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
...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.
who cares?
;)
How about those interested in clustering and not interested in paying for expensive solutions (that now exist because of high latency in ethernet)?
How about those that are interested in having a network other than their home network where 100 or 1000Mb is just not enough?
The home market isn't the ONLY market available for networking you know. Especially with FL thinking about taxing it
The article is already slashdotted so I can't read it.
/. effect still exist? Is it the server that becomes the sole limiting factor?
At those speeds, does the
-B
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...
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.
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.
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?
100 ms latency would affect a 10Mbps network and a 10 Tbps network almost equally if a clustered application is using very small packets to communicate. Only if the application is using very large packets, the bandwidth will overcome the latency. At small packet sizes the latency will largely overshadow the bandwidth. And considering that a lot of scientific applications use small payloads, latency is very important. If ethernet wants acceptance in the High-Performance-Computing-Clusters world, something has to be done about the latency.
Now take the same server, and instead of transfering a 1GB file, send a 4k message for a DSM page update, or a filesystem locking operation (4k is generous). Which network is effectively faster then? Transferring large files is far from the only use of networks. Latency *is* important, and ethernet latencies have not gotten the exponential speed boosts that the bandwidth has.
Clustering and LAN file servers are two common uses for networks that won't benifit much by increasing bandwidth beyond 2gbps compared to how much they would benefit from lower latencies.
Ever dream you could fly? Get up from the Flight Sim. I Fly
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.
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.
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
In 1995 there was a call for 100BT links trust me I was there were were doing it earlier than that. In 2002 GigE over copper was there and my persoanly first installation of GigE to the desktop was 1998. So far the PC could arguably handle them GigE pushed the PCI bus to breaking and 10GigE will do the same for PCI-X for a few years to come. Now granted I wholeheartedly agree that untill a lot of issues are worked out you wont be seeing fiber the the normal desktop.
As an asside I think the funniest part of current desktop GigE is the switches support full speed but I know of only one card that can get even close to those speeds.
No sir I dont like it.
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.