100 Gbps Via Ethernet

Doc Ruby writes, "As reported at GigaOM, 'Infinera has bonded 10 parallel 10 Gb/s channels into one logical flow while maintaining packet ordering at the receiver,' bridging 100-Gbps ethernet over 10 10-Gbps optical WAN links. Infinera's press release is here. Further from GigaOM: 'The experimental system was set up between Tampa, Florida and Houston, Texas, and back again. A 100 GbE signal was spliced into ten 10 Gb/s streams using an Infinera-proposed specification for 100GbE across multiple links. The splicing of the signal is based on a packet-reordering algorithm developed at [UC] Santa Cruz. This algorithm preserves packet order even as individual flows are striped across multiple wavelengths.' We're all going to want our share of these 100Gbps networks. The current network retailers, mainly cable and DSL dealers, still haven't brought even 10Mbps to most homes, though they're now bringing fiber to the premises to some rich/lucky customers. Are they laying fiber that will bring them to Tbps, or will that stuff clog the way to getting these speeds ourselves?" Rumors say that what runs over Verizon's FiOS is ATM, to support their aspirations for triple-play.

Bad idea for the home network...

[__aaclcg7560]

Couldn't they come up with a single 100Gb cable specification? The last thing I need is ten cables running from each computer into a monster hub. I shouldn't be turning my home into a cable closet! :P

Heh like this will ever see homes

[Durrok]

Hell, why give us even 10MB w/o paying out the arse for it when you have people paying $40/month just for 3MB/512K?

If anything like this ever came out it would probably be shared (obviously) and beyond the standard monthly fee there would be a per MB charge as well.
God I hate USA's internet :|

Fiber's still the wave of the future

[Manchot]

Let's face it, for long-term benefit, fiber's still the way to go. Though still mostly in the research and development mode, there are companies who can make complete wavelength-division multiplexed optical systems on a chip. Some of them can send and receive 40 Gb/s on 40 different channels. Do the math. That's 1.6 Tb/s per fiber. If you have a bundle of 100 fibers, you're starting to push petabits per second. Also, keep in mind that the main limiting factor for optical data transmission rates is the electrical speed of the transistors at both ends, not the fiber itself. As transistor speeds improve, the maximum data transfer rate per channel will improve. The maximum data transmission rate of copper, on the other hand, is pretty much fixed by the fermionic nature of electrons.

Re: not so whoa

[indigoid]

Increasing the bandwidth beyond a surprisingly small figure does not (automatically) improve noticeably the RTT. This is clearly demonstrated in one of the utterly wonderful Stevens books, though I forget which. Most likely one of the three TCP/IP Illustrated volumes.

Ultimately the limiting factors are (a) the transceivers terminating each segment, (b) software, and (c) the speed of light. It sounds like these guys have put their work into (b).