Researchers Transmit Optical Data at 16.4 Tbps 2550km

Stony Stevenson writes "The goal of 100 Gbps Ethernet transmission is closer to reality with the announcement Wednesday that Alcatel-Lucent researchers have recorded an optical transmission record along with three photonic integrated circuits. Carried out by researchers in Bell Labs in Villarceaux, France, the successful transmission of 16.4 Tbps of optical data over 2,550 km was assisted by Alcatel's Thales' III-V Lab and Kylia, an optical solution company. The researchers utilized 164 wavelength-division multiplexed channels modulated at 100-Gbps in the effort."

Translation please?

[davidwr]

What's that in Library-of-Congresses per fortnight?

Comment removed

[account_deleted]

Comment removed based on user account deletion

Re:

[JrnyFan]

It depends on if they grip it by the husks or hold it under the dorsal feather I hear.

Re:

[pizzutz]

I calculate roughly 248,000 Library of Congresses per fortnight.

Curse my geeky genes for making me calculate that when you asked.

Re:

[TheScorpion420]

Or how many 747's full of DVD's?

Re:

[suso]

HD DVD, Bluray or regular?

Re:

[thatskinnyguy]

Either way, I think my file server needs more space.

Re:

[michrech]

I prefer HHDD-DDVVDD, thank you.

HD DVD, Bluray or regular?

Re:

[networkBoy]

Data per boeing 747 (LCF version)

DVDR = 159238213.7 GB/747LCF
HDVD = 677609420 GB/747LCF
BDVD = 847011775 GB/747LCF

-nB

Re:

[fbjon]

Your calculations are a bit off. The LCF, like the Beluga and similar, is meant to transport aircraft parts which are large, not heavy. Additionally, the bulky airframe means it can actually lift less weight than a regular cargo carrier, and maximum takeoff weight is the limitation for bandwidth, not volume. Besides, the LCF is not for sale to customers.

Redoing for the 747-400ERF:

• Assume each disc weighs 16g, like a CD.
• This gives us a box with a volume of 1,38 m^3 that contains 80000 discs, weighing 128

Re:

[kesuki]

I'm assuming you're using dual-layer media, but technically, bd-rom and such support Dual sided, dual layer media, as dvd also supports. of course finding writable dual layer dual sided media is different, but assuming you used standard manufacturing of pressed blue ray drives, you could use dual sided dual layer media. that effectively doubles both your figures for bd-rom and dvd-rom (unless you considered the dual sided capabilities i didn't check your dvd numbers)

Re:

[aplusjimages]

Let's just say it's a lot of pr0n.

Re:

[Eddi3]

Well, I'm not exactly sure what you're asking, but here we go:

(((650 / (0.0014 * .12 * .12)) * 8.54) / 1024) / 1024 = 262.591574 Petabytes

650 cubic meters - rough volume of 747 [1] .0014 meters - rough thickness of DVD .12 meters - diameter of DVD
8.54 GB - dual layer DVD capacity
1024 GB in 1 TB
1024 TB in 1 PB

So, a 747 can carry about 250 Petabytes of data in Dual Layer DVDs at a time. Then just divide that by the time it takes to fly it wherever you want it.

[1]: All volume values for the 747 were found at h [zap16.com]

Re:

[Dagger2]

Unfortunately, according to that page, the max payload weight is 66,300kg, and DVDs weigh about 17 grams, meaning you're limited to 3.9 million DVDs = 31.763 PB.

Unless you plan on taxiing all the way there.

Re:Translation please?

[Eddi3]

(14 * 24 * 60 * 60) / (20 / 2.2) = 123,984 LoCs/fortnight

(total seconds per fortnight)
14 days per fortnight
24 hours per day
60 minutes per hour
60 seconds per minute

all over

(seconds per Library of Congress transferred)
20 terabytes per second (one LoC/second)
2.05 terabytes per second (16.4 terabits per second

Re:

[pizzutz]

I estimated a LoC as 10 TB (first number I saw after quick googling), which explains why my number is twice as big. At least my math was right :)

Re:

[a_claudiu]

But can you calculate the flux of in information in the cable in LoC/(square furlong * lapse year)? Once you go metric you never go back.

Re:

[bettega]

At last now I know what a fortnight is. It is a quinzena :)

Re:Translation please?

[thechao]

I saw "LoC" and thought "Lines of Code"; my second thought was that you have some *mad* job security.

Re:Translation please?

[u-235-sentinel]

What's that in Library-of-Congresses per fortnight?

Well... if you are Concast they will give you those numbers in terms of photos or mp3's or emails downloaded in a month.

Personally I like to know in terms of how many 8 track tapes I can download a month. ;-)

Less than you might think

[Tsar]

What's that in Library-of-Congresses per fortnight?

Assuming you want a copy of the LoC which will allow you to reconstruct the entire collection [loc.gov], you'll need scanned images of all the documents, decent MP3 (or ogg) files of the audio recordings and at least SD-quality copies of all the video. That would require something north of ten petabytes. At 1.64Tbps, that would work out to less than 25 LoC/fortnight--and that's assuming Mom doesn't pick up the kitchen phone and kill your connection.

Re:

[VE3MTM]

No, the real question is: is it faster than a station wagon full of Blu-Ray discs on the highway?

Re:

[slashqwerty]

How about channels of high definition video? High def television broadcasts are 20 Mbps. So this technology can simultaneously transfer 820,000 high def channels over a single optical fiber.

So, this speed, on a scale of 1-10...

[r_jensen11]

Would this qualify as 11?

Re:

[suggsjc]

For now...wait a couple of years and it will be a measly 5-6. Not sure what we are going to do with all of that bandwidth, but I'm sure that we'll come up with something interesting and possibly even useful.

CPU speeds?

[Anonymous Coward]

Surely there must be some incredibly processing power behind transmission speeds like this? Anyone one have any idea?

ObWalken

[Saint Aardvark]

<walken>That's a lot of cows. [imdb.com]</walken>

Re:

[Hybridan]

Be honest, how many of you followed the link above, but the first thing you looked at was the picture with the two women and Dwayne Johnson. (Ok, now be honest, how many of you followed the link after I mentioned Dwayne Johnson or the two women?)

Don't get too excited.

[geminidomino]

That's just BURST throughput. Depending on factors like time of day, how many other users there are, and environmental conditions, throughput may drop as low as 33kbps. And we do NOT filter bittorrent.

Just check your TOS agreement. It's all right there.

Re:Don't get too excited.

[holyspidoo]

Now offering the fastest 16.4 Tbps service* available anywhere

*1 Gig upload/download monthly limits apply

Re:

[BoredAtWorkWhatElse]

I know you're joking but my ISP is now offering a 50Mbps with a 50GB limit [videotron.com] download/upload combined. 1.50$ per additional GB, no limit.

Remind me again who needs a connection that can only work at 100% capacity for a little more than 2 hours per month ? Only to be charged 50c/s afterward (no limit !!!)

Re:

[gravis777]

Pitty the net is so slow. 16 Tbps connection from the phone company to my house, yet download speeds still rarely top 600k a second. Difference between now and before is I can now download 1,000 files in 30 minutes instead of just one file in 30 minutes. Sigh. Of course, with Bittorrent and dedicated Usenet servers, I can get much faster downloads. Hmph, maybe iTunes will start offering downloads at 320kbps on their songs and full 1080p on their movies.

On Neutrality

[Anonymous Coward]

In other news: American telcos wonder how French providers are able to afford research and development without additional funding from a tiered billing billing scheme that is needed to advance the science in the United States.

Re:

[mrvan]

Never applied for EU research funding, did you? :-)

Current cables?

[headkase]

With the ever-predicted bandwidth crunch always just around the corner, can existing cables be reused just by replacing the signaling equipment at substations with this? If we don't have to lay all new cables - just upgrade the nodes - then upgrading to these bandwidth capacities on our current networks would be a cinch.

Re:

[afidel]

The problem has never been the glass! There is absolute craploads of dark fiber just about everywhere. Last time I saw stats it was something like less than 1/3rd of installed fiber was lit up. It's the uber expensive routing equipment needed to keep up with the flood of data that's the expensive part.

Re:

[duncan99]

That, and the last mile (or even the last 25 feet) to YOUR house.

(I've always seen that quoted as "Five boxes preserve our freedoms: soap, ballot, witness, jury, and cartridge" But yeah, that.)

maybe its just me

[the_mind_]

"164 wavelength-division multiplexed channels modulated at..."

how very Star Trek of them.

Re:maybe its just me

[pizzutz]

"164 wavelength-division multiplexed channels modulated at..."
how very Star Trek of them.

I'm sorry Captain, but we canno' reach these speeds with time-division multiplexing. the phase coils canno' handle it!

Re:

[funaho]

A soon as they can get the multimodal reflection sorting working we can tap into the Borg collective. They have all the good warez, pr0n, music and movies from thousands of civilizations. :)

Re:

[Teiresias_UK]

To be honest I don't find this *that* amazing.

I worked at the victim-of-the-telecoms-bubble that was Marconi 2000-02 and there was a bit of kit, the snappily titled UPLx, that could deal with 160 10Gbps channels down a pair of fibres, unregenerated over about 1000km - using soliton wave shaping and some sodding great Ramen pump laser to get there (nothing to do with noodles before you ask). It was demoed in the labs reliably, and I believe sold in to Telstra Australia

In 5 years, they've added 4 Gbps ... wow

Re:

[MadUndergrad]

You're off by an order of magnitude. They've added about 15Tbps.

Re:

[fbjon]

4 Gbps as well as 1500 km, mind you.

16.4 Tbps of optical data?

[Gabest]

Tbps speed, and over 100 Gbps. Something is wrong here.

Re:16.4 Tbps of optical data?

[spectrokid]

They had 164 lasers with different colours sending 100 Gbps EACH over the same fiber, splitting the colours apart again at the other end with what probably is a little more advanced than a prism.

Re:

[EricR86]

I'd wadger they're using devices like a Diffraction Grating [wikipedia.org] or a Fabry-Perot Etalon [wikipedia.org]

Only a little more complicated than a prism :)

Re:16.4 Tbps of optical data?

[colinmcnamara]

Its called dense wave division multiplexing, or DWDM. You take independent links (in this case 100Gig links), and transmit each of them on a slightly different wavelength of light called a Lambda. Since optic is looking for a specific wavelength, you can now run many "virtual links" per physical fibre. This is the standard technology for most Telcos. The innovation here is that they are doing this with 100Gig transceivers, and they have chipsets fast enough to combine the different lambda's back together into on high speed link. And yes, you can now let the Lambda Lambda Lambda jokes fly

Re:

[Adeptus_Luminati]

100 Gbits/sec * 164 laser colours sent over a single pair of fibers = 16,400 Gbits/sec total throughput.
16,400 Gbits/sec = 16.4 Terabits/sec
16.4 Terabits/sec / 8 bits = 2.05 TeraBytes /sec

If you think about it, this is like shipping 2x 1Terabytes hard drives accross the Atlantic in 1 second.

Now if you want the SneakerNet comparison... or perhaps JetNet in this case....
Say you could fit 10,000 x 1TeraByte hard drives in a 747 air plane, and it takes you 6 hours to cross the Atlantic.
6 hours= 21600 seconds
10,

Re:

[HTH NE1]

Not all the pr0n, just the really fast pr0n.

Measuring data quantity by its speed over a distance in kilometers? What's next, measuring its speed by its acceleration over a volume in Liters?

error checks?

[sjs132]

Slim article... How long would it take to error check that much data?

on Another note... What did they do with all that Pr0n once it got to the other end?

yeah, this would fill my hard drives in .03 second

[VisiX]

But what is the latency involved in a system like this? Right now I get about 25000kbps and that is plenty for me, but what I really need is reduced latency for real time simulations.

Re:

[pizzutz]

Well the optical transmission would go nearly the speed of light, but I'm not sure how fast the transmitter and detector can keep up with splitting and recombining 164 channels of data.
I'm sure this is being looked at as a means of an intercontinental backbone, rather than something coming into your house.

Doesn't matter...

[ScaryMonkey]

No matter how much speed they create, they will still be subject to the Law of Diminishing Porn Returns, which states:

For download rate n, my demand for new porn will require me to download at a rate of n+1.

Sending "optical data"

[Splab]

Where I the only one thinking a truck filled with DVD's when the headline said optical data?

Re:Sending "optical data"

[thwack328]

Senator Stevens? Is that you?

hurr

[snarfies]

Jeepers, that's really cool.

Meanwhile, I can't even get FIOS service in Philadelphia, one of our major cities, despite my keen desire to purchase it.

Re:

[DarkSarin]

really, because I'm out in doylestown, and I have it. 5/5. and I'm very happy.

of course I forgot to pay my bill for a couple months, so they aren't happy with me...but it is still working, so whatever.

wait a minute...

[dnno]

the title says 100 Gbps
the article says approx. 16 Tbps
and the last sentance says how close we are to creating 100 Gbps ethernet and describes how the terabit link was created using multiplexed signals at 100 Gbps.
so what the heck am i missing, because im confused as hell

Re:

[Detritus]

DWDM [wikipedia.org]

Re:

[burning-toast]

The cable (fiber optic) has multiple lasers sending through it at once (multiplexing). So a single laser could operate at 100Gbps, but 164 of them at once... well...

They just use different "colors" of lasers for each 100Gbps signal.

!Ethernet

[Lars Clausen]

Part of the Ethernet spec [wikipedia.org] is to wait 9.6 microseconds after the medium appears to be idle before sending, then resend if it collides. Light moves about 3 kilometres in that time. Making an Ethernet of 2550 km pratically guarantees nothing but collisions. So while this is a hunkin' heap of net, it's not Ethernet.

Re:

[funaho]

Well in order to have collisions you need at least two transmitters on the same medium, and this is a point-to-point full duplex fiber connection; there can't be a collision because the two ends transmit on opposite fibers. It undoubtedly required some serious TCP/IP tweaking through to take advantage of that throughput.

Fortune

[Sigl]

Hilarious... The fortune that I had at the bottom of the comments for this artcle:

There is more to life than increasing its speed. -- Mahatma Gandhi

Did someone plan that?

Re:

[burning-toast]

- Did someone plan that?

Here is mine:

To doubt everything or to believe everything are two equally convenient solutions; both dispense with the necessity of reflection. -- H. Poincar'e

In other news

[BlueParrot]

The movie industry just shat a brick.

Reading stories like this are nothing more than

[MrSnivvel]

swift kicks in the groin, when all you get at the house is a "blazing" fast speed of 26.4 Kbps on dial up. Thank you Verizon, fucking thank you... ISDN is not even an option where I live.

So...

[electricbern]

Let me see if I got this right... They made 164 lights of different color blink very fast and very far. Why can't Slashdot summarize things better?

Re:

[dave420]

Surely if an ISP adopted this, they'd have people signing up left right and centre. Wouldn't it be awfully attractive to their target audience?

Re:

[darthflo]

Unfortunately both target audiences (that's 1. Supercomputing/clustering big/experimental stuff and 2. being a Tier 1 backbone provider) for this kind of technology don't need their ISP to provide it. Your average SoHo couldn't even deliberately use a single Gigabit link; even well-connected datacentres don't (yet) need 100 Gbps outside connectivity.

Re:

[Anonymous Coward]

Consider a standard computer utilizing two channels of ddr2-800. This only has a bandwidth of of 102.4 gbps. You would need to attach this connection directly to your ram in this case. Now computers are starting to utilize ddr3 which can theoretically provide double that in the same configuration. But at those speeds, amount of available ram would be limiting the actual throughput. 100gbps utilizing 128GB of ram would be emptied in 10.24s (1024gb/100gbps). Having to have a storage array capable of sen

Re:

[Gaima]

This is the reason 100gpbs isn't being considered for lan use. It just isn't feasible at this point.

Stick a thousand machines on each end, and you'll understand why 100Gbps is needed.

Re:

[Doc Ruby]

I'm running Linux on a Playstation3 with SPU video drivers in its Cell uP that can run at over 150GFLOPS. Since the PS3 has only 512MB RAM, it needs to be fed by the LAN and just buffer the LAN in its RAM. Even if SATA drives are delivering only 1.2Gbps, there's no reason I can't have multiple parallel drives on independent servers (if a single server's IO isn't fast enough for multiple SATA at full bore) on my SAN delivering multiple streams through my switch all to my Playstation. Now, the PS3's 1Gb-e is

Re:

[gnuman99]

So, you want to create an SMP type cluster where each CPU is connected with another access a 100Gbps switched network? And your application sounds like it needs SMP to work but you want to go "on the cheap" and instead of getting a SMP supercomputer or even renting space in you, you just want to have a rack of playstations instead with 100Gbps network adapters?

I suggest you fix your algorithm or get/rent a machine that can handle your data instead of guessing playstation will ship with 100Gbps ports for you

Re:

[Doc Ruby]

The part you missed was where I said "the point is that there are already machines that can use that bandwidth". My TV's HDMI port already does 10Gbps. When I want to mix a couple PiP streams with incoming videophone and a peek at the front door for the pizza delivery, all in HD swapped around my house to different TVs to get someone to answer the door so I can stay on the phone (or some other common combination), that kind of bandwidth won't seem so exotic.

Of course I want to go "on the cheap". Everyone wa

Re:

[macemoneta]

The total bandwidth doesn't have to reach 100Gbps, but only exceed 10Gbps, to require faster than 10G-e, which only 8-10 SATA drives in parallel could do today.

The SATA interface speed isn't of much use in this calculation. While SATA drives can burst to their interface speed when data is in the drive cache, they can only sustain 50-70MB/s (400-560Mb/s). In order to bring a 10G port to 80% sustained utilization, you would need 15 to 20 drives running at capacity (meaning, no seeks). In reality, with no

Re:

[Doc Ruby]

40 SATA drives is no big deal. I've got over a dozen SATA drives running in my home, mostly to store my media collection. And I haven't even begun collecting video, because 750GB-1TB drives aren't that cheap yet. Once drives drop below $0.10:GB, and there are more HD video titles (especially if for download or TiVo), 40 SATA drives will be fairly common in many homes, to say nothing of the media servers that are servicing them.

Re:

[Doc Ruby]

I've got a very large collection of live music recorded (legitimately) by people in the audience, like Deadheads, over the past 30-50 years. And a solid percentage of that by bytes is video.

A 180GB drive holds only 45 DVDs. When you're talking about hundreds of shows on video, you're talking about dozens of drives.

It's not yet at the point where I need more than 1Gbps, but that's mainly because I don't have the SW quite running seamlessly for real home multimedia. But I'm still accumulating content, includi

Re:

[shentino]

DDR using 102.4 gbps?

Wow, I didn't know you could dance that fast.

Re:

[D4rk Fx]

Where can you get 10G Ethernet cards for $50? I'd really like to know and I'm sure there would be a lot of interested people...

Re:

[Doc Ruby]

I had found with Froogle a Sun 10G-e card (probably refurbished) for $35, but it's not available now on searching again. It does seem that 10G-e cards do cost something around $500 at least, and plenty up around $900+.

But the point is that I can't buy anything faster for even 10x or 100x, except multiple cards. And maybe some really exotic interconnect that's not ethernet, so apps have to be recoded to use it.

Re:

[afidel]

You're apps don't talk to Ethernet, they talk to your TCP/IP stack! There is an IP over Infiniband standard which is supported by most HCA's and it's even fully offloaded to the HCA processor. IPoIB isn't as efficient or low latency as native Infiniband protocols but at least you don't have to recode your apps =)

And the reason there isn't anything faster is that it's such an incredibly niche market, the number of sites that need greater than 1GB/s on a single link are very, very small. Heck the storage for

Re:

[Doc Ruby]

Hmm, does IP over Infiniband run under Linux on a PC with PCI-e? Or any other <$5000 hardware?

Re:

[afidel]

Yes [mellanox.com], yes it does [mellanox.com].

Re:

[Doc Ruby]

That MHGA28-1TC is very cool. At about $800 [google.com] for dual 20Gbps, that's $200 for the equivalent of 10Gbps, which costs $500 standalone. But a much more usable package, without de/muxing to get 20Gbps, and probably better ability to "bond" (or equivalent) across both 20Gbps ports for simulated 40Gbps. If only there were more competitors, it might be closer to $100 per each 10Gbps, which is cheaper than even standalone 1Gbps now, and of course much more integrated (lower power, more manageable, less HW...).

Since

Re:

[afidel]

Qlogic makes cards too, their Silverstorm 7000 is similar to the MHGA28-1TC in that it supports dual 4x links, but because they are basically a duopoly there isn't much price competition. Actually it's quite similar to FC where there's Qlogic or Emulex.

Re:

[Doc Ruby]

PS: That post [slashdot.org] my 16,362nd. Probably fun to post #16384. My UID is (nearly exactly) 1/3 yours, so we were at equal rates when I posted #15313 - you're at 93.6% of mine. We both probably need a faster connection just to keep up with our posting rate ;).

Re:

[afidel]

If you really need greater than 10Gbps then go with Infiniband as you can get 12x HCA's that will do 24GBps (48Gbps full duplex). But if you're paying $50 for 10Gbps ethernet you're not getting offloading and your CPU's are probably swamped of your TCP/IP stack is the problem. I would suggest getting a pair of offloading 10Gbps cards and seeing if you don't see a huge improvement.

Re:

[Doc Ruby]

Well, it turned out that 10Gbps interfaces actually cost more than $50, probably more like $500 per port. But they don't require recoding apps to use the Infiniband fabric.

The point is really that there's a huge jump from a $15 1Gb-e (or $500 10Gb-e), if that jump can be made at all, while there's no 100Gb-e at any price. And instead of rolling out 100Gb-e that works for LANs, the industry is evidently waiting until it's good for continent-spanning WANs.

Re:

[afidel]

You keep talking about recoding apps, YOU DON'T NEED TO. There is a standard for IP over Infiniband. It's not as performant as native Infiniband protocols but it DOES exist and is in use. Besides without a dedicated specialized processor and gobs of buffer memory your typical server isn't going to be able to keep up with 10Gbps Ethernet let alone anything faster.

Re:Make it Short and Fast and Snappy

[leomaro]

There is another problem, and is actually the bottleneck of transmitting packets at high rates.

It doesn't really matters (yet, and considering Ethernet technology) if the BW of the fiber is a zillion Petabits/sec.
The problem is now at 1Gbps and 10Gbps in Ethernet technology, and is because the processor overloads with the amount of hardware interrupts. The processors that are general purpose have to waste too many clock cycles processing that much interrupts, the processors nowadays are superscalar [ http://en.wikipedia.org/wiki/Superscalar [wikipedia.org] ]and every time the processor have to change the context (to attend an interrupt) has to do lots of things like unloading the registers, saving the context, loading the registers of the new process, and has to drop something out of the pipeline [ http://en.wikipedia.org/wiki/Pipeline_(computing) [wikipedia.org] ] loosing performance.

Ethernet tech has a huge latency [ http://en.wikipedia.org/wiki/Latency_(engineering) [wikipedia.org] ] and a stack that makes processing not so easy (if you look at te code of a linux network device driver it handles pretty much everything including writing the mac address that is only copied when the driver initialize).

That is why there are some relative new things (NAPI in Linux) that try to make lessen the overload, there are new network devices that handle layer 2 and 3 (or at least parts of those, for example, is used to be handled the checksum algorithm) to avoid doing it in the processor. There are some white papers (one from intel, another from NetXen, I'm sorry I don't have the links now) that explain the problem and some approach to a possible solution.

Yes, I know, there is something I have not said, and is that the main switches or routers have to deal with that and have hardware specially designed to do heavy network packet processing, and that is the point, the network cards will have to do that (and are already starting to), neither is an easy job for hardware designers, nor for the market, is easier and cheaper to have a machine that you can change the behaviour only changing the firmware or changing settings from a program (routers have an operating system, and lots of those are a general purpose microprocessor with a linux kernel and a web server to configure it, for example home routers).

There is much to say yet in this field.

Re:

[Detritus]

Interrupt loads can be greatly reduced by switching to a polling-driven architecture. See FreeBSD.

Re:

[leomaro]

>Interrupt loads can be greatly reduced by switching to a polling-driven architecture. See FreeBSD.

New API (NAPI) takes a mixed approach, read: [ http://en.wikipedia.org/wiki/New_API [wikipedia.org] ], and for more information: [ http://www.linux-foundation.org/en/Net:NAPI [linux-foundation.org] ].

Re:

[Doc Ruby]

I don't see why a fast ethernet card can't have its own DSPs and/or FPGAs for decoding packets, then sending them across PCI-e to XDR memory. For $500 or $1000, 100Gbps HW should be able to deliver.

Re:

[jpmattia]

The problem is now at 1Gbps and 10Gbps in Ethernet technology, and is because the processor overloads with the amount of hardware interrupts.

That's not the point of the article. 100 Gb/s technology is not being invented to hook up just 2 or even 100 computers to each other. The 164 wavelengths each carry a different 100 Gb/s stream. This is the type of technology you use when are trying to connect a chunk of Boston to a chunk of Baltimore.

In order to process streams that fast, the first thing you

Re:

[Moskit]

"Everyone" is waiting for either 40Gbit/s or 100Gbit/s Ethernet.
The first one is what server-people push (they claim they do not need more, that's why 40Gbit/s was put into Ethernet standard),
while network people want full 100 Gbit/s.

> But what about all the LAN vendors, which have a real market for 100Gbps

They don't.
There seems to be market either for 40Gbit/s in LAN/local connections or for 100Gbit/s for core/long haul. At least judging but what happened with high-speed ethernet standard.

Re:

[Torg]

In my experience I have great demand not for 100Gbps Ethernet, but Fibre Channel. It is a common problem is replicating data between data centers. The high end approach to this is to get two DWDM switches and dark fiber (if you can afford it).

The main problem with transporting large data segments over Ethernet is quite simple. Data is read off disk (typically) at 8KB chunks, then converted to 1.5Kb Ethernet packets. This "fragmenting" and additional overhead is what causes allot of the resultant lag.

Re:

[Doc Ruby]

Well, "100"Gbps is an arbitrary number. So long as it's significantly bigger than 10Gbps. 40Gbps would be good, too, but it's not available either.

The advantage of ethernet is that apps are already coded to use it. Including all the network mgmt apps.

Re:

[Doc Ruby]

True, but the rest of the sentence said:

Since there's no other local interconnect faster than 10Gbps-e, I'd even settle for 100Gbps-e across 1m, for interconnecting in my rack without changing my software that all depends on ethernet between hosts.

Infiniband isn't ethernet.

Re:

[Doc Ruby]

How can it be a few years until "any breakthrough" in >10Gbps when we're discussing successful tests of 100Gbps across 2550Km already? Sounds like the breakthroughs have already arrived, but telcos are aiming for a totally different market than LANs. If it's working even most of the time at 2550Km, then it should be pretty close to commercial availability at 10m or 100m.

Re:

[Doc Ruby]

I already described in this thread how a single host can saturate 10Gbps. And multiple cards have sync problems. De/muxing 50Gbps across 5-8 cards is a huge problem, in sync and just CPU power that's better off in an ASIC/DSP/FPGA in the network controller.