I recently had the opportunity to participate in a live Webcast focusing on The ROI of Virtualization, along with representatives from Intel and IBM. We had a lively discussion on the subject. The webcast is still available as an archive, if you’d like to check it out.

As usual, my favorite part of the event was at the end, where my co-presenters and I finish with our prepared remarks and take questions from the audience. I also had a few questions of my own. One of the most interesting points was regarding new innovations in hardware and software design, and where that will be taking the next generation of virtualization technology. I asked my copresenters – Bob Zuber, Worldwide Product Marketing Manager from IBM, and RK Hiremane, Senior Product Marketing Engineer from Intel “to outline some of those future directions that they see their respective companies pursuing. Here is a short excerpt from that Q&A:

Steve: What do you see in the future, what types of innovations can we expect, to help us achieve even greater efficiencies through virtualization?

RK: I think today, “virtualization 2.0 is becoming very important, based on the principles of consolidation and so forth. As we go forward, as many of the analysts have predicted, this is going to lead to further automation, and we believe it will lead to more service-oriented, policy-driven automation of the data center, and better efficiencies of the data center.

Bob: From a policy point of view, there will be certain things we look at from a power point of view. You may have workloads that are more performance-oriented or more energy-conservative, so you may have policies that say, “I want to direct that workload to the most appropriate platform to get the job done, in the most efficient manner. Today, when you look at power supplies, memory DIMMs, processors — you may come back and say, for this type of workload, I’m not going to have the ultimate performance from a processor point of view, but have better wattage from that point of view. You may forego and sacrifice certain attributes, and being able to have that policy director understand the underlying hardware attributes to direct the workload, that’s the promising piece that we see and the most exciting. It’s all about that automation and how we automatically move things around, but more importantly, how does a hardware provider build the most efficient piece of hardware that addresses a certain type of workload, but then likewise, can be adaptable to change, as the customer demands change, but from a workload perspective.

This is just one example of what you might call “virtualization 3.0, or the next generation of a technology that is already gaining a major foothold in corporate data centers. Since much of the appeal today is driven by cost and energy efficiencies, the policy-driven automation built into the coming generation of virtualization solutions will address those issues directly, and compound the savings.

From where I sit, that looks pretty promising. Is there a downside? I suppose extra processing power to automatically determine where to direct each task, bouncing it between machines that are more processor-intensive or more energy efficient, could potentially add to the overhead in the hypervisor, and adversely effect performance. As with anything, it’s all in the execution. If it’s implemented skillfully, there should be no discernible performance hit.

What do you think about new virtualized servers that think for themselves, and route workloads according to their own interpretations of the policies we set. Is it IT utopia at last?

I recently came across a thought-provoking blog post by StorageIO analyst and author Greg Schultz. Ruminating on themes in his new book “The Green and Virtual Data Center,” Schultz laments that the natural link between the concepts of virtualization and data center consolidation has led many to mistakenly conclude that these terms are synonymous. They aren’t. And even though consolidation is one of the leading reasons to virtualize today, it’s not the only good reason to consider the technology.

Furthermore, while the inherent cost and energy savings in consolidation are fueling much of the growth and interest in virtualization today, that won’t always be the case. Does that mean that when the economy rebounds, virtualization will become yesterday’s news? Far from it, argues Schultz. Despite “the perception and industry messaging that incorrectly pigeon holes virtualization to mean consolidation, and consolidation to mean virtualization,” Schultz warns us not to be sucked into the notion that virtualization without consolidation doesn’t have a bright future. “To the contrary, the reality is that there is life beyond consolidation (and) there are even more scenarios and far greater market opportunity for non-consolidation virtualization deployments over time, than what has already been seen for first wave of consolidation-centric virtualization scenarios.”

What are some of the reasons besides consolidation for virtualizing your servers, storage or other IT resources? How about simplified maintenance and technology updates, not to mention load-balancing, fault tolerance, and supporting business continuance (BC) and disaster recovery (DR)? According to Schultz, “We are just seeing the tip of the virtualization iceberg (or mountain).”

That’s good news if you’re in the virtualization business, since perhaps as few as 15% of all servers and storage systems are actually suitable to be consolidated – yet nearly all are suitable to be virtualized. What non-consolidation reasons can you think of to virtualize your server, storage, or even desktop systems? Or do you think virtualization is simply a consolidation-crazed “flash in the pan,” being driven by the IT community’s collective kneejerk reaction to an abysmal economy? I’d like to hear your views.

In past blogs, I’ve discussed some of the big-picture benefits for server virtualization. This week, I wanted to give some thought to the concept of desktop virtualization. Of the two technologies, the desktop variety has been much slower to take off in the marketplace, and frankly, there are some good reasons for that.

In both cases, the fundamental underlying technology operates on the same basic principle: By uncoupling the operating system and application software layers from the binary code layer that actually operates the chip-level hardware, you can accomplish some cool things. Perhaps the number one benefit is being able to create the illusion of multiple independent physical machines (AKA “virtual” machines) all living side by side on a single hardware platform. These virtual machines can lead diverse and independent lives, being dedicated to various tasks and even running on different operating systems.

The benefits at the server level are almost self evident. For one thing, running multiple virtual machines on a single box can be more efficient, because you can eliminate underutilized machines. As a result, you can reduce hardware costs, eliminate redundancy, and slash you electric bill. Support and maintenance costs can also be reduced, as you consolidate your data center.

So what’s the value proposition for doing this at the desktop level? For me, at least, the picture is a little murkier. If you assume one user per desktop, which is the norm in most computing environments today, then the economies mentioned above for servers no longer apply. You can virtualize any number of desktop machines one a single machine, and give users access to those machines over the network, but you still have to put some kind of physical device on each user’s desk. These devices can be slimmed down, stripped of many of the features commonly included in a PC, but with hardware costs so low these days, you’d really have to sharpen your pencil to uncover significant and compelling savings in the hardware department.

And the savings must be compelling, because users will fight you every step of the way. Ever since IT came along and replaced our dumb terminals with PCs, we have been fighting tooth and nail to hold onto them. It’s human nature. We want the illusion of independence and choice, the ability to plug in our iPods and other peripherals, to be able to load our own apps and upgrades, and to generally make IT people miserable by continuously trying to corrupt their ideal world of a pristine, locked-down and homogenous desktop environment.

I’m offering a very simplistic view here, and I’m counting on knowledgeable readers to come along and set me straight with their cogent comments. In reality, there are tons of good reasons to virtualize desktops, and in fact, the technology to do so has been around quite a while and only gets better with age. But the implementations will continue to be limited, and most users will only go along grudgingly, until vendors and IT managers start selling the benefits directly to those end users, and can actually succeed in creating grass roots demand for virtualizing their desktops.

So how do you get users to the point where they are actually calling their IT managers and begging to be virtualized? Well, here’s what sold me on the idea, personally. I was rereading an excellent 2007 post from my old friend and colleague David Berlind, where he discussed his own experiments in desktop virtualization. His driving motivation was to be able to take his personal desktop and make it truly portable and crash-proof by being able to replicate it on pretty much any piece of hardware, anytime and anywhere. For me, at least, the light bulb finally went on.

Anybody who has had their hard drive crash and had to start from scratch knows the pain involved. Even someone who religiously backs up their data knows that unless you migrate to another computer with the exact same hardware configuration, recreating your comfortable old desktop environment is a laborious, painstaking and imperfect process. The ugly truth is, you can never really go back. There are some benefits of getting a fresh start every few years, but these transitions seldom come at opportune and convenient times.

But what if your entire personal computing environment – including even the subtle little things like software and security settings in your browser and related apps, and the look-ahead cache in your e-mail client that knows the names of the people you routinely correspond with and fills it in for you –all that was being stored as a complete software image that could be easily transplanted onto another machine at a moment’s notice without the slightest interruption or flicker of change or incompatibility? Now you’re talking!

I believe this is the kind of benefit that would truly resonate with end users, and start creating pull-through demand for virtualization at the desktop level. I truthfully can’t foresee a time in the very near future when the desktop virtualization market will outstrip its counterpart on the server side, but it can begin to happen once the dialog about why virtualization works finally moves beyond the server room and reaches the water cooler crowd. Of course, the software will have to be completely seamless and invisible to the end user, which includes paying no discernible performance premium for introducing that layer of abstraction between the user’s virtual machine and the actual hardware it’s running on.

So tell me, what am I missing?

There are two types of green weighing on the minds of business professionals these days: The green that denotes business practices that tread lightly on the environment, and the green that represents money – or lack thereof for capital improvements. The big question is, can you implement the former type of green without spending too much of the latter?

Apparently, you can. At least, so says a recent report written by Barb Goldworm, a virtualization analyst for Focus Consulting and co-author of the 2007 book, “Blade Servers and Virtualization: Transforming Enterprise Computing While Cutting Costs.” In the white paper titled “How to Green Your Data Center from the Server Out,” Goldworm and her co-authors Armando Acosta of Dell and Ed Kurtzer of Intel set out with the premise that the greening of data centers is not only desirable – it’s inevitable.

“Energy costs are going up dramatically. In fact, energy costs are surpassing hardware costs,” according to the report.  An accompanying chart tells the story in graphic detail, showing clearly how energy remained relatively low throughout the 90s and well into the current decade. However, in 2008, energy prices suddenly shot up, quickly crossing over the stable line representing server costs. For the first time, “We are spending more money on power and cooling for the servers than we are for the servers themselves,” the authors state.

As an example, consider a 1,000 square foot data center, which can hold 30 10kW racks. The power required to operate that infrastructure is about 300kW, with another 300kW required for cooling. In Goldworm’s estimates, that translates to an electric bill of $240,000 annually for cooling alone. This explains why, in a survey at last year’s Interop conference , 74% of the IT professionals polled said their company’s major motivation for adopting energy-conserving “green IT” practices is cost reduction. 

Goldworm advocates implementing measures such as power management, upgrading to more efficient UPS, and replacing legacy servers with new energy-efficient models. But she also goes one better, suggesting that server virtualization can significantly reduce power consumption by increasing hardware utilization, and eliminating under-utilized hardware.  In her consulting practice, Goldworm says she “sees an average of 10:1 consolidation ratios in virtualization. Virtualization reduces space use, power consumption, waste, and cooling needs.”

Blade servers, in particular, offer substantial energy savings, the report notes, by reducing the overall number of electronic components that require power and cooling, and by adding more flexibility in server load balancing, providing the ability to incrementally power down servers during periods of low utilization, such as at night.

Through savings such as these, the move to virtualization and other energy-efficient IT practices can actually become self-funding, according to the authors. However, there is a cautionary note: The savings in energy costs are usually directed at the facilities budget. IT managers may find it challenging to pinpoint the cost savings derived from their green initiatives, and to get those savings credited back to their own IT budgets. The authors suggest that IT departments should seek to a partner with their facilities counterparts at the very outset of any green IT initiative. “Then the savings on the facility side can help fund the move to green IT, including virtualization and consolidation efforts on blades.”

If you listen closely, you can almost hear the sound of belts tightening. The dreary economic forecast has IT departments across the country and around the globe looking for every imaginable way to cut corners and reduce costs without reducing services and support. It’s a tough equation – some would say impossible.

The emphasis on cutting costs is one reason why data center consolidation and virtualization are experiencing a surge of popularity.  An Intel whitepaper posted a few days ago underscores the amount of savings that can be had by using virtualization to optimize just one prominent IT cost center: storage management.

At Intel’s current run rate for racking up the terabytes, the company estimates that its storage requirements would balloon to 90 petabytes of data by 2012, a 450% increase over 2007 levels. By 2014 that could grow to encompass 165 petabytes of data. However, by virtualizing its storage area networks and network attached storage resources, combined with techniques such as fabric unification, storage tiering, thin provisioning and de-duplication, Intel experts reckon they can whittle that number down by a whopping 27 percent over the next five years.

Much like server virtualization, storage virtualization allows multiple systems to share common physical resources. In this case, it’s a single storage device. According to Intel engineers, “Virtualized storage environments make it practical to re-tier storage and migrate data among virtual storage machines with relative ease.”  The cost savings come from not only reducing the physical footprint of a company’s storage assets, but also through increased utilization and scalability, greater access to multivendor sourcing, and simplified IT management. Increased business agility can also provide a positive impact on the company’s bottom line, making the enterprise better able to respond to shifting market opportunities and customer requirements. Add to that the direct effects of reduced headcount and energy costs, and you are looking at some serious savings.

By implementing its storage optimization plan, Intel expects to drop its projected storage requirements in 2014 from 165 petabytes to only 95 petabytes.  An anticipated headcount of 166 employees would have been needed to manage the company’s NAS and SAN resources without virtualization, but a staff of 90 will be able to handle the optimized storage environment, according to the internal study project. Finally, the changes will make a significant dent in Intel’s annual energy tab, reducing the kilowatt hours consumed per year from 65.6 million in 2014 to only 34.9 million.

The real impact of storage virtualization becomes clear when the benefits are factored into a comprehensive TCO (total cost of ownership) equation. Without virtualization and related streamlining, Intel would be facing TCO inflation of 279 percent by 2014. However, by implementing its “holistic approach to storage optimization,” the company expects to realize a TCO in 2014 that represents only a 13 percent increase from 2007 levels.

As the authors of the study noted, “Intel IT faces budget constraints and competing priorities just like any other IT organization, but the clear demonstration of potential risks and benefits has created enthusiasm for moving forward with the storage optimization plan.” Maybe it’s time we all took another look at our company’s storage TCO and how virtualization could help reduce costs and increase our employer’s overall ability to survive the current economic upheaval and uncertainty in the marketplace.

Is there something IT professionals can do that has the potential of addressing this triple threat of social, economic and environmental ills? The answer could be virtualization. Proven technologies that allow a single server to take on a variety of unrelated tasks that would normally require the use of multiple dedicated servers offer some obvious benefits in the areas of cost savings and efficiency. Can those benefits also translate into improved fiscal performance, reduced consumption of energy resources and a lower carbon footprint? The consensus seems to be in the affirmative.

In fact, these are among the reasons Gartner Group recently anointed virtualization as the No. 1 strategic technology for 2009, topping trendier tech topics such as Business Intelligence (#2), Cloud Computing (#3), Green IT (#4), and Unified Communications (#5). In his blog on the unveiling of this year’s Top 10 list, Gartner’s David Cearly cited virtualization’s “significant potential to reduce IT costs” as the primary business driver, noting that widespread IT belt-tightening in 2009 would prompt popular server virtualization technologies to be augmented by an uptick in virtualization techniques applied to storage and client devices.

Next to the promise of cost reduction, energy savings is among the biggest perceived benefits of virtualization. A study performed last spring by independent Washington, D.C.-based research firm KRC Research asked 205 IT decision makers in the retail industry to name their reasons for deploying virtualization in their data centers. Thirty-one percent pointed to energy savings as a major factor in their decision. According to the authors of the report, “The rising awareness of ‘green’ energy initiatives, as well as the increasing power required to run and cool data centers, likely factored into this response.”

So can making each server do the work of several actually reduce a business’ impact on the environment, as well? According to a recent McKinsey report, data centers contribute a substantial amount of greenhouse gases – potentially climbing to a whopping 1.54 metric gigatons by the year 2020, which is 3 percent of all emissions. “The fastest-increasing contributor to emissions will be growth in the number and size of data centers, whose carbon footprint will rise more than fivefold between 2002 and 2020 as organizations in all sectors add servers to meet rising demand,” the report states. Virtualization is one of the primary tools businesses have for reducing data center sprawl and its accompanying carbon footprint.

Given the current economic climate, as well as the new priorities that are expected to be ushered in by the next administration, companies that are “lean, mean and green” will be the most likely to survive and prosper in the year ahead. Organizations that have not yet deployed virtualization need to take a long, hard look at the technology and assess what it can do — not only for their bottom line, but for their country, and even their world.