2.56 Tb/s Transmission Record

RalfM writes "2.56 terabits of data per second in new transmission record by Bell Labs, Lucent's research arm." So this thing could transmit my entire mp3 collection in under a half second.

Comments

And what then?

[Saib0t]

So this thing could transmit my entire mp3 collection in under a half second.

Good, and then you'll have to wait 4 hours for your HDD to write them ;-).

Re:And what then?

[*xpenguin*]

Let's say you have 2.5 gigabytes of mp3s.

Most harddrives can write 30 megabytes per second when tweaked with hdparm:

2500 (megabytes)/30 (megabytes/s) = 83.33 (seconds)

Re:And what then?

[mjisgod]

your math is for only 2.5GB of mp3, but by taco's math he must have over 100GB of mp3 which means way more than 83s

Re:And what then?

[Anonymous Coward]

In other words, 2.56 Tbit/s is about 10000 times faster than 30 MByte/s = 240 Mbit/s = 0.24 Gbit/s = 0.00024 Tbit/s. Which means that one such pipe could satisfy 10000 people downloading at maximum hd speed.

Re:And what then?

[Fweeky]

> Good, and then you'll have to wait 4 hours for your HDD to write them ;-).

This transmits 320GB/s; food for thought is that most system MEMORY architectures would struggle to reach 1/400th of that. Yummy.

Re:And what then?

[56ker]

Note he said less than half a second - that just means he must have between a 0 and 1.28Tb mp3 collection. All these figures people are coming up for it are just guesses.

Re:And what then?

[Saib0t]

2500 (megabytes)/30 (megabytes/s) = 83.33 (seconds)

Sure, 83 seconds, for 2.5 GB, but we're talking here about transfer capabilities of 320GB/s, so approximately 11000 times faster than your HDD can write data... I fail to understand why you replied with these figures.

Re:And what then?

[Anonymous Coward]

you forget that taco is a megagewl warez d00d with many many many more illegal mp3s on his hd.

Re:And what then?

[Anonymous Coward]

And a 2 GHz process handling the bit stream would have to process 160 bytes PER CYCLE to keep up. Talk about optimized coding. :)

Re:And what then?

[Anonymous Coward]

Your mp3's will go nowhere if the CBDTPA passes before this hits the market.

Re:And what then?

[clockwork18]

Indeed this would be true if 30 MB/s was a true measurement. Most HDD's now are 30 MB/s peak burst. There is no way a hard drive can keep up at 30 MB/s for the entire track length of the drive.

Re:And what then?

[Anonymous Coward]

Where did you get those facts?

ATA66 peaks at 66mb and ATA100 peaks at what? Hmmmm....100

Of course these are peaks and not sustained

Re:And what then?

[Anonymous Coward]

Actually, the fastest ATA disks are around 30MB/s (slowest part of the disk) to 50MB/s across the disk.

My BarracudaIV is 27MB/s through to 43MB/s..

Bandwith problems?

[mattwnet]

If Bell Lab's new technologies are used, does this mean the bandwith problems discussed recently can be fixed?

Re:Bandwith problems?

[chill]

No, 'cause the LambdaXtreme unit used is unbelievably expensive, and you need at least 2 of them.

Also, you need EBDA single-mode fiber, which isn't the majority in the ground.

Soon, though.

Charles E. Hill
Core Network Engineer
Lucent Worldwide Services

Re:Bandwith problems?

[Anonymous Coward]

Worth noting that this Lucent product isn't the only entry to the high-speed long haul market - always check the source; this was a Lucent press release.

For example, Nortel's HDX product has gone down a storm at OFC this week. However, the cost barrier remains - the HDX is something like $10 million!

Re:Bandwith problems?

[chill]

Lucent is shipping, Nortel is not. Nortel delayed the HDX recently -- insiders were citing customer dissatisfaction.

Yes, it was a Lucent press release. However, Bell Labs is the inventor of so many optical inventions (DWDM being only one). Lucent holds more patents on this area of technology than almost all their competitors combined. It really helps.

Re:Bandwith problems?

[linuxscrub]

Since I couldn't locate the presented paper online and was too busy working a booth to attend the presentation, I have a Dumb Question:

What is EBDA fiber? Where could I find out more?

Thanks,

Linuxscrub

Re:Bandwith problems?

[eracerblue]

hmmm let's see:

The release claims invetion of DWDM. Maybe, but they didn't invent WDM. What does the "Dense" mean? Maybe a locker. Woooo.

Next, DPSK, also a claimed Lucent invention. I don't know... but it's been around for years... and just now getting used? Not sounding particularly spectacular.

Now forward error correction & Raman amps... kudos to that. Same with the distance.

Now we all wait for the real advancements... pushing the 40G/channel barrier. Yeawn... old news.... old news...

True-that with the EBDA fiber. Would be nice to take advantage of the existing, dark fiber.

Re:Bandwith problems?

[chill]

"Dense" in DWDM commonly means more than 10 wavelengths simultaneously, though it varies depending on the vendor.

Pushing beyond 40 Gbps requires turning the laser on and off faster -- something that is going to be a real trick considering how fast it is moving right now.

Of course, finding the other components that can actually USE data moving at 40 Gbps, much less multiple streams of it, THAT will be the trick.

Re:Bandwith problems?

[chill]

EBDA stands for ErBium Doped something, I forget what the "A" is for. In a brief nutshell...

Traditional fiber only allows a signal to travel so far before it has to be regenerated. The actual distance depends on the quality of both the fiber and the light source. Regeneration means turning the signal back to an electrical one and retransmitting it. Bleh!

A few years back Bell Labs scientists figured out that certain rare-earth elements (Erbium) have interesting optical properties -- it will absorb energy at one frequency and when prodded, release it at a different frequency.

Erbium, it so happens, releases that stored energy at about 1351 nm. So, by placing a fiber that has erbium mixed in with it at a certain point on a run, it can be "pumped" and then triggered by an incoming 1351 nm wave to release energy and "boost" the incoming signal.

Two lasers are shown down the fiber -- the one with the signal (about 1351 nm) and the "pumping" laser, at a different frequency. The "pumping" laser "charges" the erbium-doped section. When the faltering 1351 nm signal laser comes thru, it triggers the charged section to release it's stored photons and they lockstep with the existing signal, boosting it.

Other elements are used to dope fiber from 1500 nm signals, the other common type.

I'm not sure where on the web to find technical info on this. Everything I have is training materials from Lucent (I'm an ATM/FR/Optical field Engineer).

Try...
http://www.geocities.com/SiliconValley/Circuit/8 07 0/

Re:Bandwith problems?

[eracerblue]

turning the laser on and off faster ...

This 40-Gig isn't direct-mod is it?? If it was I would be totally impressed. But at that distance I'm thinking no way. The chirp alone would be hideous. Wouldn't this be using some sort of exteral EA modulator?

As for using all this bandwidth, as soon as network-processing really takes off we will have need for all the bandwidth we can get. I pretty much mean tapping the pipes directly into processors - turning the net into a supercomputer.

And once the whole photonic crystal / optical computing thing gets taken care of... woah... all these "fat" optical pipes of the past will seem very small indeed.

Re:Bandwith problems?

[linuxscrub]

Thanks.

Based on your explanation, I believe you are referring to EDFA (erbium-doped fiber amplifier) technology, of which one important piece is the fiber (duh).

Actually, EDFA has been primarily used to optically amplify the C-band (about 1525-1565 nm), eliminating the O-E-O step. Typically, the erbium (in the doped fiber) is pumped into a more meta-stable state at 980 nm, which can then be stimulated to emit (amplify) with c-band photons.

[From a guy that works for a company that makes the test equipment for functional testing of active elements that, eventually, go into these types of networks.]

Not on my bandwidth

[Anonymous Coward]

DSL cannot hack those rates...sigh.

How does this stack up?

[SuperCal]

I was wondering... How does this stack up next to the transferrates of those fiberoptic telecomunication cables, like the ones they lay underwater and I beleave are used in the net's backbone?

Re:How does this stack up?

[Soft]

How does this stack up next to the transferrates of those fiberoptic telecomunication cables, like the ones they lay underwater and I beleave are used in the net's backbone?

Far ahead but not that far. From memory, the latest transoceanic cables must run at something like 160Gbps.

Re:How does this stack up?

[Proc6]

If Im reading this article correctly, youre not even close. It says:

According to a Gartner report, transoceanic fiber capacity ballooned from 432.7 gigabits per second (Gbps) in the fourth quarter of 1999 to nearly 3,500 Gbps at the end of the fourth quarter of 2000. Gartner analyst Bill Hahn predicts that capacity will mushroom to about 13,400 Gbps by the end of this year.

http://news.com.com/2100-1033-254520.html?legacy=c net

Re:How does this stack up?

[Anonymous Coward]

This is talking about the total transoceanic fiber cable's capacity rather than each individual cable. Thus they are not comparable.

what a fat pipe

[56ker]

I want one :o) - but no seriously can anybody think of a practical use for a tb/sec connection?

Re:what a fat pipe

[Anonymous Coward]

but no seriously can anybody think of a practical use for a tb/sec connection?

pr0n. lots and lots of pr0n.

Re:what a fat pipe

[morgajel]

this will do wonders for out backbone- maybe even help us lower the general price of high bandwidth net connections. imagine if your local ISP's incoming bandwidth could easily be doubled? that *might* mean more alternatives/chaper bandwidth for us consumers.

Re:what a fat pipe

[Peyna]

Not for one person, but for a million people, I could think of a lot of reasons for one.

Re:what a fat pipe

[glwtta]

uh, telcos? in other words the companies that products based on this will be targeted at?

Question's like "who needs this much bandwidth/disk space/ram/cpu power" seem rather silly - don't worry, we'll catch up :)

Re:what a fat pipe

[SuperCal]

I'm pretty sure this would be used by telcoms for their communications lines. Long distance voice calls are sometimes (always?) converted to a digital form and sent over these types of data lines. I think though the use of compression technologies, this is cheaper then analog.

Re:what a fat pipe

[Anonymous Coward]

56 you are a simple minded, trailer trash reject. open your fuckin eyes.

Re:what a fat pipe

[Salsaman]

Why, for downloading pr0n and playing quake of course !

Re:what a fat pipe

[Anonymous Coward]

make linuxiso.org into a huge server farm connected by this fat pipe, so even when favourite distro x comes out with a new version you can get it a the max speed the connection on your end can handle.

Re:what a fat pipe

[Anonymous Coward]

Funny.. His billness said "I can't see anybody needing more than 640kb of RAM" but look what happened...

Re:what a fat pipe

[xrayspx]

I know that genetic research companies deal in large (800GB) filesizes at times, might probably need to transmit those trans-continentally at some point to other offices, etc.

However, that also goes back to "Never underestimate the bandwidth of a 747 with box of tapes on it".

Re:what a fat pipe

[Emugamer]

okay so now you put up the challenge I had to go looking.. damn you

1/2 serious 1/2 not so serious post here...

Lets imagine the population of new york which is a tad less then 19 million. now lets give each of them a phone.
given the assumption that no more then 35% are on their phones at any given peak time we have 6.65 million pone conversations going on. Now lets assume that of these phone calls no more then 40% are inter-city phone calls which would use this type of pipe.

2.66 million calls now.

Now lets say that compression algorithims bring the average phone call bandwidth to say 20Kbit/s

quick math leads that to 53 Gb/s so all of New York uses for voice communications on a high end is 2% of this pipe.

so now we have 98% left to fill

Ive heard that an *average* (this puts us in the minority) computer user on an internet connection will use 40kbit on average during a session with the net. and with that number on average there could be 64 million people using that line (which seems high to me) but I can't find any statistics to backup that 40kbit estimate at this time.

So here of course are the lame responses:

one script kiddie with an Outlook "add-on", a remote exploit he downloaded somewhere and to much time on his hands

One large dorm full of p2p, porn, warez hungry students

one slashdot reader who wants to test to see if this article is true.

Re:what a fat pipe

[BoneFlower]

Clustering. Currently the bottleneck in clusters is network connections, simply put most computers you will cluster are faster than 100Mbps and 1Gbps networks. THe faster you move the data between systems, the faster your cluster- High end supercomputers do this, maximizing transmission speed between the individual porcessors as much or more than the CPU speed.

Lets say you take 4 Quad PIV 1Ghz systems, build two Beowulf clusters. The one with Tb/sec networking between the systems will be faster, noticeably, than the one with Gb/s networking.

This will also push things like Gb/s networking from its heights down to the average person. I don't see the average person having a Tb/s network anytime soon, but Gb/s networking will probably be more common within a couple of years. That will probably be the biggest benefit of this advance, the people that absolutely need the fastest networks go to Tb/s, and those that only WANT a fast network now get Gb/s

Re:what a fat pipe

[James Crid]

Interesting. Let's take this one step further. To broadcast "broadcast-quality" radio, you need 128k bitrate. Assuming there are 10,000 radio stations in the US, that's 1.2 Gig. Assuming there are 100,000 radio stations in the world, that's 12Gig. Broadcast quality television is about, oooh, 5Meg? The UK has, including pay-per-view, around 500 stations, so let's assume there's 50,000 stations in the world: 250 Gig. ...it's really rather difficult to fill this space...

Re:what a fat pipe

[Emugamer]

Send on Demand Entertainment ... its the only thing that could satiate this type of pipe and then only with a large subscribition base

Re:what a fat pipe

[billy_troll]

why did you get modded up?
because you said...
mmm... beowolf cluster.
karma whore.

Re:what a fat pipe

[0x0d0a]

Well, it makes for a really easy implementation of a lot of protocols. No need for some poor software engineer to run around trying to figure out what information he doesn't really need to send over the wire...just send the entire game/world state.

Same goes for VR worlds. Heck, you could have every single remote computer render a bitmap/voxel map that is your view of them and send it to you. Easy to implement, no limitations. Maybe to make things a bit more sane, only get all the renderings within a "virtual mile" radius. You don't have to worry about latency when you turn around (you've already got the images!), you can see as far as you want...

The main drawback is that a top of the line PC right now has a system bus bandwidth of only 2.05 GBps, which means that you'd need a computer about 500 times as fast or a lot of fancy dedicated hardware.

Re:what a fat pipe

[Anonymous Coward]

The computers that will deliver the matrix to millions and millions of human brains in the future will require this technology.

Re:what a fat pipe

[Anonymous Coward]

Send on Demand Entertainment ... its the only thing that could satiate this type of pipe and then only with a large subscribition base

Yeah, and 640k ought to be enough for anybody

Re:what a fat pipe

[Com2Kid]

Real time broadcasting of videos from studios. No more damned taped delays. :)

All sent in whatever formats are needed, all at once. Nice and speedy like.

I myself am sick and f*cking tired of MPEG2 compression artificats in my digital cable. :(

You realize that implies...

[Spittoon]

...that you have a terabyte worth of MP3s. Unless you mean "under a 16th of a second". :)

Re:You realize that implies...

[Anonymous Coward]

Tera-BITS per second. So that would be 320 Gigabytes per second, so half would be 160 Gigabytes of MP3's.

Re:You realize that implies...

[Anonymous Coward]

This could also mean that he has _less_ than 1.28 terabytes. He could transfer 1KB, 1MB, 1GB, or 1TB in under half a second.

Re:You realize that implies...

[Anonymous Coward]

This could also mean that he has _less_ than 160 gigabytes. He could transfer 1KB, 1MB, or 1GB in under half a second.

Re:You realize that implies...

[Anonymous Coward]

that's still an almost unbelievably huge amount of MP3s unless he runs a server

Re:You realize that implies...

[Warped-Reality]

Tera-BITS per second. So that would be 320 Gigabytes per second, so half would be 160 Gigabytes of MP3's.

Also, when you get into numbers this big, whether your using 1000 or 1024 bytes per kilobyte [or mega/giga/terabyte] makes a difference.

Using 1000: 1 Terabyte = 1,000,000,000,000 bytes
Using 1024: 1 Terabyte ~ 1,099,511,628,000 bytes
there's a difference of just under 100 gigs

Re:Terabyte?

[Peyna]

Tera is a prefix meaning one trillion (10^12), in this case it refers to one trillion bits (not bytes).

How practical exactly.....

[happyslinky]

While I have to admit 2.56 Tb/s is darn impressive the article doesnt mention if this can be applied to currently existing fiber optic networks. After having invested millions in new fiber and equipment for my area I seriously doubt my provider (twc) would be willing to just jump up and make large (read as: expensive) modifications. Especially if our network is "just good enough". Advances like this are interesting but how long will it take to "filter down" to us consumers?

Re:How practical exactly.....

[swb]

Most of these speed records are about as applicable to everyday communications problems as the Thrust SSC's land speed record is to the problems of everyday ground transportaton.

Eventually the technological advances will influence everyday communications technology, but for now they're a gee-whiz thing that's of little direct value.

Re:How practical exactly.....

[chill]

Actually, Time Warner was one of the first Lambda Router customers last year. The LambdaXtreme unit is what the article mentions and it is a super-long-haul unit. AOL/TW was supposed to be using the 1.6 Tbps version for their coast-2-coast backbone.

Re:How practical exactly.....

[ImaLamer]

If your provider [twc] is Time Warner Cable they might.

In my area they went to work faster than a lot of cities. Now they dominate the market and we are the second city to get HBO on demand and we also have another video on demand library.

They own all that content that I er you want to steal so they might actually be interested.

Nice try... but if you wanted to shoot down the practical side you should have pointed out that your computer isn't going to like all that data so fast.

Streaming mp3s, every song... ever!

Re:How practical exactly.....

[Soft]

While I have to admit 2.56 Tb/s is darn impressive the article doesnt mention if this can be applied to currently existing fiber optic networks.

It does, implicitly: this uses advanced dispersion management (say, 10km dispersion-compensating fiber every 100km) and Raman amplification (power lasers launched backwards into the fiber every segment). If your cable isn't wired this way from the beginning, upgrading it would be more expensive than starting from scratch, I guess.

I seriously doubt my provider (twc) would be willing to just jump up and make large (read as: expensive) modifications.

You're speaking of a local bandwidth provider, which just won't ramp up to these bit rates in the near future, their customers won't generate so much traffic, and they could use several fibers instead of one anyway. This is for long-haul transmission, typically transoceanic.

Advances like this are interesting but how long will it take to "filter down" to us consumers?

Just wait for the transatlantic cables to be upgraded, you might feel it.

Re:How practical exactly.....

[mericet]

You are kidding right? It is not meant for an ISP to use to your home, or to its bandwith provider for that matter!

It will be used (in a few years - I guesstimate 2-3) by major telcos for major national and international backbones and for new ones at that.

Re:So you have

[Anonymous Coward]

Tera-BITS per second. So that would be 320 Gigabytes per second, so half would be 160 Gigabytes of MP3's.

Re:Terabyte?

[Peyna]

To tell you the truth: I had to look it up to make sure of the spelling. At least I looked it up before using it! =] Maybe they really did mean a mountainous region on the moon? You never know.

Ping

[Kizzle]

Maybee I can finaly get a good ping in quake now.

Re:Ping

[Anonymous Coward]

BZZZT! WRONG! FAT PIPE does not mean low pings!

Re:Ping

[Anonymous Coward]

Not necessarily, but there is a connection. There's no way to get a good ping on a slow connection, because the packet takes too much time before enough of it is received on the other side to start sending the reply.

Re:Ping

[Anonymous Coward]

And the quake packet size is...?

Re:Ping

[Anonymous Coward]

That doesn't matter. Smaller packet -> lower ping. Faster pipe -> lower ping (when all other factors are constant).

Re:Ping

[Anonymous Coward]

Wrong. don't confuse LATENCY and THROUGHPUT.
While often latency (ping) gets lower with bandwitdh increase its often not the case. Try to play Quake on 1Mbit satellite uplink and you would go back to 56k modem after first round.

Unfortunately it would still take 10 minutes..

[teamhasnoi]

to transmit my Natalie Portman jpegs..

Re:Unfortunately it would still take 10 minutes..

[Anonymous Coward]

This may come as a shock to you, but resizing a 400x300 picture to 400000000x300000000 does not result in a more detailed picture.

Re:Unfortunately it would still take 10 minutes..

[SuperCal]

That was awsome... I almost wet my pants when I read that... I just wrote a script to change the size/res on all my Digital Photos to smaller sizes, and you are right... You can get away with much lower res then you would think. For some reason everyone wants the pictures I take, and I was starting to think I was going to need one of those terrabit connections to send them all... How many pitures at 400x300 could you send in a minuet at that speed?... note my lame attempt to bring this post back on topic...

Re:Terabyte?

[glwtta]

Actually, though technically a terrabit should be 10^12 bit, I think they mean the binary power closest to one trillion - 2^40 (or whatever it is). I believe that's technically called a Tebbibit or somesuch nonsense, that never caught on so everyone just calls it a terrabit (except for HD manufacturers who try to use this to pass off their products as having more space than the really do)

Re:Terabyte?

[Anonymous Coward]

Peyna Anders?

To where?

[SpinyNorman]

So this thing could transmit my entire mp3 collection in under a half second.

Sure, and unless you have a storage device that can accept data at that speed, the only place your MP3s are going is /dev/null, so you may as well save the net bandwidth and use the mv command.

Re:To where?

[ivan256]

Actually, and I'm serious, I'd be impressed if he could move data to /dev/null that quickly. I don't know of any small computer bus architectures available right now that could handle that kind of speed.

More impressively, almost 4 million people could streem unique mp3's over this line simultaniously.

Re:To where?

[SuperCal]

You are skipping the first problem. Its not to where.?. its from where.?. I'd be impressed if he had a disk/memory, device that could transmit that fast to the network equipment.

Re:To where?

[JordanH]

This kind of speed would not be for connecting computers to each other directly, but rather big comm backbones. On each end, fast switches would split this out into more manageble rates.

Re:To where?

[ivan256]

That's exactly what I'm trying to say.

Re:To where?

[JordanH]

Oh yeah... it is... Wish I could retract my comment.

Re:Terabyte?

[glwtta]

or whatever number of r's it has

well now I am torn

[glwtta]

Is it a Beowulf cluster of these that I want to imagine, or do I want to go for the usual "that's a whole lot of pr0n!" comment?

being trite and obvious has never been harder...

Re:well now I am torn

[Anonymous Coward]

You want to imagine a Beowulf cluster of high resolution porn. You failing to see the obvious must be what's funny about your comment.

Re:well now I am torn

[zapfie]

You could always have a Beowolf cluster of them transmitting pr0n..

Re:well now I am torn

[mother_superius]

Well, the pr0n comment would allow you to quote the Simsons...
Generic Nerd: "I wrote a program which downloads porn a million times faster!"
Marge:"Why would anyone need that much porn?"
Homer: "soo much..." (drool)

That always gets you karma.

Re:well now I am torn

[Alsee]

12:00:00.0 installed 2.56 terabit internet connection.
12:00:00.3 downloaded every existing JPG of Natalie Portman.
12:59:59.8 downloaded Natalie Portman.
12:59:59.9 Put grits on the stove.

P.S.
Ok, she was in a starwars movie, but it was a bad starwars movie. Ok, she's attractive, but she's not amazing. So, why the hell is she this huge running /. routine? And what's with the Hot Grits?

-

Re:well now I am torn

[jonnythan]

I think it's because she's young, attractive, and extremely intelligent. Kinda geekish too, I believe.

Re:well now I am torn

[Alsee]

extremely intelligent. Kinda geekish too

Ahh. I don't know much about her out-of-character.

But, uhhh... the grits? hehe

-

Re:well now I am torn

[jonnythan]

I dunno.. I remember seeing the grits thing for the first time, and I just laughed my ass off. I became an anymous grits-poster, and kinda helped it along I suppose. Sorry ;)

Re:So you have

[Anonymous Coward]

Hmm, the original poster was claiming "1.28 terrestrial bytes of mp3s" (on Earth, bytes have 8 bits). This is consistant with the "transmitted under a half second" part, so no nitpicking is necessary.

Novels?

[kanishka]

...(Sending a gigabit of information per second is equivalent to transmitting the information content of approximately 1,000 novels every second; sending 40 gigabits per second over 64 channels is equivalent to transmitting the information content of 2,560,000 novels)...

Information measured in units of novels? Novel is text only data. So, 1000 novels doesn't sound impressive. 1 DVD per second would be more impressive :).

Re:Novels?

[glwtta]

I think this is meant for the "common person" to understand. Of course the "common person" has a really good idea of how a novel, or even a giganovel compares to digital content such as web-pages. So I really think the point of the comparison was to have a Big Number. :)

Re:Novels?

[Zarquon]

Let's see.. networking and HD units are usually base 10. 1,000,000,000 / 8 / 1000 = 125,000 bytes. This is actually low; most of my ebooks are in the 300-500k range. Maybe they just read juvies?

Re:Novels?

[Random Feature]

No they're not. Grrrr...

Maxtor started the base 10 crap in the mid 90's so stupid users could figure out how much space they had.

64kbps, 128 kbps, 384, 768, 1.54 Mbps...

And file sizes are STILL in traditional base 2. When someone says a file is 1KB, it's 1024 bytes, not 1000 bytes.

64KB of RAM is 65536 bytes, not 64000.

Just because someone bastardized the numbers for idiots doesn't mean it's actually propagated into reality.

Packaging and marketing doesn't change the guts, it just makes it easier for the average joe to feel like s/he knows what s/he's talking about, even if they don't.

Re:Novels?

[NonSequor]

No, the base two numbers are stupid. They are only marginally reasonable for RAM size, but it makes no sense for harddrive sizes. Can you tell me how many bytes are in 43MB, quickly? Mixing base 2 and base 10 makes no sense because humans always have to convert it to base 10 in the end.

Re:Novels?

[mistered]

No, they are. Gtrrr indeed!

Read this:

Some sources define a megabit to mean 1,048,576 (that is, 220 ) bits. Although the bit is a unit of the binary number system, bits in data communications are discrete signal pulses and have historically been counted using the decimal number system. For example, 28.8 kilobits per second (Kbps ) is 28,800 bits per second. Because of computer architecture and memory address boundaries, bytes are always some multiple or exponent of two. See kilobyte, etc.

So what's that mean? An ISDN 64Kbps B channel is, in fact, 64000 bits per second. A typical 115.2Kbps maximum rate on a PC's serial port is 115200 bits per second.

Hard drives are also measured using SI definitions. The power-of-2 definitions come from memory. Memory devices often inherently have power-of-two sizes, since the n address bits going into a memory provide 2^n addressable cells. Hard drives have no inherent reason to be a power-of-2 size so SI units make much more sense.

Re:Novels?

[autopr0n]

Can you tell me how many bytes are in 43MB

What the hell diffrence does it make? I mean really? Are you ever going to need to know the exact number of bytes of that file? (and if you are, are you ever going to need to figure it out by hand?)

The maximum size of anything on a computer is going to be a base2 number, always. two gigs max for a file means two gigs, (2^30). There is no more reason to mesure ram in that size then hd space.

Re:Novels?

[ntr0py]

Actually,
kilo == 1000
kibi == 1024

Kosherliciousness

[Vidmaster_Steve]

Well, all them terabits are all well and good. But what about ping times? Would this system make them infantesimally small? Or would it ping as bad as satmodems do? 1 mu57 kn0w! 1 n33d 17 70 pl4y my c0un7ar57r13k!

Bah. All I really care about is that 2 terabits/second would download me a whole lotta porn, a whole lotta fast.

Er, no, scratch that. Most servers are on ADSL/T1/T3s, which can only output at a certain, arbitrary, preset rate. So. I ask you, what's really the point? It'd be like having a cablemodem back in the days that everybody's BBSes were running off of 300 baud modems. I honestly don't think that you'd see a terribly higher transfer rate than you already do off of your cablemodem or dorm T1/T3/whatever.

But, baby... Imagine these 2tb lines becoming the standard... drool baby drool.

I still long for the day that I can pull broadband out of thin air. Now THAT'D be sweet...

Heavy heavy fuel... Heavy heavy fuel... if you wanna run cool... you've got to run...

Re:Kosherliciousness

[Chicane-UK]

Well.. I guess considering ping times on a 100mbit lan are typically 0.4ms or some such figure, the ping time on such a high speed connection would be 0.1ms or better I would imagine.. no latency whatsoever.

Re:Kosherliciousness

[glwtta]

um, I don't think this thing is meant as a "consumer" kind of service.

Re:Kosherliciousness

[zaffir]

The ammount of data you can cram down the pipe has no bearing on your ping unless you saturate the pipe. And, frankly, Quake packets are TINY. Its the speed of the routers your data has to go through that effects your ping. Why do 56ks suck for gaming? Because they have to convert the signal from digital to analog, and your ISP has to do the opposite. Your nifty cable modem is 100% digital and completely avoids that nasty ms-adding conversion. But you have to go through hardware other than the wires, which is what adds the pings. Put 50 routers on a 100mbit LAN in between 30 computers and the Quake server, and have them all connect and play. See how your pings change.

Whether you have a 1" pipe or a 30ft. pipe, it doesn't matter - a drop is still a drop.

Re:Kosherliciousness

[Account 10]

Give it a few years ... lots of this trickle down to the consumer market eventually.

Re:Kosherliciousness

[fiber_halo]

Ping times (for small ping sizes) are approximately equal to the amount of time it takes for light to pass through the fiber and back. Most people in telecom use 1ms per 100 route miles of fiber as a rule of thumb. (remember the fiber does not follow a straight line between cities!) So if it is 4200 route miles between NY and LA, your ping will take 42 ms to get there and 42 ms to get back = 84 ms.

You can't change this basic fact of physics. If you were running somehow on a microwave system instead of fiber, you would actually approach the speed of light in free space, so your ping time would be a little faster.

By the way, there are other factors that go into the delay of your ping besides propagation delay. Other things such as: congested buffers in routers along the way, serialization delay to clock the packet out of your device (negligible on fast links, but a big effect on dial-up), the response time of the remote device, devices delaying packets to do an ethernet arp, etc... Propagation delay usually ends to be the biggest factor when you are talking about ping times.

Re:Terabyte?

[TRACK-YOUR-POSITION]

I dunno, I'd always heard networks people liked to use standard decimal metric prefixes too. Especially if they're talking about bits rather than bytes--those powers of two are probably more useful for software than hardware, and people who think about software think more in terms of bytes than bits, so usually when I see someone say bit, I assume they're talking decimal powers..

Was there something I missed that lead you to think they meant a binary power?

Re:Terabyte?

[Anonymous Coward]

A Terabyte is 2^40 bytes
A terabit is 10^12 bits

I hope that clears it up for you.

congrats, you're an idiot

[Anonymous Coward]

For fun, look up bit and byte in the dictionary. They're not actually the same thing.

This is not a step forward....

[tomstdenis]

.... Using the existing fiber that is in the ground would be.

Tom

Re:This is not a step forward....

[rjforster]

If a paper gets accepted for presentation at a conference like this one did, then it is always going to be a step forward.

Re:This is not a step forward....

[gusman]

These systems work over the existing fiber.

These systems reduces the optical to electrical to optical conversion points along these fibers. This
is what saves the carriers a lot of money.

Additionally, these are both time, and wave division
systems. This basically means it's like transmitting am and fm stations over the wire. (Turns 1 wire into
160).

They also allow routing of the aforementioned stations (lambdas) so that you can dynamically set
up circuits with a click of a mouse.

Re:This is not a step forward....

[tomstdenis]

Yeah, assume the technology works and its all great and that. Its still a completely different challenge to get a telco to invest in it and actually implement it.

Tom

Can they sell it?

[gusman]

Just this week, I saw that the big news pages are going to start charging for video clips, and the like. The reasoning is that bandwidth costs too much for this kind of service on the web.

What I find interesting is that the optical sector has a ton of equipment which could/should reduce the cost of bandwidth by a tremendous amount, but nobody seems to be buying it.

Re:Can they sell it?

[Derek S]

Given that this is Lucent, I think it's pretty much guaranteed that they can't sell it.

Re:Can they sell it?

[cetialphav]

This type of equipment adds bandwidth capacity to the core transport networks. This has little to do with how a site like Yahoo, etc gets its bandwidth (the access side). Given the amount of dark fiber out there, it is unlikely that bandwith costs are related to lack of supply in the core. It is because providing multi Gb/s to a customer is expensive. Lack of good multicasting on the internet also increases their bandwidth usage.

So...

[lanalyst]

On Thursday, we have a slashdot story that we're going to face a bandwith shortage RSN and today we have Lucent to the rescue Put your buy orders in now!

Re:Terabyte?

[glwtta]

I could be just plain wrong - that's been known to happen.

Impressive

[s4ltyd0g]

I'm curious about what they used to generate the data. You need some serious fire power to keep a pipe that wide full all the time.

Re:Impressive

[SonicBurst]

The data was probably just simulated using something that can modulate the signal as fast or faster than that pipe could hold. It was probably just a nonsense stream of bits randomly generated, but I'm just guessing.

Re:Impressive

[arkanes]

For the testing to be meaningful, you need to be able to check and compare it with what you get at the other end - So they need SOMETHING recording the data, at both ends.

Thats nice.

[Yarn]

The theoretical maximum (for silica) I've heard quoted is 40Tbit/s, but I'm sure you could squeeze a bit more out. The current limit is the gain spectrum of the Erbium Doped Fibre amplifiers that make sure a signal can travel long distances, these have a (relatively) narrow gain band. Semiconductor Optical Amplifiers (think of them as diode lasers, without the mirrors) could have a wider spectrum than the optical fibre! Lots of problems with them currently though.

I think I'll wait for the quantum dot lasers to catch up.

Re:Thats nice.

[dstone]

The theoretical maximum (for silica) I've heard quoted is 40Tbit/s, but I'm sure you could squeeze a bit more out.

Hmmm. I'll tell you how to squeeze more out... take whatever was giving you 40Tbit/s before. Lay down 7 more of those. In parallel. Presto! Now you've got 40TBYTES/s. Repeat as required.

"Buy 8 and I'll throw in a parity bit for free!"

Re:Thats nice.

[Yarn]

That's cheating dammit!

Re:Thats nice.

[fiber_halo]

Actually, the article said they used raman amplification, not Erbium Doped Fiber Amplifiers. Raman can be used in either the C-band (1530 to 1565nm - typically where EDFAs are used), or the L-band (1565 - 1625nm). Actually, I think Raman can be used at any point in the spectrum, but don't quote me on that because I am not a physicist!

EDFAs do allow signals to travel long distances, but the problem is that they are "single point" amplifiers. The signal gets attenuated down quite a bit after traveling 50 miles or so and then is boosted back up by the EDFA. The signal to noise ratio has already dropped too low and can't be recovered. So with EDFAs you are limited to a relatively small number of hops (six or so) before it has to be electrically regenerated (detect the signal and then electrically send it to a laser to be retransmitted cleanly).

Raman amplifiers use an effect called Stimulated Raman Scattering that uses the fiber in the ground as the amplifier itself. By using a pump laser transmitted into the fiber (typically opposite to the direction of data flow), the power of the pump laser's low wavelength is transferred in the glass to the higher wavelengths of the data signals. Amplification is then distributed along that 50 miles of fiber or so between pump lasers. The signal power never gets as low with Raman as with EDFAs, so the signal to noise ratio is kept higher. That's how they are able to get much longer distances between electrical regeneration out of these new systems.

I don't know much about SOAs, but I've heard they are not good for multichannel systems. Something about the fact that they are noisy? I think they are good for single channel applications.

This research is great and all, but telecom providers are having enough trouble selling capacity on their existing EDFA systems. Something is going to have to drive a lot of demand for bandwidth before systems like this one from Lucent get deployed.

Re:Thats nice.

[Soft]

Actually, the article said they used raman amplification, not Erbium Doped Fiber Amplifiers.

I'd be surprised if they didn't use both. Raman is nice for distributed amplification and keeping the noise factor low (as you said, signal-to-noise ratio never goes too low), but you need Erbium and derivatives to get a good boost once in a while.

Actually, I think Raman can be used at any point in the spectrum, but don't quote me on that because I am not a physicist!

Well, I am, and a telecommunications engineer as well as Ph.D. student, and you're right; as long as you have a good laser with a wavelength about 100nm lower than that of your signal and the medium responds, you can amplify. This is good for the whole fiber window (1200-1700nm or so).

I don't know much about SOAs, but I've heard they are not good for multichannel systems. Something about the fact that they are noisy?

They're nonlinear, so your signal not only gets distorted, but you get four-wave mixing: two signals at different wavelengths beat together and create harmonics at the same wavelength difference. (Optical frequency actually, but for practical purposes wavelength works too.)

So, with SOAs, there is a lot of crosstalk between different wavelength. Add to this that their output power isn't very high, and you see that they aren't good amplifiers for the moment.

Which is not to say that they don't have other uses, such as signal processing, wavelength conversion, etc. And they are easier to integrate into components.

Re:Thats nice.

[Soft]

The theoretical maximum (for silica) I've heard quoted is 40Tbit/s, but I'm sure you could squeeze a bit more out.

Yes and no. Depending on the transmission window you take, you get a (spectral) bandwidth of a few tens ofTHz. However:

• If you take Shannon's law, maximum bit rate depends on the bandwidth but also of signal to noise ratio: C=W*log2(SNR+1). If you keep the SNR high, you can have an efficiency higher than 1bps per Hertz.
• To keep the SNR high, you need good amplifiers, and that's where it gets tough: although you can find amplifiers over the whole band, no single amplifier will cover it all; your system gets complicated, with demultiplexers and separate amplifiers every 100km.
• Anyway, with current technology, we can't make good use of the window as a whole. Efficiencies are maybe 0.1bps/Hz, over windows a few tens of nm wide (i.e. a few THz).

Semiconductor Optical Amplifiers (think of them as diode lasers, without the mirrors) could have a wider spectrum than the optical fibre!

Not really. You can cover the whole window with them but only 20 or 30nm at a time.

Re:Thats nice.

[Yarn]

There are diode lasers with ~33THz bandwidth currently available (generally used in picosecond pulse generation)

These use multiple quantum dots to engineer the gain spectrum.

Re:Thats nice.

[Soft]

There are diode lasers with ~33THz bandwidth currently available (generally used in picosecond pulse generation)

These use multiple quantum dots to engineer the gain spectrum.

Interesting, thanks for the information. Do you get enough gain out of quantum dots? What about nonlinearities?

Re:Thats nice.

[Yarn]

only 20dB of gain, slightly more than half an EDFA, and far less than a Raman.

The benefit of the quantum dots is that each dot has a gaussian gain profile, so if you have a huge number of them you can get a (nominally) flat gain profile, compared to the normal sqrt curve.

Current prototypes don't have enough bandwidth for the whole fibre, but they are far more efficient and cheaper than Raman amps.

Bandwidth Wars

[Anonymous Coward]

What i'd like to see is bandwidth wars between Lucent and Nortel. Just like Intel has CPU wars with AMD.. :)

Re:Terabyte?

[Anonymous Coward]

where were you when the mega/mebi, etc, debate was on? We could have used this observation...

Time to buy...

[Sir Homer]

Good time to buy some Lucent stock again!

Re: That's no record!

[let the storm]

I'm sorry, but the record referred to (see the article) is on ...high-bandwidth, ultra long-distance transmission[s].
We're not talking last-mile here, we're talking a distance of 4000 kilometers (2500 miles), roughly the distance between Orlando, Fla., and San Diego (article).
That's a little different, wouldn't you agree?

--
m iso socially aware artistic geek pen-pal, m or f, in '1337 edu. jazz, poetry a must.

omg will u be my g/f?

[Anonymous Coward]

'N Sync - Girlfriend

(would u be my girlfriend) x 3
(u know i like u right)
I dont know why u care
he doesnt even know your there
cuz he dont love your eyes
and he dont love your smile
girl you know that i care

the middle of the night, is he gonna be by your side
or will he run and hide
u dont know cuz things aint clear
and baby when u cry, is he gonna stand by your side
does the man even know your alive
i got an idea

would u be my girlfriend
i'll treat ya good
i know u hear your friends when they say you should
cuz if u were my girlfriend
i'd be your shining star
lemme show u where u are
girl you should be my girlfriend

does he know what ya feel
are u sure that its real
does he ease your mind
or does he break your stride
dont ya know that love could be a shield

the middle of the night, is he gonna be by your side
or will he run and hide
u dont know cuz things aint clear
and baby when u cry, is he gonna stand by your side
does the man even know your alive
i got an idea

would u be my girlfriend
i'll treat ya good
i know u hear your friends when they say you should
cuz if u were my girlfriend
i'd be your shining star
lemme show u where u are
girl you should be my girlfriend

ever since i saw your face
nothing in my life has been the same
i walk around just sayin your name
cuz w/ out you girl my world would end
ive searched around this whole damn place
and everythings as if u were meant to be my girlfriend - oh!

why dont u be my girlfriend
i'll treat ya good
i know u hear your friends when they say you should
cuz if u were my girlfriend
i'd be your shining star
lemme show u where u are
girl you should be my girlfriend

Re:Terabyte?

[Anonymous Coward]

Yeah, I think that's right. It's been quite awhile since I read the book where I got my name from.

w00t!

[Anonymous Coward]

Now all we need are 'physical printers' to become more common, and we can download actual pr0n stars to play with, instead of just wanking to a video of them!

Re:WOW! Really?

[Anonymous Coward]

i agree... im sure many others do too... this is a guy who spends his day behind a computer making himself feel good about himself by telling the masses of his huge MP3 collection or his extensive knoweledge of humorous C++ tag quips. It gets old after a while. Why dont you just create another site that people can flock to where ever 30 minutes you post about how smart and cool you are. Maybe even post your picture to impress the girls. You are a stud right? You must be, you know so much about PERL!!

Engineer wanted

[dstone]

So this thing could transmit my entire mp3 collection in under a half second.

Engineer wanted for creation of 2.56Tb/s DRM system. Must be able to scan for copyright flags in data stream and deny transfer permission.

Re:Engineer wanted

[Anonymous Coward]

Ever heard of "dumb network, intelligent clients"? What if you aren't allowed to produce, sell or own client machines without DRM? That would do the trick, right?

Re:Engineer wanted

[rusty0101]

minimum 5 years documented experience required...

Re:Engineer wanted

[gatesh8r]

Must be able to code in C++, VB, Java, .NET, FORTRAN, and have MCSE, CCNA, RHCE, and be willing to sacrifice your first born child.

Very practical.

[FreeLinux]

Similar stuff has already been deployed and is in use today. Here are two examples. The first is a MCI Worldcom deployment from 2001. Your voice calls and data are already flowing around the world on these pipes. The second is, perhaps surprisingly, a Chinese deployment. I'm sure that there are others too but, frankly I can't be bothered to look them up. I know, from personal involvement that there are several other high-speed installations around but, these do not span such great distances. Rather the are 30 and 70 mile rings around metropolitan areas but, they are just as fast and in one case even faster.

Re:Very practical.

[Emugamer]

that wasn't really the question.. I think most ofus know that our data/voice is going through fiber, the question washow expensive is it to upgradecurrent systems to the newest technology.

mmmm.... spam

[paradesign]

just think of how much more spam could be sent if you had that much bandwidth. Mmmm... streaming dvd quality video spam.

or, replace spam above with...

pr0n...warez...romz...iso ripz...pr0n

i cant wait

I'll take 2.

[Gord888]

Yeah... I'll take 2... just put it on my credit card. Having a 2 tb/s would be fun to have even though it transfers information faster than my computer can process.

entire mp3 collection?

[sfrenchie]

this thing could transmit my entire mp3 collection in under a half second.

ummm ya... if you happen to have your mp3 collection in on (many) pc(s) with a memory transfer rate of 2.56 terabits/s and also happen to have a modem that can transfer 2.56 terabits/s!!

that's nothing

[BoRoG]

That speed is soo slow. Why is this a new record? I mean my TI-89 can transfer at least twice that. geez..

Re:that's nothing

[Anonymous Coward]

Whatever effect you were aiming for, you failed.

Re:that's nothing

[Anonymous Coward]

hehe

price?

[Bender Unit 22]

Damn, it must be expensive to setup a line like that. Just the boxes in each end that must deliver the data. It must take some processing power to break the flow down to slower connections, like "slow" gigabit connections.

Anyway what are the requirements for the fibers and how much could you speed up existing lines? I guess it depends on the quality of the fiber.

Re:price?

[cetialphav]

This is not about processing power. Most telecom devices use embedded processors (think 50-100 MHz motorola processors), FPGAs, and/or ASICS. The processors just setup and control the real hardware. They generally don't see the data at all.

Latency and throughput

[Anonymous Coward]

Wrong. don't confuse LATENCY and THROUGHPUT.

The previous AC was aware of the difference. He was just pointing out that ping time not only depends on latency, but also throughput.

PingTime = latency + size / bandwidth

Usually, size is small enough, and bandwidth big enough that this second term can be ignored. Actually, one way way to measure bandwidth is to do a ping -s 16000 or similar.

Try to play Quake on 1Mbit satellite uplink and you would go back to 56k modem after first round.

Correct, unless you are considering really large packets. Some satellite providers are actually using pings with large packets in order to measure bandwidth (such measurement is needed to fine-tune their load balancing between terrestrial and satellite channels).

2.56Tbps=320Gigabytes/second

[markh1967]

What sort of device can read that quickly? That's an order of magnitude or so faster than the fastest RAM I've seen. I suspect they simply transmitted a simple repeating pattern rather than actually reading and writing data from a device of some sort.

Re:2.56Tbps=320Gigabytes/second

[BoneFlower]

Probably. Still, its an advance, and with the internet being central to todays computing experience, with this tech on the horizon, its an incentive to keep Moores Law going(in addition to the fact that if AMD OR Intel slacked off the other would eat them alive)

Also, as I said in a previous comment, this would have potentially huge advantages over current network technologies in clustering.

Re:2.56Tbps=320Gigabytes/second

[MoogMan]

Bell Labs scientists transmit 64 channels of data at 40 gigabits per second per channel over 4000 kilometers (2500 miles)

You'll therefore notice that it is more like 40/8 = 5 gigabytes per second to be stored by any one interface. This is more. If you had an array of 64 lots of 5 gigabyte standard DRAM memory modules, this would easily be able to take in the data on a temporary measure. However, with more permanent things such as hard drives, I would still agree with you that they could not reach the needed speeds of 5gbytes per second

Re:2.56Tbps=320Gigabytes/second

[cetialphav]

They use specialized test sets for this. These test sets generate pseudo-random data sequences. These things are extremely common. For $100K you can get a 10Gbs (OC-192) test box from Agilent (I have two). Lucent would have used a 40Gbs box. Those aren't very common now, but I'm sure they are available for enough money. Anyway, buy 64 of those test sets and simply feed that data into the mux device. Optical muxes are generally passive devices so there is no processing involved there. There is nothing difficult about generating this much data. It is just a matter of money.

Re:2.56Tbps=320Gigabytes/second

[Anonymous Coward]

you got two at 100k ?
wow are you l33t ...

Re:2.56Tbps=320Gigabytes/second

[kdawggie]

I think you mean 32GB/s.

Re:2.56Tbps=320Gigabytes/second

[0x0d0a]

They're going to have multiple blocks of RAM that can be written to simultaneously in something like this.

Re:2.56Tbps=320Gigabytes/second

[cybergibbons]

DWDM uses multiple wavelengths to transmit data down a single fibre. This system uses 40Gbps channels agregated into one fibre. Generally, the 40Gbps is then split into 10Gbps or 2.5Gbps lines, and then the data is fed to then.

The systems I have seen in development have several devices that produce data streams with differing characterisitics (TCP/IP wrapped in another protocol, ATM, voice, etc.) and then the input is compared to the output. There is no storage bar the almost instantaneous data need to compare (though 16000km of fibre did take a while).

If and when there needed to be storage, it got split up into smalled channels and fed to the 64 way cluster which dealt with the data.

Anyway, you should be on the look out for a 4Tbps system which will be making its appearance soon.

Transmission Record

[Alsee]

And in related news:
These same engineers hope to set a new 1.00 Tb/s reception record later today.

-

Re:Transmission Record

[germanbirdman]

Actually, how do they receive this stuff at this speed?
What type of electronics run at terabit/second speeds?

Re:Transmission Record

[Alsee]

What type of electronics run at terabit/second speeds?

I'm making an educated guess here, but they probably use a passive beamsplitter. Probably 32 to 128 beams of different frequencies. (Like a rainbow from a prism.) Each beam gets one sensor with that fraction of the data rate. This is done in other high capacity optical systems.

-

Re:Transmission Record

[Tomster]

I told my girlfriend about this record. She didn't understand why I laughed when she said "Yeah, but I bet they aren't receiving it that fast".

No, I didn't try to explain it to her.

Cool, but...

[Anonymous Coward]

I'm stuck with my almost rural line modem connection :(

so...

[furchin]

*drool*

Have none of you guys heard of backbones?

[Anonymous Coward]

Who cares that a single HD can't write this fast? This is for trunking together ISP's. Your pitiful DSL connection will be just one fraction of all the traffic going through this.

*blinks*

[ZaneMcAuley]

Even just connecting to some poor web server, itll get slashdotted :D

Not much good on slashdot tho, im still throttled by the 20 second limit on posting on slashdot :D

Huh?

[autopr0n]

Most people I know have way more then 2.5gigs of MP3s, I think I have 20 or so myself. Taco indicated that he had about 150gigs himself. (1.28Tb = 163TB)

binary multiples: 1 MiB = 2^20 = 1.048576 MB

[nealmcb]

Since 1998 there has been a standard clear alternative to this mess: binary multiples.

one mebibyte = 1 MiB = 2^20 B = 1 048 576 B

See http://physics.nist.gov/cuu/Units/binary.html for more.

Factor Name Symbol Origin Derivation
2^10 kibi Ki kilobinary: (2^10)^1
2^20 mebi Mi megabinary: (2^10)^2
2^30 gibi Gi gigabinary: (2^10)^3
2^40 tebi Ti terabinary: (2^10)^4
2^50 pebi Pi petabinary: (2^10)^5
2^60 exbi Ei exabinary: (2^10)^6

Re:what a fat pipe compared to Boeing 747

[Anonymous Coward]

However, that also goes back to "Never underestimate the bandwidth of a 747 with box of tapes on it".

Following this
page (google cached) the boeing 747 can take (full of fuel) about 200000kg at max distance 13000 km and at speed of 910 km/h

I estime the DVD-ROM weight to 20g, and use the 17.1GB ones (=136.8Gb)

so "data capacity of 747" is 200000 /(20/1000) * 136,8 ~= 1,400,000,000 Gb = 1.4Eb (exabit = 10^18 bits ;-)

the time of the fly in the worst case is about 13000/910*3600 ~= 51000 seconds.

let's divide 1.4Eb / 51000 ~= 27Tb/s ;-)

So ower beloved 747 has only 10 times bigger data transfer capacity, but the Bell Labs solution must be much more than 10 times cheeper

(And we have not discused the latency yet ;-)

Re:Oooh the posibilites

[Anonymous Coward]

how in th fuck is that offtopic?

Are we not talking about bandwith?
Face it folks, the porn industry got the net where it is today. I gaurantee you that you'd have to pay a much higher premium for broadband if cable companies didn't have such a huge porn surfing userbase.

Of course porn isn't the only thing the net is good for (mp3z, warez, trolling forums, oh and that information superhighway thing) but it sure has helped spread the availability of broadband.

Bell Labs can move terabits per second...

[Anonymous Coward]

...and AT&T still can't provide cable modem service in Norwood, Massachusetts.

Re:what a fat pipe compared to Boeing 747

[xrayspx]

Latency is definitely a problem. Pinging by air-freight is not the way to go.

PR sham

[CanadaDave]

I don't mean to be negative here, but there are some things to question here. First of all, 40 Gig/s modulation has been very challenging thus far, and I know for a fact that 20 Gig/s has been achieved, but 40 Gig/s is still a ways off. This is according to one of the founders of JGKB photonics, which I talked to recently. They are trying to achieve 40 Gig/s using a slightly different type of modulator (single channel, linear polarized modulation) as oppsed to a Mach-Zehnder interferometer style modulation, but supposedly 40 Gig/s in general is far off, according to him.

Secondly, they don't mention the effective data rate on the receiving end of the transmission. They had zero errors, according to the article, because they used forward-error correction. Forward-error correction adds on more bits, to correct for errors. So they've given us the "bit rate", not the "data rate". So although they may have still set a record if you included only the data rates of this record and all previous records, it is still somewhat of a PR sham. Note that the article was written by Lucent, not a third-party news agency (not that it would be any more credible, but the news person may find holes in their "breakthough" if he/she knew enough". Very similar to the Intel "breakthrough in transistor design article" where Intel makes many claims about their new transistor, even though none of these improvements in design have ever been implemented together (although they make us believe that they have).

Re:PR sham

[0x0d0a]

I know CMU was doing terrabit ATM research at least a year and a half ago from posters in Hammerschlag Hall.

And then what ????

[Anonymous Coward]

That still leaves us with moving parts in dead slow
hard drives....
time to go and invent a cheaper alternative

free bill gates

[Anonymous Coward]

Please set Bill Gates Free!

Re:PR sham... nice try...

[univgeek]

How bout the fact that it was demonstrated at OFC, this week????

In front of most of the worlds Optical Companies?

Hmm..

[DarkProphet]

Quoth Taco: "So this thing could transmit my entire mp3 collection in under a half second."

You know the first time I read that, I equated that Taco's mp3 collection is somewhere round 1 terabyte. Then I did the double-take! Aha!, - So of course his collection is nowhere near 1 TB, but thats how I read it.

Learning some marketing tactics from the big boys, eh?!

Just kidding..

Taco's MP3 Collec

[Our Man In Redmond]

So this thing could transmit my entire mp3 collection in under a half second.

Most of those gains are due to the following ingeniuos compression scheme:

1. Download Taco's copy of Bobby Vinton's "Melody Of Love".

2. Instruct the client to make 135,275 copies locally.

And this helps me.... how?

[tweakt]

...have doubled the distance record for high-bandwidth, ultra long-distance transmission by sending 2.56 terabits (trillion bits) of information per second over a distance of 4000 kilometers (2500 miles), roughly the distance between Orlando, Fla., and San Diego.

Yet, I still can't even get 144 Kilobits/s from Verizon at 5 miles... where's my Fiber-to-the-home?

what exactly did they send?

[mcryptic]

what did they send that is several TB in size?

(besides pr0n)

terrabit

[elmo_attacks]

this may be a bit off-topic, but does anyone know what the official prefix is *after* terrabyte/bit? Like: mega/giga/terra/X Just wondering...

Re:terrabit

[Anonymous Coward]

peta dude

DRAM what about RD

[Anonymous Coward]

listen, you half whitten twat, get with the times, DDR is outdated. Gosh, i've got1024 mhz RDRAM, twice the speed of what intel uses. In my alpha server i have 4 sticks of 16 GB of it on each of the 16 mobo's. get with the times, get a compaq alpha server gs with true 64 technology. I'm waiting for their upcoming 32,000 processor machine, i hope to get one as soon as they are ready, or excuse me as soon as i finish designing it. So i will leave you retards now and retire to my computer lab

Mr. The Plague
Any women out there i'm 32 years old, and peter is 9! ;)

With Pipes Like this....

[ASyndicate]

I can see that the media industry (maggots) will have a plan for you to have a 500gb/sec connection and your machine will be a thin client to a server at the RIAA HQ (If it is not already destroyed), Cant to much about copyright 'protection' now could we?

As In, If you want a 500gb/sec pipe you have to run one of our thin clients. This pipe will only work with it. No PCs will be able to use it because of Encryption, authentication etc.....

Re:PR sham... nice try...

[CanadaDave]

I am somewhat of an engineer, and I know for a fact that half the things you see going on at a show like OFC is crap. Engineers are constantly creating crap demos whose main objective is not to prove that something does what it claims to do, but that is LOOKS like it does what it claims to do.

I believe they MAY have demonstrated error free 40 Gig/s modulation, but they may have had to use a very bandwidth-costly FEC (forward-error correcting) protocol in order to reduce the errors. So their effective data rate may have been only 10-20 G/s.

ATA Hype

[Anonymous Coward]

ATA66 is a protocol with 66MB/s peak theoretical transfer limit. Peak sustained throughput for the harddrive is much much slower.
Moving up to ATA100 and ATA133 will not increase harddrive speeds because that is not where the bottle neck resides.
Ah well, I guess the marketing dept is just doing its job. They would be out in the street without you gullible people...

Re:ATA Hype

[Anonymous Coward]

i get around 30MB/s for sequential reads. is 50% here or there really much much?

Re:ATA Hype

[John Sullivan]

Ah well, I guess the marketing dept is just doing its job. They would be out in the street without you gullible people...

Actually, my Seagate 40GB benchmarks about 78MB/s peak, 42MB/s *sustained*. Real-world I/O hungry code backs this up. Now imagine RAID 0 striping a bunch of these. You could reasonably expect to get hundreds of MB/s at reasonable cost.

Actually thats how it was unofficially measured...

[Raistlin99]

way back when. A "standard novel" in plain text and an 8pt font was usually considered to be about 1MB worth of data. I don't know if it really is a MB worth of data but I've seen that type of comparison made before. So having 1000 novel/s is only a GB/s, however a DVD/s would be somewhere between 9-18GB/s, depending on if one or two sided.

Not End User Lines

[Anonymous Coward]

Remember guys these lines are used as long haul runs for groups of multiplexed carrier lines. You might have traffic from 1/2 of a city comming out on a single line like this. These lines are used to carry many very high speed lines (IE: T3,OC3,OCx....) from datacenter to datacenter, not traffic from your local telephone operator to your home.

Base2 / Base10

[Alexis Morissette]

Actually, Base2 numbers aren't stupid, Base10 numbers are. A logical course of action would be to convert our entire mathematical system to Base8, since Base10 has no actual basis in nature or math. It just happens to be the number of fingers we have, which is where Base10 came from. Same with the 60 minutes in an hour, 24 hours in a day crap. This needs to go.

Re:Actually thats how it was unofficially measured

[Alexis Morissette]

Just out of curiosity... how does the 8-point font matter? I mean, I've heard of some people trying to save disk space by using smaller font sizes, but still...

Re:Actually thats how it was unofficially measured

[Raistlin99]

The stuff about the 8pt font was meant for the size of the text inside the novel. Just thought I would clarify, sorry about the confusion.

Re:Terabyte?

[Anonymous Coward]

Maybe they really did mean a mountainous region on the moon? You never know.

Well, I do. Terra means earth / planet sized body, whereas selena means moon from which we get the word selenitic.
Astronomer Colonel

hosting

[lposeidon]

so whos hosting a mp3 server with this connection. what about a quake 3 server??? :)

Re:what a fat pipe compared to Boeing 747

[Grail]

Latency aside, my arithmetic errors aside, the good ol' Jumbo-full-of-DDS still faces the problems of loading and unloading the data to and from the tapes (or DVDs in this case).

Which makes me wonder - what is going to be feeding this pipe?