Green Data Center Blog

Microsoft TechNet Article - Filtering the Greenwashing

TechNet has an article I just wrote in print and online, Filtering The Greenwashing.

Sustainable Computing Filtering the Greenwashing

Dave Ohara

Contents

The Need for Numbers
Measuring Energy Usage
Power Factor
Measuring in Production
The Microsoft EnterpriseEngineering Center
Wrapping Up

There are an overwhelming number of products and solutions being marketed as green, as saving energy, as being more efficient. All this marketing hype creates confusion in the market as to what is really eco-friendly. Even after evaluating the specifications on various products, it is difficult, if not impossible, for an IT pro to determine what equipment should be used when environmental impact is a key concern. When you see all the demonstrations, large energy savings are always highlighted, and this leads you to think that the return on investment (ROI) makes the upgrade easier to justify. After all, the energy savings should reduce the total cost of ownership (TCO).

The move by companies of all types to label seemingly everything as environmental and exploit the current interest in green solutions has led to the concept of "greenwashing," which refers to the over-promising of environmental benefits. So what is the truth of energy savings? This isn't as clear cut as, say, installing new energy-efficient lightbulbs in your home.

As interest in sustainable IT efforts increases and the market for environmentally friendly IT equipment expands, many people and organizations jump to the end result of deploying energy-efficient laptops, desktops, and servers, and using virtualization to reduce energy consumption. Yet few organizations run energy audits to determine the true benefits of what they have purchased.

While the ideal scenario is to actively measure in your production environment, that can also be expensive. If you aren't ready to start measuring in production, you can still move forward by performing your energy audit earlier in the process, doing so in your performance and evaluation labs. (Most companies have some lab or group responsible for testing and evaluating equipment before making a purchase.) There you can add energy performance as one of your test criteria and then take those results into account when making purchasing decisions, rather than relying on the numbers provided by manufacturers. So as you test, create your own device power-consumption database. Then you can ignore the greenwashing and see for yourself what works.

Of course, I should point out that if you want highly accurate numbers for operation under your true load, you'll need to monitor in your production environment. The quicker you begin monitoring your production environment, the better for your organization and your bottom line. This process will be critical to your long-term success.

Thanks to the Microsoft folks in the Enterprise Engineering Center, I was able to leverage their experiences in Filtering the Greenwashting.

1. 1.Turning off a device doesn't necessarily reduce energy consumption as much as you might expect (see Figure 4). In one case involving server hardware, the EEC discovered a device that actually consumed 100 watts when turned off but still plugged in. This surprised many, and the EEC went over the setup many times. They eventually used an infrared thermometer to measure inlet and outlet temperature and verified that the device did, in fact, consume 100 watts while off.
2. Software can have a significant impact on power consumption. On identical networking switches, with identical hardware and BIOS configurations, running different networking software displayed a 21 percent difference in power consumption. High-end solutions with more processes and features enabled, like security and monitoring tools, often consume more than their simpler low-end counterparts.
3. In virtualization scenarios, the EEC has measured power consumption versus I/O utilization and CPU utilization to determine when a given piece of hardware maximizes its performance per watt. The EEC found that a narrow focus on CPU utilization could lead to too many virtual machines loaded on a physical machine, actually decreasing the overall performance per watt.
4. Higher-density devices, as you might expect, have more power and cooling issues. When deploying higher- density systems, your power and cooling facilities staff should be consulted as early as possible. These devices may be good candidates for their own power-monitoring devices in production if you know the environment will be power constrained.
5. Dual power supplies can consume considerably more power than a single power supply.
6. Seemingly identical pieces of hardware with identical configurations can have significantly different power consumption. Observed differences were significant enough to make the EEC staff double-check hardware to ensure they were really configured the same.
7. The watt ratings on the product plate are not actual consumption numbers, but rated capacity for power supplies.
8. Maintaining a database of energy consumption tests and results per device and subcomponent is essential for retaining knowledge and comparing data.
9. Different configurations of equivalent amounts of RAM consume different amounts of energy. Fewer DIMMs typically consume less energy—for example, 4 x 2GB DIMMs versus 8 x 1GB DIMMs. But there have been some cases where fewer DIMMs consumed more energy.

And, one of the last minute I was able to get in is the EEC's effort's using real time temperature sensors.

Keeping Cool in the Datacenter

Datacenter cooling offers a huge potential for reducing energy consumption. It is astounding how much heat can be generated in a datacenter and how much energy is used to keep hardware cooled. But if you want to manage your cooling successfully, fix problems, and develop more efficient cooling solutions, you'll need a temperature-monitoring solution. Consider the solution the Microsoft datacenters use.

Microsoft Research built a temperature sensor network for the datacenters that allows for improved temperature control and also enables evaluation of various cooling improvements. For instance, one Microsoft datacenter was evaluating end-of-aisle air curtains to improve hot and cold air separation. After the curtains were installed, some servers started to send overheat alarms. Naturally, the operation engineers increased the air flow from the cooling system to provide more cool air. To their surprise, however, more servers sent overheat alarms. And all these servers were at the bottom of the rack—the bottom, of course, is usually the coolest area from a raised-floor cooling system.

Using the sensor network, the engineers confirmed that the racks were cooler up higher, with the bottom of the rack the hottest. And they soon figured out that hot air was being drawn from the hot aisle between the bottom of the rack and the flooring­—a result of Bernoulli's principle. They easily fixed the overheating by sealing the bottom of the rack and reducing the air flow speed.

This is just the sort of data the Microsoft Enterprise Engineering Center gathers and analyzes when doing performance testing. So the EEC recently notified Microsoft Research that they were ready for a deployment test. Within a day the system was deployed to 10 racks, and the installation took just one hour to complete. The EEC now is able to study and better understand cooling issues and their relationship to hardware performance.

Of course, simply monitoring isn't a solution in itself. The real gain is in your ability to find problem areas that you can fix, make changes, and evaluate various solutions to see if they have the result you are expecting. After all, you don't want to be caught off guard when your new cooling solution unexpectedly causes your racks to overheat.

Decisions for a Green Data Center, Get Out of Your Own Way

WSJ has a science article which helps to explain why companies are so slow in greening their data centers.

Get Out of Your Own Way

Studies Show the Value of Not Overthinking a Decision
June 27, 2008; Page A9

Fishing in the stream of consciousness, researchers now can detect our intentions and predict our choices before we are aware of them ourselves. The brain, they have found, appears to make up its mind 10 seconds before we become conscious of a decision -- an eternity at the speed of thought.

Their findings challenge conventional notions of choice.

Corbis

"We think our decisions are conscious," said neuroscientist John-Dylan Haynes at the Bernstein Center for Computational Neuroscience in Berlin, who is pioneering this research. "But these data show that consciousness is just the tip of the iceberg. This doesn't rule out free will, but it does make it implausible."

Results of their experiments are interesting.

Such experiments suggest that our best reasons for some choices we make are understood only by our cells. The findings lend credence to researchers who argue that many important decisions may be best made by going with our gut -- not by thinking about them too much.

Dutch researchers led by psychologist Ap Dijksterhuis at the University of Amsterdam recently found that people struggling to make relatively complicated consumer choices -- which car to buy, apartment to rent or vacation to take -- appeared to make sounder decisions when they were distracted and unable to focus consciously on the problem.

Moreover, the more factors to be considered in a decision, the more likely the unconscious brain handled it all better, they reported in the peer-reviewed journal Science in 2006. "The idea that conscious deliberation before making a decision is always good is simply one of those illusions consciousness creates for us," Dr. Dijksterhuis said.

As you get teams working together together, are you willing to take risks? Try something no one else has tried to save energy. The answer is a resounding NO from most companies. "This is our data center!" Yet, as this research shows, we are making mistakes in judgement all the time.  And in a corporate environment huge effort is spent to prove we did not make a mistake and the data is there to prove the right decision was made.

When is the last time you heard of a failed virtualization project?  There is tons of data to prove it was the right thing to do. But, you know someone is failing in their execution, but you don't hear the horror stories.  These stories will come with time, because there are way too many consultants making lots of money virtualizing servers.

This is why an energy monitoring system and using metrics like PUE are critical to evaluate objectively in big picture did the green project work.

Is your Green IT team set up to be efficient taking small risks to be more efficient or is it overthinking?

Centralized vs. Decentralized Green Initiatives

Centralized vs. Decentralized is a debate that has the pendulum swing from side to side. With Green's increased focus, the pendulum swings towards centralized and top down initiatives.  In Uptime Institute this was advocated as "Energy Czar" position.

Here is an example of something which may have seemed obvious on the surface, but ran into problems. University of Washington in Seattle has their #2 administrator, Provost Phyllis Wise, driving the creation of the College of Environment at UW.

To many people, the idea that the University of Washington would create a new College of the Environment seems a no-brainer: Some of the biggest issues facing humanity would get greater academic scrutiny in a city where people seem to care deeply about nature.

But within the UW, details of the plan are sparking intense debate. Many faculty who are in thriving programs have shown little interest in joining a new college. The vision publicly unveiled by Provost Phyllis Wise just three weeks ago — to create the world's largest environment college — appears to be running into serious problems.

Thanks to the college's democratic process, something most corporations do not have, the departments/colleges which would be centralized under the new school have rejected the idea.

Vote against college

In an advisory poll, the School of Aquatic and Fishery Sciences voted by an overwhelming 27-1 against joining the college. In another of the units — the Department of Earth and Space Sciences — the results were even more definitive: 29-0 against.

"Our mandate is to study things from the center of the Earth to the rim of the solar system," said Robert Winglee, who chairs Earth and Space Sciences. "The environment is that thin layer in which we live."

Winglee said faculty were concerned that elements of their study wouldn't fit in with the mandate of a new college. He informed Wise of the vote a month before she released her plan.

Was Winglee surprised, then, to see his department listed on the plan? "Yes," he replied simply, adding that he doesn't want to comment further for fear of becoming embroiled in academic politics.

One of the biggest problems with Green Initiatives and the people behind them is they get so passionate about their cause, they can't see the impact on others or understand why there would be opposition.  Sounds Ironic that a Green Initiative is not aware of the impact to others.

What I Learned from Donald Trump, the Bottom Line

One of the projects I did in my prior life was to drive a video project at Trump National Golf Club in Westchester, NY. The project was in many ways a mini-version of you're hired/fired. The Golf Course property was at that time run by Carolyn Kepcher who had appearances on The Apprentice. The details are too long for this post, so let's move to the bottom line. What I learned from Donald Trump.

We did not plan on having Donald Trump in the video, but through luck he was on site for the video shoot and agreed to be in the video. I got my cameo shot in the video and you can see me in this video capture.  (I am on the left.)

Donald above was asking "How are things working?" The partner responds by discussing how things are working. They have had problems with the Exchanged Server and connecting with HQ's email system. After 30 painful seconds of explaining Exchange and connection issues, Donald asks, "So, how are things now?" The partner responds "everything is OK now."

Then Donald looks at me, and asks, "You work for Microsoft right?" I respond yes. Donald continues, "What do you do?" My response, "I am here to make sure everything works." Donald's response. "Good."

We shoot a bit more. Get Donald with his testimonial.

We finish with a closing shot.

And we are ready to call it a day.  The video producer, partner and I are sitting by the golf cart path, and next thing we know Donald is coming over to talk to us.  Oh no!  What did we do now? Donald starts, "I have one other question. Part of doing business with Trump organization, people assume we have a lot of money to spend. I want to know did my people get a good deal." I responded, "Yes, your people got a very good deal." Donald, satisfied "Good, that's what I want to hear."

Bottom line: out of all the complexity of Green projects, all the various issues, there are only 2 things an executive wants to hear.

1. Is it working?
2. Did we get a good deal?

Anything else is not important.

Storage User Group Presentation: Don't Believe Green IT Hype

ByteandSwitch reports on a user group presentation.

ORLANDO, Fla. -- IT managers need to claw through the hype surrounding Green IT if they want to get their power costs under control, according to users here today.

”Talking green is easy, but being green is difficult,” warned Dave Vellante, senior storage analyst at the Wikibon research and user group, during a presentation this morning. “Smart companies can cut through the hype.”

Even technologies such as de-dupe, thin provisioning, and virtual storage, which are increasingly touted as a way to slash power and storage space costs, are no silver bullet, according to Vellante. “They are all tactics to improve utilization, but they do not solve the underlying problem. I would say that about 3 percent of the people that we speak to have visibility into what energy costs are in their data centers. Until that changes, it will be difficult to change the problem.”

A slew of vendors, including IBM, Xyratex, and 3PAR, are pushing technologies that aim to reduce data center power consumption, but Vellante urged users to get back to data center basics.

Focusing all your attention on servers, storage, and other IT equipment is not the way to go, according to the analyst. “If you just start there, you are missing a big opportunity,” he said, urging users to instead focus their initial efforts around legacy kit, cooling, air movement, and even lighting.

This is a good article for common sense approach to Greening the Data Center.

Focusing all your attention on servers, storage, and other IT equipment is not the way to go, according to the analyst. “If you just start there, you are missing a big opportunity,” he said, urging users to instead focus their initial efforts around legacy kit, cooling, air movement, and even lighting.

”Get rid of old stuff, turn things off [and] do simple power management. Clear out the data centers, use hot and cold aisles, use outside air [and] use water.”

These sentiments were echoed by Vellante’s co-presenter William Souder, the chief information security office at Berry College in Mount Berry, Ga. “It’s really simple, you walk the data center, you look behind your racks, you look for cable management [and] you look for your hot spots. Understand that it’s the simple things that get you there.”

Even the term "green computing" is misleading, according to Souder: “I don’t really call it green. You have to be a good steward about your spending anyway, and look to save money.”

This is not the first time that users have been urged to use common sense before spending big bucks on the latest, greatest, piece of "green technology," although it seems that relatively few IT managers even have an environmental policy in place for their data center.

Lesson from US Biofuel Subsidies, similar problems in IT Chargeback models

WSJ has a post about how US Biofuel Subsidies are being exploited in a practice to game the system.

The U.S. taxpayer forks over a $1 subsidy for every gallon of biodiesel that is blended in the U.S. for export later. The idea was to give a nudge to the U.S. biofuel industry. But it is boomeranging, as the Guardian reports today in the latest installment on biodiesel “splash-and-dash.” (Other stories on this here, here, and here.)

Increasingly, traders ship biodiesel from Asia or Europe to U.S. ports, where it is blended with a “splash” of regular diesel, the paper reports. That qualifies the shipment for U.S. export subsidies. Then it is shipped back to Europe where it is also subsidized. European biofuels organizations talk about between $30 million and $300 million in U.S. subsidies being exported that way to Europe.

The result? Biofuel’s already-tarnished environmental reputation comes under more fire, because round trips across the Atlantic add unnecessary transport emissions to the mix. And Europe’s own biodiesel industry has been shutting plants, despite its own efforts to ramp up production to meet political mandates. Imports are undercutting local producers on price.

When reading this it reminds me of how IT chargeback systems can be gamed and are actually the cause of inefficiencies like the above example. When the business units are not charged for their power use, then they have no incentive to purchase energy efficiency features like energy efficient power supplies.

The hardest in going green in the data center are the pockets of self-optimizing behavior who only have their own self-interests in mind.

11th Best Practice hidden in Microsoft's 10 Best Practices

I've been staring at the Microsoft's Best Practices for Energy Efficiency in Microsoft Data Center Operations that they published as part of Steve Ballmer's announcement at Cebit, thinking about how to use the document. I checked with some Microsoft friends and there have been 640 downloads of this document from the press release site in one week. The number will go up significantly when the content gets hosted in a higher traffic Microsoft area like TechNet. The early feedback has been good and customers are asking for more.

For those of you haven't downloaded the document here are the 10 best practices:

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.

The one thing I really liked about the list is the order. The order in which you run a Green Data Center project is the most important best practice and can be listed as the 11th Best Practice.  You can fine tune the order for your organization, but you get the idea of looking at the big picture first, putting in your green infrastructure, implement, and learn more.

• Big Picture
  • Engineer the data center for cost and energy efficiency.
  • Optimize the design to assess multiple factors.
  • Optimize provisioning for maximum efficiency and productivity.
• Green Infrastructure
  • Monitor and control data center performance in real time.
  • Make data center operational excellence part of organizational culture.
  • Measure power usage effectiveness (PUE).
• Implement
  • Use temperature control and airflow distribution.
  • Eliminate the mixing of hot and cold air.
  • Use effective air-side or water-side economizers.
• Learn More
  • Share and learn from industry partners.

This is the first step anyone should take in Greening their data center.  Answer the question:

In what order will you implement Best Practices?

This will have the largest effect on the success or failure of the project.

Moore's Law applied to the Data Center, podcast of Microsoft's Mike Manos

Techhermit posted a blog entry, pointing to an Uptime Institute podcast with Microsoft's Mike Manos, chief of data centers discussing the idea of Moore's Law Applied to the Data Center.

Can Moore's Law be applied to the data center?  The late Jim Gray wrote on Moore's Law topic, and made the following observations.

Beginning as a simple observation of trends in semiconductor device complexity, Moore's Law has become many things. It is an explanatory variable for the qualitative uniqueness of the semiconductor as a base technology. It is now recognized as a benchmark of progress for the entire semiconductor industry. And increasingly it is becoming a metaphor for technological progress on a broader scale. As to explaining the real "causes" of Moore's Law, this examination has just begun. For example, the hypothesis that semiconductor device users' expectations feed back and self-reinforce the attainment of Moore's Law (see Figure 1) is still far from being validated or disproved. There does appear to be support for this notion primarily in the software industry (e.g., "Wintel" de facto architecture). Further research, including survey research and additional interviews, is required to address this possible relationship.

What has been learned from this early investigation is the critical role that process innovations in general, and manufacturing equipment innovations in particular play in providing the technological capability to fabricate smaller and smaller semiconductor devices. The most notable of process innovations was the planar diffusion process in 1959 -- the origin of Moore's Law. Consistent with Thomas Kuhn's (1962) paradigm-shifting view of "scientific revolution," many have described the semiconductor era as a "microelectronics revolution." (Forester 1982, Braun and Macdonald 1982, Gilder 1989, Malone 1996, and others) Indeed, the broad applications and pervasive technological, economic, and social impacts that continue to come forth from "that astonishing microchip" (Economist 1996) seem almost endless. However, this phenomenon has also been aptly described by Bessant and Dickson (1982) as evolutionary, albeit at an exponential rate.

"In a definite technical sense there has been no revolution (save, perhaps, for the invention of the transistor in 1947) but rather a steady evolution since the first invention."

Moore's Law is one measure of the pace of this "steady evolution." Its regularity is daunting. The invention of the transistor, and to a lesser degree the integrated circuit a decade later, represented significant scientific and technological breakthroughs, and are both classic examples of the Schumpeterian view of "creative destruction" effects of innovation. This is evidenced by the literal creation of an entire new semiconductor industry at the expense of the large electronics firms that dominated the preceding vacuum tube technological era. This period of transition from old technology to new technology is characterized by instability, and factors that underpin very irregular performance. This would be considered a shift in the economic and technological paradigm (Dosi 1984, 1988) similar to Constant's (1980) account of the "Turbojet Revolution" where the invention of the turbojet, along with co-evolutionary developments including advancements in airframe design and materials, enabled significant performance improvements in air speed and altitude. The turbojet produced a whole new "jet engine" industry and helped redefine both military and commercial aircraft industries and their users (e.g., airlines). Following the early experimental years of the turbojet, these industries settled in on a new technological trajectory (Dosi 1984, 1988) toward the frontier of the "jet age."

Innovations within the boundary limits of this new frontier occurred at a rapid, but more regular rate. The role of accumulated knowledge -- both tacit and explicit (Freeman 1994) -- and standards (e.g., the role of the Proney brake as the benchmark for performance measurement and testing) are emphasized. Similarly, semiconductor development since the planar process has followed Klein's (1977) description of "fast history," but is more in line with Pavitt's (1986) application of "creative accumulation" (i.e., the new technology builds on the old). The "new" technology in this case is the accumulated incremental -- particularly process-oriented -- advancements indicative of the Moore's Law semiconductor "era." As for standards, indeed Moore's Law itself is used throughout the industry as the benchmark of progress, evidenced most strikingly by the kilo- to mega- to giga-bit density DRAM chips. Increasingly, regular advances in microprocessor performance measures such as MIPS (millions of instructions per second) and MHZ processing speeds follow -- and become part of -- Moore's Law.

Moore's law can apply to the data centers when you apply Jim's observations

• Process innovations play a critical role
• Steady evolution
• Role of accumulated knowledge

Is this what Mike Manos was trying to explain in his podcast?

Is this how Microsoft's Data Center Solutions group develops their data centers?

It will be interesting what Mike presents as a speaker at AFCOM and Uptime Institute.

WSJ article, How to Tap IT's Hidden Potential, ideas work for Green Data Center as well

The WSJ has an article about How to Tap IT's Hidden Potential , and many of these same ideas ideas apply to how Green Data Center projects should be executed. In fact, most companies who have green IT initiatives practice most of the ideas in this article.

Simply put, top executives at most companies fail to recognize the value of IT. It can help a company transform data from its operations, its business partners and its markets into useful competitive information. It can be the source of profitable innovations in the way a company interacts with its customers and suppliers. But there is still a tendency to think of IT as a basic utility, like plumbing or telephone service.

VIDEO: IT'S HIDDEN POTENTIAL

The chief information officer's role has become so important that it can now be a steppingstone to the CEO's office. Amit Basu discusses this development and its implications in an interview with the Journal's Carol Hymowitz.

In many industries, IT consumes a significant amount of capital expenditures and gross revenue. Though recent research has shown that managing IT well can significantly increase a firm's profits and deliver substantially higher returns on IT investments, its potential is overlooked, and even its workaday application is often mismanaged.

The result isn't just missed opportunities -- it's also wasted money. Analysts estimate that hundreds of billions of dollars are blown every year on IT projects that fail to achieve the desired goals.

This last point can include energy savings projects when you don't have a monitoring system in place to measure successes and failures.

Here are the points in summary:

1. Begin with IT literacy -- and commitment -- at the top
2. Hire an IT leader who sees the big picture
3. Create demand for IT solutions
4. Make sure nothing gets lost in translation
5. Rationalize IT spending
6. Create an IT portfolio by evaluating risks and returns

Microsoft Releases a Set of Best Practices for Energy Efficient Data Centers

Infoworld writes on Microsoft's release of a set of best practices for Energy Efficiency Data Centers.

Microsoft will release a set of best practices for administrators running datacenters, focusing on energy-saving strategies the company is implementing in its own operations, CEO Steve Ballmer said Monday.

Those tips will covers issues such as how to pick a good site for a datacenter, how to deal with heat, and how to manage power consumption, Ballmer said during a keynote presentation at the Cebit trade show in Hanover, Germany.

The move is in response to growing concern over the release of carbon dioxide, one of the byproducts of burning fossil fuels to create electricity. In addition, power demands are ever-increasing, Ballmer said.

"If you look at non-travel power consumption in the world today ... information technology is one of the most rapidly growing power consumers on the planet," Ballmer said. "We think we have a real responsibility ... to reduce power consumption by the IT industry."

The paper can be found at this location.

Let's see if we other big datacenter operators will follow Microsoft. 

Google?

Yahoo?