Beta

Slashdot: News for Nerds

×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

New Ethernet Standard — Both 40 and 100 Gbps

kdawson posted more than 6 years ago | from the keeping-everybody-or-nobody-happy dept.

Networking 141

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..."

cancel ×

141 comments

Uhhmm (-1, Offtopic)

Dr. Smoove (1099425) | more than 6 years ago | (#19998613)

In Soviet Russia, Will Linux run this? uh.. uhmm alright I failed.

Re:Uhhmm (-1, Offtopic)

Yetihehe (971185) | more than 6 years ago | (#19998681)

In Soviet Russia YOU fail?

In other news (4, Funny)

superpulpsicle (533373) | more than 6 years ago | (#19998633)

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

Re:In other news (2, Insightful)

Anonymous Coward | more than 6 years ago | (#19998915)

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 HIGHSPEED* Internet EVERYWHERE, is still years away. There is one hope though. And its name is Google......

Re:In other news (5, Funny)

Anonymous Coward | more than 6 years ago | (#19999069)

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

No. There is another.

Re:In other news (1)

Poltras (680608) | more than 6 years ago | (#19999345)

Luke Skywalker?

/out

Re:In other news (1)

jd (1658) | more than 6 years ago | (#20000919)

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:In other news (1)

nuzak (959558) | more than 6 years ago | (#19999213)

> 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:In other news (1)

Ngarrang (1023425) | more than 6 years ago | (#19999781)

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:In other news (1)

morcego (260031) | more than 6 years ago | (#20002013)

REAL* broadband service (10+Mb/s at minimum)


Isn't broadband defined as 2Mbps+ ? From what I've heard in my telco days, that was the speed threshold.

THIS IS TRULY OUTRAGEOUS!!! (-1, Troll)

Anonymous Coward | more than 6 years ago | (#19999349)

Companies don't have to pay for their costs and overhead, nor are they expected to make any profit? Simply outrageous.

You are made of fail.

Cable Length (4, Interesting)

fishybell (516991) | more than 6 years ago | (#19998729)

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:Cable Length (3, Informative)

rdejean (150504) | more than 6 years ago | (#19999083)

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:Cable Length (2, Funny)

jd (1658) | more than 6 years ago | (#20000807)

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:Cable Length (1)

anticypher (48312) | more than 6 years ago | (#20001019)

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 (4, Funny)

hackstraw (262471) | more than 6 years ago | (#20002257)

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

My mom's basement is HUGE!

Re:Cable Length (1)

pacman on prozac (448607) | more than 6 years ago | (#20001005)

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

speed vs. robustness? (1)

volpe (58112) | more than 6 years ago | (#19998741)

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? (4, Informative)

ciroknight (601098) | more than 6 years ago | (#19998817)

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:speed vs. robustness? (1)

GeckoX (259575) | more than 6 years ago | (#19998995)

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? (1, Informative)

Anonymous Coward | more than 6 years ago | (#19999065)

Looks like the 40 allows for fiber or copper connections, while the 100 is pretty much fiber-only (for now?). Fiber is still far more expensive than copper, especially when you're just interconnecting two switches that are next to one another in the rack.

Re:speed vs. robustness? (1)

jabuzz (182671) | more than 6 years ago | (#20001439)

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 stocking both types quickly outweighs the slight increase in cost for single mode.

Re:speed vs. robustness? (1)

psmears (629712) | more than 6 years ago | (#20003249)

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.
I'd be surprised if they did that—the biggest advantage of copper over fibre is that everyone still has it! If you're going to move to Infiniband (multi-coax) cables, you might as well go for fibre as you say...—

What beats me is why they are bothering with multimode fibre. The cost of stocking both types quickly outweighs the slight increase in cost for single mode.
There are plenty of places where it's practical and economical just stocking multimode fibre...

Re:speed vs. robustness? (5, Informative)

Midnight Thunder (17205) | more than 6 years ago | (#19999073)

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:speed vs. robustness? (2, Funny)

steveo777 (183629) | more than 6 years ago | (#20000857)

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 (1)

ImaLamer (260199) | more than 6 years ago | (#20001341)

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

Then you can move onto normalization.

Thanks in advance.

Re:speed vs. robustness? (1, Informative)

Anonymous Coward | more than 6 years ago | (#20001919)

Let me clarify this even more. The 40Gb standard is aimed at LANs. The 100Gb standard is aimed at WANs / the Internet backbone. One is a method well suited to connecting machines in one room or a building to each other, the other is a way to connect cities. This is actually a very remarkable new role for "ethernet" standards, since most backbone trunk lines use special protocols today.

Make sense?

Re:speed vs. robustness? (1)

GeckoX (259575) | more than 6 years ago | (#20002205)

Yes actually, thanks :)

Re:speed vs. robustness? (3, Interesting)

Doctor Memory (6336) | more than 6 years ago | (#19999043)

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...

'HSSG'? (0)

Anonymous Coward | more than 6 years ago | (#19998745)

HSSG decided to standardize both 40Gbps and 100Gbps speeds...

'HSSG'? Is that some weird acronym for 'market'?

Re:'HSSG'? (2, Insightful)

Linkiroth (952123) | more than 6 years ago | (#19998841)

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'? (3, Funny)

fbjon (692006) | more than 6 years ago | (#19999157)

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

Re:'HSSG'? (4, Informative)

TechyImmigrant (175943) | more than 6 years ago | (#19999173)

>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:'HSSG'? (0)

Anonymous Coward | more than 6 years ago | (#19999237)

Except it is actually the Higher Speed Study Group not the High Speeds Standard Group. How do I know this? I read the summary.

Ars Technica? (5, Interesting)

conigs (866121) | more than 6 years ago | (#19998747)

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.

MOD PARENT UP! (0, Offtopic)

Anonymous Coward | more than 6 years ago | (#19998837)

Mod parent up!

Re:Ars Technica? (1, Insightful)

Anonymous Coward | more than 6 years ago | (#19998877)

More likely is that they both cribbed the same press release.

Re:Ars Technica? (2, Informative)

Red Flayer (890720) | more than 6 years ago | (#19998999)

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 (5, Informative)

evw (172810) | more than 6 years ago | (#19999011)

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

Apple is coming up it seems (0)

Anonymous Coward | more than 6 years ago | (#19999837)

I for one am glad that for once they're thinking about MACs while designing standards, and not only PCs.

Hardy-har-har

Standards (1, Offtopic)

edittard (805475) | more than 6 years ago | (#19998783)

The great thing about standards is ther's so many to choose from.

Re:Standards (1)

andrewd18 (989408) | more than 6 years ago | (#19999393)

The great thing about standards is ther's so many to choose from.
Unfortunately, not everyone chooses to follow them.

Re:Standards (0)

Anonymous Coward | more than 6 years ago | (#19999697)

You got me ther!

Is this standard by committee just newspeak? (0)

Anonymous Coward | more than 6 years ago | (#19998853)

Will these two standards interoperate compatibly? Or will I have to pay great attention to which interfaces I am purchasing and deploying? If not, it could hardly be considered a standard in the "standard" sense. Is this just a committee that couldn't come to agreement so they just "declared" a non-standard as a standard?

Re:Is this standard by committee just newspeak? (2, Informative)

Anonymous Coward | more than 6 years ago | (#19999163)

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.

why ethernet? (1)

irw (204684) | more than 6 years ago | (#19998855)

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:why ethernet? (1)

XSforMe (446716) | more than 6 years ago | (#19998919)

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

Re:why ethernet? (3, Insightful)

DFDumont (19326) | more than 6 years ago | (#19999215)

>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 everything else to get to 100Mbps. Now with 1Gbps and 10Gbps firmly entrenched in the market I look forward to deploying 100Gbps links.

Ethernet is (and was) better.

Dennis Dumont
P.S. I've already scavenged all of my lobe cables for their copper.

Re:why ethernet? (1)

Nynaeve (163450) | more than 6 years ago | (#20003439)

Ethernet ... beat everything else to get to 100Mbps.

Are you forgetting FDDI/CDDI [cisco.com] ? As I recall, it was available before 100 Mbps Ethernet.

"The Fiber Distributed Data Interface (FDDI) specifies a 100-Mbps token-passing, dual-ring LAN using fiber-optic cable."

"Copper Distributed Data Interface (CDDI) is the implementation of FDDI protocols over twisted-pair copper wire."

Re:why ethernet? (1)

Intron (870560) | more than 6 years ago | (#19999239)

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:why ethernet? (1)

jabuzz (182671) | more than 6 years ago | (#20001479)

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:why ethernet? (1)

Intron (870560) | more than 6 years ago | (#20002419)

If you only have two connections, you can do point-to-point, there is no need to run the arbitrated loop protocol.

Re:why ethernet? (2, Informative)

hardburn (141468) | more than 6 years ago | (#19998991)

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:why ethernet? (1)

On Lawn (1073) | more than 6 years ago | (#19999409)


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

Re:why ethernet? (2, Insightful)

silas_moeckel (234313) | more than 6 years ago | (#19999959)

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 suppliers to build it and make it cheap. Scale and cutting every corner possible drive down the costs so that it's a couple bucks to add multiple ports of 1000bt today and 10kbt is getting cheaper and cheaper.

Re:why ethernet? (1)

sharkey (16670) | more than 6 years ago | (#20000289)

As I understand it there were problems with 1Gbp/s as first planned leading to jumbo frames

So we'll move on to Hyper and Monster frames as the tech speeds up. Going along with those will be Mini-Hyper and Mini-Monster frames, of course.

Re:why ethernet? (2, Insightful)

gad_zuki! (70830) | more than 6 years ago | (#20001343)

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.

Re:why ethernet? Why not LocalTalk? (1)

xquercus (801916) | more than 6 years ago | (#20001897)

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?

Perhaps we should look toward a high speed LocalTalk or PhoneNet implementation?

Two For One (0, Offtopic)

shutupkevin (1127139) | more than 6 years ago | (#19998861)

In other news... A major open source project could not decide between GPLv2 and GPLv3 today, so they dual licensed it!


And then the world exploded.

Looks like (1, Funny)

iminplaya (723125) | more than 6 years ago | (#19998873)

the network will soon be faster than the computer. Any chance we can syphon off of this speed to do some computing? Make the network become the computer?

Re:Looks like (2, Insightful)

DaMattster (977781) | more than 6 years ago | (#19998927)

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:Looks like (2, Insightful)

brsmith4 (567390) | more than 6 years ago | (#20000105)

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 management and a storage pathway onto one network. Our current storage solution over 10Gb leaves us with a 25:1 oversubscription ratio which will work quite well for our current crop of applications and how they are used, but it could become a bottleneck in the future.

I think having 40Gb will be really nice once pNFS implementations start to take off. Imagine a pNFS cluster of 32 fully loaded x4500's with 40Gb links between hosts and a 100Gb copper uplink to feed an army processing nodes. Getting close to 1PB of really really fast storage... over NFS and with today's capacities, no less.

Re:Looks like (1)

iminplaya (723125) | more than 6 years ago | (#20000323)

...you can perform some serious parallel processing.

You know, I wish people would make up their mind on these things. First we are being told that parallel is faster, then it's serial. Using hard drive interfacing here. What's it gonna be? Are we going to be told ten years from now the inline serial processing is faster? This is like these "nutritionists" telling us that eggs are bad for you and margarine is good. Later they come out with just the opposite. I guess I'll just keep what I have until it runs out of smoke and then buy whatever is out there. Well, okay, dumpster dive for whatever is in there.

But anyway, your point is well taken, it's like using RAID to move data faster in and out of a set of hard drives. I can hardly wait for the same speeds to come out of my service provider :-)

Re:Looks like (1)

CETS (573881) | more than 6 years ago | (#20002633)

Whooooosh.

Re:Looks like (1)

gad_zuki! (70830) | more than 6 years ago | (#20001477)

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.

nice increase (2, Interesting)

poetmatt (793785) | more than 6 years ago | (#19999029)

Considering that this stuff was doing 10 GB in 2005, to see 100 in 2007 is a pretty nice upgrade...my question is, given that the speeds are increasing, will we see any of this as consumers in the US? Not a "providers suck" (which we already know), but more of a "will this potentially make connections cheaper"?

Re:nice increase (2, Interesting)

Martin Blank (154261) | more than 6 years ago | (#20000423)

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.

Thank you for the answer, lots more questions (1)

poetmatt (793785) | more than 6 years ago | (#20000725)

I am not trying to rationalize this but as computing power increases doesn't the capability to handle a larger data stream become realistic or no? I'm looking it this from a fairly simple perspective.

Also isn't someone already having to handle such streams? Don't tier 1 networks have to be able to handle far more than such things already? What about the likes of Google or MSFT perhaps? (not that it means that it's viable for the rest of the world). In another thread with similar questions(but not the ones I pose here) [slashdot.org] I mentioned a similar idea and people expressed that it is not difficult to handle large amounts of traffic, the idea seems circular once again.

Can you give me a general idea of how much bandwith a computer could handle and/or what type of computer? Being someone who has never worked in such security I have no quantifiable idea of how much processing is needed. Would this be like a dual 8core pc with 16gigs of ram can handle 1/2 a GB of continual data? Would this be essentially a server with a built in switch?

In addition, if there was sufficiently high amounts of bandwith for everyone, would you have to monitor anything other than variants of DDOS or other distributed attacks that use multiple pcs? If everyone on the planet had a 1 or 2GB/S down and upstream connection (think perhaps 10,20,30 years down the road I have no idea how long really), would it matter what else slows down the internet connection on their PC's?

Re:nice increase (1)

TooMuchToDo (882796) | more than 6 years ago | (#20000773)

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.

Re:nice increase (1)

Kadin2048 (468275) | more than 6 years ago | (#20001709)

I think the problem with connections in the U.S. is mostly related to problems with the last mile, or the "last few miles" (the backhaul from the local node to the C.O.).

I suppose that this might make the node-to-CO link faster/cheaper, which would be good because it would raise the amount of actual capacity that the ISPs have to oversell, meaning that when everyone else in your neighborhood is trying to get online and play WoW, there's still some bandwidth left ... but in terms of actually making your internet connection dramatically faster? I don't really think so.

What's holding back domestic broadband right now is less technological than economic problems. The ISPs know they can get away with taking a 256kb/s connection and sell it as a "6 megabit!!!111" pipe, and I don't see why they'd change that, particularly when there's basically no competition to speak of.

Edit much? (3, Funny)

sakonofie (979872) | more than 6 years ago | (#19999137)

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.

Re:Edit much? (1)

rackirlen (749169) | more than 6 years ago | (#19999815)

I misspeak and write these words all the time, all the while understanding their proper meanings, but nonetheless... say what?

OT: Close to 2,000,000 posts! (1)

JJRRutgers (595466) | more than 6 years ago | (#19999169)

Who will be the lucky slashdotter?

Re:OT: Close to 2,000,000 posts! (1)

gregarican (694358) | more than 6 years ago | (#19999685)

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

Re:OT: Close to 2,000,000 posts! (0)

Anonymous Coward | more than 6 years ago | (#20000945)

All the posts are odd numbered, so the actual post count is lower.

Re:OT: Close to 2,000,000 posts! (1)

Ant P. (974313) | more than 6 years ago | (#20002471)

Not true, I saw post 15000000 happen. Or was it 10 million...

Re:OT: Close to 2,000,000 posts! (0)

Anonymous Coward | more than 6 years ago | (#19999883)

Moooo!!!

Re:OT: Close to 2,000,000 posts! (0)

Anonymous Coward | more than 6 years ago | (#20000483)

FailGET !!!

OT: cid=20000000 (1)

Kadin2048 (468275) | more than 6 years ago | (#20001315)

It didn't happen in this thread, apparently.

Watch: 40 in USA, World: 100 (0, Troll)

Ralph Spoilsport (673134) | more than 6 years ago | (#19999175)

Watch the captains of American Industry opt for the 40 for the public because "it's easier and cheaper" while the rest of the planet and big business goes to 100.

I'm just sayin'....

RS

Re:Watch: 40 in USA, World: 100 (0, Troll)

Gothmolly (148874) | more than 6 years ago | (#19999989)

-1, Troll.

Re:Watch: 40 in USA, World: 100 (1)

Gadgit (1067790) | more than 6 years ago | (#20000415)

Granted it seems like the US is often time far behind the world in most things, but speaking from experience there are quite a few TelCo's throughout the country that are currently, or soon upgrading to, using 10Gbps links within their core. Every mention of these speed increases always seems to make people think that they will have 40Gbps to their household. The purpose of these technologies is almost always to provide transport for a bunch of other traffic MUXed onto it whether it be DS3s, OCns, etc... That coupled with DWDM technology which already allows providers to send up to 80 'channels' of 10Gbps each of a single pair of fiber...it's hard to imagine ever needing that much bandwidth...

Re:Watch: 40 in USA, World: 100 (0)

Anonymous Coward | more than 6 years ago | (#20000421)

umm. you must not understand the diff between where 40 is to be used and where 100 is to be used. you fail!!

Re:Watch: 40 in USA, World: 100 (0)

Anonymous Coward | more than 6 years ago | (#20000555)

Hahaha, you're wrong! Teh rest of the world is gonna crank it all the way up to 110, baby!

I for one... (0)

Anonymous Coward | more than 6 years ago | (#19999669)

welcome our New Ethernet Standard overlords

Can you imagine... (1)

CautionaryX (1061226) | more than 6 years ago | (#20001281)

... making a Beowulf cluster with these?

(I'm sorry... I just had to!)

excellent! (2, Funny)

hcdejong (561314) | more than 6 years ago | (#19999777)

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

Re:excellent! (1)

jeffasselin (566598) | more than 6 years ago | (#20000417)

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.

Exactly! (0)

Anonymous Coward | more than 6 years ago | (#20001831)

You're point so perceptive! That is exactly why 10/100 MPS ethernet cards were such a failure!

netwurking iz ghey (1)

kayditty (641006) | more than 6 years ago | (#20000007)

lol.

10 gig still not totally utilized... (1)

Odinson (4523) | more than 6 years ago | (#20000571)

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 obvious without an order of magnitude jump.

Nothing new (2, Informative)

Wesley Felter (138342) | more than 6 years ago | (#20001295)

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:Nothing new (0)

Anonymous Coward | more than 6 years ago | (#20002783)

Yep. I put a 3C501 card into a machine (3com's first ethernet card -- 8-bit ISA.. the driver says "don't install this even as a joke. The performance is horrible and it's broken in many ways), -- this card would max out at 150KB/sec (that is, about 1.2mbit).

          The cheapest of the old 100mbit cards were like a cranked up NE2000 clone, and would from what I've heard max at about 70mbits/sec.

          Gigabit? That's 125MB/sec more or less; PCI maxes at 133MB/sec (well, 32-bit 33mhz) so I'm sure there were plenty of cheapo gigabit setups that wouldn't reach max speed (given overhead, it'd be hard to get a real 125MB/sec if 133 is theoretical peak.)

          10gigabit and up, I'm sure many cards either can't or won't max out the link.

Stevens (1)

Kryptonian Jor-El (970056) | more than 6 years ago | (#20000781)

This should take care of the "Enormous amounts of material" the great Ted Stevens warned us about.

I want one for my home! (1)

cyberjock1980 (1131059) | more than 6 years ago | (#20001293)

So they couldn't come to a resolution on who to make happy, so they decided to make both people happy. If only Microsoft offered 2 versions, 1 for those hardcore performance nazi's(myself included) that has no extras, just the OS and that's all, or a slow performance sapping, DRM loaded, 'feature' full version! Microsoft should take notes from these guys. So 40 Gbps or 100 Gpbs? I'll settle for just the 40Gbps internet connection for now.

c"ock (-1, Redundant)

Anonymous Coward | more than 6 years ago | (#20003151)

share. *BSD is a losing battle; impaired its USERS OF BSD/OS. A PEOPLE PLAYING CAN and building is Is not prone to New faces and many about outside confirmed that *BSD Charnel house. DISEASES. THE developers. The Fear the reaper And what supplies sUpplies to private clearly become unpleasant ~280MB MPEG off of and other party superior to slow, states that there [slashdot.org], cuntwipes Jordan are a pathetic I don't want to can really ask of handy, you Are free Minutes. At home, Serves to reinforce Working on various legitimise doing before playing to Usenet is roughly
Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Create a Slashdot Account

Loading...