Slashdot Mirror
10 Terabit Ethernet By 2010
Eric Frost writes "From Directions Magazine: 'Because it is now impossible to sell networking unless it is called Ethernet (regardless of the actual protocols used), it is likely that 1 Terabit Ethernet and even 10 Terabit Ethernet (using 100 wavelengths used by 100 gigabit per second transmitter / receiver pairs) may soon be announced. Only a protocol name change is needed. And the name change is merely the acknowledgment that Ethernet protocols can tunnel through other protocols (and vice versa).'"
From the article: "iSCSI (Internet SCSI) over Ethernet is replacing: *SCSI (Small Computer Systems Interface..."
iSCSI is far superior to stadard SCSI for obvious reasons, and its widespread adoption will really spark a massive gain in the SAN (Storage Area Network) market. The technology is there, now we just need more major vendors of SCSI devices (especially storage and image filing systems) to make more SCSI devices that support iSCSI natively and applications that take advantage of it. Combined with practical solutions from vendors of network storage software like Veritas we could see some major spending in IT. And more money being spent on IT is always a good thing.
I don't keep up much with the progress of the Ethernet technologies at hand, so is it realistic to suppose that the practical implementation/creation of 100 Gigabit Ethernet, 1 Terabit Ethernet, and 10 Terabit Ethernet will be seperated by merely two years each?
"Because it is now impossible to sell networking unless it is called Ethernet". Incorrect. You can easily sell network gear that is tagged with the "WiFi" designation.
Is there going to be storage that can read/write that fast by 2010 too?
paintball
Bandwidth is good, but what about latency? Ethernet has traditionally suffered from high latencies and doesn't work very well for High-Performance-Computing-Clusters. Myrinet and other ridiculously overpriced networking hardware works much better for clustering. I wish terabit ethernet does something about ethernet latency so that efficient clustering becomes a little cheaper.
What is that article actually supposed to be about? Seems like a scrambled mess of acronymic buzzwords with no actual content to me.
...is there going to be a bus on desktop machines that can read or write that fast?
Probably not. But I could definitely see it being useful for top-end server systems with hugely parallel storage and memory access.
The article is already slashdotted so I can't read it. So what is it refering to? 10Tb LAN speeds? If so - who cares? My existing 100Mb (200Mb switched full duplex) LAN is hardly the weakest link.
10 Terabit Ethernet: from 10 Gigabit Ethernet, to 100 Gigabit Ethernet, to 1 Terabit Ethernet
By: Steve Gilheany
(Aug 27, 2003)
Ethernet Timeline
* 10 Megabit Ethernet 1990*
* 100 Megabit Ethernet 1995
* 1 Gigabit Ethernet 1998
* 10 Gigabit Ethernet 2002
* 100 Gigabit Ethernet 2006**
* 1 Terabit Ethernet 2008**
* 10 Terabit Ethernet 2010**
* Invented 1976, 10BaseT 1990
** projected
Every kind of networking is coming together: LANs (Local Area Networks), SANs (Storage / System Area Networks), telephony, cable TV, inter-city optical fiber links, etc., but if you don't call it Ethernet you cannot sell it. Your networking must also include a reference to IP (Internet Protocol) to be marketable.
Above 10 Gigabit Ethernet lies 100 Gigabit Ethernet. The fastest commercial bit rate on a fiber transmitter/receiver pair is 80 Gigabits per second. Each Ethernet speed increase must be an order of magnitude (a factor of 10) to be worth the effort to incorporate a change, and 100 Gigabit Ethernet has not been commercially possible with a simple bit multiplexing solution, but NTT has solved this problem and has the first 100 Gigabit per second chip to begin a 10 Gigabit system [http://www.ntt.co.jp/news/news02e/0212/021204.htm l]. Currently, Nortel Networks offers DWDM (Dense Wavelength Division Multiplexing) where 160 of the 40 Gigabit transmitter/receiver pairs are used to transmit 160 wavelengths (infrared colors) on the same fiber yielding a composite, multi-channel, bandwidth of 6.4 terabits per second. Because it is now impossible to sell networking unless it is called Ethernet (regardless of the actual protocols used), it is likely that 1 Terabit Ethernet and even 10 Terabit Ethernet (using 100 wavelengths used by 100 gigabit per second transmitter / receiver pairs) may soon be announced. Only a protocol name change is needed. And the name change is merely the acknowledgment that Ethernet protocols can tunnel through other protocols (such as DWDM) (and vice versa). In fact, Atrica has been advertising such a multiplexed version of 100 Gigabit Ethernet since 2001. [http://www.atrica.com/products/a_8000.html] Now that NTT has announced a reliable 100 Gigabit per second transmitter/receiver pair, the progression may be 1 wavelength for 100 Gigabit Ethernet, 10 wavelength (10 x 100 Gigabits per second) CWDM (Coarse Wavelength Division Multiplexing) for 1 Terabit Ethernet, and 100 wavelength (100 x 100 Gigabits per second) DWDM for 10 Terabit per second Ethernet in the near future.
iSCSI (Internet SCSI) over Ethernet is replacing: *SCSI (Small Computer Systems Interface, in 1979 it was Shugart Associates Systems Interface: *SASI), *FC (Fibre Channel), and even *ATA (IBM PC AT Attachment) aka (also known as) *IDE (Integrated Drive Electronics) *see [http://www.pcguide.com], Ethernet is replacing ATM (Asynchronous Transfer Mode), Sonet (Synchronous Optical NETwork), POTS (Plain Old Telephone Service, which is being replaced with Gigabit Ethernet to the home in Grant County, Washington, USA ) [see references from Cisco Systems 1, 2, 3, or 4] [www.wwp.com], *PCI (Peripheral Component Interconnect local bus), Infiniband, and every other protocol, because, as described above, if you don't call it Ethernet you cannot sell it. Everything, in every type of, communications must now also include a reference to IP (Internet Protocol) for the same reason.
At the same time that the transmitter / receiver pairs are getting faster, and DWMD is adding channels, the capacity of fibers is increasing, as is the transmission distance available without repeaters. Omni-Guide [http://www.omni-guide.com/; then click on enter] is working on fibers that "could substantially reduce or even eliminate the need for amplifiers in optical networks. Secondly it will offer a bandwidth capacity that could potentially be several orders of magnitude greater than conventional single-mode optical fibers." Eliminating
Tethernet?
"Teachers leave us kids alone
Meh, the article already appears to be slashdotted, but from a first read I have to wonder if I am missing something here with iSCSI. Is not this simply a different protocol that Firewire already takes care of, especially with faster iterations? Firewire is already a subset of SCSI, but hot plug and play and you can also TCP/IP over Firewire.
Visit Jonesblog and say hello.
Pretty cool for LANs, but otherwise rather useless.
We already have gigabit Ethernet - which (even rounding down somewhat to account for checksum and overhead and such) should be capable of transferring around 100 megabytes of data per second. How many of us have ever seen even 10% of this in practice for a general Internet connection? I'm lucky if I can pull one megabyte per second from an Internet site that doesn't happen to be, y'know, next door.
- David Stein
Computer over. Virus = very yes.
Imagine how much pr0n....er....um...I mean valuable business data you could get with this!
I used to get high on life, but I developed a tolerance. Now I need something stronger.
And only today I was in complete awe when I was able to download stuff using a 1 Gbps line...
BOO! TERRO
Gigabit ethernet, and 10 gigabit ethernet both have it in their specs to accomodate 100 ethernet and 10 ethernet. Therefore 10 Tb ethernet will be called 10000000/1000000/100000/10000/1000/100/10Base T for the OTHER technologies included. The chip will be bigger unless its fancy FPGAing with the FPGA code downloaded from the driver.
So to sell it as Ethernet they have to make it compatible as such. Or to make things cheaper, they will have to settle on a different name to sell cheaper 10Tb cards only. Cheaper 10Tb cards will sell more than compatible ones.
"Give orange me give eat orange me eat orange give me eat orange give me you." -Nim Chimpsky
The only time I see utilization above 10% is when I'm backing up systems across the wire.
This might be good for SAN's. But I'd be looking at iSCSI for that.
We haven't even deployed gigabit Ethernet yet.
I shudder to think of the size of the files that will need that much bandwidth for decent performance.
iSCSI bascially takes native SCSI commands, wraps it up (encapsulates it), and sends it over the wire. In other words, you could use a SCSI scanner over a network without having to resort to PC Anywhere or something.
is here
---
WARNING:Slashdot karma not redeemable in the afterlife.
Well, it *is* ironic!
The REAL jabber has the user id: 13196
What you do today will cost you a day of your life
Interestingly enough, if you did it wouldn't be a very big success because the internal PCI or PCI-X bus in the system would bottleneck the interconnects. The NICs would need on-board processors to scale with their enormous bandwidth potential so that they could solve problems like matching checksums and other package management tasks and not have to pound on the system bus so hard.
It wasn't long ago that we really started exploiting video chipsets for rendering graphics, either...
10 Terabit Ethernet: from 10 Gigabit Ethernet, to 100 Gigabit Ethernet, to 1 Terabit Ethernet
By: Steve Gilheany
(May 28, 2003)
Ethernet Timeline
* 10 Megabit Ethernet 1990*
* 100 Megabit Ethernet 1995
* 1 Gigabit Ethernet 1998
* 10 Gigabit Ethernet 2002
* 100 Gigabit Ethernet 2006**
* 1 Terabit Ethernet 2008**
* 10 Terabit Ethernet 2010**
* Invented 1976, 10BaseT 1990
** projected
Every kind of networking is coming together: LANs (Local Area Networks), SANs (Storage / System Area Networks), telephony, cable TV, inter-city optical fiber links, etc., but if you don't call it Ethernet you cannot sell it. Your networking must also include a reference to IP (Internet Protocol) to be marketable.
Above 10 Gigabit Ethernet lies 100 Gigabit Ethernet. The fastest commercial bit rate on a fiber transmitter/receiver pair is 80 Gigabits per second. Each Ethernet speed increase must be an order of magnitude (a factor of 10) to be worth the effort to incorporate a change, and 100 Gigabit Ethernet has not been commercially possible with a simple bit multiplexing solution, but NTT has solved this problem and has the first 100 Gigabit per second chip to begin a 10 Gigabit system [http://www.ntt.co.jp/news/news02e/0212/021204.htm l]. Currently, Nortel Networks offers DWDM (Dense Wavelength Division Multiplexing) where 160 of the 40 Gigabit transmitter/receiver pairs are used to transmit 160 wavelengths (infrared colors) on the same fiber yielding a composite, multi-channel, bandwidth of 6.4 terabits per second. Because it is now impossible to sell networking unless it is called Ethernet (regardless of the actual protocols used), it is likely that 1 Terabit Ethernet and even 10 Terabit Ethernet (using 100 wavelengths used by 100 gigabit per second transmitter / receiver pairs) may soon be announced. Only a protocol name change is needed. And the name change is merely the acknowledgment that Ethernet protocols can tunnel through other protocols (such as DWDM) (and vice versa). In fact, Atrica has been advertising such a multiplexed version of 100 Gigabit Ethernet since 2001. [http://www.atrica.com/products/a_8000.html] Now that NTT has announced a reliable 100 Gigabit per second transmitter/receiver pair, the progression may be 1 wavelength for 100 Gigabit Ethernet, 10 wavelength (10 x 100 Gigabits per second) CWDM (Coarse Wavelength Division Multiplexing) for 1 Terabit Ethernet, and 100 wavelength (100 x 100 Gigabits per second) DWDM for 10 Terabit per second Ethernet in the near future.
iSCSI (Internet SCSI) over Ethernet is replacing: *SCSI (Small Computer Systems Interface, in 1979 it was Shugart Associates Systems Interface: *SASI), *FC (Fibre Channel), and even *ATA (IBM PC AT Attachment) aka (also known as) *IDE (Integrated Drive Electronics) *see [http://www.pcguide.com], Ethernet is replacing ATM (Asynchronous Transfer Mode), Sonet (Synchronous Optical NETwork), POTS (Plain Old Telephone Service, which is being replaced with Gigabit Ethernet to the home in Grant County, Washington, USA ) [see references from Cisco Systems 1, 2, 3, or 4] [www.wwp.com], *PCI (Peripheral Component Interconnect local bus), Infiniband, and every other protocol, because, as described above, if you don't call it Ethernet you cannot sell it. Everything, in every type of, communications must now also include a reference to IP (Internet Protocol) for the same reason.
At the same time that the transmitter / receiver pairs are getting faster, and DWMD is adding channels, the capacity of fibers is increasing, as is the transmission distance available without repeaters. Omni-Guide [http://www.omni-guide.com/; then click on enter] is working on fibers that "could substantially reduce or even eliminate the need for amplifiers in optical networks. Secondly it will offer a bandwidth capacity that could potentially be several orders of magnitude greater than conventional single-mode optical fibers." Eliminating
---
WARNING:Slashdot karma not redeemable in the afterlife.
My prediction for the year 2010... I'll still be on a 56k modem. :-(
Adidas To Bring Back Sneakernet
...to prevent the Slashdot Effect?
dinner: it's what's for beer
These high speed DWDM systems talked about in this article aren't designed to be used for LANs or home internet connections - they are meant for high speed backbones that span huge distances (such as across the US or Australia).
They carry mutiple 10Gb/s or 40Gb/s channels on one fibre pair - and these individual channels can be added or removed as necessary, and can be treated independantly. Saying this, 10Gb/s is still a lot, and generally that needs to be broken down into more managable sections, such as gigabit copper ethernet or maybe even 100Mb/s.
It may seem like overkill, but at the core of most networks, there is a distinct lack of bandwidth. Maybe the VOD and video calling predicted 10 years back won't happen on these networks, but more applications are requiring these huge amounts of bandwidth.
An example of this sort of system being rolled out is the Marconi Solstis system in Australia. A very small part of that system was designed by me :)
iSCSI bascially takes native SCSI commands, wraps it up (encapsulates it), and sends it over the wire. In other words, you could use a SCSI scanner over a network without having to resort to PC Anywhere or something.
I believe the same concept is possible with Firewire. In fact, the Firewire protocol allows for use completely independently of any computer or CPU.
Visit Jonesblog and say hello.
Latency is the killer there, not really bandwidth.
paintball
I am sure packetengines (http://www.scyld.com/network/yellowfin.html) is all over this.
These guys had gigabit routers four years ago when I was helping to set up the AFN (ashlandfiber.com)
Cool to see.. mo'faster is mo'betta
anime+manga together at last.. in real time.
I am an EE major and when I was going to university in the late 80s early 90s everybody was going on how fiber was the future and that we'd run out of capacity on copper RealSoonNow: who'd have thought about 10TERABIT ethernet back then! (heck, I was happy as a clam when my lab upgraded from coax to baseT so the jokers couldn't bring down my box by unscrewing their terminators...)
-- the cake is a lie
that magazine needs it right now...already slashdotted.
Lucent was selling their all-optical DWDM switches (Lambda Series) last year. The LambdaXtreme is a 40 Gbps DWDM unit that uses micro-mirrors (MEMS) for switching. Data is not converted to electricity, but stays as photons the entire route. It is capable of sending data through optical fibers for 1,000 KM *without regeneration* and at 4,000 KM *without regeneration* at reduced (10 Gbps) speeds.
They sold a pair of units (and you have to buy at least 2 or they are useless) to Time-Warner. There is one on the East Coast and one on the West and it forms a major part of their cross-country backbone.
8-10 of the units were sold to Korea (South) for use in wiring up their national rail systems. I also believe NTT DoCoMo (Japan) bought a couple.
This is all last year. Since I'm no longer with that company (layoffs), I no longer get all the product updates. These units were in my product group for install, service and support.
Learning HOW to think is more important than learning WHAT to think.
Maybe it can be used by groups of Terra card readers all at once! Yeah uhh ..
... a neural network one day, and skylab the next :)
On a real note, this could bring about a huge change in Wide Area Multi Processing(WAMP) - such as several large companies do now, have one master and a bunch of slave machines that all respond to the tasks given to them, (a big Beuowolf) write speeds on storage might not be up to speed, but given directly to precessors on other machines, and Whola! One really big super computer, or one big network
Holla
10TB by 2003+rand()%20;
20TB by 2020+rand()%40;
but really, who cares?
Yes, woho, 20THZ prosessors in 2030! I can hardly wait!
Think of how fast you could download porn...
My harddrive would fill faster then it does now.
[sig]www.masterslate.org[/sig]
And what am I going to do with 10TB ethernet?
Pr0n. Lots of pr0n.
Cheers,
-- RLJ
250 and 300GB SATA disks are already pushing sustained over 50 mbytes/sec, at 7200 rpm. That's enough to max out most gigabit cards, except for the higher end ones.
As long as the aerial density keep increasing, we will see slow but steady increases in speed too.
If anything, networking has been the stagnant factor lately. Gigabit over copper has been out for years now, and the hardware for it is still overpriced, and mostly made by a few manufacturers.
I've had enough abrasive sigs. Kittens are cute and fuzzy.
Well, I think that the reason that things can't be sold without the ethernet label on it has got to be because of the increase in the popularity of networking.
Go driving around a neighborhood with Kismet and you'll see what I mean. There are tons of people with Wireless networks in thier homes. Now every Joe user in the world can set up thier own network in thier home. Now, Joe doesn't know the difference between ethernet and cat5. But what is the main thing that he sees on all of his packaging? ETHERNET. ETHERNET is printed all over boxes and labels, and so Joe assumes that all networking is just called ethernet. Once you get this term being thrown around, everyone calling everything ethernet, who wants to be the know-it-all explaining protocols and going off with technical babble that he wont get anyways?
When you're wiring up your home so that you can have high-quality, practically uncompressed high definition video coming from a central video server such that every room can be watching a different stream simultaneously, while some may be actively editing data and rerendering, you're going to want the fastest, fattest pipe you can get.
And who knows what bandwidth-hungry LAN application you're going to want to do in the future. Have you any idea how long it takes to render a cup of tea, Earl Grey, hot in spacetime over a 100 Mbit/sec connection? I can tell you one thing: it's not going to be hot.
More bandwidth than you'll ever need is always better than not enough. Especially when you aren't leasing it from an outside party!
Oh, say does that Star-Spangled Banner entwine / The myrtle of Venus with Bacchus's vine?
Ever dream you could fly? Get up from the Flight Sim. I Fly
Forget MS Passpost, you must now send your complete Genome to login to Hotmail. Just stick your finger on the MS Gene-o-matic to login and check your email. Special Delivery packages will still require a neck scraping.
Great if you have very long arms to reach the scanner from your desk.
That's the next step in fast bus speeds over copper. ;) Look it up on Google.
Ok, so here's my situation.
Just bought a house. Got a sweet deal with the builder where I sign a waiver (if you kill yourself it's not our fault), and I'm able to go in and put network cable in the walls. This will probably happen in a month or so (they just poured the foundation two weeks ago).
I was seriously going to go in there and put 2-4 Cat5e ports in each room, and I've already bought a 1000ft spool of the stuff for the occasion. Unfortunately due to building codes (so they say), they will not allow me to run conduits, so whatever I put in will have to do.
Will this make my copper cable obsolete? What can I do to future-proof this installation?
And no, I don't have the money to deal with fibre, nor the necessary tools or patience. But I suppose in the future the air return ducts or the central vac tubes might come in handy.
You can accomplish anything you set your mind to. The impossible just takes a little longer.
"You keep using that word...I do not think it means what you think it means..."
Article has far too many (uneccessary) parentheses (brackets) makes random claims (must be called Ethernet) than doesnt back any of its claims up. It's not even (slightly) interesting (but at least it wasnt an advert)
Imagine a beowulf cluster of nodes connected by this!
"Freedom means freedom for everybody" -- Dick Cheney
My apologies for both the recursive quoting and name dropping.
Use Python
I'll stop trolling here after I get this out: stop thinking this has anything to do with your top-of-the-line, supergeekin' Athlon.
:(
This technology is namely meant for backbones, be it on a campus level or as a longer haul backbone. Obviously, your desktop will not need to transfer anywhere near that much data within the next, say, 25 years. If you were using your head while you were reading the (albiet poorly written) article, I wouldn't have to troll.
I just wasted your mod points! HA!
mao che minh bascially takes common sense and widely known information, wraps it up (rewords it), and reposts it for karma whoring. In other words, you could use a mao che minh scanner over a network to find plenty of worthless posts modded to +5.
Last time i checked.. ethernet on the backbone was a setup for disaster..
Having worked in large WANS before.. saying ethernet is replacing ATM is like saying *BSD is dying
I know of more places that have deployed ethernet on the backbone to have problems with colisions, "coloring packets" for QOS (MPLS) and other crap, youd wonder why people just wouldn't spend the 5 minutes to learn a bit about ATM and do it right in the first place.
Plus.. once you realize you can tunnel ANY protocol though ATM, and put QOS and multiple vlans in to elans and setup specific bandwidth PVC's and SPVC's why use ethernet on the backbone.
On the desktop.. tokenring has been proven to outperform ethernet as it's able to balance a load many magnitudes greater than ethernet could ever possibly hope. (collision avoidance and not ethernet's collision detection)
You wouldn't use windows and IIS for a high volume highly customizable webserver.. why the hell would you use ethernet on the backbone.
Ethernet is for the edge.. ATM IS the backbone.
My manager keeps correcting me: "It's not Ethernet, it's 802.3!" Uh, then why is the driver name "eth0"??? Is "eth" a contraction of "Eight oh two dot THree"?
"Freedom means freedom for everybody" -- Dick Cheney
First Off: HIGH Bandwidth HIGH SPEED.
So for those of you people who say who cares, cause my puny little hard drive or puny little computer can't pump that amount of data anyway.
NO SHIT. NO one give a flying rats ass about your little personal computer or your little 10 person lan.
What this article is about is for the large companies with 1000's of employees all around the world will be able to all hop on the 1TB link and each send their data around TOGETHER.
MORE people can use the link simultaneously as opposed to one person goin REALLY fast.
haha, Rock on Charles. :)
I just wasted your mod points! HA!
Protocol to transfer data through the Aether. It's a magic network weeeeeeeeeee! Gives a new meaning to Wireless Ethernet.
Trolls dont like to be Flamebait, because they burn so well. Protect our Troll heritage!
Can you imagine trying to stop mp3 transfers with this technology?
A 5MB mp3 would take 0.000004 seconds. A whole CD would take a whopping 0.00056 seconds.
I certainly hope so, or there's no way in the world I'll be able to play "Unreal Tournament 2010" with internet multiplayer.
One would think that if they have a device that could route such traffic, then it must have some sort of bus/hardware capable of handling it. Somwhere along the line this traffic has to hit a node-point, right?
Now really, I don't see much point in directing 10Tb ethernet to one machine anyhow. But it would be great for large node-points. I you think about 100Mbps, generally no single machine is going to use that much in a normal network. However, many machines will, and sometimes quite easily in large situations.
For huge networks, or ISP's, 10Tb would be the way to go.
I allready get 10 terabits per second, everytime I connect to windowsupdate.microsoft.com.
Oh wait, that's 10 Tera(ble) Bits.
dude, that SUCKS. still looking for a job? how long were you out of work, if not? i got axed by HP (i was a cpq'er) back in january and it took me 7 fucking months to find a job. very bad time indeed to be a propeller head :-/
mas cerveza, por favor politically incorrect stu
And that assumes that transfer occurs at chip speed, which it doesn't. Assuming a modest clock multiplier of 8 between system bus and chip, that's a 15x overcapacity, even if the entire computer were used to transmit.
-Looking for a job as a materials chemist or multivariat
10 TB/s? 10 TB/min? 10 TB/millenium? It's too bad the author can't distinguish between a rate and a quantity.
I am afraid by 2010 slashdotting will vanish ...
Perhaps "Not/." would be a good name for the protocol?
10Tb/s means
5 million 2Mb/sec compressed video streams
Copy a 250GB drive in 1/4sec
23 thousand streams of 24bit x 1600*1200pix x 75hz uncompressed
1.5k byte packets at 670 million/sec
2 billion x 50 byte packets per sec
port scan all ports on all IPv4 addresses in 20 minutes
Every US resident downloads Metallical's new track in 30 minutes of my http server
And this will all be available at Fry's for a $50 NIC and $30 cable ? When ? I'll hold off buying any new network HW 'till then :^)
Seriously, there are some significant implications here. For 1, you won't need a monitor connected directly to the "fast video card" to get the next fancy 3D graphics features. Memory bandwidth and network bandwidth will be similar meaning that clustered NUMA systems will be interesting. Some of the design decisions we deal with today have been because getting the person close to the computer to improve the experience was a critical factor will disappear.
Laid off April 30, paid thru June 30. used that money plus unemployment to float me along long enough to start a consultant business and snag just enough clients to survive.
Next month is a big push for growth. We have the clients lined up and almost ready to sign. Just have to get all the last duck in a row.
Not a nibble on all the resumes sent out in April/May/June. Bad time in deed.
Learning HOW to think is more important than learning WHAT to think.
From the article they have a snippet at the top that goes like this - i've added the years in between on my own:
10 Megabit Ethernet 1990*
(5 years)
* 100 Megabit Ethernet 1995
(3 years)
* 1 Gigabit Ethernet 1998
(4 years)
* 10 Gigabit Ethernet 2002
(4 years)
* 100 Gigabit Ethernet 2006**
(2 years)
* 1 Terabit Ethernet 2008**
(2 years)
* 10 Terabit Ethernet 2010**
I think this would be more accurate though:
* 100 Gigabit Ethernet 2006**
(3 years)
* 1 Terabit Ethernet 2009**
(3 years)
* 10 Terabit Ethernet 2012**
Basically I don't see the technology being developed any faster than 3-4 years because as it stands, home main stream still opperates at DSL connections of 10mb and home networks run at 100mbs. As far as the business world goes, the majority of companies I have had the opportunity of working at run only 100mb networks with IT "thinking/testing" going 1gb.
In short - there is NO demand for 10gb networks currently and especially NO demand for 100gb let alone a freakin terrabyte pipe. Although those things are "nice" and very "cool", there is not a big enough demand/NEED for this kind of transfer - YET.
You could also use the analogy of the current PC market. There is not a big demand for new systems right now because even for business use a P4 1.6ghz with 512mb of mem runs everything work and game related fine. As soon as something comes out that REQUIRES/needs more power THEN you will see a rise in pc sales.
Ave Molech Setting
I am still waiting for DSL and/or Cable. Ho hum.
Life is like pants... fit in or you don't fit in.
glad to here you're making ends meet :) 7 months was just too much for us :/ so we pretty much "popped" financially. starting over ain't all bad, though. finally got another decent paying job, had to move from houston to phoenix to get it, but phoenix doth kick much ass-age compared to houston - so we're enjoying it :P
mas cerveza, por favor politically incorrect stu
Does anybody know how fast a Corvis network is? Also the author leaves out Hypertransport, Serial ATA, and several other in the box transport modes. Are we going to call everything ethernet? I don't think so, I also don't see any proof of his statment, you have to call it ethernet, he may be write that you have to explain the equivalent ethernet speeds, but that just helps there be an apples to apples comparison (well you also have to compare latency and the like). DWDM seems to be a well know concept in the network/telco worlds.
Onward to the Aether Sphere!
It's even simpler than this, in a way. "Ethernet" denotes a protocol. But in Ethernet parlance, "DWDM" is a Physical Medium Dependent (PMD) sublayer. 10 Gb/s Ethernet (802.3ae) already includes a WDM PMD, 10GBASE-LX4.
He's right on the money.
The man who trades freedom for security does not deserve nor will he ever receive either. - Benjamin Franklin
However does a beowulf interconnect actually need 10 terrabits per second? Currently a PCI-X 133mhz bus is capable of transferring between 500 mbytes/sec and 1 gbytes/sec. 10 terrabit/sec = approx 1.3 terrabytes/sec or 1300 gigabytes per second. So using a shared medium (ie a hub not a switch) 1300 nodes could thoeretically pump out a gigabyte per second each into the network. This is a lot more than pretty much any application in use today needs (think even sending 60fps 1024x768 24 bit bitmaped graphics takes 135 megabytes per second). The real holy grail of interconnects is low latency, the fastest interconnects (such as Quadrics elan and Myricomm's myrinet) have latencies of about 5-9 microseconds. Your PCs RAM has a latency of 10 nanoseconds, thats a thousand times+ less. A large SMP machine will be between half a microsecond and 1 microsecond for a far memory access. If we could build an interconnect with say 50 nano second latency then network RAM becomes a reality, this would greatly benefit all kinds of applications, it would be possible to perform tasks using hundreds of terrabytes of RAM across thousands of nodes at speeds similar to those of local memory. Actually the quadrics elan already works in this way and allows you to effectivley map in far memory, but your limited to less than 2 gigabits per second and relativley high latency. Elan cards + switches also cost over $6k per node, so they're often more expensive than the machine's they're placed in. Plus the latency and bandwidth of it means application desginers have to minimise interconnect usage. 40 gigabit ethernet would make a wonderful interconnect *PROVIDING IT WAS LOW LATENCY*. One also has to wonder that if your network can do 10 terrabits per second, whats your clock speed got to be? gig ether causes a lot of problems with high cpuload due to the shear number of interrupts occuring. Even if you dont use interrupts a high speed network needs to get its data to memory, if your data comes in at even a terrabit you need the memory bandwidth to handle that, this would mean you'd need memory clock speed's in the ten's maybe hundreds of gigahertz. I somehow think its gonna be more like 2025 before 10 terrabit networks are feasible to connect to PCs. I maybe wrong, we'll see.....
Now we can all have one big lan party without bandwidth limitations. The internet will be like one giant lan. ;-)
Where will you find a Firewire cable long enough to reach the disk on the other side of the country? Studios already run into length limits with Firewire all the time, a multistory office building would be impossible to wire for Firewire everywhere. Plus Firewire networking equipment is basically non-existant, there are no failover, multipath, routed Firewire implementations because that's not what it's for, it's for a cheap multipurpose local connection. There are great uses for Firewire like Magik but it is definitly not the end all and be all of storage connections.
There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
10 gigabit Ethernet is called 10GBase-X, since 10000Base-X is too long. A few startups are betting that it's possible to create 10GBase-T, but few people believe them. Currently, 10 Gigabit Ethernet only runs over fiber and InfiniBand cables, so it's not backwards-compatible with slower speeds.
What economic incentives are there to improve last-mile bandwidth to WANs? Will such bandwidth always be woefully lacking?
100 Terabit Ethernet = RidiulousNet
1 Petabit Ethernet = LudicrousNet
10 Petabit Ethernet = PlaidNet
Well, there's spam egg sausage and spam, that's not got much spam in it.
Does this mean I can download porn faster?
_________ Help me get a PSP!
Enlarge your penis emails as it is.
Is there a version of PC Anywhere for X11?
...so we are way overdue for the next wave of hype about how thin clients will revolutionize the workplace, this time they really mean business, this is no joke and we're going to go the distance this time around!
The article mentions DWDM systems with 100 Gb/s per wavelength. That's bogus.
I am an optical engineer at a 40 Gb/s startup. The jump from 10 Gb/s to 40 Gb/s is huge. Many signal degradations (chromatic dispersion, polarization mode dispersion, nonlinearity,
Compensating for chromatic dispersion, PMD, et. al. requires optical components which DO NOT follow Moore's law. These components are handmade specialty devices.
While a business case can be made for 40 Gb/s, the jump to 100 Gb/s is commercially pointless. If you are building a DWDM system anyway, just spread the same data across more 10 Gb/s channels.
What the hell is "Directions", anyway? It sounds like sci-fi fluff meant to entice VC's.
> Lucent was selling their all-optical DWDM
> switches (Lambda Series) last year. The
> LambdaXtreme is a 40 Gbps DWDM unit that
> uses micro-mirrors (MEMS) for switching.
You must not have worked anywhere near either the LambdaRouter or
LambdaXtreme as your descriptions of the systems are entirely off base.
LambdaRouter is a MEMS-based "OOO" (!OEO) so-called photonic switch.
LambdaXtreme is a ultra long haul (ULH) class DWDM transmission system.
> They sold a pair of units...
> 8-10 of the units were sold to Korea...
And now it's really obvious you didn't even work in the same zipcode as these two products.
Awwww, but I want it now!!!
I love the smell of Karma in the morning
You must not have worked anywhere near either the LambdaRouter or
i cle.asp ?ID=80579 25.nsa.htm l
0 10117.nsa.html
LambdaXtreme as your descriptions of the systems are entirely off base.
LambdaRouter is a MEMS-based "OOO" (!OEO) so-called photonic switch.
LambdaXtreme is a ultra long haul (ULH) class DWDM transmission system.
> They sold a pair of units...
> 8-10 of the units were sold to Korea...
And now it's really obvious you didn't even work in the same zipcode as these two products.
Nice troll.
LambdaRouter was renamed to Wavestar OLS, my mistake. Same product base, different configs.
Korean sale:
http://www.convergedigest.com/DWDM/dwdmart
http://www.lucent.com.au/press/0901/010
Time-Warner:
http://www.lucent.com/press/0101/
1.6 Tbps isn't all that bad.
Learning HOW to think is more important than learning WHAT to think.
like, DVD-quality, streamed pr0n?
Here comes another solution looking for a problem! Let's all go back to ARCnet and Netware. It was fast enough, and guaranteed full employment for networking techs! Appletalk rocked too, but was far too easy to configure. How many people made 6 figures installing Appletalk?
AC's have an irrestible urge to point out idiot's tactics in the hopes that the greater idiots that the idiot is fooling will see the light, because the AC is jealous that the idiot got the idiots' recognition without actually exerting effort or helping the idiots instead of the AC getting the idiots' recognition, no matter how hard he has worked in the past.
This is proven by the fact that the AC is an AC. The AC does not wish to recieve a flamebait moderation with their account. I welcome your flamebait moderation. Mod points and 800 combo boxes on one screen slow my browser at work to a crawl, and I never bother anyway unless I see someone requesting moderation. I give people exactly what they request in that case.
I'm on lots of codiene. Don't wait to have your wisdom teeth pulled, kids, or you'll end up making insane posts like this one on slashdot when they become impacted!
"Verbing weirds language." -- Calvin
> LambdaRouter was renamed to Wavestar OLS, my mistake.
BZZZZZZZT! Thanks for playing. Keep digging ace. LambdaRouter, I'll repeat, is a MEMS-based OOO "cross connect". On the other hand, Wavestar OLS (aka 400G aka 1.6T) is a long haul (LH) DWDM transmission system. And yes, there are tons of Wavestar OLS 400G systems out in the field. Some even have more than 10 wavelengths lit. BTW, OLS=optical line system. The OLS (transmission only) systems have no "optical switching" functionality whatsoever.
The follow-on product to the LH Wavestar OLS 400G is the UltraLH LambdaXtreme, which sports 40Gb/s OT's and Raman pumps -- neither of which the OLS 400G product had.
It should by now be immediately obvious that:
a) LambdaRouter is a totally different product than Wavestar OLS
and
b) Wavestar OLS preceded LambdaRouter by several years
therefore your statement
"LambdaRouter was renamed to Wavestar OLS" is completely nonsensical.
To summaraize.
Transmission systems:
OLS 400G and 1.6T (10Gbps EDFA-based system)
LambdaXtreme (40Gbps Raman-based system)
Switching system:
LambdaRouter, again, a MEMS-based OOO switch (basically an automated optical patch panel).
The press releases you cite have to do with 400G OLS, not LambdaRouter nor LambdaXtreme.
I stand by my assertion that you didn't even work in the same zipcode as these two products. Thanks for the follow-up and proving my point.
I like faster too.
My thought is, has it really been "ethernet" all the times it is just an ethernet frame (ethernet_ii, 802.3, snap, whatever) without CSMA/CD, or do you need a half duplex shared net with collisions for "real" ethernet?
Maybe Cowboy Neal or Bob Metcalfe know...
50 Ohm
~8^]