Feeds

Facebook crashes into networking with open switch

Puckering ensues at Cisco, Juniper, Brocade

Boost IT visibility and business value

Not content with shaking up storage and servers, Facebook is creating an open source switch to help it save money on networking equipment and stop it being dependent on technologies pioneered by any single company.

The switch was announced by Facebook's infrastructure czar Frank Frankovsky in a keynote speech at Interop on Wednesday, and it seeks to remove much of the proprietary elements that have typically defined networking gear. We're sure Cisco, Juniper, and Brocade will be pleased.

The "aim is to produce a completely open sourced hardware switch, as well as being OS agnostic," Frankovsky told us. With the switch, the OCP hopes to "break the current appliance model. Most switches today have a tightly integrated software solutions."

The switch specification is being defined by the community at present, and full hardware should be available in nine to 12 months, Frankovsky said. Development will be steered by Facebook's networking chief Najam Ahmad.

VMware, Big Switch Networks, Intel, Broadcom, OpenDaylight, the Open Networking Foundation, Netronome, Cumulus Networks and Facebook have already signed up to participate in designing the specification and fleshing out the design, and more are expected to join.

"Since we've been envisioning this people have been coming out of the woodwork looking to support this project." Frankovsky said.

As with storage and servers, it's certain that incumbent data center equipment suppliers will belch forth a cloud of FUD in response to the announcement.

Facebook has been motivated to get into networking so it need not "be beholden to a black box solution," Frankovsky said. "I've always wondered why we don't think of switches as servers within a rack that don't just happen to have a lot I/O ports on them – really what we're talking about is a bare metal switch that should appear on the network like any other server."

After the switch specification has been firmed up, Frankovsky indicated that Facebook could go even further into networking, and may even dramatically revamp how the network is distributed through a rack.

I don't want to sound like I know what the future will hold, but I think one of the natural reasons for why the networking project makes sense for OCP at this time is that the lines between network and server within the rack are going to be blurring further than they've blurred so far

The Open Compute Project scheme was founded by Facebook and is motivated by a desire by service providers to rid themselves of a dependence on proprietary gear in an attempt to draw greater efficiencies from their hardware than ever before. This has put the frighteners on the traditional IT industry, and caused a wave of commitments to openness by IT giants – claims that are more ambition than fact at the moment.

But much of what Facebook does with its infrastructure comes from the huge scale at which the social network operates, and so Facebook's OCP designs may not necessarily fit the needs of smaller providers. But Facebook thinks the OCP design methodology – stripped down gear, with a minimum of proprietary components – could become the dominant design approach for large technology operators.

"What OCP is promoting is what we believe is a leading indicator of what mainstream IT consumers desire longer term, whether they consume it themselves or through someone else's." ®

The essential guide to IT transformation

More from The Register

next story
The Return of BSOD: Does ANYONE trust Microsoft patches?
Sysadmins, you're either fighting fires or seen as incompetents now
Microsoft: Azure isn't ready for biz-critical apps … yet
Microsoft will move its own IT to the cloud to avoid $200m server bill
US regulators OK sale of IBM's x86 server biz to Lenovo
Now all that remains is for gov't offices to ban the boxes
Flash could be CHEAPER than SAS DISK? Come off it, NetApp
Stats analysis reckons we'll hit that point in just three years
Oracle reveals 32-core, 10 BEEELLION-transistor SPARC M7
New chip scales to 1024 cores, 8192 threads 64 TB RAM, at speeds over 3.6GHz
Object storage bods Exablox: RAID is dead, baby. RAID is dead
Bring your own disks to its object appliances
Nimble's latest mutants GORGE themselves on unlucky forerunners
Crossing Sandy Bridges without stopping for breath
prev story

Whitepapers

5 things you didn’t know about cloud backup
IT departments are embracing cloud backup, but there’s a lot you need to know before choosing a service provider. Learn all the critical things you need to know.
Implementing global e-invoicing with guaranteed legal certainty
Explaining the role local tax compliance plays in successful supply chain management and e-business and how leading global brands are addressing this.
Build a business case: developing custom apps
Learn how to maximize the value of custom applications by accelerating and simplifying their development.
Rethinking backup and recovery in the modern data center
Combining intelligence, operational analytics, and automation to enable efficient, data-driven IT organizations using the HP ABR approach.
Next gen security for virtualised datacentres
Legacy security solutions are inefficient due to the architectural differences between physical and virtual environments.