New Florence. New Renaissance.

Your new data center location: Iceland

“Iceland has been busying itself laying fibre optic cables to connect the country with North America and Europe.

The cables coming in provide a capacity of more than five terabits/sec - all with server farms in mind.

Travelling down this pipe, data sited in Iceland is just 17 milliseconds from London. Sitting at home on YouTube you would never know, but even that is too slow for some. “

BBC

"The New Masters on Wall Street"

“Making it in high-frequency trading these days requires the latest technology. Lots of it. Getco won't talk details, but others will. Infinium Capital is the biggest marketmaker in natural gas futures and runs its computers in 100,000 square feet near the Chicago River. The core of its operation is 40 racks of servers overseen by quant traders who man up to a dozen screens each.

Infinium's operation runs on a piece of the public electricity grid backed up by two separate power substations and 196,000 pounds of batteries. Not safe enough. Infinium is paying to install a 2,000-kilowatt diesel generator just in case. Infinium taps into the CME Group's computers, housed on the same floor of a data center, via dedicated fiber-optic lines capable of transmitting up to 5,000 orders per second with a lag time of no more than 10 milliseconds. Infinium has other servers strategically situated near exchange computers in New Jersey, London and Singapore.”

Forbes

 

The Datacenter as Computer

Move on Sun, here’s Google substituting Data Center for Network as the computer in this paper

“We believe the problems that today’s large Internet services (Google, amazon, Microsoft, Yahoo) face will soon be meaningful to a much larger constituency because many organizations will soon be able to afford similarly sized computers at a much lower cost. Even today, the attractive economics of low-end server class computing platforms puts clusters of hundreds of nodes within the reach of a relatively broad range of corporations and research institutions. When combined with the trends toward large numbers of processor cores on a single die, a single rack of servers may soon have as many or more hardware threads than many of today’s datacenters. For example, a rack with 40 servers, each with four 8-core dual-threaded CPUs, would contain more than two thousand hardware threads. Such systems will arguably be affordable to a very large number of organizations within just a few years, while exhibiting some of the scale, architectural organization, and fault behavior of today’s WSC (Warehouse Scale Machines). Therefore, we believe that our experience building these unique systems will be useful in understanding the design issues and programming challenges for those potentially ubiquitous next-generation machines.”

Computational Fluid Dynamics in Data Centers

“In the past, most data-center cooling systems were designed based on rules of thumb or trial and error, and large margins of safety were used to compensate for the inaccuracies in those approaches …Computational-fluid-dynamics (CFD) software tools provide the ability to simulate the performance of data centers and predict the effects of air handlers, power-dissipation sources, raised floors, and other features on temperatures throughout a data center.”

HPAC Engineering

Photo Credit: Data Center Knowledge

Microsoft Containerized Data Centers

It takes mucho computes and terabytes to create the 3D models used in Microsoft’s Virtual Earth online mapping service. So how do they cram 5,000 cores and 10,000 terabytes - 10 petabytes - of storage into 3 40 ft. shipping containers?

ZDNet

 

The rise of the Mega Data Center

"Intel estimates that by 2012, up to a quarter of the server chips it sells will go into such mega data centers. Dell, which nearly two years ago created its Data Center Solutions Group to address the needs of customers buying more than 2,000 servers at a time, now says that division is the fourth- or fifth-largest server vendor in the world. In the meantime, suppliers are creating product lines and spending money on R&D to adjust to the needs of these mega data center operators, as those operators are fulfilling an increasing demand for applications and services delivered via the cloud."

GigaOm

AT&T Disaster Recovery Trailers

Disaster recovery - yawn, right?

But packing so much into trailers is what was innovative about AT&T's recent network disaster recovery exercise in Houston

"All of the telecommunications equipment required to recover a destroyed AT&T Central Office is transported to a recovery site in specially-designed technology trailers. Each trailer has self-contained or dedicated power and environmental capabilities and each houses a component of the network technology that would normally be part of a permanent office. Once on site, the individual components are interconnected to match the unique configuration of a heavily damaged or destroyed central office."

Read more here about the large amount of equipment in the trailers

Google...one of the world's largest server manufacturers

Yup, you read it right. They may not sell them to you and me, but Google's tens of thousands of proprietary servers run its own massive operations.

But you may be able to buy them soon. But not from Google.

"Rackable, a system integrator that built Google's first 10,000 systems, launched a so-called CloudRack in late October, geared for big data centers. Early next year Rackable will ship for the enclosure its first 12V-only motherboards with two servers per board. Boards sporting four and six servers are running in Rackable's lab, said George Reitz, the company's vice president of sales."

EETimes

Goodness Gracious: Great Balls of Kevlar!

I have written before that some of the most exciting things happening in IT are in the boring old data centers - green computing, virtualization, clouds, containers and more.

And some of the most passionate speaking and writing on next-gen data centers is coming from folks like Urs Hoelzle at Google and Michael Manos at Microsoft - not from traditional outsourcers and hosting firms which run the majority of our data centers.

So I was highly entertained recently to hear Josh Snowhorn of Terremark talk glowingly - and irreverently about the giant balls - of their Miami NAP.  The center switches the majority of South America, Central America and the Caribbean's data traffic bound to the rest of the world.

He was talking about the business continuity challenges of having a Tier IV data center in Hurricane Central. And the usual DC challenges of space optimization, cooling, physical and cyber security (accented by several top-secret government clients) and more.

Who would have thought data centers could be this fascinating?

"Gen 4" Modular Data Centers

"This is our vision and will be the foundation of our cloud data center infrastructure in the next five years. We believe it is one of the most revolutionary changes to happen to data centers in the last 30 years. Joining me, in writing this blog are Daniel Costello, my director of Data Center Research and Engineering and Christian Belady, principal power and cooling architect. I feel their voices will add significant value to driving understanding around the many benefits included in this new design paradigm.

Our “Gen 4” modular data centers will take the flexibility of containerized servers—like those in our Chicago data center—and apply it across the entire facility. So what do we mean by modular? Think of it like “building blocks”, where the data center will be composed of modular units of prefabricated mechanical, electrical, security components, etc., in addition to containerized servers."

Michael Manos on his blog - he is responsible for the global data center design, construction and ongoing operations for Microsoft’s online services