Nationwide Fiber Optic Science Network
zCyl writes "An article at SMH describes a large fiber optic network called the National LambdaRail, which has completed 1,084 out of a planned 16,000 kilometers between major universities and research institutions. Upon completion it should transmit 400 Gbps and stretch across the continental U.S. Access to the network will be intentionally restricted to scientists and researchers only 'for research and experimentation in networking technologies and applications'."
Linking up universities and research centers with high-speed data communications. That has a real deja-ecoute sound to it.
One line blog. I hear that they're called Twitters now.
Any plans to string a few lines up to Canada and connect our institutions up here?
I volunteer my computer to be a test node on the new system.
If your pipe is as fat as you say it is, what do you need pr0n for?
Give me Classic Slashdot or give me death!
Somebody moderated this Interesting? Jesus.
You're not going to get 50GB/sec from one node to another. it's from one network to another. PCI-X 533 (the next gen PCI-X) can only do 4.3GB/s. However, if you want to connect a cluster of, say, a dozen nodes with PCI-X 533 to another dozen nodes with PCI-X 533 across the country...
We don't have a state-run media we have a media-run state.
Shouldn't getting broadband communication capabilities to rural America be a top priority also? Where I live, I cannot subscribe to DSL due to the poor quality of the telephone lines. Hell, just 4 years ago, the telephone company,(Inland Telephone), changed all the lines from the old aluminum wiring to the "new" copper wire. The fastest I can transfer connect out here is only at 33.6k on a good day. As we speak, I am only connected at 26.4k. I find this assanine, esepecially when I can move 14 miles to town, and have access to DSL, Cable, and WiFi. Out here, the only option for high speed data transfers is sattilite. Far too expensive for me. This should be a major priority if we intend to bring rural america out of the mid-ninteys, and into the 21st century of data transfer speed. Hell, I would be happy if I could connect at just 53k, but I do not think that the monopolistic telephone companies will be upgrading the lines within the next 20 years. After all, the aluminum wiring went out of common usage during the 1970's, when copper wire replaced it. How long am I going to have to wait for 56k capabilities, 40 more years? I will propanbly be dead by then, as that would put me at 65 years old.
Get your free Dropbox account with 2 GB Free storage!
One Cisco 12000 router can easliy move 320Gbps of data. As another poster noted, this kind of capacity is meant to handle many nodes at full speed.
Give me Ludicrious speed! ZOOOOMMMMM!!!!!!! My GOD! They've gone to plaid.........
~corporate tool, but employed~
You answered your own question: "I can move 14 miles to town, and have access to DSL, Cable, and WiFi"
The concept of rural is that which is distinguished from the city. While cities are havens for technology, the countryside is for nature. If you want tech, go where tech is, don't get angry because tech won't come to you. It's not cost effective to wire rural areas - isolated household require up to several miles of dedicated lines serving only one customer, which is not cost effective. It would require decades of subscription from you to pay for the lines to your house. This isn't the case in urban/suburban areas where individual houses only require a few dozen feet of cable.
Oh, and you wouldn't have the internet at all if not for the academics you're trying to fight. If you want a better connection, support the people trying to invent the technology to make it feasible.
GL
That's part of the research; designing equipment that can forward, filter, prioritise, and route traffic at that kind of bandwidth.
455fe10422ca29c4933f95052b792ab2
If this network is to stretch across the USA then no matter how fast it transfers data, there will still be a noticeable latency between one end and the other. The speed of light is not getting any faster. The limiting factor for serving files over NFS, for example, might end up being latency rater than bandwidth or server performance (if CPUs are also getting faster and RAM cheaper).
Perhaps in the future bandwidth will be an almost infinite resource and protocols will be designed around minimizing latency. For example for a remote filesystem you might design a server that spews out all changes to all files as they happen - to every other host that is looking at the filesystem. The bandwidth cost of sending unnecessary files is not significant, and it means a saving in latency because file data will be immediately available at the client end rather than requiring a round trip. (This assumes you don't care about locking and race conditions - but classical NFS doesn't anyway.)
Similarly, web servers might be designed to spew forth a whole bunch of pages you might possibly be interested in as soon as you connect to their site, and your browser's job is to cache them and then show the ones you want. If you want a page that isn't in the set the server sent you, you'll need to make another round trip, and that could be the slowest part. We will certainly need something like this for interplanetary web browsing at acceptable speeds.
-- Ed Avis ed@membled.com
Since SCO claimed ownership of physics.
I think they mispelled 'pr0n'.
Buy Steampunk Clothing Online!
The european research network (up to 10Gbit/s) has an infomercial at their webpage that is interesting, since all the applications and benefits discussed pretty much applies in the US as well.
Some poor NSF grant application reviewer will be saying, "WTF is with all of these grad student projects dealing with 'researching and networking simultaneous transfer of multiple large binary multimedia files'. "
__ Someday, but not this morning, I'll finally learn to use the preview button.
Nope. A Cisco 12000 has 16 ports of 10Gbps. It receives 160Gbps, and transmits 160Gbps, so it "can move" only 160Gbps. Cisco calls this "320Gbps." the internet industry calls this "Cisco math." A Juniper T540 has 32 lines of 10Gbps, so it can actually "move" 320Gbps. A big Avici router can do better.
They are cooperating networks
From what I can understand (amongst all the blurb) this LambdaRail is all about a complete network of (lots-and-lots-of) switched 10Gbps Lambdas (optical wavelengths). So at any point you can dedicate N Lambdas to a particular use and guarantee (at a physical/optical level) bandwidth/latency/QoS.
Specifically, absolutely unconditionally zero impact to any other data transmissions across the network because these transmissions are actually physically (ie optically) seperate and distinct transmissions.
In short, if we could literally segment a 'slice' off the network and isolate it from everything else running around, what would/could we do with it?
Internet2 is a completely different concept.
All the data is transmitted across one network (ie not guaranteed via 'optical separation'; ie 'just like The Internet Today, only much faster') and researching how to route/switch/filter a trillion-zillion packets with minimal latency/guaranteed QoS/additional application-specific functionality and then given those network-abilities researching how to manage that network and what new uses you can apply to that network.With (apparently) the specific intention of eventually, one day, before-the-heat-death-of-the-universe, rolling out said network and enhanced functionality to "the real world/the rest of us humans".
Visit CryptoGnome in his home.