the fact is, being “lean and green” is good for both the business and the environment, and organizations that focus their attentions accordingly will see clear benefits. Reducing energy use and waste improves a company’s bottom line and boosting the use of recycled materials is a proven way to demonstrate good corporate citizenship to your customers, employees, and the communities you do business in.

by Arne Josefsberg

As you may have already read, Mike Manos will be leaving Microsoft in early May to return to Chicago and take a leadership position with Digital Realty Trust. Those of you who read this blog regularly, or who followed his Loose Bolts blog, know that Mike’s been an integral leader in our data center organization.  I feel privileged to have had Mike as part of my Infrastructure Services leadership team -- he’s done an outstanding job delivering on our data center strategy, encouraging cross-industry information sharing, and was instrumental in helping us build a world-class data center team.

I want to publicly thank Mike for his excellent work and wish him the best in his new position.  All of us here are going to miss his enthusiasm and passion.  And, I'm fortunate to have the fantastic data center team he helped build here to continue driving data center innovation and delivering on our Generation 4 data centers and beyond.  There is so much more we want to do to take cloud infrastructure, including data centers, to the next level.

I’m sure we’ll continue to see great things from Mike in the data center industry.  And he's got one more post in mind for this blog, you'll see that sometime next week.

 By Christian Belady

What’s the upside to a downturn? As the economy shrinks and budget and program cutting expands throughout our industry, how can data center facility and IT infrastructure teams identify opportunities that create value for their companies?  In other words, how do we emerge stronger from a recession?  For most business services professionals (people in any organization for that matter), acknowledging inefficiencies is the first step towards taking action, and with action comes insight, evidence, and real options. Like any well-managed business, we routinely check our assumptions and planning needs against our assessment of the economic environment.  As part of this process, we look at many scenarios and options to improve efficiencies, reduce costs, and increase the return on our investments.

We have spoken at many conferences in the past couple of years and shared our experiences and ideas on how this industry could collectively improve to become more efficient, in part by reducing our carbon footprint.  The uncertainty presented in our industry today – regarding the environment, the economy, and how people react to change – reconfirms the importance of developing a data center strategy that can react to unpredictable and dynamic business needs.  In this blog we would like to share some of our experiences over the past couple years and the lessons we’ve learned about how to measure and increase efficiency.

We’d also like to turn up the dial on our invitation to the rest of the industry to work together with us in these areas.  An important example involves our belief that data centers could operate at much higher temperatures, which would end much of the need for expensive, energy inefficient cooling equipment. To that end we urge all companies to encourage ASHRAE to further open its recommended operating temperature ranges beyond the adjustments they recently made. Additionally, if we all work towards recommending improvements to hardware specifications, server manufacturers could increase the efficiency of their products. With so much at stake--both in helping our companies through difficult financial times and in protecting our global environment--it’s time to work together. We should be striving to run more efficiently as an industry, not just as separate corporations.

Sharing Microsoft’s Energy Efficiency Best Practices for Data Center Operations

So what are some of the elements in our efficiency program that have reduced our needs? Here are some examples:

1) To begin with, we applied our own best practices on energy efficiency that we published about a year ago.  These were all things that we felt were pretty important for foundational improvement in our data center operations efficiency.  They included:

1. Engineer the data center for cost and energy efficiency

2. Optimize the design to assess multiple factors

3. Optimize provisioning for maximum efficiency and productivity

4. Monitor and control data center performance in real time

5. Make data center operational excellence part of organizational culture

6. Measure power usage effectiveness (PUE)

7. Use temperature control and airflow distribution

8. Eliminate the mixing of hot and cold air

9. Use effective air-side or water-side economizers

10. Share and learn from industry partners

2) We also invested in a team led by computer industry veteran Dr. Dileep Bhandarkar (a distinguished engineer in our organization), to optimize our server performance, cost, and power.  These technologists are turning over every stone to squeeze efficiency out of our hardware.  The focus has been on working with hardware suppliers to increase the efficiency of power supplies and right-size the system, including the processor, memory, and storage.  More importantly, the team has focused on selecting hardware based not only on total cost of ownership but also on the best performance per watt for the particular application.  As a result we have seen a 13% drop in average server power in operations, driven by an even steeper drop in power for the servers we added in the past year.  During that same period, interestingly, ASHRAE power curves actually showed an increase in server power by 4%. 

3) But perhaps the overarching thing that drove the above elements was when we changed our internal chargeback model about 1.5 years ago from charging for space to charging for power allocated/consumed.  We presented on this for the first time in July 2008 to the EPA.  This proved to help reduce energy and also reduce carbon emissions. We later blogged about this and how efficiency is not only a technology problem but perhaps even more a behavior problem. If you are interested in more details on how we do our chargeback models, visit our Power of Software blog on this topic. 

4) Also, it’s in our DNA to use software—especially Microsoft software—to achieve our goals. Virtualization technology such as Hyper-V and our new Windows Azure platform in Windows Server is being utilized to reduce energy use, and using Microsoft System Center management products to improve efficiency throughout our operations. The purpose of this blog isn’t to promote these products, and we realize many data centers are built on other platforms. But the point is that smart use of software can give you a lot more bang for your hardware buck, and at the same time help you make significant gains in reducing your carbon footprint.

So our key takeaways from this experience are:

1) All of the best practices and technology we are pursuing help improve efficiency and reduce carbon footprint, but only if adoption occurs.  As we have seen within the industry, adoption has been slow.  However, with the right incentives, adoption can and will happen.

2) Our chargeback models provided incentives that improved efficiency far beyond our expectations and drove our total mega watt needs for our operations much lower than expected. 

3) New software solutions are enabling data center teams to make dramatic efficiency improvements, primarily in the areas of virtualization, automation, and streamlined management functions. Moving to new software may be a tough sell in this economic climate, but the right products will make the purchases well worth the investment.

We feel it’s important for us to openly share information and best practices around energy efficiency because we believe the data center industry as a whole needs to work together in order to make the dramatic gains needed to make a difference for our companies and the planet. We invite other data center teams to explore our best practices and approaches, enhance them with your own, and apply them in your situation as you see fit.

We certainly don’t pretend to have all the answers, and we’re very interested in considering approaches that have worked for other companies, or ideas that may bear fruit in the future. The data center industry is an exciting place to work right now because there is so much focus on what we do and so much opportunity for our work to make the world a better place—whether that’s by reducing our carbon footprint and the amount of water we use, or by enabling further advances in online services that take our societies to new levels of collaboration and opportunities for all.

Please join us in sharing information about what your company or team is doing to increase efficiency, or comment on the opinions we’ve expressed here, so that we can engage in a dialogue that benefits us all.

Thank you, in advance, for helping to advance the industry as a whole.

Also, be sure to visit our team’s blog in a couple of weeks when Daniel Costello, director of Research & Engineering, will be sharing more information on how we are advancing our efficiency best practices within our Generation 4 Modular Data Center plans.

/cb

Christian Belady, power and cooling architect, Global Foundation Services, Microsoft