New Ethernet Standard — Both 40 and 100 Gbps

Artemis recommends a blog entry that does a nice job of summarizing the history and current state of the Higher Speed Study Group and the IEEE's next-generation Ethernet standard. "When IEEE 802.3ba was originally proposed [there] were multiple possible speeds that were being discussed, including 40, 80, 100, and 120Gbps. While there options were eventually narrowed down to just two, 40 and 100Gbps, the HSSG had difficulties [deciding] on the one specific speed they wanted to become the new standard... [T]wo different groups formed, one which wanted faster server-to-switch connections at 40Gbps and one which wanted a more robust network backbone at 100Gbps... Unable to come up with a consensus the HSSG decided to standardize both 40Gbps and 100Gbps speeds..."

In other news

[superpulpsicle (533373)]

Major telcos has increased the upload speed to 800k at a cost for only $70.00 a month.

Re:

[by Anonymous Coward]

The Telco's know full and well that once they let the genie out of the bottle, there is no turning back. REAL* broadband service (10+Mb/s at minimum) across the entire US, i.e. DIAL-UP becomes infrastructurably(new word??) unmanageable and non-existent, means Cable TV and Satellite become unstable as a market. Period. The media companies know this, which is why HD mandates keep getting pushed back. Its an all out fight for who can get their fist in the cookie jar first.

Better get used to the idea that HIGHS

Re:In other news

[by Anonymous Coward]

"There is one hope though. And its name is Google......"

No. There is another.

Re:

[Poltras (680608)]

Luke Skywalker?

/out

Re:

[jd (1658)]

But [itnews.com.au] now [freerepublic.com] his [geek.com] provider [theregister.co.uk] is [bbc.co.uk] complete...

(Given that last link, expect the RIAA to become part of Homeland Security.)

The Japanese have gigabit with IPv6 to the home already, but this makes that look like dial-up in comparison.

Re:

[nuzak (959558)]

> There is one hope though. And its name is Google

Google's proposed free ad-supported wi-fi for SF is like 300 kilobits. Better than nothing, I'll grant, but the phone companies are pitching a screaming hissy fit over even that. Why on earth do you think Google can implement or is even interested in universal high-speed access?

Re:

[Ngarrang (1023425)]

Google's proposed free ad-supported wi-fi for SF is like 300 kilobits. Better than nothing, I'll grant, but the phone companies are pitching a screaming hissy fit over even that. Why on earth do you think Google can implement or is even interested in universal high-speed access?

Because it will make them more money?

Re:

[Detritus (11846)]

Not really. Broadband usually means FDM, like a cable plant or a microwave relay.

I like this definition:

Narrowband, Wideband, and Broadband

Narrowband is a transmission medium or channel with a single voice channel (with a carrier wave of a certain modulated frequency). Wideband is a transmission medium or channel that has a wider bandwidth than one voice channel (also with a carrier wave of a certain modulated frequency). Broadband refers to telecommunication that provides multiple channels of data over a single communications medium using frequency division multiplexing.

Through the Wires: Bandwidth [thinkquest.org]

Re:In other news, You are correct Broadband=2Mb/s+

[OldHawk777 (19923)]

You are correct Broadband=2Mb/s+, all other contrary comments are silly marketeer-spin for politicians and corporatist.
Also, the USA ranks 20+ in telecommunications (we ain't #1), because of corporatist marketeer-spin to silly politicians.

AAMOMFF, the USA ranks #1 in international debt only. We're #1, We're #1, We're #1 in debtor nations. THANK GOD and POLITICIANS!

!HAVEFUN!

Cable Length

[fishybell (516991)]

Interesting to see that the faster 100Gbps also has the longer cable lengths built into the standard. From TFA:

40Gbps can be 1 meter long on the backplane, 10 meters for copper cable and 100 meters for fiber-optics. The 100Gbps standard includes specifications for 10 kilometer and 40 kilometer connections over single-mode fiber.

I'm seeing the 100Gbps used for infrastructure with its larger bandwidth and longer cable length while the 40Gbps would be used for datacenters, server rooms, etc. with its faster "connect" speeds (clarification on what exactly this would mean?).

Re:

[rdejean (150504)]

The FA says that 40gbps is intended for server-to-switch connections. 100meters should be plenty for that. How often is your server 40 kilometers from the nearest switch?

I'd also suspect that 40gbps will be a whole lot cheaper than 100gbps.

Re:

[jd (1658)]

Given the way people wire this office? I'd want a network that supports at LEAST 40 kilometers, just to reach the server in the next room!

Re:

[anticypher (48312)]

Do I know you? Do we work in the same circus^Woffice?

If not, then my worst suspicions are confirmed, screwed up cabling plans exist everywhere.

the AC
my monomode fibre from home to datacentre is 38Kms, 100GigE will soon be mine

Re:Cable Length

[hackstraw (262471)]

How often is your server 40 kilometers from the nearest switch?

My mom's basement is HUGE!

Re:

[pacman on prozac (448607)]

Does current tech allow 100Gbps signals to travel 40km over singlemode without using some kind of repeater?

speed vs. robustness?

[volpe (58112)]

one which wanted faster server-to-switch connections at 40Gbps and one which wanted a more robust network backbone at 100Gbps

Why is the 40 Gbps one considered "faster" and the 100 Gbps one considered "more robust"?

Re:speed vs. robustness?

[ciroknight (601098)]

You misunderstand; one group said "We need to connect our servers to the switches with a faster connection." The other group said "we need to make our network backbone more robust by adding faster connections between buildings and such." The group that needed faster server-switch speeds don't need 100Gbps, they just need better than what they've got. The group that needed faster building-building/infrastructure links didn't believe 40Gbps is fast enough.

Adding both takes care of both groups of people.

Re:

[GeckoX (259575)]

That's where I'm confused on this though...adding ONE would appear to take care of both groups of people...what am I missing? What does the 40Gb standard have that the 100Gb standard doesn't cover?

If the answer is nothing, than this seems to be a pretty stupid move...

Re:speed vs. robustness?

[Midnight Thunder (17205)]

What does the 40Gb standard have that the 100Gb standard doesn't cover?

In one word: cost. The 100Gb connection is limited to fibre optics, whereas the slower connection support copper. Fibre optics are still more expensive than copper. It should also be noted that backbones deal with more traffic than non-backbone networks. Think of the difference between inter-city high ways and local back streets and you should get the picture.

Re:

[steveo777 (183629)]

Think of the difference between inter-city high ways and local back streets and you should get the picture.

So does that mean that their either coated in ice or being dug up by MN/Dot [state.mn.us]?

great analogy, just one request

[ImaLamer (260199)]

Would you mind coming to my office to explain a 'database' to the manager?

Then you can move onto normalization.

Thanks in advance.

Re:

[jabuzz (182671)]

That is just such complete nonsense. Firstly fibre is not "far" more expensive than copper, it is a bit more expensive. However look at the cost of a 10Gbps switch, and now tell me that the cost of fibre is prohibitive. If you can afford the switch you can sure as hell afford a few fibre patch leads. Not only that I bet it will be CX4 type Infiniband cables which are not cheap, and far more trouble in a rack than a fibre patch lead.

What beats me is why they are bothering with multimode fibre. The cost of st

Re:speed vs. robustness?

[Doctor Memory (6336)]

I wonder if it has something to do with latency. Maybe the 40Gb connections are faster because they have a simpler routing protocol or they use smaller packet sizes with no CRC. I haven't been able to get through to the actual proposed spec yet, so it's hard to say...

Ars Technica?

[conigs (866121)]

I'm normally not one to do this, but the article linked is nearly identical to the coverage over at Ars Technica [arstechnica.com]. It seems that only a few words were changed and without even a link to the original ars article.

Re:

[Red Flayer (890720)]

It's a press release. Check out ITwire.au, or do a google news search for HSSG. You'll see that the release went out 7/23, with almost everyone publishing on 7/24 [google.com]. This guy was just a day late (7/25).

Read all the gory details yourself

[evw (172810)]

If you want all the gory details rather than a copy of a summary of a summary, here is a link to all the presentations at the meeting.

http://www.ieee802.org/3/hssg/public/july07/index. html [ieee802.org]

Read through the minutes [ieee802.org] (warning PDF) to get a summary.

Motion #4: Move that the HSSG adopt the following objectives in replacement of
existing HSSG objectives:

o Support full-duplex operation only
o Preserve the 802.3 / Ethernet frame format utilizing the 802.3 MAC
o Preserve minimum and maximum FrameSize of current 802.3 standard
o Support a BER better than or equal to 10-12 at the MAC/PLS service interface
o Provide appropriate support for OTN
o Support a MAC data rate of 40 Gb/s
o Provide Physical Layer specifications which support 40 Gb/s operation over:
- at least 100m on OM3 MMF
- at least 10m over a copper cable assembly
- at least 1m over a backplane
o Support a MAC data rate of 100 Gb/s
o Provide Physical Layer specifications which support 100 Gb/s operation over:
- at least 40km on SMF
- at least 10km on SMF
- at least 100m on OM3 MMF
- at least 10m over a copper cable assembly

why ethernet?

[irw (204684)]

Exactly how far will ethernet efficiently scale? As I understand it there were problems with 1Gbp/s as first planned leading to jumbo frames, and ethernet isn't (wasn't) that efficient a protocol.

Are there any other serious contenders which could/should be examined as a replacement for ethernet?

Re:

[XSforMe (446716)]

Yep, Token Ring was indeed more efficient. Good luck reviving it.

Re:

[DFDumont (19326)]

>Yep, Token Ring was indeed more efficient. Good luck reviving it.

Token Ring (spitting) was only more efficient as compared to the original ethernet specification, with all of its collisions. Once we went to a switched architecture and reduced all conversations to two participants that advantage evaporated.

Remember this, being deterministically bad is still bad. Have you ever been on a ring with > 200 nodes? Don't.

Ethernet won because it was cheap. It beat token ring to switching. It beat everyth

Re:

[Intron (870560)]

fibre channel arbitrated loop was pretty much like token ring, and has been largely abandoned for the same reasons. Switched fabrics support multiple connections, and single misbehaving machines can't create havoc for everyone else on the loop.

Re:

[jabuzz (182671)]

Except most if not all fibre channel devices still support arbitrated loops. I have an arbitrated loop at 4Gbps at work hooking up a tape library to a server. I would have been nuts to buy a fibre channel switch for the job.

Re:

[hardburn (141468)]

The big problem with ethernet's design was its "spew everything to everyone" mentality. In practice, this was fixed by good switches becoming almost as cheap as hubs.

The main alternative to ethernet was token ring, which works much like a meeting where you have big stick that's passed around, and only the person with the stick can talk.

Re:

[On Lawn (1073)]

Good advice for a meeting. Speak softly and carry a big stick...

Re:

[silas_moeckel (234313)]

Ethernet is useful because it's cheap, I can attach a 10bt host to a switch and have it transmit the same frame over 100kbt with very little work. I have clients that love Ethernet it's orders of magnitude cheaper than it's main alternative Packet over Sonet. So pretty much it's good enough for most and cheap. In the PC server world the marketing guys want to say they have the latest and greatest copper Ethernet built in and supporting every old standard back to 10bt. This means they ask there chip supp

Re:

[gad_zuki! (70830)]

Probably for quite a bit. The biggest hurdle with ethernet is dealing with half-duplex connections and all the collions/detections. These new standards dont even do half-duplex. Everything is full duplex, thus requiring a switch. You've tossed out your biggest setback right there.

Ethernet still is pretty lean. I can imagine an alternative to it, but it might not be worth the trouble, like the anyLAN stuff from a while back. We also still used TCP, but really dont need all the overhead it generates.

Edit much?

[sakonofie (979872)]

When IEEE 802.3ba was originally proposed [there] were multiple possible speeds that were being discussed, including 40, 80, 100, and 120Gbps. While there options were eventually narrowed down to just two, 40 and 100Gbps, the HSSG had difficulties [deciding] on the one specific speed they wanted to become the new standard...

Slashdot editors and their homonyms have a wonderful relationship. There may be "there"s in the summary, but they're subject their edits.

excellent!

[hcdejong (561314)]

Why have one standard when you can have two instead! This strategy has worked so well in the past...

Re:

[jeffasselin (566598)]

If you'd read the information properly, you'd realize they're directed at different needs and cost. The 40Gbps can work over copper, but has limited range, whereas the 100Gbps is high-distance but fiber-only.

10 gig still not totally utilized...

[Odinson (4523)]

Assuming it's adopted, the 40gb standard may be the first Ethernet standard to have widespread fraud in the capabilities of hardware sold. Lots of hardware will be built that can't even come close to actually getting 40 gigabits advertised. Why? Many motherboards still can't utilize the full 10gbps even if the card can. The bad guys will catch on to this the second time around.

If you are the type to do the numbers and get a MB with sufficent bus speed. Buyer beware. The lack of speed may not be obv

Nothing new

[Wesley Felter (138342)]

When 10Mb Ethernet came out there was widespread debate about its performance, because computers weren't fast enough to saturate it. It was probably the same for 100Mb, and I know the early 1Gb NICs could only handle ~700Mb.

Re:

[Linkiroth (952123)]

High Speeds Standards Group. How hard is it to read the summary? Slashdot: where people don't only RTFA, they don't RTFS.

Re:'HSSG'?

[fbjon (692006)]

You must be... no, you're definitely new here.

Re:'HSSG'?

[TechyImmigrant (175943)]

>High Speeds Standards Group. How hard is it to read the summary? Slashdot: where people don't only RTFA, they don't RTFS.

No. It's High Speed Study Group. In IEEE 802 this makes a huge difference.

A study group studies and recommends what standards are to be written by a Working Group (in this case, the WG is 802.3). They do this by arguing for a while then drafting a scope and purpose for the new spec (you'll find this in the first few pages of each IEEE spec). This is sent up the hierachy (the IEEE 802 EC (executive committee) and IEEE SA NESCOM (IEEE Standards Association New Standards Committee)The Working Group then goes off and writes the spec if the EC and NESCOM approve the PAR (Project Authorization Request).

So the HSSG is not a standards writing group at all, it is a bit of pre work to decide what work is going to be done. Arguing over link speeds is exactly the sort of arguing it is chartered to do.

Re:

[DaMattster (977781)]

Well, if you think about it, Beowulf and similar Linux clusters take advantage of network speed to distribute processing load. This isn't really a case where the network does the computing but with 40 GBs of bandwith, you can perform some serious parallel processing.

Re:

[brsmith4 (567390)]

With the 12x QDR InfiniBand spec, 96Gb (after factoring the protocol's overhead) is already on the table and at much lower latencies. This is more helpful for parallel applications (though it really depends on the properties of your application). I've not even worked with 12x nor any applications that would benefit from it. We currently run a 4x SDR setup (which will soon be upgraded to DDR) and it is ample for most of our needs. A cheap 40Gb ethernet solution would be killer for consolidating node mana

Re:

[gad_zuki! (70830)]

You can think of it this way:

If CPUs are so fast that pushing the data to be executed elsewhere over a LAN is a performance hit then parallel processing will go out of style.

If networks are so fast that pushing data to be executed elsewhere over a LAN is a net perofrmance gain then parallel processing is back in style.

Right now, we're seeing some pretty damn fast CPUs with multiple cores. Once these gains show down and network gains increase you'll see parallel stuff everywhere again.

Re:

[by Anonymous Coward]

There is already precedent for this at 10G. The LAN people wanted the data rate to be 10.0 Gbps so that it was exactly 10x 1G while the WAN people wanted something compatible with SONET OC-192 wide area transport gear (9.95328 Gbps including framing bits). So they adopted both. They're not compatible at the physical layer so you'd never plug one into another. However they use compatible layer 2 formats so it's easy to switch packets from one to another.

Re:

[gregarican (694358)]

Actually 20,000,000 posts. Of course in honor of the fencepost effect I wonder if t he first post was #0?

Re:

[Martin Blank (154261)]

Those of us in security are dreading this. IDS/IPS companies are only now dealing efficiently with multi-gigabit solutions for a reasonable price, and no one that I have talked to will do line-speed 10Gbs processing (some boxes can use parallel processing to handle streams from multiple inputs going up to 10Gbps, but not from a single line through a single processor to ensure that attack streams are properly reviewed). I shudder to think of what a 40Gbps stream will be like to monitor.

Re:

[TooMuchToDo (882796)]

40Gbps is from server or desktop to the switch chief. Try doing IDS/IPS on a 100Gbps link.

I'll be able to cook eggs on my Snort box.