Slashdot Mirror
Researcher Only High Bandwidth Network
Icarus1919 writes "A brand-new 10 gigabit per second per user optical fiber network is now available to researchers in the U.S. (compared to Internet2, which offers only 10 gigabits of bandwidth total, regardless of the number of users). The National Lambda Rail, as it is known, is named for the 40 different wavelengths of light it uses to send data within the fiber network. In the past, researchers have complained about the relatively (relative when you're dealing with terabytes of data) small bandwidth they can access to send data, and the addition of the NLR will most likely be a boon to research."
From what I understand, they will be using quite a bit of the bandwidth in this as well. Do we know how much data must be trasfered at once? Is this continuous data, or is it in chunks? How much ram would it take to hold all of this data until it can be placed unto a disk for storage?
-- johntracy.com, because everybody else is wrong.
I did a paper on this for my introductory networking class LAST YEAR and the topic had been a subject in the class for a few semesters before mine.
------------------------------ SirPhreak - "It's Thinking..."
the addition of the NLR will most likely be a boon to research."
:)
and, of course, bittorrent
relative when you're dealing with terabytes of data
They should be recompressing all those movies to Xvid, then they wouldnt have that bandwidth issue. I mean isn't that what you would do if you had a network dedicated to "research"? (the above post was meant to be humorous, not trollish)
sig?
most of the Lambda team was killed in that indcident at Black Mesa a few years ago....
Me: Hello, I am a researcher and I would like access to this network
Them: And what is your field of research, sir?
Me: Why, I am researching human biology and behaviour in group situations.
Them: Well that sounds very interesting. How exactly would having 10 Gbps help you.
Me: Glad you asked. First I download all the pr0n I can find, then I watch it...
Them: Look, this is about the 1000th application we have had that wants to download porn. Good day, sir.
Me: But, but....
Them: I said good day!
Chaos will always win out over order because chaos is more organized
AnimeNEXT anime convention
So Bush was right and there are internets?!?!
"There is no time, sir, at which ties do not matter," Jeeves, (Jeeves and the Impending Doom)
... oh wait, this isn't Fark. My bad.
They're both 10Gbps, but the difference is that this new one is 10Gbps per *user,* while Internet2 is 10Gbps for *all* users. That's a rather significant difference, I suspect.
Bít, zabít, jen proto, ze su liska!
This is really not so different from how the present internet got started. Will researchers pave the way for a new international fiberoptic network?
When things get complex, multiply by the complex conjugate.
how does this compare to a station wagon full of DVDs hurtling down the highway?
I haven't seen too many disk sub-systems out there that can store data faster than 640 Mbits per second. Will 10Gbit per second really be that useful? Maybe I am wrong...
10Gb/s = 1TB transfered in 800 seconds, or 13 minutes 20 seconds. 10Gb/s per user is far far greater than 10Gb aggrigate.
The Doormat
If you're not outraged, then you're not paying attention.
10 gigabit per second per user
What is that in breasts per second?
That's Newscientist and Wired btw.
They're quite used to the Slashdot effect, and there is no way they're going to go down that easily.
If you must provide a backup, at the very least provide a coralized link or a google cache.
Nice try though.
I think the main application of this improvement is that it could boost the video conferencing applications or video streaming (which has seen so less improvement in the recent days). When talking about 10 Gb/s bandwidth, it does not help anything with our system unless you are dealing with huge amounts of data - like video streaming or conferencing.
Also considering the fibre optic communication(FOC) systems it is been quite some time since we knew the potential of the FOC. Seriouly, we had 1Tb/s experimental systems 4 years back and only now do we have a 10Gb/s per user system.
make love
make: *** No rule to make target `love'. Stop.
ps:Sorry I forgot the html formatting and reposting it for better understanding!
... in the US?
What do you need to be researching? Who do you need to be affiliated with?
Do people like RMS count?
"Nine times out of ten, starting a fire is not the best way to solve the problem." - my wife
Yes that is true they actually did a comparison, which if I remeber correctly endedup here on slashdot about the "bandwidth" of the US postal service just using Netflix DVD rentals and AOL disks as the "data" being transferred. It was astonishing that with just those the bandwidth was something like a factor 300 times faster than then internet in mbps and resulted in more total data being transfered than the internet over the course of a month.
Actually I came to that realization myself a few years back at the hight of my MP3 collecting days. A 40gb drive passed among friends through the mail was much faster and had better results than looking on the net.
You may remember that the "internet 1" was a researcher-only network once and we all know how that turned out.
With even more competition now that the Electric companies can offer broadband service I think we'll see a Moores-law type situation in Telecom (albeit with a longer cycle then 18 months). With networks like this serving as a proving ground for new technology I think we'll see a speed-race among providers. Americans love Horsepower, RPM, GhZ, and they may not know it yet but Mb/s. Shane
That's a great speed, but how much data can be processed on the recieving end? Would it just shove it into RAM or ? I'm just trying to think how a network card would handle/distribute that much data at once.
CB#@(*(#$_@J
free ipod and free gmail!
By "user" they mean "institution connected to our network" not "individual person". As the previous reply said, they're limited to 40 wdm channels, one per user. To put this in perspective (from wikipedia):
Anyone know what the shannon limit for single mode fiber is?
-jim
More information is available at nlr.net including a network map. The first link that went up was between Chicago and the Pittsburgh Supercomputer Center which is run by CMU (where I go). The only problem I think we only have 1 (maybe 2) gigabit links to them, so the bandwidth isn't available onto campus.
I have customers that have single databases over 20TB in size and petabytes of storage in a single datacenter, the biggest well over 25PB. They would pay millions of dollars ever month to be able to replicate that to a disaster recovery or bunker site at realtime.
http://www.leadmagnet.50megs.com
It is not really 10 Gbps per user. New Scientist got that wrong. It's a fiber-optic infrastructure capable with 40 lambdas max. A lambda is a wavelength of light. They use DWDM to split the light on the fiber into 40 lambdas. One lamdda = 10 Gbps.
Now, a single user can, for a period of time, get a whole lambda for himself for a particular application. That's a big deal for researchers. But don't think that everyone at an NLR connected institution automatically has a 10 Gbps link to everyone else on NLR. Most of the users, at best, probably have 1 Gbps ethernet to their desktop. This isn't for browsing the web and playing Doom. It's to connect huge data stores in San Diego to supercomputers in Pittsburgh.
Sounds like we are a step closer to not needing secondary storage anymore.
The point of the lambda rail system is not necessarily the bandwidth. Its that there is no "routing" involved on the base network in the traditional sense. High bandwidth combined with low latency is the goal.
--
WHO ATE MY BREAKFAST PANTS?
Last week we celebrated
the 50th anniversary of CERN (European Laboratory for High Energy Physics).
There was an "Open Day" organized (visits to tens of interesting places at CERN) and the Computing Center was one of the most popular places.
I was honoured to be one of the guides there.
The LHC will produce proton-proton collisions 40 million times per second.
Even after a first pre-selection of the events, there will be around 100 "potentially interesting" events per second that have to be recorded for further (so called "off-line") analysis.
There will be 4 detectors running on LHC (ATLAS, CMS,LHCb and ALICE).
The size of the data describing a typical "event" (collision) depends on the detector, but it is of order of Megabytes.
Assuming 1MB/event/detector that gives
1MB*100events/s*4 detectors*86400s/day=
34560000 MBytes of data produced every day.
That is almost 35 Terabytes of data per day (24 hours).
We expect to have some 10 Petabytes of data per year. And we hope to run the LHC for some 20 years.
Obviously, this amount of data cannot be stored/analysed locally; it will be therefore transmitted to scientific institutes worldwide.
You may have a look at the presentation:
[PPT]
PDF
The answer to computing power is the Grid: more information at http://gridcafe.org/
cheers,
Piotr Golonka
CERN IT/CO