Archive for March, 2012

My day in a nutshell: Tech Ecosystem in Action – Tracky & the SuperNAP

27 Mar

7:00 AM PT: Had a great discussion with a friend regarding my blog on the importance of being a part of a strong technology ecosystem.

7:45 AM PT: Shared a few emails with someone regarding bringing a potential startup to Las Vegas.

8:20 AM PT: Head to SFO for my weekly flight to Switch in Las Vegas.

11:50 AM PT: Land in Las Vegas and receive a request for an appointment from the CEO of a Cloud company to chat over dinner

12:00 AM PT:  Find out that some idiot (Me) left the front door unlatched at my house, causing the alarm to go off and forcing my wife to call a neighbor and ask them to close the door  (sorry honey).

1:00 PM PT: Meet with my boss (Rob Roy) to discuss current Switch activities. Wow, who needs caffeine when you work at the SuperNAP.

2:00 PM PT: Attended a Vegastech event held in the SuperNAP’s conference facilities. The event was attended by over 80 people from Las Vegas and Los Angeles and featured the launch of Tracky. If you haven’t looked at the Tracky site to see what they’ve got going on, you really should. It’s an amazing “project management” meets “modern social media and connections” solution.  This event illustrated another incredible example of how the ecosystem of people, tech, connectivity, services, and space here at Switch are making a huge difference in helping people and companies get things done.  I listened to David Gosse (CEO & Founder of Tracky) introduce his product and then demonstrate its capabilities. But just as importantly, I heard his heart felt remarks about how the incredible technology ecosystem of the Switch SuperNAP has been such a terrific enabler for his rapidly growing startup.

4:30 PM PT: Met with a friend who’s considering building a new web show about I- can’t- say, sorry.

5:30 PM PT: Get back to my office, catch up on emails and decide to write this short blog. Sometimes I really wish I was the diary type, because this is an incredible place and I’m fairly certain I’m going to look back someday and wish I could remember half of what we did here.

7:00 PM PT: Leave for my dinner meeting with the Cloud CEO, who will remain nameless (for the time being).

Just another day in the office at Switch

 
 

Fluid IT – The IT Ecosystem & Cloud Operating Model

19 Mar

We’ve all seen the clichés regarding cloud and business; I know I’ve written a few. It’s not that they’re wrong, at least not in all cases. More appropriately it’s that I don’t think the future for IT has been effectively verbalized.

Will modern IT, let’s call it “Cloud” enable business to forget IT when making strategic decisions. I know it sounds odd to suggest the business should “forget” IT, but I will explain. In a recent blog about the data center being a 15 year business plan I talked about how the business is often put into a position of making strategic decisions based on the inflexibility of IT solutions, specifically data centers.  As a company, how can you allow any IT decision to determine where and how you can do business, It just doesn’t make sense.

IT in the way of Business

I’ve been a part of the “IT needs to be considered” problem in the past. I can’t remember how many times I’ve bemoaned the fact that the business didn’t effectively consider IT before making a decision.  I always wanted to be front and center during M&A discussions or plans for growth, because the more I knew, the better I could prepare my team, and the infrastructure. I also wanted to be able to explain what we couldn’t do, so that our executives wouldn’t promise too much to a customer, an acquisition target or a new partner and therein lies the problem.  The business should be able to forget IT, they should be able to look at the business opportunity and determine its viability solely on its merits, not on whether IT can keep up.  However, I’m not trying to say IT should become invisible. On the contrary, the need to have IT working “in” the business has never been more important. Who better to translate a business process or work effort into a potential IT opportunity than someone who understands how IT can be applied. If you’re the type of CIO who is waiting for the business to call you and tell you what they need, you’ve already lost the race.

The Vision of Fluid IT

Why is “Fluid IT” different from Agile IT or any other definition of modern cloud operating model phrases?  I’m not sure Fluid IT is so much different, as it’s maybe more thorough.  Many of the traditional assumed benefits of a cloud operating model are as follows:

-          Rapid deployment of new workloads

-          Try before you buy

-          Buy only what you need, only for as long as you need it

-          Get out of the business of running infrastructure and instead deliver higher level strategic value

-          Greater flexibility in technology adoption strategies

-          Lower costs (maybe)

-          Greener (maybe)

There are other terms that help to define the opportunity with cloud, but they are likely to be associated with one of the above bullets.

My vision for Fluid IT is that there are literally no circumstances when the customer needs to plan around whether or not IT can handle the task at hand.  Let’s put the problem into perspective; A CEO finds a short term, but potentially very profitable opportunity with a partner in Turkey. Unfortunately, the tools and data the partner will need are based in two data centers in North America. Because the CEO has gone through this drill before, she immediately assumes that there’s no way to attack this opportunity.  She can hear the CIO’s voice in her head “the app won’t work because of latency”, “it will take us months and cost 10s of thousands to find a partner in Turkey or somewhere nearby where we can build some infrastructure, and then we have to worry about security and tearing it down when we’re done”, etc., etc.

Solving the aforementioned problem is where I see Fluid IT helping.  Fluid IT isn’t one technology, or one cloud, it’s more of a best of breed technology strategy meets the cloud operating model organization. Is it possible that you could create a true fluid IT environment with just a few traditional vendors, maybe, but more likely it’s going to be an environment using the philosophy of the IT Ecosystem.  The following is a simple breakdown of where fluidity should be built in:

-          Access to applications

  • Remove the current restrictions that most of us in IT assume are required for enabling external access to applications. Look to a model that protects the data, while making it available in real time. A great blog on this topic was recently written by @bmkatz
  • Performance tools that remove the overhead of end-point acceleration, while providing near real-time speed, with security (like Framehawk)

-          An application infrastructure strategy that exemplifies modular design

  • The ability to add applications or capabilities to your application framework quickly and easily, while maintaining accessibility from any form factor device from any location.
  • Infrastructure platforms that will allow you to replicate processes and function rapidly in a new language and or with region specific regulations.
  • A Cloud management solution (like ServiceMesh or Enstratus) that will allow you to utilize any cloud environment quickly and efficiently, while still maintaining enterprise policy and governance, etc.

-          Partner with providers that can help you quickly scale and distribute work

  • Maintaining your own data center(s) is a risk most business can’t afford anymore. It’s practically criminal to allow a decision around the location or size of the company data center become the deciding factor in a business strategy or growth opportunity ( See 15 year business plan)
  • A data center ecosystem that allows you to connect once and be connected everywhere. You must remove each of the barriers to rapid delivery the traditional connectivity strategies with 1-1 relationships and new fiber pulls are not the answer.  This also means you would have access to a variety of clouds, with replication or geographic diversification designed into the ecosystem.
  • There are other risk mitigation benefits of using a multi-cloud model as suggested in the “Outages prompt multi-cloud evaluations” on GigaOm.

-          Leverage experts in key areas of IT design and delivery

  • You should not expect that your internal team will have the background and expertise to fully execute on a plan to become Fluid. In fact, you may find that many will resist the idea because it will threaten how IT employees work and what they work on.

-          An organization designed for performance and agility

  • Reduce the focus on application or infrastructure ownership
    • As long as the team feels their performance and opportunity will be measured and rewarded on their ability to be the best Oracle DB or SAN engineer, then you will likely always be running those solutions, regardless of the potential alternatives. (See server huggers disease)
    • Consider developing a an organization along the lines of Global Foundation Services as created by eBay & Microsoft among others.
  • Design org structures around capability delivery not on technology delivery
    • If the “capability” can be delivered quickly, efficiently and securely then it doesn’t matter where it comes from. The focus on internal design is fine, as long as you’ve developed a framework that doesn’t cause you to make pragmatic (read poor) decisions about what solutions you can offer your customers.
    • Stop thinking like a cost center, and start delivering business opportunity. IT isn’t a resource to be used to reduce the cost of IT. Do you see the problem here? There are many companies out there that spend a much higher than average percent of revenue on IT, yet are very profitable. While that model may not work in every business, the fact remains that you don’t build IT for IT’s sake, you build it because it’s allowing the business to increase revenue or drive up margins, more efficiently and more quickly.

I could go on for another two pages continuing to list the areas of opportunity for creating a Fluid IT model, but I still wouldn’t hit on everything. The truth be told, I would need to seek the council of five or six industry expert friends in the areas of networking, security, application design, data gravity, cloud platforms, etc. in order to more fully address the above assertions.

There isn’t a Magic Bullet, and it will take Work

I’d love to be able to tell you that you can go to vendor X and buy the “Fluid IT for Pharma” package, but unfortunately it’s not that easy and probably won’t be for a long time.  The good news is that working towards Fluid IT is very similar to your goals for getting to a “Cloud Operating” or “Agile IT” model. The key distinction is that you shouldn’t focus on specific technology verticals, or cloud solutions without having considered what the delivery model  will be that will ensure your business partners can “Forget IT” when they’re doing the next deal.

Credits:
Richard Donaldson (@rhdonaldson) for patiently listening to my thoughts on this for an hour on Saturday morning and offering some great ideas.
Bernard Golden (@bernardgolden) for the inspiration I got from his recent IT Evolution blog
Brian Katz (@bmkatz) for using a reference to his blog on data vs. devices
Dave McCrory (@mccrory) for again referencing his “data gravity” blog
Jason Mendenhall (@jasonmendenhall) for letting me bother him while he’s working on real cloud opportunities

 

 
 

High vs. Low Density Data Centers, Cloud, Cost, PUE & Sustainability

11 Mar

Did I put enough in the title to make you think “what could this guy possibly be talking about”? I guess that was the point, and strangely enough, the title does have meaning.

There has been a religious war raging in the data center community for several years now on the subject of server cabinet densities. The question is whether high density server cabinets (typically 15-30kW) should be installed versus distributing your compute over a larger area in low density (typically 4-10kW) cabs. The basic argument is that the overhead of designing for high density, doesn’t justify the benefits. I’m here to say that high density is the best answer, but probably not for the same reasons that most have been arguing.

How Does Sustainability Fit Into This Argument?

Sustainability plays into the density argument because of the facilities.  A data center is a complex and expensive facility and building one to cool 25kW server cabinets definitely has added cost vs. the alternative. There’s increased electrical per square foot and of course extra cooling (air conditioning). However, beyond those two things, a data center is still a data center.  In fact, even the airflow management (ducting, etc.) when done effectively doesn’t need to change significantly regardless of density, it’s the ability to cycle the right amount of air to and from the correct locations that matters. The real problem with choosing low density vs. high density is it increases the space required for your servers. You also need more network cable (fiber & Ethernet), more cabinets, switches, electrical copper, ladder rack, patch panels, and, well you get the idea.

So my basic tenet is that in the long run it’s not just wasteful and more expensive to plan, build and run low density environments, its bad practice from a sustainability standpoint.  Even if you discount all the extra materials I discussed in the previous paragraph, you can’t discount the building of another structure or a larger than necessary one. If you accept the fact that the incremental design and materials required to support 25kW cabinets is only a fraction of the cost and construction material of one facility, how could you possibly justify building a whole new facility to support a 5kW design. Even if you could somehow justify the cost of building low density, you can’t justify the environmental and sustainability concerns associated with the construction and management of extra facilities.

There is roughly 1 ton of carbon created by every ton of cement and total global cement production is estimated to create 7% of all carbon output. In case you were wondering, the cement for a large data center equates to tens of thousands of tons.

So, you’re probably starting to get the picture of my sustainability point, and I haven’t even talked about the extra pavement, roofing materials, steel, cars and trucks, paint, and cleaning materials, etc., etc..

OK, How Does Cloud fit into this Story?

Simply put, IT infrastructure, applications and data benefit from having proximity. Unless you’re distributing workloads to balance geographic risks or latency concerns, the closer you can keep your servers and applications to each other the better. So if you’re building data centers that spread servers across 100 cabinets, when they could have put them in 15-25 cabinets, you’re not only wasting space and money, you’re also causing headaches for your infrastructure and application design teams.

The Switch SuperNAP is designed to 1500 Watts a square foot or roughly 25kW per cabinet at a year round average PUE of 1.24. While you don’t have to build environments that require that kind of density, when you do it provides significant cost savings and potential infrastructure performance improvements.

The original objective of building to 1500 Watts a square foot was to support the real application needs of organizations that are maximizing the use of modern infrastructure. Our customers are running hundreds of racks between 15kW and 28kW and several hundred more are running between 6 and 15kW.  Besides the benefits our customers derive from the ability to run modern infrastructure, this density has also allowed us to dramatically reduce our data center construction footprint as compared to the vast majority of other facilities. The result of these low density environments is that we are potentially using up to five times (5X) the amount of space necessary.

To put the previous paragraph into perspective I estimate the total global data center foot print exceeds 700 million square feet and we are adding roughly 10% in new capacity every year.  When you consider that up to 18% of a buildings carbon output is created during the manufacture of materials and the construction phase, that’s an immense figure.

So the next time you hear someone talk about their PUE number, ask them two things;

-          How is your power generated (Fossil, renewables, Clean, etc.)?

  • The energy source is key to determining the actual carbon impact of DC operations, vs. simply measuring the effective use of the power (I.e., PUE)

-          What’s your power density per square foot?

When you can make a decision that helps your company’s bottom line and reduces negative impact on the environment, why wouldn’t you?

 

The links below are a few additional resources used in the writing of this blog:

sutmundo.com/impact-buildings-sustainability/

bis.gov.uk/assets/biscore/business-sectors/docs/e/10-1316-estimating-co2-emissions-supporting-low-carbon-igt-report

 
4 Comments

Posted in Uncategorized