Feeds

Network boffins say Terabit Ethernet is TOO FAST

Sticking to 400Gb for now

Top 5 reasons to deploy VMware with Tegile

The IEEE consensus group in charge of developing future networking standards has some words for anyone who was hoping to see Terabit Ethernet in the next few years: not so fast.

In July, the IEEE Ethernet Bandwidth Assessment ad hoc group issued a report stating that global demand for network bandwidth is growing at such an alarming rate that terabit-speed networks will be the only way to support capacity, should current trends continue through 2015.

But according to participants in the IEEE Industry Connections Higher Speed Ethernet Consensus group meeting in Geneva, Switzerland this week, such blazing-fast speeds might be just a little too impractical given today's technology, making 400 gigabits per second a much more likely target for the next generation of the Ethernet standard.

Don't expect to see a 400Gb Ethernet port on your laptop any time soon, though – or even a port running the current maximum of 100Gb/sec, for that matter. Such speeds simply aren't necessary for individual PCs, or even most servers.

Large-scale data centers that move lots of packets across network backbones are seeing their links become steadily more congested, however, meaning higher speeds will soon become necessary if overall network traffic growth is to continue.

Forget about RJ-45 cables, too. The only practical way to achieve such stratospheric bandwidth rates is through optical links – and therein lies the problem, because today's top-speed networks are already pushing the envelope of how fast we can push data through fiber optic cable.

According to a presentation given at the IEEE meeting by Kai Cui and Peter Stassar of Huawei, the current 100Gb Ethernet technology has yet to reach a broad market, largely owing to its high cost. Terabit Ethernet would be even more expensive; therefore, to justify its existence it would have to deliver a significantly lower cost per bit than 100Gb Ethernet.

One way to achieve that would be to reuse the building blocks of the existing 100Gb Ethernet standard as the basis for Terabit Ethernet. But Cui and Stassar say doing so "would imply impractically big packages and large amount of interface signals" – that is, it wouldn't work.

The other way would be to develop new light-modulation technology that could transmit data more efficiently. But although several such ideas are in the works, they're still too immature for commercial applications.

"The technology needed to implement advanced modulation formats is currently very far from technical and economic feasibility," Cui and Stassar conclude. "This would suggest that on the short term 1Tb/s would be a too high rate from an engineering perspective and it is unlikely to justify the major R&D cost needed to develop the required technology platform."

On the other hand, 400Gb Ethernet might just be feasible. According to a second presentation developed by a broad cross-section of IEEE Ethernet consensus group members, 400Gb/second is just about as fast as you can go with the current 100Gb Ethernet technology before you get diminishing returns, and there are several technical solutions that could be used to reach that level.

So that's it, then. Following the presentations, IEEE committee chair John D'Ambrosia took a straw poll to see who was in favor of which plan. Of the 62 attendees, 61 voted in favor of 400Gb Ethernet as the next target and one voted to decide later, making Terabit Ethernet effectively a lost cause – at least for now. ®

Beginner's guide to SSL certificates

More from The Register

next story
It's Big, it's Blue... it's simply FABLESS! IBM's chip-free future
Or why the reversal of globalisation ain't gonna 'appen
IBM storage revenues sink: 'We are disappointed,' says CEO
Time to put the storage biz up for sale?
'Hmm, why CAN'T I run a water pipe through that rack of media servers?'
Leaving Las Vegas for Armenia kludging and Dubai dune bashing
Microsoft and Dell’s cloud in a box: Instant Azure for the data centre
A less painful way to run Microsoft’s private cloud
Facebook slurps 'paste sites' for STOLEN passwords, sprinkles on hash and salt
Zuck's ad empire DOESN'T see details in plain text. Phew!
Windows 10: Forget Cloudobile, put Security and Privacy First
But - dammit - It would be insane to say 'don't collect, because NSA'
prev story

Whitepapers

Cloud and hybrid-cloud data protection for VMware
Learn how quick and easy it is to configure backups and perform restores for VMware environments.
A strategic approach to identity relationship management
ForgeRock commissioned Forrester to evaluate companies’ IAM practices and requirements when it comes to customer-facing scenarios versus employee-facing ones.
High Performance for All
While HPC is not new, it has traditionally been seen as a specialist area – is it now geared up to meet more mainstream requirements?
Three 1TB solid state scorchers up for grabs
Big SSDs can be expensive but think big and think free because you could be the lucky winner of one of three 1TB Samsung SSD 840 EVO drives that we’re giving away worth over £300 apiece.
Security for virtualized datacentres
Legacy security solutions are inefficient due to the architectural differences between physical and virtual environments.