Slashdot Mirror
ARPANet Co-Founder Predicts An Internet Crisis
The Insultant writes "Dr. Larry Roberts, co-founder of the ARPANET and inventor of packet switching, predicts the Internet is headed for a major crisis in an article published on the Internet Evolution web site today. Internet traffic is now growing much more quickly than the rate at which router cost is decreasing, Roberts says. At current growth levels, the cost of deploying Internet capacity to handle new services like social networking, gaming, video, VOIP, and digital entertainment will double every three years, he predicts, creating an economic crisis. Of course, Roberts has an agenda. He's now CEO of Anagran Inc., which makes a technology called flow-based routing that, Roberts claims, will solve all of the world's routing problems in one go."
Kwisatz Haderach
Sell the spice to CHOAM
This Mahdi took Shaddam's Throne
Man with Solution says the is a Problem.
Yeah, not buyin it. A similar thing happened with electricity, when everyone bought TVs everyone bought computers etc. suddenly of course power usage sky rocketed, and lots of people said, well this is going to be the rate of growth now. Of course, with that, as it is with this, everyone go their TVs and then the demand levelled out, with this, everyone will start downloading videos, and the bandwith usage will level out. Yes, soon we'll need some new routers, but the problem isn't permanent, and it isn't something that we should trust a salesman to deal with.
Robert Metcalfe predicted this in 1995. He literally ate his words (a printed InfoWorld article mixed with liquid in a blender) in front of an audience in 1997.
Windows 3.1x calc: 3.11 - 3.10 = 0.00
Create a problem. Solve that problem. Uniquely own that solution in the market. Make everyone need what you have to offer.
Of course, the first step is that these guys need to really convince everyone that the internet is about to implode and that the companies who need the enormous bandwidth and services simply can't or won't make the hardware investment that is necessary.
The real threat to the internet are the legislators and lobbyists who want to nerf the internet so that the only use for it is the commercial enterprises and everything should be nerfed down to a Disney-fied toddler's level. That's an actual legitimate threat.
However, maybe he should peddle the "piracy and torrents are killing the internet and I can save you!" angle. Might work.
Someone submits a slashvertisement, acknowledges it in the summary, and it still gets put on the front page. Brilliant! Also, routing will be just fine. F-U-D.
1. Run around screaming that the sky is falling
2. Develop and market a product that fixes the sky
3. ?
4. Profit!
He must have read Chicken Little.
What happened to all that talk of "dark fiber"? /.) wanting to fiddle with packets instead of simply routing them?
And how much of the routing problems stem from backbone ISPs (Comcast, Verizon, etc.; see recent
Can we get a "-1 Wrong" moderation option?
When the ice caps melt, the tubes will get clogged with dead polar bears.
See "On Distributed Communications", published in 1964.
If the cost increases, they will invest the money and upgrade the network. What is the problem? When MSFT thinks Facebook is worth 15 billion dollars, routers are chump change for them. What is the crisis here? Cost of something is going to go up? Big deal. Oil prices are shooting up. College tuition costs are shooting up. Y ! routing costs?
sed -e 's/Chuck Norris/Rajnikant/g' joke > fact
People have been claiming "new technology $foo is going to overwhelm the Internet!" for ages. Yet somehow the Internet keeps up. I'm not worried - especially since this guy just so happens to be offering to sell us a solution.
So, how does one get inoculated with your special seed?
If you want news from today, you have to come back tomorrow.
There's no explicit circuit setup or teardown: the flows are detected by the router rather than being established by the endpoints.
If it's too expensive to deploy the services, then perhaps people will do without the services?
The traffic will only increase dramatically if people continue to use the services that demand the traffic, and pay for the bandwidth they need to do it.
--- JurassicPizza
It's not a watermelon seed is it? I hear if you swallow those, they grow into a watermelon in your stomach. Then maybe you'd forget about that pesky disease and worry more about your serious melon-based intestinal backup problem.
Leave my internet protocols ALONE thank you very much.
We will do quite OK without you meddling with our open standards.
We only need linux, an open TCP stack, and anything that happens I am sure we can handle it with JUST those tools.
Well, that and an army of a million penguin volunteers.
We will do fine, really.
Please peddle your proprietary CRAP OLA somewhere else.
Thank you.
-Hack
Got Geometrodynamics? Awe, too hard to figure out? Too bad.
I wonder if everyone on Krypton walked around saying, "That Jor-El! Trying to sell us a rocket to escape an 'impending planetary disaster' to some backwater planet where we'll all have 'superpowers'. Yeah right. What a loser."
Zonk you fucking moron. You already posted this earlier this month right here. Different website, but same guy and same company, of course. Same message, same bullshit!
You have officially crossed into the JonKatz zone. Not only do you post duplicates, but you post slanted slashvertisment duplicates! Your articles are worthless.
It's too bad all I can do is ignore you, but it's about time I finally did. I recommend everyone else do the same, so we can finally hit home that bullshit editors will not be tolerated.
"All great wisdom is contained in .signature files"
From the looks of Anagran's description of their 'flow' based routing, routers analyze individual TCP flows very closely and rate them according to behavior in order to predict future needs of each flow, and then make adjustments on the fly by various means (closely timed discard of TCP segments to force endpoint TCP adjustments, QOS-like throttling of flows that look like they may be coming from slow endpoints, etc.)
All of this looks to be enhancements and accelerations to QOS. It could be really cool, or highly evil as well, since these boxes would be perfect for retarding P2P traffic without actually blocking it on backbone links. It looks to be the same "steal from peter to feed paul" way of dealing with bandwidth congestion without investing in network infrastructure.
Getting telecoms away from corporate welfare and into genuine market competition will go much farther to address bandwidth problems.
"We are all geniuses when we dream"
- E.M. Cioran
What's the difference between this flow routing and circuit switching?
Flow-based routing attempts to identify flows of packets - TCP connections, related streams of UDP packets, etc. - and cache information about them. Then when future packets of the flow arrive and are successfully identified they can be handled using the cached information, rather than performing a full lookup of routing, QoS labeling, permission checking, etc.
It may also attempt to identify more things about it - such as what kind of traffic it is. Then it can do other things: Identify what quality of service it requires. For instance:
Streams such as VoIP and broadcast audio and video need low latencey and jitter (variability of transit time), but packets that are already delayed too much should be discarded, and the bandwidth SHOULD be limited. Meanwhile file transfers prefer delaying the packets to losing them but they're happy to take all the bandwidth left over from more critical stuff. So streams may go to the front of the line if they're timely but the trashcan if they're already delayed or there are too many of them than there should be.
Once a flow has been identified the knowledge can also be used to do other things with it: Find a better route that it has rights to use, give it preference if the customer's contract guarantees delivery (i.e. "you get 4 VoIP lines worth of bandwidth with high quality of service before your VoIP packets start getting best-effort handling".), perform "deep content inspection" (such as running email through a spam filter as a service), etc.
Circuit switching explicitly reserves resources through the network switches at the start of a session ("setup") and releases them at the end ("teardown"). Flow-based routing attempts to identify the flows of sessions on-the-fly, to speed routing decisions and be "smarter" about the flow - sometimes to the point of being able to emulate circuit-switched quality of service. But it doesn't REQUIRE setup/teardown and end-to-end cooperation to get things to happen. Instead, anything it can't identify goes through in the old way, with the router thinking about each packet of a flow from scratch, just as if the flow-related features didn't exist.
And Anagram is far from the only company working on it. B-) It's a major industry buzzword, on its way to becoming a (set of) required check-boxes for getting networking companies to buy your boxes.
Bantam Dominique roosters crow a four-note song. Once you've heard it as "Happy BIRTHday" you can't NOT hear it that way
You and your knowledge of "economics" can go! We're predicting disaster here!
People have been predicting that we'd run out of item X by time Y for hundreds of years. The reason we don't is because (as you said) when supply dwindles, there is incentive to find news supplies and substitutes.
During WWII, it was thought that we'd completely run out of rubber, and this would kill our war effort, due to lack of tires, hoses, gaskets, etc. Along comes synthetic rubber, and magically we don't run out. These days most rubber is synthetic.
This stuff happens all the time. When oil becomes expensive enough, alternative fuel use will become so desirable that an efficient solution will present itself. Hell, that's why we switched to cars in the first place, because our previous transportation (horses) produced untold...uhh..."pollution". A little Co2 seemed like heaven compared to mountains of horse crap, and it didn't take long before cars needed less maintenance than horses.
There was a time, however, when the car was a choice only the rich could afford, one less reliable and less efficient than a good horse. Economics rarely gets the solution ahead of the problem, which is why it's an uphill battle to force people to switch to alternatives when the alternatives aren't as efficient as what they're already using.
The biggest issue right now is that the government is mucking with the damn problem by subsidizing industries to artificially make petroleum/cars seem more efficient than they actually are. For a bunch of "free market economists" they sure love to give away money to un-free the market. They're also dropping the ball by shouldering the pollution costs created by the fossil fuel industry, instead of passing it back to the industry in the form of taxes and fees. Take away the subsidies and fairly apply the costs to the industry that created them, and you'd see a much broader adoption of alternatives as the prices rose to reflect the "real" costs.
China is a good example of this right now...They're polluting like mad, and passing the costs of that on to their citizens so that they can be super-competitive in the global market against people who have to actually pay some of those costs. It's going to catch up with them in a big way...It's like their propping up our currency. The more the dollar deflates, the more money China dumps down the drain trying to keep the dollar high, at the same time trying to keep their own money as depressed as possible.
As the dollar deflates past a certain point, American goods will become "cheaper" and Chinese goods more expensive, leading to a local manufacturing resurgence, yadda yadda, whereas when the Chinese lose hold of their own money, they're going to have this explosion of costs internally, as well as having to watch their goods become much less competitive globally.
ad logicam Claiming a proposition is false because it was presented as the conclusion of a fallacious argument.
People who freak out about scarcity don't understand economics. Economic pressures drive alternatives and expanded production; we've been seeing this with food since Malthus confidently predicted that food generation could never keep up with current population growth...in 1798.
As the demand rises, people leap to fill it. When Metcalf decided we were going to run out of switching capacity, he was looking at current manufacturing capacity, and a projected increase in demand, and he was sure that capacity could never keep up with demand.
What he didn't see is a horde of people looking for ways to make money, who were looking at the same numbers and thinking, "Holy crap! If I make switches I'll be RICH!" Demand drives supply, not the other way around.
ad logicam Claiming a proposition is false because it was presented as the conclusion of a fallacious argument.