ms datacenters : chargeback

The Polarization of the Data Center Industry (at least for now): Part 2 of 2

msdcblog — Tue, 08 Dec 2009 04:21:00 GMT

The Inflection Point for Efficiency in the Data Center

By Christian Belady,
Principal Infrastructure Architect
Global Foundation Services, Microsoft Corporation

The Gartner graph (included in Part 1 of this blog) also made me think about the fact-- that had the same survey been asked 5 years ago-- it would have shown100 percent are either looking at internal metrics and/or not considering anything when it comes to energy or efficiency. In my opinion, it wasn’t until 2006 that the industry really did go through a paradigm shift. While there were a few of us who had been pushing efficient computing approaches for over a decade), we had limited success in moving the industry until 2006. What happened in 2006? I think the notion of establishing an industry efficiency metric and data center metrics were born. I thought it would be interesting to recap those milestones based on my perspective:

January 31 2006: Conference on Enterprise Servers and Data Centers: Opportunities for Energy Savings

This conference really brought Efficiency on the main stage of our industry. Andrew Fanara’s (EPA) presence was the key to waking up the industry and his goal was to drive metrics for delivering efficiency into computing. This (to me) was a pivotal day since it marked the first time we collectively got together as an industry to address efficiency. It was no longer a voice of a few, thanks to Andrew.

March 27, 2006: Energy Efficiency Server Benchmark Technical Workshop

This event was a follow-up meeting to the EPA conference in January. I led a work group on the Applicability of Benchmarks to the real world” with members from HP, Intel, AMD, LBNL, Cisco, Dell, Sun, Rumsey Engineers and others. The group concluded that a benchmark should be developed with power on the y-axis and workload on the x-axis. This recommendation is what drove the publication of the paper later that year that Jon Koomey spearheaded (with many of us in the industry co-authoring) titled “Server Energy Measurement Protocol”. This paper was the foundation of what SPECpower is today.

April 23-26, 2006: High-Density Computing: Trends, Challenges, Benefits, Costs, and Solutions

This symposium was the Uptime Institute’s first and it focused on Density trends. However, it was this conference where I first presented an Efficiency Metric called PUE which seemed to capture the attention of many of the attendees. As a result, I published a paper on PUE with my good friend Chris Malone later in the year at the Digital Power Forum. At this same conference, AMD’s Larry Vertal and Bruce Shaw sat down with Paul Perez (my former VP) and I to discuss the idea of starting a consortium called the Green Grid. Ten months later the Green Grid was officially announced with one of its first whitepapers evangelizing metrics and in particular PUE.

These three events to me really started it all. If you look at the Gartner graph, you can argue that all of the metrics were seeded in these three events and are really making an impact today.

So our industry woke up in 2006 and while the Gartner graph does show we have work ahead of us, I do think we can say that in less than four years the industry has made great strides (and perhaps I shouldn’t complain so much!).

/cb

For more information on Microsoft's datacenter best practices visit our external web site at www.globalfoundationservices.com and check out Rob Bernard's feature “Using the Power of IT to Drive Environmental Sustainability” that highlights the effort Microsoft is making in environmental sustainability, as well as how that directly relates to what world leaders are currently discussing in Copenhagen for the United Nations Climate Change Conference 2009.

Designing Generation 4.0 Data Centers: The Engineers’ Approach to Solving Business Challenges…continued

msdcblog — Mon, 04 May 2009 10:01:00 GMT

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.

Microsoft’s Top 10 Business Practices for Environmentally Sustainable Data Centers (celebrating Earth Day)

msdcblog — Tue, 21 Apr 2009 10:00:00 GMT

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.

That said, with so much on the plates of data center and IT professionals these days it isn’t always easy to know where to begin in moving to greener and more efficient operations. With that in mind—along with Microsoft’s commitment to share best practices with the rest of the data center industry—we asked some of the senior members our Global Foundation Services’ Infrastructure Services team to send us their top ten best business practices for environmentally sustainable data centers and IT.

Their favorite practices are reflected in our new “Microsoft’s Top 10 Business Practices for Environmentally Sustainable Data Centers” paper.

You can explore other data center resources on our GFS web site here.

Microsoft announced in March 2009 that it is taking a proactive corporate approach to reduce our carbon emissions per unit of revenue by at least 30 percent below 2007 levels by 2012. The data centers managed by GFS are a significant component of Microsoft’s carbon footprint, and our organization plays a vital role in Microsoft’s efforts to meet this corporate goal.

As you’ll read in the list of best practices we’ve compiled, companies can make major gains in energy efficiency by increasing server utilization and moving to virtualization, plus you can employ a wide range of smaller initiatives that collectively add up to significant gains. Microsoft has been using these practices for several years now and found that in addition to helping us protect the environment, they make best use of our resources and help us stay tightly aligned with our core strategies and goals. We hope they work for you as well.

Below is an overview of the best practices list.

1. Provide incentives that support your primary goals.

2. Focus on effective resource utilization.

3. Use virtualization to improve server utilization and increase operational efficiency.

4. Drive quality up through compliance.

5. Embrace change management.

6. Invest in understanding your application workload and behavior.

7. Right-size your server platforms to meet your application requirements.

8. Evaluate and test servers for performance, power, and total cost of ownership.

9. Converge on as small a number of stock-keeping units (SKUs) as you can.

10. Take advantage of competitive bids from multiple vendors to foster innovation and reduce costs.

Beyond the business practices listed above, Microsoft’s data center team is taking significant steps in four areas important to environmental sustainability:

· Using recycled resources whenever practical: The Microsoft data center in San Antonio, Texas, for example, uses approximately eight million gallons of recycled water a month from the city’s waste water system during peak cooling months.

· Using renewable resources whenever available: In the process we have developed for deciding where to build our data center facilities, renewable energy sources play a key role. For instance, the Microsoft data center in Quincy, Washington, uses 100 percent renewable hydropower from the Columbia Basin River. The San Antonio facility obtains part of its electricity from wind power. And the company’s Dublin, Ireland, data center will use outside air for cooling, thus reducing the need for energy-intensive coolers.

· Reducing waste in operations: One example of Microsoft’s focus on reducing waste is the company’s transition to using standard shipping containers to house thousands of servers apiece. Ordering servers by the truckload eliminates the need for large amounts of packaging and other materials previously required when servers were delivered individually or in racks.

· Actively participating in industry environmental groups: Microsoft plays leadership roles in Climate Savers Computing Initiative and The Green Grid—industry organizations focused on improving computer systems and data center energy efficiency and establishing a standard methodology for measuring Power Usage Effectiveness (PUE) accurately and consistently. We also feel it’s important for us to openly share information and best practices around data center energy efficiency, because we believe the data center industry needs to work together to make dramatic gains toward environmental sustainability.

The teams that contributed to this white paper are represented by our power and cooling architect Christian Belady, our distinguished engineer Dileep Bhandarkar, our Data Center Services director Daniel Costello (“the father” of our Generation 4 modular data center vision and the leader of the team of engineers that created it), our Data Center Software Services general manager Jawaid Ekram, and myself.

Their backgrounds include expertise in data center electrical and mechanical engineering, power and cooling architecture and design, research and development, and business operations and administration. It has been my distinct pleasure to work with and lead these subject matter experts and to share their thoughts with the industry via our blogs and participation in industry events.

Arne

Arne Josefsberg,

General Manager of Infrastructure Services

Global Foundation Services

What’s the Upside to a Downturn? Recessions Heighten Focus on Efficiency!

msdcblog — Wed, 04 Feb 2009 21:01:00 GMT

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