We’ve discussed the topic of data center energy management in numerous posts, and we’ve talked about a Green Data Center Maturity Model.  If the topic of energy efficiency in the data center is of interest to you (and it should be) I’d like to recommend an excellent resource for you.

Cisco is conducting a webinar next Thursday, 8/21/2008 focused on the topic of data center energy efficiency.  This will be available online for free.   I had the pleasure of viewing the entire feature in advance of the public release, and the relevance of the content to this topic make this an hour well spent.  You can see a preview now at this link.

In this webinar, you will hear a great overview of the current state of this problem and some history explaining how we got to this point.  You’ll be introduced to some free resources for analysis and planning of energy efficiency in your data center, including planning for carbon footprint targets.  Also included are descriptions of new developments in storage, switching, and server technology as related to energy efficiency.  It even features Doug Gourlay, and who doesn’t like to hear Doug talk (there’s a plug for you, Buddy)?  In short, this hour contains a wealth of quick-hit information that should be top-of-mind for anyone tasked to address this problem.

To participate in the webinar you’ll need to register here.   Another page with the preview video and links to related white papers can be found at this site.

I recommend you watch the webinar and I hope you find it useful.

So many discussions with prospective Clients begin with the subject of data center tier ratings.  Many companies are struggling with data center facilities that no longer adequately serve their Business, and are seeking a path toward better scalability, availability, security, and lower cost of ownership.

In the mid-market segment, while there are exceptions to the rule to be sure, most often I find enterprise data centers that are in need of help.   The staff supporting these spaces is always top-notch and very committed to doing the right thing all the time, but an accumulation of circumstances has created a data center environment in which few would be proud.

While we could talk about many problems nearly universally found in these enterprise data centers (hint- MEP capacity limitations, cable-clogging under raised floors, thermal management,…), the problem most often mentioned by the CIO has to do with the misalignment of the data center tier rating to the Business.

What do we mean by saying that the tier rating is misaligned with the Business?  Well, for the purposes of most conversations in this context, the higher the tier rating of the facility, the higher level of availability afforded to the data processing environment.  Businesses that operate across multiple time zones, that do business globally, are involved in financial transactions, operate 24-hour call centers, or that incur significant financial penalties for violation of stated customer service levels, require high availability facilities.  These businesses need to have their systems and data available around the clock.  The data center facility is the foundation upon which any high-availability data processing implementation stands.  When the facility fails, the impact to the Business is substantial.

Most mid-market data centers that we encounter in this situation are Tier-1 facilities.  A Business that operates with the parameters mentioned above is simply not well served by a Tier-1 or Tier-2 facility.  There’s simply too much revenue at risk.  This is what we mean by saying there is a misalignment between the tier level of the facility and the Business.  Executive management usually knows this, or they strongly suspect it.  They ask for help in charting the course from where they are today, to a Tier-3 or Tier-4 facility.

In many cases the answer to this question is, “you can’t get there from here,” or said another way, “you can’t get there if you stay here.”  Moving from even a Tier-2 to a Tier-3 is a step that bridges a very wide gap, and oftentimes the architecture or setting of the existing facility presents a roadblock in the path.   Let’s discuss just one or two factors to elaborate upon this point.

Space is often a limiting factor in elevating the tier level of an existing site.  All three dimensions come into play.  The X-Y dimensions are most obviously limiting because of the boundaries placed on the extent to which we can place “stuff” on the floor.  A Tier-3 facility, for example, typically requires an equal amount of square footage for the MEP infrastructure as the IT space itself.  Often, there simply is not enough empty space to sufficiently accommodate the MEP equipment room, nor the distribution infrastructure that accompanies the added redundancy of MEP systems.  This becomes an exercise in “squeezing a balloon” - squeezing the air on one side only makes it pop out on the other side.

Another limiting space factor is the floor-to-ceiling clearance in the Z dimension.  If you’re using the raised floor as a cool air plenum, then the higher tier facilities will need deeper raised floors.  If your building has a 12 foot ceiling clearance, and you plan on a 36 inch raised floor, you’re out of space for racks and cable management.  This is also a factor that often disqualifies core/shell properties for consideration as a new data center.

The space around the building and the environment in which it’s located is another important factor.  If your existing site is in an office park, near a residential neighborhood, or otherwise influenced by zoning you may not be able to install (or operate) the necessary generator and chiller equipment near the building.  The fuel storage requirements of the generators may also present a problem.   Beyond zoning restrictions, it’s important to consider the space that this equipment occupies and the impact that has to other uses of the property (e.g., parking).

Physical security and location-based risk factors must be considered as well.  If the business activity justifies the need for a high tier data center it probably also deserves robust physical security.  Adequate perimeter fencing and physical access control is difficult to accomplish in many typical business settings.  Proximity to major highways, rail lines, air traffic landing approach paths, and so on present risks that need to be balanced against investment in secure facilities with high-value assets.

These are but a few of the issues involved in this decision.  Of course there are many other factors  including cost projections, component lead times, architectural factors, resource requirements, compliance, technology, security, and of course TCO and long term value to the firm.  Some are obvious and others are nuanced.

When the answer to the question, “Can I raise the tier level of my data center” is “No,” the firm must then consider a broader set of roadmap options including collocation, hosting, outsourcing, buy, buy/build, and build-new.   When considering the investment to improve the tier level of data center facilities, careful and thorough assessment is necessary to support the decision process with substantive, credible, and actionable data.

In April we predicted that this would be the break-out year for container data centers.  In July we posted more information about container data centers when we were working MEP cost models for container-based facilities.  The year is half over now, and though the “break-out” has yet to happen there have been some very notable developments that deserve discussion.  Let’s start here by reflecting on those things that make container data centers interesting for enterprise IT.

Features and Opportunities

Agile IT is critical in order to meet the dynamic demands of the Business today, and in this respect, containers can be a valuable weapon in the arsenal.  Containers bring agility in several ways. 

First, they can be mobile or not.  This delivers a capability to quickly implement a substantial data processing footprint (because container data centers are very dense in CPU, disk, or both) where it’s needed, and to consider that placement of data processing as either temporary or permanent.  This temporal implementation opportunity is a feature of containers that has endeared Disaster Recovery planners.  In fact, some executives at container manufacturers have publicly stated that DR is the key market for containers.  I think that geographically diverse multi-site enterprises (e.g., chain big-box retail) are a great application for a mobile DR capability.  While surely there’s interest within the DR market space, I think it’s important to be broader minded toward more active roles within the enterprise.

The mobility aspect is a key advantage too, for applications in which lots of processing power has to be relocated often.  Military and Homeland Security applications are a perfect example of this.  My posts about the cargo ship data centers and the use of containers for on-deck IT space show a rather natural environment for containers in the mobility context.

The modularity of container data centers is another interesting feature that brings opportunities for the enterprise.  Containers can be a solution for an enterprise whose data center facility has run out of space but circumstances do not permit immediate relocation or construction of a new facility.  I see examples of this very frequently.  I also think that this modularity has a role in planning new data center facility construction, as a mitigation of the risk of overbuilding (which is also quite real).

On this point about designing facilities around the container data center concept, the Microsoft Chicago data center is the most public example.  I’ve been collaborating with data center construction partners on this topic too, and so far we estimate that the MEP implementation costs are more or less on par with one another, when comparing equally capable facilities with a traditional model versus one in which the raised floor is delivered through a collection of containers.

New Product Developments, but Buyers Remain on the Sidelines

The continued development and steady release of products in the container data center space shows that there’s strong confidence in the market opportunity for these products. 

Hewlett-Packard introduced the HP Performance Optimized Data Center (HP POD).  HP is known to do an exceptional job with product development and the fact that the POD is said to accommodate 3^rd part equipment as well as HP’s own, this could be a formidable player on the field.  I don’t know of any POD implementations (or sales) at this writing.

We’ve also seen a European player enter the game.  Lampertz released the Outdoor Room container data center.  Leveraging their pedigree in physical security, the differentiator for the Outdoor Room is the WK II burglary and fire class B1 protection, as well as a stated resilience to water and dust.  In addition, EMP protection and even handgun and rifle ammunition tolerance is available.

Sun continues to market its product, the Modular Datacenter S20 (MD).  Dell continues to talk about its container product, but as best I can tell this is still in development.  We’ll look forward to that release as there are some interesting MEP features included.   IBM is pushing the Portable Modular Data Center (PMDC), which is offered in more than one physical format.  We’ve discussed IBM’s efforts in this area in earlier posts.  The Verari FOREST container data center is mentioned in discussions, but from what I can tell there’s very little momentum there.  My repeated calls to Verari sales in this area have all fallen as unreturned voice mail, even after polite escalation at Verari corporate.

The product that seems to have the most wind in its sales still seems to be Rackable’s Ice Cube.  Between Rackable and Sun, it seems progress has moved beyond the tire-kicking stage and perhaps one or both of these manufacturers will create the break-out we’ve expected.  A big advance for Rackable in my opinion is their recent partnership with IBM to equip Ice Cubes with BladeCenter equipment as an option.  While Rackable is a leader in high density, low power data processing equipment, enterprise sales would be challenged by IT departments already wedded to the 2-3 letter acronym hardware vendors.  This is a big deal in my view, and kudos to Rackable for advancing in this area.  Rackable has also been identified as the container provider for IDS’s cargo ship data center fleet that is anticipated soon this year.

In summary, the momentum around containers continues to build and the opportunities we saw earlier still exist and in fact are becoming even more tempting.  Time will tell what development or critical mass is necessary to break the ice and create the sales activity to keep this ball rolling.

IDS continues to see the ship-based data center concept as a lucrative opportunity, given the continued demand for data center space, the notion that ship-based data centers can reduce the time to market by as much as 65% and that the Cap-Ex is estimated to be a third less than a comparable brick and mortar facility.

We talked in the earlier post about the potential Green opportunities with this concept, leveraging the massive on-board (bio-diesel fueled) generators and use of ambient sea water for cooling.  IDS now adds that since the ship does not need access to transmission lines there is greater efficiency through elimination of transmission loss, does not use in-ground fuel storage tanks, and the fact that they are salvaging cargo ships that would otherwise be scrapped.  That final point is perhaps a reach, given that retired ships are often used for recycled steel anyway.

I did find the point interesting that, with the first vessel to be docked in San Francisco, this concept provides a degree of earthquake tolerance, since the ship itself is unaffected by earthquakes.  That’s an advantage I hadn’t thought of before and is an interesting option for metropolitan areas subject to those sorts of events.

Besides the updates from Silverback and IDS, I’ve also learned that it’s likely that the Container Data Center units installed on-deck will be Rackable’s Ice Cube.  This is another feather in the cap for the Ice Cube and Container Data Center applications in general.

IDS is still in the hunt for Customers, so if you’re in need of trend-setting data center space in San Francisco there’s still time to climb aboard (oh no, another pun).

Many companies are aggressively consolidating data centers as one way to address this demand.  There are a number of significant cost savings opportunities with data center consolidation, in spite of the complexity involved in successfully executing a consolidation plan.  Many of those, in turn, come from savings due to increased efficiencies of operation as compared to the pre-consolidated state of affairs.  In particular, we’re talking about efficiencies from removing redundancy of maintenance costs, and centralized control of operational and support expenses.

Forrester came up with the term “MOOSE” to represent the combined categories of cost to maintain and operate the enterprise.  I’m unsure about the exact wording comprising the acronym.  I’ve seen Maintain and Operate the Organization, Systems and Equipment.  I’ve also seen Maintenance, Operation, and Ongoing Support Expenses.  It’s clear what we mean here, regardless of the exact assembly of words for the acronym.  Companies have their own tribal terms for this too.  I’ve seen firms simply call it Keeping-The-Lights-On (simple enough), and one that uses “Ready To Serve” (must be some history there).  …‘But we digress.  I like the MOOSE term and its analogy when talking about IT Governance.

The MOOSE often represents as much as 70% of the IT spend.  This is a fact that those of us responsible for IT Governance joust with on a daily basis.  MOOSE costs are usually very difficult to trim.  It’s probably safe to say also, that a lot of your MOOSE lives in the data center.  Painting your MOOSE green is one way to positively impact this problem (so we’ve managed to bring the conversation back around now).  By “painting green” we of course mean addressing energy efficiency, carbon footprint, and sustainability of resources consumed in conducting operations.

Consider a few energy efficiency data points:

• On average, electricity costs are over 40% of data center operational expenses.
• The cost to power a typical server exceeds the cost to buy it, when viewed over a three-year horizon.
• On average, less than 50% of the air in a chilled-air data center actually makes it to the IT equipment

Consider a few security risk data points:

• Emerging carbon footprint regulations will expose companies to financial penalties for violating energy efficiency thresholds
• Emerging carbon footprint regulations are likely to impose consumption caps on local access to public utilities
• Customer service level agreements can be exposed to limitations on energy consumption or resource availability
• Newly imposed water consumption restrictions may limit enterprise IT growth or force investment in alternative MEP technologies

If you’re not saying, “yeah,… I know all that already” then these are issues that very soon will come to your attention.  This is a wave that’s gaining momentum and has entered the daily dialogue in data center operations and planning.  The good part of this is that because there’s so much discussion around this topic, there are lots of good sources from which to draw information.

We (in my practice at this company) have been working on a Green Maturity Model for data centers.  I’ll share progress on this in a separate post, but suffice to say that any given organization is going to be at some level of the green maturity curve.  Wherever your organization happens to be in this regard, our current soft economic climate is likely to stir the call of the MOOSE.  MOOSE are difficult to control, and embarking on a plan to turn your MOOSE green may be a way to answer the call.

For those of you who are regular visitors to this blog, this topic may seem rather basic.  However, I was recently asked to write an article on this subject and thought that if it’s good enough for that venue then perhaps someone will find benefit in reading here as well.  So here are some highlights from that piece-

Clients often come to us for help with data center consolidation or new data center implementation projects.  The discussion quickly comes around to the appropriate “Tier Level” for their IT facilities.  What we’re talking about here (to a large extent) is an industry standard way of describing the availability of the data center facility.  Availability, in this case, is referring to the degree to which the facility can support constant uninterrupted operation of the contained data processing systems. 

We know that the systems themselves can be architected with high-availability configurations.  Autonomous failover of network connections, clustered server environments, and so on are ways that the systems can sustain operation even if, say, a server crashes.  What the Tier Levels of a data center refer to though, is the capability of the facility itself to support the systems it serves.  Utility power can fail, the temperature in the building can rise to cause damage to equipment, and so on.  These are facilities issues, and are the foundation upon which any amount of data processing fault-tolerance stands.

A bit of history on standards for data center facilities

As with most areas of business, we rely on industry standards as reference-able qualifications and guidelines to avoid the dangers and ambiguities of qualitative references.  Instead of, “very robust,” “fully fault-tolerant,” “top notch,” or “Class-A,” we use industry standards to articulate quantifiable guidelines for exactly how “top notch” a certain thing really is.

The American National Standards Institute (ANSI) and the Telecommunications Industry Association (TIA) are examples of organizations that formulate standards for the industry to follow.  The TIA developed a specification entitled TIA-942: Telecommunications Infrastructure Standard for Data Centers.  This is perhaps the most widely referenced standard when talking about data center facility availability.  From the title one might be inclined to think this is a specification of telecom for data centers.  It is that, but it’s much broader than that including cabling, space layout, site selection criteria, and infrastructure tiers/availability.  This last point, represented by Annex G in the TIA-942 standard, is where all the talk about data center tiers comes from.

As it turns out, the TIA relied upon an organization called The Uptime Institute (or, ‘The Institute” for short) to develop this part of the standard.  The Institute’s charter is to provide research-based information on high density computing and mission critical facilities in a vendor-neutral manner.  As such, the Institute has become the industry’s trusted source of information in this regard.  The Institute continually gathers benchmark data by surveying existing data centers and data center projects.  Its research includes models for estimating implementation costs and Total Cost of Ownership (TCO) for data center projects.

Perhaps the one piece of research that most strongly defines the Institute’s work is the definition of tier classifications for data center performance.  This is the definition of the four-tier system for classifying Data Center capabilities.  Thus, when we hear people speak of, say, a “Tier-4 Data Center,” they are referring to the tier classifications from TIA-942, or the Uptime Institute.

The Tier Classifications for Data Centers

The tier classification model provides an objective basis for comparing or describing the functionality, capacity, and cost of a data center’s facility architecture.  In particular, the tier classification model is focused on the Availability of the facility itself, and is driven by the infrastructure to power and cool the data processing environment.

The power and cooling capabilities of a facility are delivered by its Mechanical, Electrical, and Plumbing (MEP) infrastructure.  The Mechanical systems provide cooling to the environment in which the data processing equipment is installed.  It is comprised of air handlers, air conditioners, chillers, plenums to channel air flow, and so on.  The Electrical systems provide the power to the data processing equipment.  It is comprised of the utility service to the facility, transfer switches, generators and Uninterruptible Power Supplies (UPS), batteries, Power Distribution Units (PDUs), load banks, breaker panels, copper cabling, and so on.  The Plumbing systems support the Mechanical and Electrical systems by routing cabling, air, water, fire suppression gases, and so on.  There are multiple plumbing circuits in the facility and is analogous to the vascular system of the building.

Very simply put, the tier classifications refer to the degree of resilience the facility has to failures of MEP systems.  Resilience to failures is provided by redundancy and topology of the infrastructure design.  In the tier classification model, a Tier-1 facility is the least resilient and a Tier-4 is the most resilient.  Said another way, a Tier-1 facility has the lowest availability and a Tier-4 has the highest availability.  Said yet another way, a Tier-1 facility carries the highest risk to the business and a Tier-4 carries the lowest risk to the business.

Let’s discuss each of the four tier levels and compare their capabilities:

Tier-1:  Basic Data Center Infrastructure

A Tier-1 facility has no redundant capacity components.  It provides basic power and cooling to the data processing footprint with no excess capacity for backup or failover, and has no redundancy in the MEP distribution paths.

In this type of facility, any unplanned outage or failure of a capacity component or distribution element will impact the data processing equipment and end-users.  Whenever maintenance is needed for the MEP infrastructure (utility work, replacement of components, certification testing, preventative maintenance, and so on) the impact is just as if there were an unplanned outage.  All systems and users are affected.

Per Institute benchmark data, Tier-1 sites typically experience two separate 12-hour site-wide shutdowns per year for repair work.  In addition, Tier-1 sites typically experience 1.2 equipment or distribution component failures on average each year.  Statistically, this means 28.8 hours of downtime per year, or 99.67% availability.

What kind of business is suited for this type of facility?  In general, a Tier-1 facility is suitable for small businesses or start-ups where IT is an enhancement to internal business processes, where the principal use of web-presence is for passive marketing, or where there is no enforceable financial penalty to customer quality-of-service commitments.

Tier-2: Data Center with Redundant Capacity Components

A Tier-2 Data Center has redundant capacity components, but only a single non-redundant distribution path serving the data processing equipment.  The benefit of this level is that any redundant capacity component can be removed from service on a planned basis (e.g., for preventative maintenance) without causing the data processing to be shut down.  However, an unplanned outage or failure of any capacity component or any disruption to the distribution path may impact the computer equipment.

On average, Tier-2 sites have one unplanned outage per year, and schedule three maintenance activities over a two-year period.  The annual impact to operations is 22 hours of downtime per year, or 99.75% availability.

Businesses appropriate for Tier-2 facilities are small businesses whose IT requirements are mostly limited to traditional 9-5 business hours, companies without serious financial penalties for customer quality-of-service commitments, services without real-time delivery obligations, and call centers with multiple sites.

Tier-3: Concurrently Maintainable

A Tier-3 Data Center has redundant capacity components and multiple independent distribution paths serving the data processing footprint.  There is sufficient MEP capacity to meet the needs of the data processing systems even when one of these redundant MEP components has been removed from the infrastructure.  In a Tier-3 Data Center, maintenance activities and certain unplanned events can occur without interruption to the computing systems.

Because of the concurrently maintainable characteristic of Tier-3 facilities, no annual shutdowns for routine maintenance are required.  This allows for very aggressive preventative maintenance programs to be implemented, extending further the operational duty of the MEP components.  The Institute has concluded that Tier-3 Data Centers have unplanned events totaling only 1.6 hours per year.  Tier-3 sites then, deliver 99.98% availability.

Notice that both the Tier-1 and Tier-2 levels deliver “two-nines” availability, but the step to Tier-3 delivers “three-nines.”  This is a big improvement in uptime, and comes with a cost as well, which we’ll discuss later.

Businesses appropriately supported by a Tier-3 Data Center are companies that serve both internal and external customers 24×7 and whose IT resources support automation of business processes, so that the customer impact of short shutdowns due to facility outage are manageable.  Tier-3 is appropriate for businesses that span multiple time zones and corresponding geographic diversity of employees and customers.  Businesses which have significant financial exposure due to customer quality-of-service issues are well supported by Tier-3 facilities.

Tier-4: Fault-tolerant

Tier-4 facilities have multiple, independent, and physically separate systems that each have redundant capacity components and multiple, independent, diverse, AND active distribution paths supporting the data processing footprint.  In a Tier-4 Data Center, any single failure of an MEP component or distribution path has no negative impact to the data processing systems, and the infrastructure automatically responds to the failure to prevent further impact to the facility.

Because of the degree of redundancy and fault-tolerance in Tier-4 infrastructures, facility-related failures that impact the data processing equipment are statistically reduced to 0.8 hours per year.  This yields 99.99% availability.

Companies that operate in international markets, with a “24 by forever” services commitment, and in a market space in which processes are continuous are well served by Tier-4 facilities.  This also includes businesses that are based upon market transactions, financial settlement, e-commerce, or where customer access to applications or employee access to IT is competitively advantageous.

Notes of caution about Tier Classifications

Those of us working in the Data Center and mission critical facility fields are very reliant on the TIA-942/ Uptime Institute tier classification guidelines.  Some additional background and words of caution are important to keep in mind as well.

There has been a temptation to stretch the definition of the Institute’s tier classifications.  One may hear of a “strong Tier-2″ Data Center or a “Tier-3 +” Data Center.  In actuality, there is no such thing.  The best one can conclude from those example terms are that the facility qualifies as a Tier-3 (in the case of a “Tier-3 +”), and has some other availability-supportive features.  If any single system in a Tier-n Data Center does not meet the Tier-n requirements, then the facility as a whole is not Tier-n.  There is no such thing as a fractional tier rating.

Similarly, one cannot “back into” a tier rating based on the empirical uptime of the site.  That is, if one has determined that a certain facility has been up a sufficient number of hours over a five year period to show a 99.95% availability, that in and of itself does not qualify it as a Tier-3 facility.  Furthermore, the tier rating is determined by capacity and topology of the MEP infrastructure.

Finally, a word or two about costs.  The cost of any mission critical facility is driven predominantly by the MEP infrastructure.  The power and cooling capacity necessary for the Data Center are the dominant drivers of cost in implementing a new facility.  This cannot be understated.  Similarly, because the tier classifications imply redundancy, the higher the intended tier rating, the higher the cost.  This is not a linear incrementing cost, and estimating the costs of a new facility project should involve your Data Center consultant.

Tier Classifications and your project

Data Center consolidation and Data Center construction or outsourcings are top of mind for many CIO’s these days.  Many companies have ‘90s vintage IT facilities that not only do not have the availability to align with the Business’ operating model but also are struggling to keep up with the power and cooling demands of contemporary computing systems.  The deployment of multi-core processors and blade-based systems has pulled the rug out from beneath many a facility manager.  The rapidly growing consumption and cost of energy due to the Data Center have caused many a CFO to define facility operational costs as an IT problem.

Whatever the motivation for your Data Center project, one will have to become familiar with the spirit of the TIA-942 tier classifications as well as the nuances thereof to exercise the proper degree of due care necessary in planning these very expensive projects.

Well, we’ve talked about data centers in salt mines, in abandoned ICBM silos, in renovated shopping malls, and now… on boats. ‘Big boats.

This one has been hard to get much information on, because the company is being stealthy about details. A firm by the name of International Data Security (IDS) has acquired a fleet of decommissioned cargo ships, and plans to outfit them as floating data centers. The first is said to be going online at Pier 50 in San Francisco imminently.

Before you say either, “Why didn’t I think of that?” or “These guys must be crazy,” consider the following points:

First, these ships are big and sturdy. ‘Really big. According to IDS, there’s 200,000 SF of space available below deck to use for IT floor and office space. These ships were built for carrying cargo containers, so guess what? That’s right; the space above deck can be used for even more IT space by dropping in container data center units. What a match!

Secondly, remember what makes these big ships move- really large diesel engines. You guessed it again. These can be repurposed as large generators. Using the ship’s massive fuel tanks (with bio diesel) these can provide operation without utility power for a full month. Wow.

Thirdly, what about cooling that 200,000+ SF of servers and storage? You guessed right again- sea water…. Right there all around the ship. The excess heat from the cooling water is to be pumped within the ship to warm crew compartments, which is intended to improve the efficiency of the mechanical systems but also to minimize thermal impact to the immediate area occupied by the vessel.

IDS plans to outfit 50 of these vessels in this way. Twenty-two of them are targeted for deployment in the USA and the others elsewhere.

Ok, so we get the point about the ready-made large space, the built-in generator capability, and natural source of water for cooling… but what’s the business case? Well, if you’ve not guessed already, there are a number of pretty compelling cases.

One obvious case is the idea of mobility for very large and dense computing footprints, either for disaster recovery purposes or primary facilities. The government vertical certainly has use cases for such a scenario.

Another case is the mundane benefit of having a data center nearby, but not taking up space on land. Customers in large coastal cities (e.g., New York, San Francisco) could make great use of such a facility docked at a nearby port. The idea of floating casinos in the Gulf of Mexico comes to mind as well. There are data processing activities that are restricted by state and local laws but still have an audience. Looking at this from the opposite direction, perhaps an offshore data processing platform could be a friendly island for more noble data processing applications that are otherwise at risk due to politics. Placing that data processing just offshore could be an answer someone is waiting for.

Speaking of borders and data processing, one has to wonder what sorts of international data storage and transmission laws would be encountered as a platform like this actually sails. I’ve stumbled over Patriot Act issues, for example, with Clients who have customers outside the USA but data centers inside the USA, and there are many national and international laws that would be encountered by this new capability.

Shiver me timbers, scurvy dogs,… intarstin’ t’ see how this goes.

Garrr.

In earlier posts and conversations, I’ve mentioned my interest in container data centers and the opportunities they bring for certain types of implementations and use cases.  As a big fan of agility in IT in order to meet the dynamic demands of the Business, containers can be a valuable weapon in the arsenal.

In my conversations with Clients about the applicability of containers to their data center roadmaps, I often find myself involved in philosophical debates.  Part of this is due to the newness of the technology as well as preconceived notions of use cases for containers.  Part too, is due to the real fact that containers are very strong solutions in some use cases, and more of a strategic option to be evaluated in others.

One could say that containers are at the same time very similar to and very different from conventional approaches to creating data center space.  The similarities and the differences are amplified depending on the features of the particular container in question (i.e., which manufacturer’s product) as well as from the intended programming of the data center floor space.  In order to consider the full range of options available through the use of containers, we have to consider the options of the (off-the-shelf) container fully and densely populated with servers and/or storage as well as the use of a container just as a (more capable) shell for IT floor space.

Let’s start with the easy one- how are containers similar to traditional data center space?  Well, for one thing, they can be viewed as just that- space.  This space comes in rather small, modular increments.  Current container products come in 20′ and 40′ flavors, so one could view this as say, 300 square foot (SF) increments of IT space.

That similarity carries a corresponding difference though, if you will.  Containers have at least some degree of MEP infrastructure on board that supports very high density IT yield of that space.  For example, Rackable’s Ice Cube container can pack over 22,000 cores in 1,400U over 28 racks (using Rackable System’s server hardware) in that 300 SF and has cooling capacity to spare.  Because of that built-in MEP capability, there are efficiency differences too in the way one would plan the overall IT floor.  Space that might be chalked up to inefficiency because of on-floor CRAH, CRAC, PDU’s, and so on would be calculated differently.  Because the container vendors out there now are all selling a range of product variations, and because one’s data center architecture plan can vary in its approach to MEP space versus IT space, it’s tough to say what that efficiency calculation ought to look like.  Suffice to say though, that it’s a different design approach to the IT floor when containers are involved (‘good question to throw at your data center consultant). 

When we focus on that subject of how the data center architecture allocates MEP and IT space, the conversation becomes even more philosophical and subject to lots of “what-if’s.”  This is necessary, actually, because (I know, we’ve said it a thousand times already) the MEP infrastructure is by far the dominant driver of data center construction costs.  In this context, the spectrum of solution opportunities begins with a full container-based data center design all the way through the use of containers as a use-case specific or a contingency component in an otherwise traditional mission critical facility build.  As such, the impact on MEP architecture and MEP planning will be driven by how the container concept plays into the overall data center plan, and what MEP capabilities come with the container to begin with.

If one considers a data center in which the floor space component (needed square footage of IT space) is delivered either through traditional raised floors or containers, we remove many of the advantages facilitated by the container concept.  In this approach, the MEP infrastructure for whatever tier level one intends still must be built and whether or not we use containers the overall construction costs are not impacted to a significant degree.  Containers do provide modularity and mitigation of risk of overbuilding from a space perspective, but it is difficult to claim a significant cost advantage in that alone (not to mention that the Cost/SF of the IT floor alone is approximately 50% higher if delivered via a container).  A possible exception is in the case of containers with fully self contained MEP, but in order to comment on an advantage one way or another we would need more case-specific information.

The strongest advantage of the container solution becomes apparent when one considers a container fully and densely populated with processors and/or storage.  This is the true power alley of containers.  They provide a very cost effective way to scale very dense computing footprints.  The on-board MEP of container solutions are designed to power and cool a very high density of contained IT equipment.  Much the same as one would build an enclosure with inline cooling to address a very dense hot spot on the raised floor, the fully populated container is a special instance of that sort of situation. 

Of course it’s still the case even with containers that the MEP costs are the dominant up-front investment component.  Keep in mind though that a densely populated container solution can bring an opportunity for a much more favorable TCO model.

Of course there’s much to be said about government control of the Internet in China, the national firewall, and so on.  This post is not meant to debate any of that.  It is interesting though, that the government of China at the very highest levels seems to recognize the power in leveraging the Internet internal to the nation and recognizes the capabilities of Web 2.0 technologies.

Earlier this month, China’s President Hu Jintao joined an online chat forum to answer questions from connected citizens.  In the brief chat, President Hu mentioned that he uses the Internet often, and considers it a good source for understanding the concerns of citizens and to gather their opinions.  To quote (a translation), he “hopes to see what opinions and comments our Netizen friends have about the work of the Party and the State.”  He also mentioned the importance of “collecting the wisdom of the masses” as “an important channel” as a component of decision making in a ‘people-based’ government.

Now we do understand that China’s experience with the Internet is a complicated one, and many have posited about the internet being a balance between a potential threat to China’s political system and a powerful tool for propaganda, monitoring, and surveillance.  In fact, foretelling which way that balance will tilt is made difficult because of that country’s contradictory attitude and behavior.  The same can be said for the behavior of China’s online population.  This is a complicated matter.

However, and returning to the very simple point to be made by this post, the statements made by President Hu himself in terms of “collecting the wisdom of the masses” for decision making,… and the very high profile use of Internet chat as a dialogue between government and its citizens, is a pretty striking demonstration of recognition of Web 2.0 technologies.  It’s been reported that Chinese officials at many levels are using the Internet to solicit public opinion at the grass roots level as a part of their bureaucratic process.  To whatever degree one feels about the “openness” of the process, it’s certainly interesting to observe the recognition of the value in collaboration from the masses.

I’ve spoken often about the promise of Web 2.0 technologies for the enterprise (and society in general) and the potential of rich collaboration that these technologies facilitate.  Recently, I’ve been working on a concept that applies a social networking layer on top of ITIL processes.  Let me elaborate on that a bit.

If we look at say, ITIL Service Management, we can see a multitude of interfaces between the process framework itself, and the IT organization and the Business.  These interfaces represent points of communication.  In some cases, these interface points represent rather simple communications- access to content, a simple query, delivery of content, and so on.  In other cases, the interface point can represent a dialogue.  These dialogues can be rich and complex (though to date they rarely have been).  Other points too are interfaces that in practice represent fairly shallow communications, but are however opportunities to be accelerants under the proper conditions.

I think that V3 of ITIL has made such opportunities even more pronounced.  V3 has taken activities that in V2 were assigned to separate roles and has mashed them up into a fewer number of roles. 

If we agree that ITIL Service Management gives us an engagement model between IT and the Business, then there’s a real opportunity to be realized if the richness of the communication interfaces can be amplified.  There’s an opportunity to improve the efficiency of Services Delivery.  There’s an opportunity to improve alignment of services with the needs of the Business by introducing collaboration.  There’s an opportunity to elevate the competency of the IT staff by increasing the awareness of factors critical to the Business.  There’s an opportunity to create the linkages that will serve to pull the IT organization further up the maturity model ladder.  Many have commented on their doubts about “the wisdom of crowds,” but most business leaders now recognize the value of customer collaboration.  This is no different in that regard.

In later posts, I’ll describe in more detail what these Web 2.0 technology components are that will comprise this social layer applied to ITIL processes.