Grow A Greener Data Center by IT Architect Douglas Alger From Cisco

“Green IT is ultimately about resource efficiency – maximizing what you have and optimizing how it is consumed.  Beyond the admirable environmental benefits from being green, such optimization lets you accomplish more and spend less.”

This is just a sampling of the insight you’ll find below as our Data Center Leaders Interview Series details necessary tactics and quantifiable benefits for taking your data center green.  Helping us is Douglas Alger, IT Architect for Physical Infrastructure from Cisco and author of the book Grow A Greener Data Center.

For anyone who still feels that Green IT is simply an altruistic business fad nearing an end, rather than a significant strategy for saving capital and optimizing power usage, this interview is for you:

Evolving Solutions:
What tips would you offer for businesses prior to launching a Green IT initiative?

Douglas Alger:
Specific to  the Data Center space, I recommend having tools in place to monitor your Data Center resources.

Being able to track power consumption down to the cabinet level, temperature conditions, and hardware utilization is invaluable for developing and implementing Data Center green initiatives.

Monitoring tools can help uncover inefficiencies such as short-cycling of an air handler or which servers in your Data Center are consuming a disproportionate amount of power.  They also can help you prioritize potential improvements, calculate the return on investment, and – after implementation – accurately track efficiency gains.  Without them are you left to guess at the impact of the improvements you are making.

Evolving Solutions:
How would you recommend selling the idea of green IT to upper management who see it as little more than a fad?

Douglas Alger:
I think it’s important to emphasize that green IT is ultimately about resource efficiency – maximizing what you have and optimizing how it is consumed.  Beyond the admirable environmental benefits from being green, such optimization lets you accomplish more and spend less, conditions that are always going to be of interest to a company.

For Data Centers, being green saves money by reducing energy consumption (the largest operational expense of a Data Center) and cutting down on the use of consumable items such as patch cords.  Being green also extends the lifespan of your facility (deferring future construction costs), provides more flexibility to accommodate future technologies, and positions your company well in the event that environmental regulations around energy-efficiency or carbon emissions are enacted in the future.

Evolving Solutions:
With business movements that emerge quickly, such as Green, it is not uncommon for mistakes to be made due to rapid deployment.   What implementation mistakes have you witnessed, in regards to Green IT initiatives?

Douglas Alger:
Companies sometimes launch green initiatives without developing an overall strategy.  That’s fine for the short term and individual green projects can definitely be successful, but as more uncoordinated green activities are initiated you can end up with redundant efforts and other inefficiencies, especially at large companies.

Any green initiative that you can think of – recycling programs, promoting alternate transportation, server virtualization, etc. – are bound to accomplish more if they’re implemented as part an organized program with defined goals.

Evolving Solutions:
Your book, “Grow A Greener Data Center,” walks companies through a bottom-up approach to building a green data center, beginning with physical construction.  For companies that do not have the option to physically build a new data center, what do you recommend as an ideal starting point?

Douglas Alger:
There are a lot of green improvements that can be made to existing server environments that are very low cost, paying for themselves many times over, and easy to implement.  One simple step, for example, is to install timers and motion sensors on your Data Center lighting, causing non-emergency lights to turn off whenever the room is unoccupied.  (This can be done for other building spaces that are unoccupied for extended periods of time as well, such as conference rooms and bathrooms.)

If your Data Center’s power and cabling infrastructure are routed under a raised floor, seal any excess gaps at the floor tile openings where patch cords and power cables enter the plenum space.   This will improve the performance of your cooling system, reducing your energy consumption.

Yet another green improvement that can be implemented unobtrusively is to make energy-efficiency a key purchasing criteria for hardware that goes in your Data Center.  Newer, more energy efficient devices can be introduced as part of your company’s normal refresh cycle for hardware.  This can lead to significant savings over time.  When you factor in a server’s cooling needs and the conversion losses that occur along a Data Center’s power delivery chain, your energy savings will ultimately be nearly three times the number of watts you conserve at the hardware level.

Evolving Solutions:
Toby Velte, Global Technology Strategies with Microsoft, describes how he helps to ensure Green IT initiatives are funded by always relating projects to the pressures of capitalism, rather than the pressures of altruism.  Do you find this to be true across the board, or have you seen some firms consider start to implement green IT purely from a sense of corporate responsibility?

Douglas Alger:
I have seen businesses undertake green activities because they want to do the right thing, but I agree that if you want to truly entrench green initiatives within your company you need to demonstrate their business value.  When budgets get tight, upper management is more likely to cut a “feel good” program than one known to contribute in a proven way to the company’s success.

Evolving Solutions:
Wild Card:  Anything else you would like to add?

Douglas Alger:
Some people don’t immediately associate Data Centers with opportunities to be green.  With the tremendous consumption that occurs in these facilities, though – often 20 to 40 times the energy usage of traditional office space – there are ample opportunities to be more efficient and thereby save energy, save money, and reduce your carbon footprint.

Storage Consolidation Expert Rajeev Bhardwaj

Behind labor, energy costs are emerging as the second highest operating cost in most data centers worldwide. Operating in an economy still in the early stages of recovery, companies must explore all options available for reducing data center energy costs.

Today’s entry in our Data Center Leaders Interview Series sets out to help companies make the critical IT decisions that will lower costs, including those associated with storage consolidation, without hindering performance.

For help, we turn to Rajeev Bhardwaj, Senior Director, Data Center Switching Technology Group, Cisco:

Evolving Solutions:
What do you recommend as a first step in the development of a cost efficient storage consolidation or networking plan?

Rajeev Bhardwaj:
End-to-end virtualization will consolidate the datacenter and will deliver operational efficiencies from the perspective of being cost-effective and applications being easier to manage, provision, and deploy. End-to-end virtualization in the datacenter includes server virtualization, server I/O virtualization, Storage Area Network (SAN) virtualization, and Storage virtualization.

End-to-end virtualization should begin with SAN virtualization as the SAN network interconnects all the storage and server elements in the datacenter and a consolidated SAN can serve as a platform for further virtualization of servers, server I/Os, and storage.

Customers typically deploy silo’ed infrastructure with multiple SAN islands based on departmental, application, and performance needs. The consolidated SAN must maintain the logical separation between the SAN Islands from both data path and control plane perspectives while consolidating them on a single, physical infrastructure: Virtual SAN (VSAN) allows to easily achieve that virtualization abstraction.

Consolidating multiple SAN islands in a virtualized SAN allows to significantly reducing the number of infrastructure assets required, being now shared and dynamically allocated based on actual needs.

This approach optimizes assets’ utilization and dramatically reduces deployment, management, as well as power, space and cooling costs. A consolidated SAN has the additional advantage that intelligence can now be deployed in the SAN to enable both server virtualization and storage virtualization.

Evolving Solutions:
What are the inherent dangers in trying to make your storage consolidation plan too cost efficient?

Rajeev Bhardwaj:
It is very important to consider the underlying architecture of each device required to deliver the consolidated SAN. If the SAN switch architecture is not robust and delivers unpredictable performance and latency, the consolidated SAN becomes a central bottleneck affecting all applications and all departments.

One should consider questions such as – how does the switch architecture handle congestion, does it exhibit consistent latency and performance, does it provide enough buffer-to-buffer credits per port to handle different applications and distances, does it provide high availability and in particular for links that carry a lot of bandwidth between switches?

Evolving Solutions:
Green IT is seen by many as a solution to upgrading existing data centers to be more cost efficient.  Do you feel green IT practices can significantly impact the cost of storage consolidation?

Rajeev Bhardwaj:
A piecemeal approach of deciding each IT component based on its power consumption can work fine for marginally reducing power as a first step, but can actually be counter-productive overall if a holistic view of the data center power is not considered.

Solutions that at the chassis level seem to provide slightly better power consumption, have proven to increase the overall power cost of the datacenter: poor network support of server virtualization constraints the consolidation of servers, consuming over 75% of the overall datacenter power budget; limited networking capabilities and unpredictable performance require to increase network size as soon as new applications are deployed in the datacenter, transforming the initial minimal saving in a major cost.

Green IT can reduce cost and power usage while increasing operational efficiency in the data center if achieving end-to-end virtualization is maintained as a goal. Deploying the right networking infrastructure can provide security, performance, Quality of Service (QOS), and ease of management required to enable reductions in the size of the server farm, the number of LAN and SAN switches, and the number of storage arrays.

Evolving Solutions:
In a recent interview, author and StorageIO found Greg Schulz helped dispel the myth that storage networking and consolidation are business expenses that only apply to large enterprises.  In your experience, are smaller businesses aware of the need for storage consolidation and networking plans?

Rajeev Bhardwaj:
In these tough economic times, smaller businesses are looking to reduce both capital and operational expenditure. Smaller businesses understand that times are tough but are also looking to position themselves for the turn-around in the economy and so are not willing to sacrifice on scalability.

IT is increasingly considered as a means to increase the company efficiency and competitiveness by providing real-time data to any sales person, partner, or executive anywhere at any time while maintaining security and keeping costs low.

Smaller businesses are very much interested in buying and maintaining fewer servers, fewer switches, and getting more mileage out of their existing storage arrays. Thus we see smaller companies collapsing their multiple fabric switches into a larger director to gain scalability and high availability while reducing management expenses.
Similarly, we have also seen keen interest in our Fibre Channel over Ethernet (FCoE) portfolio from smaller business looking to consolidate their LAN and SAN expertise and infrastructures.

Evolving Solutions:
Omar Sultan, your colleague from Cisco, envisioned matured virtualization, greater use of automation and the evolution of cloud computing as solutions that would lower data center costs five years from now.  What would you add to this list?

Rajeev Bhardwaj:
Most organizations have separate LAN and SAN departments managing separate networks today. Five years from now I see this distinction being blurred and administrators who are aware of both LAN and SAN environments running a common network based on common switching components.

I see this common, cost-efficient network providing the under-pinning for higher data center virtualization, automation, and ultimately evolution of highly scalable, secure, and highly available private and public cloud infrastructures.

Evolving Solutions:
Wild Card:  Anything else you would like to add?

Rajeev Bhardwaj:
Energy costs are emerging as the second highest operating cost (behind labor) in most of the data centers worldwide. While networks consume a very small percentage of the overall data center power, deployment of intelligent networks can drastically reduce end-to-end power consumption and management costs while reducing provisioning time for new applications and achieving greater operational efficiencies in the data center.

VMware & Virtualization Expert Edward L. Haletky

When asked for technologies key towards sustained IT cost reductions, data center leaders commonly cite server virtualization technologies.

Our Data Center Leaders interview series digs deeper into this subject today as we discuss VMware virtualization with AstroArch founder Edward L. Haletky.

Haletky is a leading expert on VMware and virtualization who has authored the books VMware ESX Server in the Enterprise: Planning and Securing Virtualization Servers and the upcoming Virtual Infrastructure Security: Securing ESX and the Virtual Environment.

Haletky shares insight below on virtualization best practices, including how to identify and eliminate security threats common to virtual platforms:

Evolving Solutions:
Your book, VMware ESX Server in the Enterprise: Planning and Securing Virtualization Servers, offers VMware deployment tips and best practices.  What top three tips would you offer to businesses who’ve just implemented server virtualization through VMware?

Edward L. Haletky:
Now that the implementation is complete, it is time to review everything to make sure no changes are necessary. In some cases, these changes could mean a reinstall due to a change in usage or the plan.

You can now gather performance data to see how things are working and adjust the system appropriately.  This is the time to make sure your investment in virtualization succeeds. Verify memory limits, perhaps you have allocated more memory than what is actually used, verify Disk and Network IO, you may need to adjust this as well by adding new LUNs or more pNIC to the vSwitch, etc.

Form a Team that comprises the Security, Storage, Server, Network, and Virtualization Administrators to discuss issues as they come up. Sort of an advisory board of sorts within the company. With virtualization, the traditional siloed approaches do not work very well.

When considering new hardware, always choose something that is on the Hardware Compatibility Lists and nothing off them.

Evolving Solutions:
When asked for technologies designed to reduce costs in larger data centers, Cisco’s Omar Sultan cited virtualization technologies such as VMware and Hyper-V. How soon after implementation of these technologies can businesses expect to see cost savings?

Edward L. Haletky:
That depends on quite a few things, but most companies see an immediate lower consumption in power and possibly even cooling.  Those are always the big savings and immediate ones.  Cost savings also occur when hardware is to be updated as you are updating less hardware but license costs tend to eat into those savings.

Over time more items will be virtualized and a new baseline for cost savings will be created that already includes virtualization.

The real savings will end up being in efficiency.

Evolving Solutions:
Your upcoming book, Virtual Infrastructure Security: Securing ESX and the Virtual Environment promises to help identify and mitigate security related threats in all VMware platforms.  What would you identify as the single largest security threat present in VMware platforms today?

Edward L. Haletky:
This is a tough one, but it can boil down to the fact that currently virtualization security does not encompass the entire virtual environment but concentrates just on virtualization host security.

There is quite a bit more to virtualization than just a hypervisor to consider: there is management, backup, storage, clustering, and virtual networking.

In addition, security is often considered a bolt-on or after thought when it should be considered from the very beginning, when you are architecting and designing your virtual environment.

Evolving Solutions:
In regards to leaving themselves open to security threats, what are the biggest mistakes companies make after implementing a virtualization initiative and how can they be avoided?

Edward L. Haletky:
Many companies bolt on security instead of design/architect it in from the beginning.

That aside, the biggest error I see is the use of a flat network for management, IP storage, and VMotion. These three networks should actually be separate from each other and the normal production networks using firewalls and perhaps separate physical switches.

The other item that comes to mind on virtual networking is the level of trust in VLANs. This is not a security construct but people use it as such.

The other issue that comes up is to overlook aspects of storage security such as how backups are made.

In general, most people feel that they cannot be attacked and that they are safe from attack due to having an external firewall. Until a Penetration Tester comes in and shows how false that is, ignorance is bliss.

Evolving Solutions:
VMware vSphere 4 is bringing virtualization to small businesses. How have small businesses reacted to this opportunity promising to improve data center efficiency?

Edward L. Haletky:
vSphere 4 is not really doing that, it was done when VI 3.x was released as well as when VMware Server and ESXi were offered for free. Yes vSphere 4 builds on this, but the promise was made when ESX v3 was released.

Over the last few years I have seen more and more small organizations like Doctor’s offices turning to virtualization. They do this to cut their electrical costs. The last place a Doctor tends to invest is into IT.

I think vSphere 4 as critical new tools for the Enterprise and some specific SMBs, but in general, they like what was already available. Now that is improved.

Evolving Solutions:.
Wild Card: Anything else you’d like to add?

Edward L. Haletky:
Visit www.astroarch.com/wiki/index.php/VMware_Virtual_Infrastructure_Security for the latest information on my latest book “VMware vSphere(TM) and Virtual Infrastructure Security”, which is now available in a pre-edited version on Rough-Cuts.

Is Green IT The Answer?

Last month, we at Evolving Solutions celebrated Earth Day.

In the spirit of the day, I conducted an online search on Green IT to see how others in the industry are discussing green initiatives, and found the excellent post, “Saving Green by Being Virtually Green,” by Lilac Berniker.

“The focus of IT departments has shifted palpably in the last few months. Until last year, their focus was on becoming more environmentally conscious and making concerted efforts towards ‘greening the datacenters,’” begins Berniker.  ”Today, the entire focus is on cost savings, cost avoidance and cost deferment. Few organizations realize that virtualization can be a critical link to creating a utopian world where IT can lower costs while at the same time be more green.”

So, can data center cost saving strategies, like server and storage virtualization, transform our world into the utopia envisioned by major proponents of a green lifestyle?

The answer is a resounding ‘maybe.’

Despite its name, Green IT’s focus is almost entirely on cost-savings.  However, when someone offers Green IT as a solution, many see this as trusting a vital part of your business to a faddy, green movement.

A business’ fundamental purpose for existing is to be a profitable entity, and part of what’s keeping this entity alive is a robust, efficient IT infrastructure.  While many businesses have implemented green initiatives, these initiatives are secondary, and more philanthropic than fundamental.

The reason why few organizations realize that Green IT, or initiatives like server and storage virtualization, can be beneficial to the environment is because this is not their fundamental purpose for existing.

Hence the revised focus on selling Green IT as a cost saving initiative.

So, will Green IT save costs?

Absolutely.  The idea behind green IT is lower power costs, essentially.

Will Green IT be beneficial to business?

Yes.  Solutions like server and storage virtualization, while using less power, bring with them the added benefit of more efficient IT processes, leading to a more efficient business altogether.

Will Green IT make our world a better place to live?

Likely so.  In using fewer resources, it would not be out of line to suggest that we are collectively reducing our impact on the planet.

When someone mentions Green IT in your organization, realize that while its benefit towards the greater good for our planet remains to be proven beyond a doubt, its benefit to your business is not the least bit in question.

Businesses today are finding themselves on a predatory quest to cut costs now, and in some cases, think about the ramifications to efficiency later.  Remarkably, strategies designed to lower data center costs are simultaneously designed to increase efficiency.

Evolving Solutions has gathered insight from top industry thought leaders designed to help our readers lower data center costs and improve efficiency.  Thought leaders, including Microsoft Global Strategist Toby Velte and FOCUS Consulting President Barb Goldworm, have contributed their insight to the Data Center Leaders interview series.   Below, are 5 data center cost avoidance tips from our thought leaders:

1.    Completely Reevaluate The Management Of Your Data Center: Today’s advances in technology, particularly green IT initiatives, offer tremendous potential to minimize consumption of current resources.  Per Microsoft Global Technology Strategist Toby Velte,  by reevaluating data center needs, including how much storage and speed is truly necessary, companies will become armed with the knowledge necessary to achieve sustained data center cost reduction in future projections.

2.    Server and Storage Virtualization: In the long run, virtualization is best for sustained cost reduction, states Omar Sultan, Senior Solution Manager for Data Center Switching at Cisco.  Virtualization, replacing physical servers with a virtual environment, lowers the total cost of server infrastructure, thereby lowering the total energy costs of a business overall.

3.    Move to Blade Systems: Blade systems, self-contained computer servers designed for high data density, can increase your efficiencies in power and cooling, per Barb Goldworm, President and Chief Analyst at FOCUS Consulting.   The amount of servers common in a data center have oftentimes led to power consumption concerns as these large servers must run in a temperature controlled environment.  By minimizing the heating and cooling costs necessary for a  data center, blade centers minimize the heating and cooling costs for a business as a whole.

4.    Go Green: “Organizations are finding that there simply is no more power available to them unless they pay to build the generation plants necessary to support them,” shares Dan Kusnetzky, ZDNet contributor and founding partner of the Kusnetzky Group. It can be tempting to see the green movement as just another fad, but at the end of the day, it is about saving power costs by utilizing more energy efficient technology, such as virtualization, and little else.

5.    Have a Disaster Backup and Data Recovery Plan: “If your server room imploded, what would you do?” asks Susan Snedaker, Principal Consultant with VirtualTeam.  The likely answer is, you would pay – and pay any amount – to get your critical data back.  Disasters happen, and to recover will cost money. By developing a disaster backup and data recovery plan in advance, however, companies can mitigate much of the desperation costs involved with recovery.

Offered to steer your business in the right direction, the cost avoidance tips provided in our Data Center Thought Leaders interview series illustrate ways your businesses can achieve cost cutting initiatives without sacrificing efficiency or productivity.

If you have more tips to share, we welcome your insight and invite you to share via a comment below.

Neil McAllister at InfoWorld wrote a great piece recently titled “Server Virtualization Under The Hood.”

Beyond offering insight purely on the benefits of server virtualization, McAllister takes the time to define and offer historical perspective on this burgeoning solution.

McCallister begins with an excellent definition that simplifies the idea of server virtualization, stating:

“Virtualization is a solution that basically fools an operating system (and any applications that run on top of it) into thinking the virtual machine is actual hardware. Running multiple virtual machines can fully exploit a physical server’s compute potential – and provide a rapid response to shifting datacenter demands.”

The benefit of virtualization is essentially this:  as a physical server will cost business capital to run, and only have so much computing power, it makes sense from both a financial and technical standpoint to minimize its inherent limitations and enable  virtual servers to shoulder the work.

As McAllister alerts us, the concept behind virtualization is not a new one.

Individual computers have been running multiple instances of operating systems simultaneously as far back as the 1970s.

What is new, however, is the feverish pitch surrounding virtualization as it has made its way into the general business lexicon as a cost-saving and efficiency enhancing solution.

For those seeking more detail on the different types of server virtualization available, McAllister defines the advantages of those most typically in play today:

• Full virtualization – allows nearly any operating system to be virtualized without modification
• Para virtualization – similar to full virtualization, but offering greatly improved response time for virtual servers
• OS-Level virtualization – an architecture that uses a single, standard  operating system across all virtual servers providing even greater speed

If you are considering implementing a server virtualization solution, more important than the different types of solution are the benefits your company will receive from the solution.

To get to the heart of the ultimate benefits of server virtualization, assess your IT solution needs by asking yourself questions like:

• Are you seeking primarily to reduce data center costs?
• What type of response time is necessary to ensure IT efficiency?
• What are your data capacity requirements?
• What is your timeline for implementation of a solution?

In the end, any IT solution, including server virtualization, should be looked at and discussed through the lens of its end-benefit to your business.

This is perhaps the most important idea to keep in mind when looking under the hood of any new solution.

From too many physical servers to server provisioning processes that can stretch for weeks, many clients we work with at Evolving Solutions describe similar symptoms when detailing the data center inefficiencies they are striving to solve.  Oftentimes, the solutions we architect and deploy will immediately and significantly reduce the money and resources that for years had gone into working around these inefficiencies.

United Sugars Corporation, and parent company American Crystal Sugars Company first contacted Evolving Solutions describing the lengthy server provisioning process experienced by their IT professionals.

United Sugars and American Crystal manage a nationwide sugar supply chain, all via massive data centers.  When it came time to upgrade the tracking software applications within these data centers, the necessary server provisioning process stretched nearly two weeks and cost thousands of dollars.

We architected and deployed a server virtualization for United Sugars and American Crystal that reduced the two week server provisioning process in the companies’ data centers to a ten minute upgrade.

In doing so, we enabled the IT professionals at United Sugars and American Crystal to focus more time on mission critical tasks, including upgrading a disaster recovery process.

We’re very proud of the solution architected for United Sugars and American Crystal (we even won a Beacon Award for it!) and are happy to share with you the full server virtualization success story via a complimentary download.

Virtualization Expert Cisco's Omar Sultan

Bottom-line, companies today are looking for any way to decrease costs.  Cost savings strategies currently being implemented by many companies include upgrading data centers by leveraging solutions such as server, storage and network virtualization.

Evolving Solution’ Data Center Leaders interview series turns its attention back to the subject of data center cost avoidance this week in our interview with Omar Sultan, Senior Solution Manager for Data Center Switching for the Cisco Data Center Solutions team.

Sultan has over 25 years of experience in the IT industry working work for a number of Fortune 500 companies. Prior to joining Cisco, Sultan developed a broad range of experience ranging from data center management to network operations.  A member of Cisco’s team since 1999, Sultan’s current responsibilities center on the Cisco data center switching portfolio.

In our interview with Sultan below, we discuss how server, storage and network virtualization can lower data center costs today and look into our crystal balls to determine what solutions may be on tap for the future:

Evolving Solutions:
What tips would you offer for business seeking to reduce data center costs?

Omar Sultan:
I think, in the long run, server, storage and network virtualization is the best bet for sustained cost reductions. Technologies such as VMware or Hyper-V can be enormously helpful in reducing the cost of server infrastructure.  Similarly switch virtualization technologies such as virtual device contents (VDC) and virtual port channels (vPC) on our data center switches can simplify network infrastructure.

So, these technologies can save you CapEx up front, but they open up a second area of savings by reducing OpEx–less infrastructure will lower costs around power, cooling, cabling and rack space.

Unified fabric would be another example of both reducing upfront costs and setting the stage for sustained savings. Virtualized infrastructure is also simpler to manage, so that opens up another avenue of savings–increased productivity of your operations staff.

This brings us to the second area, which is improved operations efficiency.  While this is often viewed as “soft” savings, the truth is the people are often still the biggest single budget line item so anything that can be done on this front is important, whether it is improved management and automation tools or a more efficient organizational structure.

Evolving Solutions:
Are there inherent dangers in trying to make your data center too cost efficient?

Omar Sultan:
With a few exceptions, customers are telling us that their year-over-year budgets are flat to declining, so I am not sure “too efficient” is an issue.  I think the bigger risk is not being able to provide support to the business in the areas it needs–and these days, that especially means areas that impact the top line.

Things like energy efficiency and server, storage and network virtualization help drive budget efficiency–they let you target spending where it does the most good.  They also give you more efficient and flexible access to you IT resources so you can run a leaner provisioning model (i.e. less over-provisioning) without running the risk of being caught flat-footed if the business buts some kind of unexpected demand on the IT infrastructure.

Evolving Solutions:
What products or solutions do you envision reducing data center costs 5 years down the road?

Omar Sultan:
If we fast forward 5 years, I think we will continue to see the existing virtualization trends mature–I think they will be fully mainstream by them and will be the de facto operating environment for most companies.

I think we will see a sea change in management in the next five years, with greater use of automation and the introduction of more holistic management models, which will further drive up operations productivity and reduce the costs associated with management and operations.  I also think we will see a continued evolution and maturing of cloud computing as a solution to the point that enterprise companies will start designing their facilities to handle more typical loads and rely on cloud providers to help weather peak load situations.

Server Virtualization Expert Dan Kusnetzky

Server virtualization is gaining mainstream awareness in the business continuity as a viable strategy for data center cost avoidance.  As such, this week’s post in Evolving Solutions’ Data Center Leaders interview series shares best practices regarding server virtualization to those companies who have either just implemented or are planning to implement this solution.

Offering insight on the subject is Dan Kusnetzky.  Kusnetzky, along with Paula Rooney, posts regularly to ZDNet’s Virtually Speaking and is a founding partner of the Kusnetzky Group. Since the late 1970’s, Kusnetzky has been involved with information technology, including his work with the Kusnetzky Group, as executive vice president of corporate and marketing strategy for Open-Xchange, and as vice president for IDC’s System Software.  At IDC, Kusnetzky was responsible for research and analysis on the worldwide market for operating environments and virtualization software.

In Evolving Solutions interview with Kusnetzky below, we discuss best practices for companies regarding server virtualization:

Evolving Solutions:
What tips would you offer businesses who’ve just implemented server virtualization?

Dan Kusnetzky:
I’d say “Whoa, big fella (or lovely lady in the case of a female executive). I’d ask them what their overall plan was to deploy virtualization technology and how that fits into their overall IT plan.  If all they’ve done is install virtual machine software from VMware, Citrix, Microsoft, Virtual Iron, or through one of the distributions of Linux, they may have unknowingly stepped onto a slippery slope that leads to big problems. After all, virtualization technology includes access virtualization, application virtualization, processing virtualization, storage virtualization, network virtualization and both security and management in that environment.

Evolving Solutions:
What are the biggest mistakes companies make after implementing a virtualization initiative, and how can they be avoided?

Dan Kusnetzky:
I’m often surprised that executives who have grabbed onto virtual machine technology as a panacea don’t have a clear understanding of the following:
•    What applications and application components are running on what physical and/or virtual machines?
•    What are the dependencies among these components?
•    How do these components relate to both the network and storage infrastructure?
•    Who is responsible for managing each component, for the underlying physical machines, for the underlying network, for the underlying storage? Do they know one another? Do they have effective processes in place to pass issues to one another for resolution
•    Do the organization’s license management and support policies have a way to deal with easily copied virtual machines that could, in the end, be updated at different rates.
•    Have failure scenarios been explored and plans been created to address what happens if a physical machine, a disk or a network router fail.
I could go on and on about this. One clear message to remember is something Alan Lakein once said “Failing to plan is planning to fail.”

Evolving Solutions:
In “Has Virtualization Jumped The Shark”, Data Center Central’s Arthur Cole negates the idea that virtualization is losing its luster as little else brings more IT value to an organization.  How would you respond to the idea that virtualization is losing its luster in concurrence with its increased awareness?

Dan Kusnetzky:
Virtualization, taken as a whole, has been in use for well over 30 years in the world of mainframes.  It has been in use for well over 20 years in the world of midrange systems. I expect the technology to be of as lasting importance on industry standard hardware.

What’s likely to change, however, is the giddy feeling about virtual machine technology being the be all and end all of datacenter technology.

Evolving Solutions:
Five years down the road, how do you see virtualization evolving, and what other solutions do you feel will make the leap towards mainstream awareness currently being experienced by virtualization?

Dan Kusnetzky:
I expect that many will realize that a virtual environment (virtual access, virtual application environments, virtual processing environments, virtual storage environments, virtual network environments and the necessary security and management tools for those environments) has many of the same characteristics as a purely physical environments and some strikingly different characteristics.  For example, it is quite possible for a virtual server to run in one part of the datacenter in the morning, a different part of the datacenter in the afternoon and might be assigned to sleep on a disk somewhere overnight. People simply can’t do that with a physical machine.

Functions can be replicated for performance, scalability or reliability reasons. Functions can be replicated for development and testing as well.

Evolving Solutions:
Your post on ZDNet’s “Virtually Speaking” titled “The Green Datacenter” is the latest in a series describing how virtualization can ensure data center energy efficiency.  In your experience, is energy efficiency a driving force for companies to implement virtualization, or a secondary force?

Dan Kusnetzky:
This is a big issue in places in which organizations have found that there simply is no more power available to them unless they pay to build the generation plants It is also a big issue when organizations have no more floor space for computers, storage, networking equipment, power supplies and cooling equipment. It is a secondary or, perhaps, tertiary issue in other places.

It is clear to me that it will become an ever more pressing issue in the coming years.

Evolving Solutions:
Wild Card: Anything else you’d like to add?

Dan Kusnetzky:
As an alumni of Digital Equipment Corporation (may it rest in pieces), I’m convince that building an architecture and then bringing products in that fit the organizations architecture is better than being product driven.  There are times that an organization would be best advised to ignore a specific product or technology because the disruption it would cause far outweighs the value it provides.

Virtualization Expert Barb Goldworm

Evolving Solutions Data Center Leaders interview series continues into the new year below in our interview with Barb Goldworm, President and Chief Analyst of FOCUS and author of Blade Servers and Virtualization: Transforming Enterprise Computing While Cutting Costs. Barb has spent over 30 years in the data systems and storage arena has published articles extensively since the 1990’s. Barb is a frequent speaker at industry events and was recently ranked as one of the top 3 knowledge expert speakers at Storage Networking World’s Global Conference Series.

In Evolving Solutions interview with Barb below, strategies including moving towards green IT and implementing server virtualization are discussed as potential avenues pointing towards data center cost avoidance.

Evolving Solutions:
What tips would you offer for business seeking to reduce data center costs?

Barb Goldworm:
There are a number of technology areas today that offer significant value in reducing total cost of ownership, with an excellent return on investment.

At a high level, virtualization across the entire infrastructure can reduce costs, especially on the opex side – reducing space, power, cooling, hardware, maintenance and management costs. Green computing overall also can contribute major cost reductions, due to the reduction in power and cooling costs. Moving to blade systems can also increase your efficiencies in power and cooling, as well as reducing space and decreasing cabling costs. Other specific areas in storage that can allow information growth while getting more out of storage resources would include features such as data deduplication and thin provisioning.

Evolving Solutions:
Are there inherent dangers in trying to make your data center too cost efficient?

Barb Goldworm:
As with anything in IT, there are trade-offs, and finding the balancepoints between efficiency, cost containment and flexibility is a challenge. Likewise in terms of capacity management, finding the balancepoint between underprovisioning and overprovisioning is really the goal.

Evolving Solutions:
Your book, Blade Servers and Virtualization: Transforming Enterprise Computing While Cutting Costs was published in 2007.  In the year since its release, what would you point to as the most major innovation in virtualization?

Barb Goldworm:
The biggest innovation has probably come in the area of I/O virtualization with advances such as HP Virtual Connect and IBM Open Fabric Manager. The other key improvement is that blades have increased in horsepower – cpu, memory and number of NICs/HBAs, making them an even better platform for running virtual servers. There are also now a variety of purpose built blades and chassis for key areas including virtualization and SMB environments.

Evolving Solutions:
Server virtualization has been gaining recognition in the mainstream as a data center cost avoidance solution.  What other products or solutions do you envision reducing data center costs 5 years down the road?

Barb Goldworm:
Desktop and application virtualization are now coming into their own in terms of cost benefits (particularly with some recent and upcoming enhancements) and will be even bigger than server virtualization in the long run.

Mobility advances will also play a key role in changing the way IT works, which will have both costs and benefits, and major productivity advantages. The other longer term change will be the incorporation of cloud computing into the enterprise model, including functions like bursting to the cloud, which can have big cost benefits.

Evolving Solutions:
“Green IT”, like server virtualization, has at its heart reducing data costs, but is becoming a hard sell as many see it only as a “hot topic”.  How would you recommend selling the idea of green IT to upper management?

Barb Goldworm:
Green IT has huge financial benefits, but often the benefits (reduced power and cooling) fall into the facilities budget.
The costs (virtualization and moving to green hardware like blades and other newer green servers and storage) fall in the IT budget.

Success comes when the two organizations work together at the upper management level and see the overall benefit to the corporation. In a way, green IT is a great way to fund the move to a new virtual infrastructure running on new and improved modular hardware.