The project, in a presentation by Frank Frankovsy at Interop, said it was taking a slightly different tack with its design, deciding to get input from others before actually making and releasing the hardware to the community. However, just because the hardware isn’t designed yet, Facebook isn’t going to twiddle its thumbs for a traditional multi-year design cycle. Frankovsky told me in an interview that he expects the hardware to b out in 9 to 12 months.

“We have built these islands of openness in the data center but the last element, and the one that was connecting the compute and storage, was the network,” said Frankovsky. “And there is a lot of pent-up passion out there for breaking open this appliance model.”

Networking is the last bastion of proprietary profits

Prepare to be disaggregated, switch!

For those who don’t dwell in data centers, the top-of-rack switch is the networking gear that sits on the top of a rack of servers directing traffic between those boxes and between the other racks in the data center. While the networking world is all aflutter over the promise of OpenFlow and software-defined networking, very little real progress has been made in building switches for the webscale data center.

Google, a few years back, had famously issued a request for a new type of switch that would fit its very specific scaled-out needs and no one responded. Now the search giant makes its own hardware. But soon after that, Andy Bechtolsheim saw the need for Google-like speeds and scale and started Arista, a switch company that has dominated in the webscale, financial and high-performance switching space. Meanwhile, at the lower end, Cisco’s cheaper Nexus line of switches have done really well.

Facebook’s Najam Ahmad.

Yet, these options aren’t palatable for Frankovsky or Najam Ahmad of Facebook (Ahmad will be at our Structure conference in June discussing more about Facebook’s networking strategy). On the existing product side, Frankovsky is frustrated by hardware that doesn’t play nicely at scale. He specifically mentioned that the side venting of heat on switches means he can’t place them right next to another switch. Ahmad, who is in charge of the social-networking giant’s network, is concerned about getting out of the proprietary OS model.

“We want it to be OS-agnostic so we can use one from our existing provider or build our own,” he said. He added that he’d prefer an open Linux-based implementation. These proprietary OSes — Cisco has IOS, Juniper has Junos and Arista has EOS — are one of the reasons that companies are locked into one networking gear provider. They are also stuck using proprietary code to make changes.

Who will be the Red Hat of the networking OS?

Networking cables along the ceiling at Facebook HQ.

If you are chock full of technically savvy people, losing the agility that comes from writing your own code as well as paying higher prices for the proprietary hardware and software combination is probably maddening. Hence Facebook’s interest in the open source OS. Of course, building out the underlying hardware is only the first step, the next will be supporting an OS that runs on top of that system.

While Facebook might build its own OS, not every company will want to do that, and Facebook may not open source its own networking OS if it ever makes one. That leaves a market opportunity. Perhaps a firm like Arista might move in here with an open source version of EOS, although given that Arista uses merchant silicon in its boxes, putting up an open-source version of its software would eat into its margins.

This is neither Open Flow nor SDN

But let’s go back to the box. Facebook is working with Broadcom, Intel, The Open Daylight Foundation, the Open Networking Foundation and Big Switch as some of its collaborators on this project. The box itself might run x86 hardware or a proprietary ASIC, according to Frankovsky. As for the protocols, Open Compute is going to see what the other collaborators want.

Software-defined networking

But for those wondering about Open Flow support, it’s likely. Frankovsky said that the Open Networking Foundation asked Facebook to get involved via the Open Compute Project with making open networking hardware. While Frankovsky and Ahmad didn’t cop to it, I know there has been frustration in many areas of the webscale and networking world that the promise of commodity hardware that Open Flow could offer has not really hit the market in a way that offers the most flexibility for data center operators.

Frankovsky said that the ONF approached Open Compute (Facebook is a founding member of both organizations) in part because it believed it could move quickly on this. And it will. But it’s worth noting that this announcement is about an open source top-of-rack switch, not a controller and not some type of software-defined networking play.

Other companies may take this box and perhaps an open source OS if one is developed, and then layer on some type of controller software to make a software-defined network, but this is just a box.

That being said, this is a box that could seriously disrupt the existing players in networking, from giants like Cisco and Dell all the way to smaller startups like NoviFlow or even Pica8. Much like Facebook is changing the server market with Open Compute, we’ll see if it can tweak the model and do the same in networking.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• Cloud computing infrastructure: 2012 and beyond
• OpenFlow and beyond: future opportunities in networking
• The promise of SDNs in the enterprise

Facebook formally announced the construction of a new data center in Altoona, Iowa. Construction on the first phase will begin this summer and your Facebook likes and photos will start traveling over the data center in late 2014 according to Tom Furlong, vice president of site operations at Facebook.

He said that while newspaper reports placed the value of the center at $1 billion to $1.5 billion, he’s unsure where those figures came from. This first phase will cost $300 million and result in a 476,000 square-foot data center. That square footage includes both offices and floor space. Like Facebook’s data center in Lulea, Sweden the hardware inside will be built for Facebook to its Open Compute standards.

Facebook’s data center in Prineville, Ore.

When I asked Furlong if the Altoona data center would be built for disaster recovery purposes — as some of my sources had suggested — he told me, “we’re in the N+1 mode,” meaning he was building out capacity beyond what he needs to serve customers. While Furlong was clear that the data center would be more than just a failover site for Facebook’s Prineville, Ore.; Forest City, N.C.; Lulea, Sweden or leased data center space, it would represent excess capacity that could still support traffic from other sites if a region failed.

He also alluded to mechanical, electrical and networking improvements, but other than saying that servers handling similar products would be grouped together he declined to get specific. But I’m hoping his boss, Jay Parikh, the VP of infrastructure engineering at Facebook who is speaking at Structure in June will share the details.

On the capital investment side, Facebook said in its 10-K filing that it planned to spend $1.8 billion in capital expenditures in 2013. When asked if this data represented a large chunk of that, Furlong said it didn’t. AND at $300 million it probably wouldn’t, especially if servers and gear wouldn’t make it into the data center until 2014 as Furlong suggested.

But wait, there’s more!

But in a curious bit of timing, Google today said it would expand its Iowa data center operations in (relatively) nearby Council Bluff, Iowa. The search giant will spend $400 million building out its existing data center operations, bringing its total spent in the area to $1.5 billion. The data center houses computer systems and associated components that support services such as Google Search, Gmail, Google Maps and Google+.

In the data center world, the growing rivalry between Google and Facebook is common — if quietly addresses –knowledge, which is why the timing of Google’s announcement seems designed to steal Facebook’s thunder. However, Google’s spokeswoman attributed the timing to an Iowa Economic Development Board meeting held this morning, where the board approved incentives for both Facebook and Google.

However, it’s no secret that Facebook has been stealing pages from Google’s book and is also pushing for more openness than it’s famously “open” rival. Facebook’s Open Compute project announced in April 2011 clearly found inspiration in Google’s own efforts to build its own hardware to maximize efficiency. With Open Compute, Facebook took Google’s basic idea and opened it up to masses after putting considerable engineering talent behind it.

That’s only one example. Facebook has also been open about how it builds and operates its data centers, which has led to many of those in the industry to start releasing their own data. For example, after Google published a blog post last year noting the power usage effectiveness ratio for its data centers, Facebook countered with an email indicating the differences between its calculations and Google’s. Microsoft also was quick to respond with details on its own PUE calculations.

Facebook’s Forest City, North Carolina data center.

The search giant’s appearance and presentation last November at an industry conference that shared seven years of knowledge gained at Google, plus its invitation of a CBS news crew to tour its data center in North Carolina (where Apple and Facebook both have data centers and our own Katie Fehrenbacher was yelled at for snapping a picture) are a few examples.

These steps are unheard of for the search giant, which is famous for holding its infrastructure details close to the vest. In the CBS video, Google’s infrastructure czar Urs Hölzle said that the tour granted to the CBS crew is the only time he’ll allow cameras into the data center. Google once asked me to avoid using a picture of a slide I had taken at a conference that showed a switch it had designed. I didn’t run the picture, but that was because it was blurry.

So as Facebook pushes Google, perhaps Google is now pushing back a bit today with its own Iowa news. Google’s is a bigger project announcement, coming the same day after Facebook’s might just be a coincidence enabled by incentive packages, or it might be an attempt to steal Facebook’s thunder.

Regardless, two web giants striving to make computing faster, more efficient and in Facebook’s case, more open, is a good thing: both for Iowa and for the rest of us.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• Locating data centers in an energy-constrained world
• Power in the data center: Can it drive disruption?
• How a Snapshot of a Green Data Center Can Be Misleading

CloudFlare Founder and CEO Matthew Prince detailed the problems the company is trying to solve in a blog post earlier this week. In a nutshell, although its network edge that spans 23 data centers is (usually) capable of handling most traditional DDoS attacks, there are a couple types of attacks that target different bottlenecks at the local area network level. In these cases, the 1 Gbps networks ports on CloudFlare’s servers can get overwhelmed, as can the processors themselves.

Of course, when you’re running a multitenant cloud-based service like CloudFlare is, these types of events take on a different urgency:

“Both these problems are annoying if it affects the customer under attack, but it is unacceptable it spills over and affects customers who are not under attack. To ensure that would never happen, we needed to find a way to both increase network capacity and ensure that customer attacks were isolated from one another.”

So, over the course of 2012, CloudFlare spent its time working on what it calls “Project Bondage.” Essentially, that meant configuring the individual ports to look and act like a single port capable of handling much more bandwidth, and then reworking the CloudFlare operating system to prevent external CPU-level attacks from affecting internal workloads.

But the company didn’t stop there. Prince wrote in the blog that CloudFlare’s next-generation servers feature 10 Gbps ports to significantly increase network bandwidth even without port bonding. In an email, he confirmed that rather than use off-the-shelf servers as it has been doing, CloudFlare’s “G4″ servers were designed in tandem with and built by Quanta, the same company that builds Facebook’s servers as well as servers for other large web companies.

CloudFlare still uses off-the-shelf Juniper switches but, Prince added, “[W]e’re tinkering.”

Feature image courtesy of Shutterstock user teflon_timmy.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• How tomorrow’s mobile-centric data centers will look
• Web startups: How to guard against security breaches
• What the Data Center World Can — and Can’t — Take from Facebook’s Open Compute Project

(download)

iTunes

Stitcher Radio

SHOW NOTES:
Hosts: Chris Albrecht and Erica Ogg
Guests: Eliza Kern, Stacey Higginbotham and Janko Roettgers

PREVIOUS GIGAOM PODCAST EPISODES:
Why Big Data Will Be Even Bigger in 2013

Instgram’s Twit-storm, Netflix nabs Disney, GMail’s Pretty iPad App

RoadMap re-run, our talk with Instagram’s Kevin Systrom

iTunes 11, When Things Connect, Sun Volt

What Aspiring New Media Stars Should Know About Agents and Managers

Holiday Gadget Gift Guide

War Tweets, Google TV and Nexus 4

Director Jay Duplass on low-fi movies through high-tech

Election Dissection, Ditching DSL and Dumping the iPad

Sandy’s Social, Infrastructure Impact and Forstall

Windows 8 Surfaces, and disruption eruption

iPad Mini, iMac gets skinny

Boxee Cloud DVR, Apple Rumors and Chromebook

Commutist interview: Joy of X author Steven Strogatz

Commutist podcast: Patent trolls, Costco ban and Passbook’s home run

Commutist, meet Nerdist, and interview with Chris Hardwick

T-Metro, Broadband Caps, Remembering Steve Jobs

Apple’s iO-Mess, Dirty Data Centers and Tesla

News from the Mobilize Conference

Paul Tough: How Children Succeed and what you can learn from them

The iPhone 5 Event

Come on, Kindle, Light My 4G Fire

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• How consumer media will change in 2013
• What the shift to the cloud means for the future EPG
• Takeaways from connected consumer’s second quarter

While the Facebook-founded Open Compute Project is working hard to drive margins and any sense of stability entirely out of the server business, Facebook itself is telling the storage industry where it should be focusing its attention next — on a wide array of storage options to address a wide array of big data applications. Essentially, Facebook is Goldilocks to the storage industry’s three bears — it wants its storage just right.

Stacey Higginbotham (left) and Jay Parikh (right) JULIADEBOER PHOTOGRAPHY http://www.juliadeboer.com

During a keynote at the Open Compute Summit on Wednesday, Facebook VP of Engineering Jay Parikh laid out his vision for a storage architecture that encompasses everything from hard disk to flash to — yes — Blu-ray in order to meet the needs of the company’s growing number of applications. The idea (and one that we’ll be discussing at Structure: Data in March) is that storage companies need to think more broadly about how companies might use their technologies in order to serve applications that have different requirements about how they access and deliver data.

Facebook’s concerns are especially relevant in the era of big data, when companies are amassing always-growing volumes of data that they might not want to, or be able to, throw away. So, while database performance might be critical for applications such as wall posts on Facebook — thus necessitating all-flash servers like Facebook’s new Dragonstone design — it’s markedly less important when it comes to storing petabytes worth of user photos that haven’t been accessed in two years. In the middle might fall something like Hadoop, which Facebook uses as a massive data warehouse that, really, just needs to be fast enough to be useful.

Parikh, for what it’s worth, likes to use a car analogy instead of a fairy-tale one. Discussing the company’s desire to use more flash at our Structure Europe conference in October, he said the current process of flash deployment is “like adding a Ferrari engine to your server.” During his presentation at the Open Compute Summit, he compared hard disks to minivans, flash to sports cars and pined for something like a Toyota Prius to be the third car in the garage.

Facebook’s new Dragonstone server.

Although Blu-ray might be a stretch at this point, he told me during a hallway chat after the session, it actually holds some promise. After all, it’s fairly fast, it’s very low power and it’s highly durable. If he were producing Blu-ray disks or flash drives, Parikh said, he’d try to consider a world where hard drives don’t exist and then start thinking about how to expand the storage medium’s utility to fill that void in a way hard drives never could.

And where Facebook goes on infrastructure, large industries and their IT budgets often follow. Facebook’s Open Compute server designs might have seemed somewhat crazy two years ago, but now large banks and cloud providers are on board evaluating and even building their own servers. Server makers such as Dell saw the writing on the wall and are getting behind Open Compute early in order to meet demand for this type of hardware in the future.

As more companies look to match their storage media with the specific needs of myriad types of data applications, the storage vendors and manufacturers that provide this capability might be the big winners. Companies might like to see hard drives go the way of tape drives, but that can’t happen until something better — and better suited to a big data world — take their place.

Feature image courtesy of Shutterstock user Nomad_Soul.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• DataSift highlights more limitations in the public cloud
• 9 Companies that Pushed the Infrastructure Discussion in 2010
• How to Make Cloud Computing Greener

The company announced at the Open Compute Summit on Wednesday that it will build its own servers designed for the hosting market. Rackspace has a prototype of the design in its labs and plans to test it with the idea of putting it into production before the end of this year. Unlike Facebook, which built out what it called vanity-free servers aimed squarely at its application, the technicians at Rackspace needed a server that will a bit more general purpose, but still designed for operating a cloud service as the lowest total cost of ownership.

For HP and Dell, the two companies that designed and built most of the 90,000 servers Rackspace runs today, this news will be a blow. After all, Wesley Jess, VP of supply chain operations at Rackspace, told me in an interview that the company is adding servers as a much faster rate because it is building out OpenStack based clouds in various places around the world. Jess expects that the switch to its own servers will save the company between 20 to 30 percent in the overall cost of running its data centers.

Rackspace is contracting with Wistron and Quanta, two server manufacturers that also build boxes for Dell and HP. The catch is, the Dell and HP boxes aren’t optimized for Rackspace and because of the groundwork already laid by the Open Compute Project, Rackspace can now afford to tweak the existing designs offered by Open Compute for its own use.

“We’ve been very transparent with our supply base and one of the issues we face is we have a lot of suppliers who try to differentiate themselves from others, but where they think they are adding value doesn’t really add value to me,” said Jess. “The server industry has been focused on the areas where they are innovating, but we find they are iterating on areas we don’t care about.”

With other hosting providers such as NTT and Orange joining the Open Compute Foundation, it’s pretty easy to imagine Rackspace’s work getting picked up by other companies eager to build their own optimized hardware. Not only are the plans now out there, but they are out in a forum and backed by vendors that are encouraging innovation and iteration on the existing designs. Thanks to the modularity of these designs and the openness around them, the pace of change in hardware is approaching that of hardware.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• Infrastructure Q3: OpenStack and flash step into the spotlight
• Infrastructure Q2: Big data and PaaS gain more momentum
• A field guide to cloud computing: current trends, future opportunities

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• Migrating media applications to the private cloud: best practices for businesses
• 12 tech leaders’ resolutions for 2012
• Infrastructure Q2: Big data and PaaS gain more momentum

Sasquatch watches over the lobby of Facebook’s data center in Oregon

In a rare visit to Facebook’s Prineville data center on Thursday, the temperature hit a high of 93 degrees outside. While the cows we passed on the 20-minute drive from the Redmond, Ore. airport searched for any semblance of shade, Building No. 1 of the data center was as noisy as an industrial factory, with air flowing through the cooling rooms and the humidifier room spraying purified water onto the incoming air at a rapid rate. It’s like peeking inside a brand new Porsche while it’s being driven at its fullest capacity.

Facebook’s data center here is one of the most energy efficient in the world. The social network invested $210 million for just the first phase of the data center, which GigaOM got a chance to check out during a two-hour tour. Building No. 1 is where Facebook first started designing its ultra-efficient data centers and gear, and where it wanted the first round of servers that it open sourced under the Open Compute Project to live. Since then — Building No. 1 was opened up in the spring of 2011 — Facebook has slightly tweaked its designs for Building No. 2 at the Prineville site, as well as the designs for its data centers in North Carolina and Sweden. Building No. 2 will use a new type of cooling system that involves media (made of fiberglass) instead of misters.

Facebook is currently investing heavily in its infrastructure boom. It now has an estimated 180,000 servers for its 900 million plus users — that’s up from its estimated 30,000 in the winter of 2009, and 60,000 in the summer of 2010. While that’s tiny compared to Google’s estimated 1 million-plus servers, Facebook, like Google did years before it, is now learning how to be an infrastructure company.

Follow our tour as we take you through the facility, along the air flow route, and down into the secret server room:

The solar panel project next to the data center (it’s small and doesn’t provide much power for the system).

The entrance to Facebook’s Prineville facility shows off the facility’s energy usage, energy efficiency (called PUE) and water usage.

The outside air flows into the data center through a wall with openings, a rubber flow, and a bug zapper in the corner.

Facebook’s Ken Patchett showing how the air flows in.

It really is outside air, folks, hence the bug zapper.

Then the air moves through filters.

Facebook’s Patchett shows off the air filters.

This the room where the air gets humidified with purified sprayed water. In Building No. 2 Facebook is changing up the system.

Facebook’s Patchett shows off the water spraying system.

A closeup of the water spray system.

There are about 15 motors per server bank.

We’re standing above the server room; the cooled air is pushed down and the hot air moves up and out

This is where the hot air moves up and out of the building

Now we’re outside on the roof, where the air leaves.

This is the small solar field as seen from the roof.

The water has to be purified before its used to spray the air. This is a reverse osmosis machine from Siemens. In Building No. 2 Facebook won’t use this system.

Workers grab time to exercise between shifts.

Where the magic happens: the servers.

Ken describes how the air moves into the server room and also why they separated the Open Compute servers from some of the older store bought servers.

The non Open Compute servers.

The Open Compute servers.

Close up of the Open Compute servers.

The Open Compute servers run more efficiently and the aisles with them are cooler

More server shots.

Ken explains how the backup energy systems work with the Open Compute servers.

A top down view of an open compute server.

Ken explains how engineers fix and swap out open compute parts.

Some of the servers that house sensitive financial information are kept behind locked gates.

Of course, the big Facebook Like button

A napkin that Facebook execs say is the drawing of the original power plan for the building

To review the photos check out the gallery:

For more info on data centers check out:

• The ultimate geek road trip: North Carolina’s mega data center cluster
• 10 reasons Apple, Google & Facebook chose North Carolina for their mega data centers
• The controversial world of clean power and data centers
• The story behind how Apple’s iCloud data center got built

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• Locating data centers in an energy-constrained world
• A near-term outlook for big data
• DataSift highlights more limitations in the public cloud

While plenty of companies spend money buying gear from IBM, HP and Dell, others are going direct to the companies that build servers for those giants. For companies such as Facebook, Baidu, Zynga, and Amazon which are building at such scale, the idea of wasting a single cent or milliwatt on an unnecessary feature or frill is economically and ecologically stupid.

Many of these web scale companies have businesses that depend on IT to deliver their product — a webpage or ad — that generates a few cents each time a user loads the page. Cutting costs in IT has huge effects on the bottom line. For example, Facebook spent 16 percent and Google both spent about 9 percent of its revenue on infrastructure and capital expenditures in 2011. For details read the GigaOM Pro item on the topic, found here (subscription req’d).

More infrastructure, more users, less money.

What’s occurring here is a shift in the value of a server, and thus of server makers. What used to be high-end machines with features driven by the engineers inside Dell, IBM, HP, etc., have now become a commodity, and not a Dell-like commodity either — a really low-end commodity. These servers are stripped-down machines custom-built by the guys who built Dell’s and HP’s boxes. The rise of manufacturers like Quanta has begun.

This rise was a direct result of the industry refusing to listen to the demands of its customers, especially because those demands didn’t seem to involve a way for the server guys to make much money. At first, Rackable, now called SGI, picked up on the business, but as Forrest Norrad, the VP of servers at Dell pointed out on Wednesday at the Open Compute Summit, Dell realized that companies like Facebook were not just one-off complainers. They were the leading edge of a new way of doing business– and IT was a fundamental element of that business.

So Dell created its DCS group in 2006 to serve customers buying more than 2,000 servers at time. About five years ago Norrad estimated that the webscale server market DCS served was perhaps 4 percent of the market. Today, Norrad says its about 20 percent of the market. And it’s growing. So while traditional enterprise servers might be that $34.4 billion a year business, that business isn’t where the growth is. Check out this illustration shown by Facebook’s Frank Frankovsky for where he thinks the real growth is.

Throw the server vendors a bone and let’s keep moving.

And here’s where the Open Compute Project comes in. Unlike DCS, which was a successful effort to serve the market once Dell had validated it, the Open Compute Project is a coup by the buyers of servers to take control of their hardware destiny. As such, I wondered if this coup would leave room for Dell or HP to continue to build their businesses. After attending Wednesday’s Open Compute Summit, I can say it seems like it will.

From the talk of creating “innovation zones” within the Open Rack design where vendors can try to create value above and beyond the Open Compute standard, to the AMD and Intel motherboards that were created with the financial services industry, it seems like vendors can work within the confines of Open Compute and still see margins. We’ll have to see what those margins are, but neither HP nor Dell are betting solely on hardware. Both are making big plays into software and services associated with the webscale market as they adapt not just to the changes in servers, but also to the overall change in IT.

Is this a mainframe transitions or a minicomputer transition?

Going forward, the question that should keep the industry up at night is how the infrastructure market will shake out and how quickly this will happen. Norrad says he’s wondering if the legacy enterprise servers will be more like mainframes or more like the minicomputers PC. Mainframes are still around (and super profitable), although not at all a growing business, while minicomputers PCs have all but disappeared. For the legacy gear vendors, the question is will the enterprise server business stick around, even if it doesn’t grow, or will it die out?

The next obvious question is how fast this transition will happen. If this is a rapid shift, companies like Cisco, HP or IBM risk having significant portions of their businesses erode seemingly overnight. If the transition is slow, then vendors can take their time buying promising startups, working with efforts like Open Compute and building up their services or other lines business. So far, the consensus on how fast a shift this will be is mixed, but everyone agrees that transitions happen faster now and that the rise of an open source hardware framework will accelerate it. This will be an ongoing topic of conversation at our upcoming Structure 2012 conference held this June in San Francisco.

Even Open Compute lets vendors like Dell and HP maintain a profit margin, the bigger story here is how servers are no longer the cornerstone of an IT strategy. As our data centers get bigger and the needs of webscale and cloud providers take over more of the industry, servers are mere components of a much larger machine. While components can be valuable, they are no longer the entire system and as such their value can’t be divorced from the data center where they sit.

This means companies must start with a commodity and really work to add value, not just cool features. Historically, the infrastructure business hasn’t been good at this. Maybe it’s learning.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• The capex connection: Why we pay for privacy on the Web
• Infrastructure Overview, Q2 2010
• The promise of SDNs in the enterprise

I know Yahoo is in a mess of trouble — what with patent trolling, a lying CEO and its stock in the toilet — but it’s a particularly bizarre move to go after technologies that your company directly benefits from. Yahoo, for example uses memcached, likely a version that has evolved over time thanks to the alleged infringement. Yes, patent trolls go after widely adopted technologies with an eye toward profit, but in this case it’s like Yahoo is putting a gift horse on notice that it may shoot it in the mouth.

So what does Yahoo want here? This isn’t a posture that will win it any friends. Without seeing the letter or getting a comment from Yahoo (I’ve reached out), this story feels incomplete. Here’s what we know so far. From the Facebook S-1, at the tail end of a section about Facebook’s ongoing patent fight with Yahoo:

For example, we received a letter dated April 23, 2012 from Yahoo indicating that they believe 16 patents they claim to hold “may be relevant” to open source technology they allege is being used in our data centers and servers. Yahoo has not threatened or initiated litigation with respect to matters described in this letter but it may do so in the future.

Lacey has a Facebook statement:

Yahoo’s letter takes aim not just at Facebook but at open source and energy-efficient green technologies developed and employed by countless innovative, forward-thinking companies and engineers. We’re defending vigorously against Yahoo’s current lawsuit, and would likewise do so against any new assertion.

This put Facebook in the cape defending against the machinations of the evil troll, but given Yahoo’s history in developing and open sourcing technologies that underlie the physical infrastructure of the web, it seems odd that it would suddenly reverse positions. Perhaps this is a negotiating ploy for a cross license that Facebook is spinning into drama, but I’m curious to see what’s going on here.

Image courtesy of Flickr user Stefan.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• A near-term outlook for big data
• Dissecting the data: 5 issues for our digital future
• Why the Hoopla About Hadoop?