Gartner on Extreme Data Centers

December 14, 2010

One of the best sessions I went to at the Gartner Data Center conference last week, was entitled Extreme Data Centers – Attaining Massive scalability – in the minimum space at the lowest cost.

The talk was given by David Cappuccio who is a managing vice president and chief of research for the Infrastructure teams with Gartner, responsible for research in data center futures, servers, power/cooling, green IT, enterprise management and IT operations.

Dell's Modular Data center, mentioned in David's talk, a few days before it went live at Tier 5 in Australia.

Here are my notes from the talk:

The Extreme Data Center definition

  • Designed for efficiency first
  • Designed for optimal performance per kilowatt and or per square foot
  • They leverage new design principles to attain the biggest benefit

An example he then gave was supporting 2,107 servers, 18,300 images and 19 petabytes of storage in 2,600 sq. feet of IT space

New data centers are designed around efficiency

  • In power utilization
  • In space allocation
  • In capital expenditures

Three ways to solve your problem

  • Build your own datacenter from the ground up — greatest control but most expensive
  • Retrofit what you have to extend its life – greatest potential risk but least expensive
  • Use modular ideas to build and expand later
    • Reduce capital upfront costs
    • Simple growth when needed
    • Can use existing land or building

Emerging Design trends

  • Build small, build often
  • Build for density
  • Scale vertically and then horizontally
  • Build and rebuild pods (or sections of your data center)
  • Build density zones (group your systems by how dense they are – high, medium or low– and then match the power and cooling at the zone level.  Density is usually based on the workload mix)
  • Consider multi tiered designs (all apps aren’t created equal)
  • Use free air and reuse heat
  • Design for the unknown

Modular Designs for sustained growth/The evolution of pre-built solutions

  • David felt this approach was a really good idea and made sense
  • He felt the drawback was that there weren’t any reference accounts: he mentioned HP at Purdue and “some company down in Australia” (which dear readers is the Dell MDC down at Tier5, pictured above).
  • He cited Azure as the poster child for containers
  • Besides citing Sun’s “Black Box” as the granddaddy of all these, the pre-built solutions he mentioned were:
    • HP Flexible data center
    • IBM scalable modular datacenter
    • I/O anywhere
    • Dell Modular Data center

Energy consumption and efficiency

  • PUE, DCiE are defacto standards – use them
  • But PUE is not the goal – it’s the beginning
  • PPE: performance and capacity per kilowatt are key

Three examples of some cool new designs

  • Yahoo Computing coop: outside air cooled, minimal fans no chillers and a PUE of 1.08
  • Microsoft containers:  8×40 feet versions, 8-12 weeks for delivery, 2K servers per container
  • Net App: Slab-based w/overhead air design: first energy star rated data center, 25 megawatts

Stay tuned for more

The extreme data center space is an “extremely” hot one.  Watch this space to learn more about how Dell plays here going forward. :)

Pau for now…

Extra-credit reading:


Welcome to the Wild and Wacky World of Data Centers

December 8, 2010

I got back last night from the Gartner Data Center conference in Las Vegas which runs through the end of this week.  Although one of the biggest topics of conversation was cloud computing, I was most interested in learning about what’s happening more generally in the world of data centers.  I’m pretty up to speed on the cloud yet the intricacies of the data center are still new to me.

A couple of great presentations

There was a great presentation yesterday morning from Ebay’s VP of technical operations, Mazen  Rawashdeh, talking about their “Northstar” project and how they have completely  redesigned their data center strategy to support the business (I hope to do a short post on that soon).   The other presentation that I found very educational was “Extreme Data Centers – Attaining Massive scalability” by Gartner’s David Cappuccio (something else I hope to do a post about).

Learning from those in the know

The other way I got up to speed about the wild world of data centers is by talking with a couple of the folks who cover the field.  The first person I met with was Rich Miller, founder of Data Center Knowledge.  Here is what Rich had to say:

Some of the ground Rich covers:

  • How the interest in data centers seems to grow every year
  • What are the current hot topics that he see’s
    • Energy and efficiency
    • Data center design and thinking outside the box
    • Some of the funkier designs people are coming up with

If you’re interested in data centers, stay tuned for a few more entries based on the Gartner Data Center conference.

Pau for now…

Extra-credit reading


Gartner’s Data Center Conference: The Keynote

December 2, 2009

Viva Las Vegas & Los Data Centers!

I’m currently here in Las Vegas attending Gartner’s Data Center conference.  It’s day two and I’ve been very impressed with the quality of the sessions so far.  In particular I thought yesterday’s keynote was very good and I wanted to share my notes from the talk.

The presentation was entitled, “Infrastructure and Operations: Charting a course for the coming decade” and was delivered by David Cappuccio.  In his talk, David walked us through the “10 Trends to watch carefully.”

10 Trends to watch — Carefully

Virtualization

  • Virtualize beyond servers: Desktops, network, storage, Hardware
  • Desktop virtualization is a very hot topic right now (thick client image, thin client delivery model),

Data Deluge

  • Estimate enterprise data growth over the next 5 years is 650%
  • The surprising figure is that 80% of this will be unstructured data and this will be a big issue.
  • Attack with virtualization, de-duping…

Energy and Green IT

  • CIO’s KPI goes from “keep it running” to “keep it running, but make it efficient”

Consumerism and Social Software

  • Twitter grew by 1,382% in ’08, 62% of that growth came from 39-51 year olds.
  • Advice for CIOs: start paying attention to what’s going on in this space and get involved.  It won’t go away.

Unified Collaboration and communications

  • # of text msgs sent in the last 24 hours exceeded the total population of the planet (and this stat is a year old!).
  • Texting isn’t a convenience it’s a way of life

Mobile and Wireless:  It’s all about the apps

  • Mobile apps will need new servers for delivery
  • App delivery is highly complex
  • The management tools in this space are immature
  • This is the next target for virtualization
  • Apps are typically priced around $1.99 (when they’re not free), think of how much the same app would have cost if you had to buy it for your PC.

System Density

  • Operating expense (energy cost) of current x86 system will exceed its purchase price in three years
  • Energy cost per year for 2 typical racks is $105,000
  • Blades are leading toward componentized servers
  • Today blades are proprietary server infrastructure in a chassis solution
  • This is evolving into a componentized datacenter in a chassis solution (but still proprietary)

Mash-ups and Enterprise Portals

  • These are private cloud enablers
  • They allow for rapid/flexible development
  • There are creeping standards, but it is largely uncontrolled
  • Need to set clear standards but also encourage innovation

Cloud

  • Private clouds improve agility and will dominate
  • 70-80% of investments over the next 5 years will be in private clouds
  • Advice: ignore the hype, focus on the results
  • Focus on service levels
  • Common services are available now and may reduce operating costs
  • Managing cloud sourcing:  Service brokers
    • Represent an evolution of today’s SI’s and VARs
    • They will orchestrate cloud providers to meet an organizations needs
    • They will be small enterprises and industry specific
  • Managing cloud sourcing:  Dynamic Sourcing Team
    • Large enterprises
    • New team, new skills(business- and IT-savvy)
    • Manages day-to-day sourcing decisions
  • Advice
    • Evaluate commodity services you provide and what can move to the cloud
    • Evaluate cloud delivery model for internal use
    • Categorize applications/services based on SLAs and risk before proceeding

Stay tuned, more from the conference to come.

Pau for now…


Follow

Get every new post delivered to your Inbox.

Join 96 other followers

%d bloggers like this: