A Peak into IT in FedEx Green Data Center

FedEx announced its Green Data Center in Colorado in Feb 2011.

FedEx Unveils “Green” Data Center in Colorado Springs

 

February 16, 2011

FedEx Corp. (NYSE: FDX) today celebrated the grand opening of its first environmentally sustainable (“green”) data center, located adjacent to the FedEx Rocky Mountain Tech Center in Colorado Springs, CO. Based on the application of a number of green design standards, the Enterprise Data Center–West (EDC-W) can be counted among the most energy efficient data centers in the U.S.

...

The EDC-W PUE is 1.28, with a ratio of “1.0” indicating perfect efficiency.

...

The Technology

Over the next three years, FedEx technology teams will move core systems and applications from the Customer Technology Center (CTC) in Memphis to Colorado Springs. The massive migration of data, already in progress, will require thousands of hours of work to ensure the successful implementation of the simplified and consolidated infrastructure.

So what is some of the technology moving into FedEx's green data center?

FedEx is thinking like an information company.

The so-called Internet of things is one of the emerging technology themes at the Gartner conference. For CIOs, these sensors connect many distinct disciplines, including data management, analytics, business intelligence and customer service.

Other themes from Carter included:

  • FedEx is an information services question. The company’s ethos is that the information about the package is as important as the package itself.
  • Enterprise IT is a young discipline. “Enterprise IT as a profession is only about 35 years old. It’s a new science,” said Carter.
  • FedEx is architecture around service oriented architecture. The company is broken down into 22 services that are delivered to various operating units. These services cover addresses, locations, labeling and other items that “are foundational services that really matter to the business.”
  • Once those services are in place, interfaces and applications that aren’t necessary fall away. “You’re not entitled to an enterprise stack,” said Carter, referring to operating units.
  • FedEx’s data centers run on VMware as an internal cloud. The hardware revolves around commodity x86 servers, said Carter. That architecture is the dominant design that is used by Amazon, Salesforce and others.

And the CIO drove some action.

4. Enlist reluctant top management.

To persuade top management to make the move, Carter didn't do five-year plans or 10-year projected returns on investment. Instead, he drew a map of what the existing data center environment looked like versus the simplified one he wanted to operate. His mappings of the existing application infrastructure and dependencies were so complex, intense, and confusing that his CEO dubbed them scenes from "Hurricane Rob" in his honor. "I had a lot of ugly pictures," he said.

5. You don't have to wait for just the right software.

Carter didn't get caught in analysis paralysis. Carter wasn't looking to bring in an external supplier's private cloud system to get started or waiting for a cloud computing standard, such as OpenStack, to firm up. As a Salesforce.com customer, he and his IT staff "compared notes" with Salesforce on its data center operations and FedEx knew how Twitter and Facebook had built their new data centers. His staff worked with the LAMP stack--Linux with a proven set of integrated open source code--to build a shared x86 infrastructure, then created pilot services on top of it.

There were cultural issues. Some IT staffers felt they were doing a good job with the way legacy systems were running. Carter illustrated that FedEx was using 200 different applications to manage addresses, a key component of its business, when one address service could do the same thing more efficiently and at a lower cost. Another new service supplied currency conversions throughout the company. Carter told his staff, you're doing a good job of managing the details of the existing infrastructure. "It was the macro picture (of future data center operation) that looked unsustainable."

And, note that FedEx skipped the public cloud step and went straight to the private cloud, but has his options open for AWS.

6. What about the public cloud?

Carter acknowledged his approach doesn't include a blueprint for working with the public cloud. But FedEx is a close partner with Salesforce.com--"I've known Marc Benioff for a long time," said Carter--and initially, FedEx will "live in a hybrid cloud world with Salesforce" CRM applications. But Carter also noted the seasonal nature of FedEx's business and how it doubles with the approach of the holidays. "Our business is unique in its peaking factor ... Amazon Web Services' capacity to handle intense workloads, like Netflix streaming, means it might be quite suitable for some of our work," he said.

Netflix Outage, can't sign in

We'll see how this one plays out.  Depending on how long it takes Netflix to fix this one, we'll see how the stock takes a hit tomorrow.


Rachel Lightfoot
My Netflix isnt working. 
Megg Thomas   
Netflix flow
tess myers
brb, crying that i can't log-in to my netflix account ;-;
erin delanty
Having a hard time explaining to my 5 y/o why she can't watch her "flix movie" I promised ALL day long to her! Come on !!
S.A.
You better figure it out ...
Allison Parman
Can't log on to  tonight. Looks like a lot of others can't either. Sad.
Emily Reid
decided in the last 30 min my password isn't valid anymore...but I haven't changed it.  I am beyond 

Bechtolsheim talks data centers, Cloud/AWS, and Open Compute

Andy Bechtolstheim presented at GigaOm and discussed a bunch of cool topics for the data center crowd.  I am going to cheat and refer to Barb Darrow's notes as I was sitting next to her during the presentation and why type when I can copy the good stuff. :-)  I saw Andy a few weeks ago in NYC at the Open Compute and was curious what he would say at GigaOm Roadmap.

Bechtolsheim: AWS, open source rewrite rules for startups

Arista's Andy Bechtolsheim at GigaOM RoadMap 2011Today’s tech entrepreneurs would be out of their minds to build out their own data centers rather than renting capacity from Amazon or another low-cost provider.

That wasn’t a direct quote, but it’s pretty much the takeaway from Andy Bechtolsheim, the co-founder of Arista Networks(and also of Sun

 

 

 

 

 

Andy made the point people would be nuts to build their own data centers.

A company might build out its own infrastructure only if it’s raised a lot of venture capital, he said. But it needs to be a lot. And even then, maybe AWS is a better way. “Netflix  … uses Amazon for infrastructure. Here’s the leading, largest company in a field deciding it’s cheaper and more efficient to use a competitor for infrastructure rather than building its own.”

Andy mentioned the Open Compute Project.

Bechtolsheim is also on the board of the new Open Compute Foundation, formed by Facebook to propagate specs for standard, energy-efficient data center infrastructure. OCF hopes to bring open-source innovation that so improved software tools into the hardware realm.

For those brave souls wanting to build data centers, the OCF blueprint could help. But, Bechtolsheim said, that’s for truly big companies that need to do huge webscale computing, not for startups.

Bottom Line.

For nearly every entrepreneur weighing a tech startup, it’s better to rent than to buy or build.

The full presentation is here.

Watch live streaming video from gigaomroadmap at livestream.com

Roundtable Discussion - Cloud Delivery Strategies for Digital Services

You can register for a webinar on Nov 16 10-11a PT, Cloud Delivery Strategies for Digital Services - games, video, audio, and ads.

 

 

Cloud Delivery Strategies for Media Services

 

Providers of media applications and web services often launch via public cloud, only to discover they want more control as their products scale. This analyst roundtable will discuss the pros and cons and how-tos of using public, private and hybrid cloud solutions for media delivery. It examines the tradeoffs among performance, cost, scalability and control in cloud-based strategies for delivering content to customers on a global scale.

What You Will Learn:

  • How to view data centers as “information factories”
  • Determining which media services work best on what type of cloud
  • Managing traffic aggregation and CDN distribution
  • Controlling bandwidth costs while delivering scalable performance
  • Managing and migrating across public, private and hybrid clouds

Who Should Attend

  • CIOs, CTOs at media and content companies
  • Cloud platform executives and managers
  • Media company asset managers and business planners
  • Content distribution network executives

I am interested in this topic and have join the panel.

Moderator

Research Director, GigaOM Pro

Panelists

Infrastructure Curator, GigaOM Network
GigaOM Pro Analyst, Founder Greenm3.com
GM Content & Digital Media, Equinix

 

 

Open Compute Project as a lower cost model, Rackspace and Facebook

Rackspace and Facebook are on the board of the Open Compute project.  SeekingAlpha has post on the open source process both of these companies embrace.

 

 

 

 

 

 

 

The author drills to the bottom line of why Open Compute?  lower costs.

Strip away its adherence to the open source ethos, after all, and Rackspace is just a hosting vendor, no different from hundreds of other small hosting companies like Westhost or SoftLayer. At some point this competition will come down to costs, as usage of the resource scales exponentially. Low cost infrastructure will win.

Right now costs are not the key issue in the cloud. Right monetization is the issue. That's why every vendor – from Oracle (ORCL) to Dell (DELL) to Apple (AAPL) – can call what they do “cloud.” But as usage increases 10 times, then 100 times and 1,000 times, what seem like small differences in costs now will become magnified into big differences in profitability.

One way to look at Open Compute Project is it is an effort to build a lower cost data center ecosystem.

Open source, and the Open Compute project, put Rackspace at the forefront of these changes. They are key to its long term survival.