Content in Intel Communities

Data Center Power: Zooming in Where it Matters

webadmin@intel.com — Mon, 06 May 2013 15:56:08 GMT

This post originally appeared in Information Management on December 26, 2012

Politics aside, the subject of energy is of great concern in every large data center. Why, then, is power consumption still an afterthought for most server deployments? Because IT and facilities teams typically work independently and neither team can control consumption or predict requirements when data center energy costs are buried in the overall utility bill.

Let’s face it: Energy costs are spiking, server sprawl is pushing against site capacity limits, and the Internet and smart device adoption rates are calling for aggressive increases in data center compute densities. Industry analyst firms agree that power and associated cooling requirements account for the fastest increasing components of operational costs. To protect the bottom line, and to comply with the latest EPA Energy Star standards, data centers need to change the way they monitor and manage energy consumption for power-hungry assets, like servers. New power and cooling management approaches are available that offer greater energy efficiency and reduced costs.

Traditional approaches to managing power and cooling have failed to control costs, in large part because they typically force over-budgeting to ensure priority needs are met. Ironically, even with overestimating and over provisioning cooling, data center hotspots continue to crop up, thereby impacting server availability, reducing data center cooling efficiency and driving up operational costs. These factors and their impact demand that facilities and IT professionals find a better way to achieve their common objectives.

Zooming in on the Right Measurement Points

One of the most fundamental barriers to achieving greater power efficiency and curbing runaway energy spend rates has been the inability to obtain accurate readings of actual server energy consumption levels. Various models have been developed that translate temperature and power consumption into overall data center energy requirements for servers and their associated cooling systems. However, even the best of these models lack the real-time visibility required to accurately understand and predict energy trends. Actual usage can vary significantly (up to 40 percent) from modeled predictions, and the models do not provide the immediate feedback required to pinpoint hot spots before they impact services or identify areas of waste where conservation can lead to savings.

Energy models are limited in terms of day-to-day management of power consumption. For example, we know from in-field measurements that an average of 15 percent of data center servers are “ghost” or “zombie” servers (servers that are not producing useful work, drawing energy just to stand idle). When we do the math, assuming that a server draws approximately 400 watts of power, which currently costs about $800 per year, companies are spending on average more than $24 billion per year for these “ghost” servers in their data centers.

Aggregating Server Thermal and Power Data

A second problem has been the technical challenges of aggregating data from varied and disparate systems within the data center. Facilities managers have been forced to cobble together, manually or with crude homegrown systems, vital data such as power supply of the server, inlet and outlet temperatures, asset information contained in RFID tags as well as temperature and humidity readings of the air conditioning units. This prevents the achievement of a “big picture” perspective of facilities’ server inlet temperatures and power consumption data from rack servers, blade servers, and the power-distribution units and uninterrupted power supplies related to those servers. The crippling effects of this piecemeal view are analogous to a long-distance truck driver suffering from tunnel vision.

By shifting attention from the cooling systems to the servers which account for the majority of the power consumed in the data center, managers can introduce a holistic energy optimization solution. Accurate monitoring of power consumption and thermal patterns creates a foundation for enterprise-wide decision-making with the ability to:

Monitor and analyze power data by server, rack, row or room;
Track usage for logical groups of resources that correlate to the organization or data center services;
Automate condition alerts and triggered power controls, based on consumption or thermal conditions and limits; and
Provide aggregated and fine-grained data to Web-accessible consoles and dashboards for intuitive views of energy use that are integrated with other data center and facilities management views.

Identifying temperatures at the server, versus at the room or even rack levels, can also help data center managers more accurately understand what the real ambient temperature should be for individual servers to have optimal life spans. This assessment of real temperatures has enabled data centers to increase the overall room temperature by one to two degrees, which can create significant savings in the air-conditioning expense.

Disseminating the power and cooling data, without impacting ongoing processing in the data center, is another challenge. Invasive monitoring approaches have the potential for adversely affecting the performance of existing systems. Agentless monitoring capabilities should have little impact on the overall system performance, and therefore are virtually undetectable to the end users’ experiences.

Where should all of this energy monitoring and aggregation functionality be placed within the data center? Ideally, all of this would take place transparently and non-invasively, to avoid impacting the servers and end users. Agentless approaches, without the need for any software on the managed nodes, are available. Data center managers should also look for solutions that are easily integrated, such as those based on Web Services Description Language APIs, and able to coexist with other applications on the designated host server or virtual machine.

Where Power is Going

Today, the goal is improved efficiency and reduced costs, but energy management will become even more critical in the future, as compute models continue to tax power infrastructures. Whatever the goal, the monitoring and aggregation of server energy metrics set the stage for much more comprehensive energy management and a far deeper and richer set of usage models for IT assets. Besides enabling accurate power planning and forecasting, logging and trending power data provides knowledge for data center “right-sizing” and accurate equipment scheduling to meet workload demands.

The thermal data can also be used for more efficient designs of integrated facilities systems, such as cooling and air-flow solutions. Optimized resource balancing in the data center will always be closely tied to power; the expanded insight offered by intelligent energy management approaches will contribute to cost-saving decisions for years to come.

Jeff Klaus is the director of Intel Data Center manager (DCM). Jeff leads a global team that designs, builds, sells, and supports Intel® DCM.

Reflecting on Carbon: Why Invest now in Efficiency

webadmin@intel.com — Fri, 03 May 2013 15:05:38 GMT

I’ll admit it. I read some dismay the stories about the collapsing market for European carbon dioxide emissions allowances, as covered in the New York Times.

Without going into great detail, I feel the most economically efficient way to reduce the deferred costs of carbon emissions is to simply set a price for them today. Does buying roses grown in Africa produce more or less carbon than those grown in the Holland? I’d say a carbon analysis of that supply chain borders on too complex. But if carbon impacts were fairly encumbered at each point of use with a cost, an efficient market would prefer the lower impact source to the extent that carbon futures affect the price of the commodity.

Sadly it appears we have taken a step away not only from that efficiency, but also from addressing the carbon problem.

So are the carbon credits DOA? After some digging, I think not. Here's why - carbon futures are traded on a market like any other commodity and are affected by the same supply and demand economics that affect the price of everything else. So let’s look at both.

The first data I looked at was to compare the fluctuating price of carbon with economic data in this case the changes in combined GDP of four major European economies (Germany, France, UK, and Italy). This shows an important correlation in the demand side. The amount of money available to chase EUA credits is limited.

Another correlation is with electricity generation, which is a reasonable proxy for the demand to use credits. Here I just looked at France and Germany together. Although Europe uses multiple sources for electricity, the majority source is from fossil fuels.

Again, the trend (at least of available data) shows a pretty good correlation. This is yet another way to look at the demand side of the equation. With lower economic output driving lower demand for electricity in turn diving lower demand for carbon allocations, the drop in price seems natural.

On the supply side, of course, the decision by the commission to not limit the number of allocations guaranteed an abundant supply of credits.

So do I think the carbon market idea is dead? No, I don’t. The data “behind the curtain” support the idea that the falling price of carbon allocations is just a simple matter of supply and demand.

Will demand rise and EUA prices rise in the future? Of course they will. Hence, while there may not be any short term imperative to oinvenst in low carbon and efficient technolgies, smart industries should be, I believe, investing now, in the down turn, to gain advantages from efficiency in the longer term.

Energy Proportionality Trends

webadmin@intel.com — Thu, 21 Jun 2012 18:55:51 GMT

I recently published a blog on Data Center Knowledge about how energy proportionality has essentially doubled the server efficiency gains beyond what “Moore’s Law.” This doubling was done by improving the “energy proportionality” of workload scaling.

A problem I’ve been stewing about is how to express proportionality in a simple way. There are of course lots of ways to think about it (and many of them equivalent). So what I am going to do here is propose a generic idea to emphasize an interesting insight into the proportionality of Xeon, and let other argue about the details.

Let’s divide this into three parts: 1) A framework, 2) Practical application to SPECPower results and 3) Insight from historical trends.

Part 1. A Framework

Establishing a framework for a “proportionality index,” of course, has some arbitrariness to it. Following some simple ideas about “what works for managers” let me just propose the following ideas. Looking at the graph of two hypothetical (and idealized) server load lines in the graph below you can see what distinguishes ideally Proportional Server “A” from non-ideal Server B is the area between the two curves. We can use this area difference as a metric of proportionality.

It is relatively easy to show that the area difference, which I will call SPI, between straight line (B)

Power = b + (1-b) * Workload

and an ideal line (A) is

Area = b/2

Where b = Idle Power/Max Power.

We can turn this into a Server Proportionality Index (SPI) with the following formula

SPI = 2(1 - Area) = 2*(1 - b/2 )

The index is zero for a server that has no energy scaling and one for a server with “ideal” linear scaling.

Part 2. Application to SPECPower

This idea can easily be applied to data readily available in the SPECpower benchmark.

In the figure below some data from a recent measurement on a Dell PowerEdge Server based Xeon E5-2600 are shown.

A little intuition will persuade you, and a little algebra will prove, that

SPI = 2(1 - AveragePower/PeakPower)

Where AveragePower is just the arithmetic average of the “average active power” measurements of SPECpower and PeakPower is the power at the targeted 100% load point. In the data set shown

SPI = 2(1 - (134 Watts)/(246 Watts)) = 0.90

This value is very close to ideal. Note that the idle power to max power ratio is about 0.21. The higher efficiency of the system mid-load improves the SPI. This emphasizes the importance of measuring the whole load line and not just the end points.

Part 3. Understanding Trends

Going back to the SPECPower database, I pulled the historical trends of volume two socket servers based on the Intel Xeon Processor and calculated the SPI for them all. I plotted the results in two ways to emphasize particular aspects about the dependence on the load line.

The graph on the left shows the trend of SPI versus the ratio of Idle/Max Power. The points generally follow closely the “ideal line” show as a dashed line on the plot. The notable exception is the departure at the lower end as noted above. This departure reveals very clearly why an improved way of thinking about proportionality is needed; the load lines of real servers are no longer well approximated by linear functions.

Looking at the second graph the historical trend of proportionality reveals very clearly the architectural transitions between families of Xeon processors. With each successive generation the proportionality index (as measured here) has improved in the range of 0.2 per generation.

So there you have it: a simple way to analyze the energy proportionality of non-linear servers and a simple formula for calculating a “Proportionality Index.” The historical trend shows not only the clear deviation from linearity but reveals the major architectural transitions in Xeon processor families.

The data pose an interesting question: is a straight line really the “ideal load line?” It is very conceivable (and certainly theoretically possible) that we will see SPI > 1 in the near future. So is proportionality really the right end goal? What would be the ideal load line? Is there such a thing? Any opinions out there?

The Growing Energy Demands Of Living Your Life In The Cloud

webadmin@intel.com — Wed, 13 Mar 2013 17:09:28 GMT

This post originally appeared in Forbes on October 22nd, 2012

Follow @jsklaus on Twitter for more

You recycle, drive a hybrid, and run your major appliances during off-peak hours. You are doing all you can to help reduce your energy consumption, right? Maybe not.

Have you considered how your lifestyle is driving up power use in the cloud? Personal energy use is no longer reflected solely in utility bills. A rapidly growing fraction of the average person’s day now involves an online component, and what we’ve come to think of as personally essential apps and services are driving up the power requirements for a global network of Web portals and online information hosting and delivery services.

Think about how different our at-home lives were before the digital revolution. An alarm clock – not a smart phone – buzzed us awake. We read newspapers and watched over-the-air broadcast television. We went to the shopping mall, and called the airlines to book travel. Our calendars hung on the wall next to the phone, and Post-It notes, time-manager notebooks, and PDAs were our essential life tools.

Click on the present day. Dad turns on the television to play back a pre-recorded game. He checks his fantasy football stats on his smart phone while Mom uses her iPad to Facebook a relative on the other side of the country. The kids are Googling to research homework assignments, and dinner is courtesy of the family’s favorite recipe app. After dinner, e-mail is checked, and IMs go out to coworkers about tomorrow’s meeting agenda. One teenager is in a virtual multiplayer online game world with a few schoolmates, and another is streaming a favorite show from an entertainment site.

The point is that we are living in a connected world, and we are tapping into cloud-based services more than ever before. And unless you are a technology holdout, you now live in an Internet-centric world where you use multiple smart devices and enjoy instant access to information. And besides the obvious accesses to online resources, there are a growing number of cloud accesses that might surprise you. When you talk to Siri on your iPhone, for example, you are using the extensive data centers behind the voice recognition system. Similarly, your navigation and location-based services are tied to cloud services hosted on servers around the globe.

Connectivity and online services are much more than just conveniences or entertainment sources. Besides serving up music, movies and information about our favorite sports or entertainment stars, the online world has improved the delivery of services that are vital to our everyday lives. Community police departments send out automated alerts from their central data centers. Patient health information is managed within online health services to help hospitals and treatment centers improve medical outcomes. And emergency response teams and relief agencies post essential information on their web sites, to update residents hit by natural disasters like hurricane Sandy.

So, we not only enjoy convenient access to information and services, we have become dependent on it. Digital experiences are improving the quality of our lives. And that brings us back to the question of energy. What price are we all going to pay for these conveniences and safety services if cloud applications keep escalating energy consumption?

Each online activity has an energy price tag in the cloud. Behind every online experience are global networks and data centers. It is currently estimated that data centers account for consumption of at least 1.5 percent of all of the world’s available energy . This statistic should raise our concern, and in fact, this power draw has doubled in the last five years and continues to grow about 20 percent annually in part because of the growing popularity and variety of online apps and services.

Just how popular are online services? How fast is the cloud driving up energy consumption? The most popular sites and services are publicizing amazing growth in their user bases and site activity. Amazon reports that it now sells more e-books than hard copies. Tablet sales expanded 98 percent last year; there are now more than 1 million online apps. A growing number of subscribers are cancelling traditional TV services, as online video streaming increases. And the user bases for music and video streaming should reach the one billion mark within the next three to five years along with total mobile devices projected to reach eight billion by 2016 .

The digital world is here to stay, and somehow the data centers are going to have to keep up. Fortunately, the power challenge is not new to technology providers who have experienced the result of higher consumption and grid utilization. High demand and aging delivery grids have forced some utility companies to restrict the amount of power delivered to a data center. Other data center operators are seeing energy prices increase and/or spike as demand grows, which strains operational budgets. Recognizing that these trends are here to stay, IT equipment manufacturers are innovating a new generation of data center, software tools, and networking products that are more energy-efficient than predecessors.

A data center full of energy-efficient servers can still waste power, however, if these servers are always powered up, but under-utilized. Power efficiency and optimization calls for an intelligent combination of the automated monitoring of power conditions and the ability to adjust power, temperatures, computer performance and workloads on the fly.

The trends and industry needs mentioned above are driving the evolution of holistic data center power management solutions. The approaches and implementations vary, but industry leaders that are emerging, and documented user results are helping to advance the most promising methodologies and products for data center energy efficiencies.

With the potential for rapid returns on investments, the world’s largest data centers are leading a wave of energy management best practices adoption. They are curbing run-away energy with a combination of micro-level controls (for individual servers, power distribution units, air-flow controllers, and cooling units) as well as macro-level controls and policies (for racks of servers, rows of racks, and entire data centers).

While you might say that technology got us into this situation, it is equally true that technology is helping us to mitigate this energy challenge. As long as energy is a precious resource, data center managers will continue looking for ways to improve conservation. The business case encourages them to do the right thing.

So go ahead and immerse yourself in the digital world. Guilt free. Thanks to data center managers who are seeking improved energy efficiency on your behalf, your power usage in the cloud is being managed responsibly.

Jeff Klaus is the director of Intel Data Center manager (DCM). Jeff leads a global team that designs, builds, sells, and supports Intel® DCM.

Follow-the-Moon Scheduling to Lower Energy Costs

webadmin@intel.com — Tue, 19 Feb 2013 16:42:33 GMT

This post originally appeared in Industry Perspectives on October 22nd, 2012

Follow jsklaus on Twitter

Power and cooling continue to strain even the most modern data centers. Industry analysts estimate that data centers
consume ~1.5 percent of the total available energy supply worldwide. And this percentage is going up.

In addition to dealing with the rising costs and the limits of the local utility companies to meet their needs, data center managers face other pressures for curbing energy consumption. For example, “cap-and-trade” programs – in effect in 27 European countries and, more recently, in California and other states and provinces in North America – are being introduced to force conservation of energy.

Lowering energy consumption is clearly a primary goal for just about every data center manager on this planet. Online group discussion forums, blogs, and publications like this one have been debating the various approaches and proposed solutions to the energy crisis in the data center. The answer, however, might come in the form of a combination of multiple emerging technologies.

Cloud Computing: Energy Cost Saver?

Cloud computing, when combined with a power management solution, can effectively lower the total energy costs tied to the data center’s workloads.

For example, consider a company with a large, central data center in New Jersey. The company also operates aWest-coast colocation site for disaster recovery and handling overflow requests for the main data center. The colo’s energy rates are slightly lower than New Jersey’s. The company’s private cloud computing model can flexibly meet service requests, with workloads distributed between New Jersey and the West coast data center – on the fly – for optimal server utilization and performance.

What does this have to do with driving down energy costs? Consider how service request scheduling could be adjusted if data center managers knew, with fine-grained accuracy, the energy requirements for the various workloads and service requests. Energy costs could be compared at the time of any service request.

As a first step, the New Jersey-based data center team might shift some applications or service requests to the West coast during the three hours when they pay peak power rates, and the West coast data center is still getting off-peak rates for consumed power. The next step would be to off-shore service requests to another hemisphere. A follow-the-moon strategy would allocate tasks to data centers where the cheapest night-time power rates could be used to drive down the cost of the service request.

Technology Hurdles

Taking advantage of the cheapest energy rates—wherever they may be offered—is not an unrealistic scenario, technologically speaking. Cloud computing is rapidly advancing, especially as security technologies evolve for virtualized servers, and as high-speed networks are being built out. Certainly, there are some regions that still lack reliable, affordable network bandwidth for avoiding application latencies, but there are plenty of off-shore regions that are building out infrastructure at a rapid pace—regions where power is affordable, and the service provider industry is subsidized by government infrastructure investments. The data centers popping up in those areas can offer lower compute rates for off-shored data center service requests and workloads.

So, the critical component becomes the power management or power dashboard—the solution that gives the data center manager the visibility and control of a workload’s power profile. Real-time power management has evolved at a rapid pace over the last decade, and today many enterprises already use thermal and power maps to drive down power consumption in the data center, avoid equipment-damaging power spikes, and throttle down server performance when necessary to remain under the power ceiling for the data center, or the row, or rack of servers within a data center.

These same power management solutions can be used to profile workloads and for making intelligent decisions about which workloads to offshore at which times of day.

Leveraging the Cloud

Cloud computing is a natural progression, when compared to today’s highly virtualized data centers. It promises enterprises unprecedented agility, in terms of cost-effectively meeting the compute needs for dynamic organizations and fast-changing markets. When the cost of power is considered as yet another resource to include in the business case for cloud computing, it makes the evolving loud models even more exciting in terms of the potential for cutting costs.

Jeff Klaus is the director of Intel Data Center manager (DCM). Jeff leads a global team that designs, builds, sells, and supports Intel® DCM.

Data centers: What does it take to heat things up?

webadmin@intel.com — Wed, 13 Feb 2013 00:01:35 GMT

This post originally appeared in GreenBiz on December 26, 2012

Follow IntelDCM on Twitter

Keeping things cool has long been a mantra for data center operators, but new research suggests it may not be essential for everyone.

Data centers have historically operated at temperatures ranging between 64° and 68° Fahrenheit (or 17° to 20° Celsius), prompting them to spend approximately 44 percent of their total power budgets on cooling.

Originally, the varied mix of equipment and associated warranties dictated these relativelycool temperatures, and service level agreements (SLAs) often included explicit language about how much deviation was acceptable.

But while it's true temperature control can affect equipment reliability and appropriatemanagement and monitoring is needed for business continuity, new research supports the idea that higher temperatures are beneficial for most data centers.

So, how do you know when to raise the temperature, and by how much? Are there any changes recommended to reduce business risks?

Should every data center cut back on cooling?

When we ask, many data center managers can’t tell us why they set the thermostat at a particular temperature. It’s just the way it has been done for years.

But when well-known companies -- including Facebook, Google, Yahoo!, Korea Telecom andothers -- publicize their high temperature ambient (HTA) successes at 80°F and above, we all pay attention. And when research and on-the-ground examples support the efficacy of HTA data centers, suddenly we are all tempted to reduce our cooling costs by just pushing up the thermostat.

Before arbitrarily cutting back on cooling and letting the ambient temperature rise, however, as a data center manager, you’ll want to review your equipment warranties, SLAs and compliance requirements. For those responsible for data centers supporting legacy systems that require lower operating temperatures, or for those whose organizations are subject to extremely stringent compliance requirements, you’ll want to continue to take a very conservative approach.

HTA Best Practices

That said, today’s major vendors of data center equipment generally design and warrant systems and products for reliable operation at 40°C or 100°F. It makes economical sense to take advantage of the latest product specifications and warranties. This means considering simple as well as more involved changes:

Thermostat-only changes. Data centers potentially reduce cooling costs by 4 percent for every 1°C increase in operating temperature. (Cooling accounts for up to 44 percent of the power consumed in an un-optimized data center, which is the typical design being implemented in emerging economies.)
Retrofitting the data center. Besides raising ambient temperature, hot and cold air aisle separation drives up the savings, and replacing chillers with economizers (heat exchangers) can yield dramatic savings. In one of Intel’s data centers (with 900 production servers), retrofitting and raising the temperature to 33°C or 91.4°F has translated to a 67 percent annual power savings ($2.87 million in a 10MW data center).
Optimized data centers. Hot aisle containment, energy-efficient servers and a node-level power management solution capable of dynamic resource management (e.g., power capping servers, racks and rows; adjusting server performance and fan speeds) have been shown to dramatically drive up energy efficiency and support operation at the highest temperatures without increasing risk to the business. Real-world results show power utilization efficiencies can be increased so that IT power utilization improves from 50 percent to 81 percent of the total.

All things -- and temperatures -- in moderation

Your data center can take some steps to reap the cost benefits of HTA operation. Start with a plan to phase out, relocate or outsource any legacy system that is keeping your data center at the lower, more expensive operating temperatures. As soon as possible, bump up the temperature by one degree or two, to get on a path toward HTA.

However far along you are, an energy management solution may improve your visibility into energy use and thermal patterns within your data center. Among the foundations necessary for achieving power efficiency through HTA practices are real-time visibility and the abilities to log power and temperature data, and to analyze usage trends based on the logged data.

These same capabilities can also enable other energy management practices such as lowering carbon emissions, thus allowing you to expand a data center without exceeding power limits, and efficiently balancing services and workloads to avoid power spikes.

The cost and power savings achievable by adopting HTA as a model may well represent the new norm. The timing is perfect: Data centers currently consume 1.5 percent of all of the world’s power. Annual server energy costs exceed $27 billion. By 2014, these numbers are expected to double. Bumping up your data center’s ambient temperature directly reduces cooling costs and power consumption, and simultaneously reduces CO₂ emissions.

HTA makes business sense, and it makes sense for our planet. Get ready for the data center world to heat up!

Jeff Klaus is the director of Intel Data Center manager (DCM). Jeff leads a global team that designs, builds, sells, and supports Intel® DCM.

Computacenter Consults the Future

webadmin@intel.com — Sat, 26 Jan 2013 01:10:06 GMT

Download Now

Computacenter is Europe’s leading provider of IT infrastructure services. It advises organizations on their IT strategies, implements the most appropriate technology from a wide range of vendors, and, if required, manages its customers' technology infrastructures.

Computacenter introduced its SAP Procedural and Service Model* to help customers identify the best SAP HANA* appliance, based on the Intel® Xeon® processor E7 family, to suit their SAP platform strategies, together with a roadmap for installation. Several features of the Intel Xeon processor E7 family make it the ideal platform for performance, reliability, availability, and energy efficiency. Within the first month of launching its SAP HANA Procedural and Service Model, Computacenter had signed up three customers.

“Ultimately, we will be able to generate new revenue streams and develop much closer relationships with our customers,” explained Rene Stolte, solution manager for Computacenter.

To learn more, download our new Computacenter business success story. You can find more like this one on Intel.com and iTunes. And to keep up to date on the latest business success stories, be sure to follow ReferenceRoom on Twitter.

*Other names and brands may be claimed as the property of others.

Data Center Energy: Past, Present and Future (Part Two)

webadmin@intel.com — Mon, 07 Jan 2013 23:43:11 GMT

Nothing Is Certain but Death and Taxes—Even in the Data Center

This article is the part two of a three-part series on energy management in the data center. (See parts one and three.)

Last week, I wrote about the past approaches to data center power management and the state of rising inefficiency. I presented a case for more accurately assessing current power consumption and explained why past approaches for calculating power requirements or manually measuring power were insufficient for establishing proactive energy-management policies.

In this article, I will overview some of the current trends that make it imperative that data center teams consider a more holistic approach for monitoring and controlling temperature, airflow and power in the data center. These trends have been widely reported in the industry, or observed first-hand in data centers around the world that are owned and operated by our customers and our partners’ customers.

The good news is that there are many trends and innovations that make it possible to drive up conservation even within the largest sites and facilities. Before we talk about next steps, consider the trends in this article and ask yourself at least some of the questions raised in each section.

Trend: Virtualization and Consolidation

Originally virtualization initiatives delivered on their promises of reducing operating costs, improving service delivery and contributing to a more scalable data center model; but as a power-management mechanism, VMs proved to be a crude tool that was soon overtaken through increased VM load (as VMs became a standard service). But the combination of application consolidation and device consolidation/minimization has introduced larger numbers of blade servers and much higher utilization rates for those blades. As a result, power consumption per rack has increased significantly.

The higher-density racks are problematic in two ways. First, they can result in a data center exceeding the capacity of a site that was not designed for a virtualized environment. Second, they introduce hot spots in the data center that can lead to equipment failures unless air-conditioning and airflow adjustments are made. These can, in turn, increase costs.

What is the rack density in your data center? Are you maximizing the return on investment in blade servers, or are you buying more racks than you need to accommodate power requirements? Many legacy centers today, especially in countries with older power-delivery infrastructures, operate with underutilized racks and inefficient power distribution in the data center as they try to take advantage of virtualization.

Trend: Power Availability Issues

With data center compute densities on the rise, building a new facility calls for a survey of utility companies and their power-delivery limitations, rate scales and failure rates. Larger companies cannot necessarily build in the location of their choice if the local power company is unprepared for the additional energy requirements.

Besides the impact on site selection, existing facilities around the world are approaching power ceilings as utility companies struggle to keep up with demand. For example, in Japan only 2 out of the country’s 54 nuclear power plants are online following the March 2011 Tsunami. So far this summer, conservation efforts have worked and there have been no planned blackouts, but the possibility still looms. And other countries, it is typical that regions are consuming 90% of available energy on a consistent and rising basis. In Japan, a micro-industry has emerged, with companies that evaluate and report on real-time consumption of electricity by city and region.

Whether it is an infrastructure issue that impedes delivery, a production capacity limitation, or a natural disaster that takes a major supplier offline, the impact on local businesses can result in severe restrictions on their growth and ability to operate data centers to their fullest.

Does your company have a plan for operating at severely restricted levels of power, if necessary, as a result of a natural disaster? Do you have an energy-management solution in place that can help you introduce controls and lower consumption in an orderly fashion that aligns with your business priorities?

Trend: Power “Quality of Service” Becoming Mission Critical

As businesses and markets globalize and day-to-day business becomes Internet-centric, even a small power outage can be damaging to a company’s bottom line. Highly dense data centers and today’s much faster compute platforms are also able to generate surges of demand that can themselves result in damage to the data center equipment.

Being able to monitor power and proactively make adjustments in the event of a power failure have become cost-effective practices that prolong the life of equipment while they also avoid disruptions to business. Is your data center monitored? Do you understand the power and thermal patterns that affect reliability, service continuity and cost of service delivery at your site?

Trend: Energy Regulations and Taxes Add to Data Center OPEX

In the U.S., the Environmental Protection Agency (EPA) is expected to introduce new Energy Star standards for the data center in the near future.

These regulatory practices and the related fines and taxes are also being adopted in other countries. In Japan, for example, the Ministry of Economy, Trade, and Industry (METI) operates its “Top Runner” program, offering guidance similar to that of the U.S. EPA’s Energy Star program, for energy-efficiency equipment selection support. METI has been working to develop data center efficiency metrics and to harmonize them with those of the U.S. DoE, U.S. EPA, U.S. CoC and The Green Grid (a global organization focusing on data center efficiency improvement). METI and the Ministry of Internal Affairs (MIC) each publish recommendations for data centers, and they plan to consolidate these recommendations into a single guideline in the next few years.

Taxing energy is being debated in various countries.[1] Japan previously taxed energy, but the tax has been since repealed. In the U.S., “cap and trade” programs are being introduced in some states.

California is receiving a lot of attention currently, as it prepares to launch the nation’s first cap-and-trade program aimed at reducing emissions.[2] This summer, the state is starting a trial run of an online auction site where 150 major “emitters” can bid on carbon allowances. Starting this fall, California will distribute annual allowances to industrial entities and factories; in 2015, the program will also apply to fuel distributors.

Foreseeably, companies will have to actively monitor and restrict power use to stay under government-mandated “for-free” levels of consumption and avoid taxes or extra purchases at higher rates. What are your company’s peak consumption rates and how much could you cut back if budgets forced conservation?

Conclusions

This look at power restrictions, environmental variables and taxes would be depressing if there were no remedies in sight. But power-management solutions are evolving and can put you back in control with a broad range of effective, proactive energy-monitoring and on-the-fly adjustment capabilities, some of which were hinted at in this article.

[1] Global taxes on carbon emissions/energy consumption:http://www.sbs.com.au/news/article/1492651/Factbox-Carbon-taxes-around-the-world

http://en.wikipedia.org/wiki/Carbon_tax

[2] San Jose Mercury News, August 30, 2012, “California’s cap-and-trade program to cut emissions starts trial run” by Dana Hull (dhull@mercurynews.com),http://www.mercurynews.com/business/ci_21428079/trial-run-california-cap-trade-program-thursday-cut-emissions

About the Author

Jeffrey S. Klaus is the director of Data Center Manager (DCM) at Intel Corporation.

Jeff concludes this series with suggestions for forward-looking data center best practices. Look for Part Three to learn how you can keep your company on a path that allows you to adjust for the real-world future of energy as it relates to—or restricts—the delivery of business infrastructures and services.

Leading article photo courtesy of 401(K) 2012

Atom for the Data Center: Matching the Right Solution for Workload Requirements

webadmin@intel.com — Mon, 07 Jan 2013 18:42:50 GMT

When Intel Announced the first 6W, 64 bit processor for servers a couple weeks ago with the introduction of its first Atom SoC for the data center, many folks were interested to hear about how Atom fits into Intel’s broader data center strategy. To get the inside scoop, I decided to chat with Raejeanne Skillern, Intel’s director of cloud marketing and frequent guest on my Chip Chat program.

Raejeanne and I chatted about why Intel decided to drive Atom to the data center, what specific customer requirements were driving this development, and who was expected to deploy Atom platforms…and for what purpose. The short story: as it has many times in the past, Intel is utilizing Atom to address a pretty specific need in the data center for low compute intensive workloads where extreme density is required. And the good news is that our webscale data center customers who are expected to deploy these platforms will benefit from the common instruction set architecture with our existing Xeon platforms today, meaning that the software running these workloads on Xeon today can easily migrate to Atom tomorrow.

Telecom Italia Powers Down

webadmin@intel.com — Fri, 04 Jan 2013 20:55:56 GMT

Download Now

Telecom Italia is Italy’s main information and communications technology (ICT) group and an important player on the Latin American market segment, which represents 38 percent of the company’s turnover. Today, Telecom Italia infrastructures and technological platforms allow voice and data to be transformed into advanced telecom services as well as leading-edge ICT solutions. The company is constantly innovating and incorporating new technologies into its offerings. Such a demanding goal, however, is putting pressure on data center energy consumption. To improve energy efficiency and better manage power consumption, it decided to run a proof of concept (PoC) on Intel® Data Center Manager (Intel® DCM) and the Intel® Xeon® processor E7-4807.

“The pilot shows that using the latest Intel processors with Joulex Energy Master* and Intel DCM, we could potentially reduce server power consumption," explained Luigi Bellani, IT infrastructure engineering director for Telecom Italia. "We may also be able to identify servers that are using too much power and replace them. Based on our experience and results to date, we believe Intel Node Manager could also help us further reduce power consumption.”

To learn more, download our new Telecom Italia case study. You can find more real-world business success stories like this one on Intel.com and iTunes. And to keep up to date on the latest business success stories, be sure to follow ReferenceRoom on Twitter.