Follow Slashdot stories on Twitter

 


Forgot your password?
Close
typodupeerror
×
Wireless Networking Intel Hardware

Automatic Wireless Network Organisation 125

Posted by CowboyNeal from the every-machine-to-become-a-router dept.
babycakes writes "Interesting article over at the BBC about the future of wireless networks. Researchers at Intel are developing mesh networking technology that automatically organizes the best routes between wireless devices for better bandwidth control, now that the number of wireless devices is set to explode." Neat stuff, but they've yet to implement any sort of security controls. Until they do, it's going to be a real party for wireless eavesdroppers. timothy adds: La Camiseta writes "Wired has an article discussing the extent that some people will go to in order to stay connected. My favorite is their 4-way SMP system that fits into a briefcase."
This discussion has been archived. No new comments can be posted.

Automatic Wireless Network Organisation More

Automatic Wireless Network Organisation

Comments Filter:

  • 4-way SMP? (Score:3, Insightful)

    by Malc ( 1751 ) on Monday February 24, 2003 @11:04AM (#5370216)
    It has four uniprocessor motherboards. Can it really be called 4-way SMP? 4-way cluster perhaps.

    • Re:4-way SMP? (Score:2, Interesting)

      by stratjakt ( 596332 )
      If they're all working for the same task, like distributed compiling, or just running the same OS, then I think it can be called SMP. If it's just 4 redundant servers, I'd say not.

      I dont think SMP means all the procs need be on the same sheet of fiberglass.

      Then again, I may be wrong and will be shouted down by some nitpicking geek.

      • Re:4-way SMP? (Score:5, Informative)

        by benwb ( 96829 ) on Monday February 24, 2003 @11:29AM (#5370353)
        SMP requires shared memory so this box doesn't fit the bill.
        Best Regards,
        Your friendly nitpicking geek.

        • Re:4-way SMP? (Score:2, Interesting)

          by AssFace ( 118098 )
          exactly - I was going to say there doesn't look to be any use of shared memory (not even sure how they would).

          I'm curious if they are writing stuff with something like PVM for a beowulf type thing, or the more likely OpenMosix option.

          Also curious as to what they are using it for. (didn't read the article but checked out that briefcase b/c it sounded and looked cool)

        • Yeah, but imagine a Beowulf cluster of... oh, never mind.

    • Re:4-way SMP? (Score:1, Insightful)

      by Anonymous Coward
      SMP refers to how multiple processors gain access memory.

      a.) That's a 4-way cluster...
      b.) Someone forgot to plug in the memory and power supplies...
      c.) That's not even P ... let-alone SMP

  • Security implications? (Score:5, Interesting)

    by tjansen ( 2845 ) on Monday February 24, 2003 @11:06AM (#5370228) Homepage
    I wonder what the security implications are. If every device is able to route, a malicious device could claim to have great connections to other devices in the mesh and then drop packets. Unless there is some way of authentication in the mesh (so that only authenticated devices can participate), it would need some trust/rating system so devices can exchange information about the reliability of other devices...

    • Re:Security implications? (Score:4, Insightful)

      by TopShelf ( 92521 ) on Monday February 24, 2003 @11:14AM (#5370277) Homepage Journal
      Security seems to be taking a back seat yet again to feature development. For wireless to really explode in the business arena, however, security needs to be built-in from the start. I know at my workplace we have a genuine need to upgrade a wireless network, but we're waiting for better security which is supposed to be available this summer before moving forward.
      • Who cares who can listen in on the wireless? Echelon is still going to listen when it hits the wired internet. Either you encrypt all of your traffic, or you have to accept sniffing as a fact of life.

        I prefer double rot-13 encryption myself, for most things. Otherwise SSL is good enough if I actually care.

        --Mike--

      • Re:Security implications? (Score:4, Informative)

        by grumpygrodyguy ( 603716 ) on Monday February 24, 2003 @12:06PM (#5370581)
        For wireless to really explode in the business arena, however, security needs to be built-in from the start.

        Security is at least as important to the home user.

        If P2P filesharing is going to keep from dying on the vine, a very robust IP masking security layer needs to be implemented soon. An IP address is like a license plate. Now that ISP's can be bullied into identifying thier users, there's really nothing we can take for granted. Those of you who take issue with filesharing may not agree, but the next application to be blacklisted may be yours.

        IP anonymity is the 21st century equivalent of the proverbial "right to bear arms". It should be protected in order to ensure that we are protected from our government.

        • Re:Security implications? (Score:1, Interesting)

          by Anonymous Coward
          So you expect people to reply to you when you talk, but they're not allowed to know where to reply to? Care to explain how that works?
      • Three syllables say it all:

        Prototype.

        As the article says, they're still doing research on mesh networks. They're not yet designing an actual product.

        Karma whores.

      • Re:Security implications? (Score:4, Informative)

        by dnoyeb ( 547705 ) on Monday February 24, 2003 @12:46PM (#5370791) Homepage Journal
        I fail to share your concerns. A hardwire network has only access security. Anyone is able to plug into it and your so called security turns instantly into anti-security.

        You should be using encryption at the software level, and the data level, not the hardwire level. Software level encryption and data level encryption can be changed on a daily basis. hardware level security is permanent and once broken you can toss your foolish devices in the toilet.
        • When you're in a facility that has controlled physical access (as I am), a wireless network represents a huge gap in that level of security. Software & data-level security are separate issues, which need to be tackled whether you're wireless or not.
          • Yes I know. Its much more convient for me to store my money on my front lawn. Easy access. But should I start complainign about its insecurity?

            And should I start creating contraptions to secure something which is fundamentally insecure?
      • IPSec anyone?

        Seriously, stick an IPSec VPN gateway behind your AP and just use VPN tunnels to get your wireless clients on your network.

    • Re:Security implications? (Score:4, Insightful)

      by Anonymous MadCoe ( 613739 ) <maakiee@NoSpam.yahoo.com> on Monday February 24, 2003 @11:26AM (#5370333) Homepage
      And another question would be:
      If we get the security part of it right, how about privacy assurances.

    • Re:Security implications? (Score:4, Informative)

      by meese ( 9260 ) on Monday February 24, 2003 @12:03PM (#5370564)
      There have been several research efforts to ensure security and prevent misbehavior in ad hoc networks.

      The following papers address many of the issues:

      The Ariadne System [rice.edu] (for secure routing)

      Mitigating routing misbehavior [stanford.edu]

      There are several others that solve similar problems in the research literature.
    • It would need some payment system so you pay the other devices a tiny amount for successfully delivered packets, and they agree to compensate you for any that are dropped.

      (Well it wouldn't _need_ that, a simple trust-everyone system will be good enough to start with, but it would be kewl. And promote commercial-yet-decentralized growth of wireless networks.)
      • There's also research (some of which I'm working on) that tries to address payment schemes in ad hoc networks as you suggest.

        The premise is that hosts will behave in a greedy, "self-interested" fashion in a game-theoretic sense. One main difficulty is in creating a distributed virtual-currency system without a centralized authority. Several approaches either use a centralized authority or require secure hardware at each node.
    • If every device is able to route, a malicious device could claim to have great connections to other devices in the mesh and then drop packets.
      Hopefully the architecture would be smart enough to recognise the disparity between claimed and actual performance, and act accordingly.

  • Ok, we should ask ourselves (Score:4, Insightful)

    by Anonymous Coward on Monday February 24, 2003 @11:07AM (#5370229)
    We should ask ourselves, is this a real mesh? having the 'big mama' setting up the network for us, or a real mesh protocol is needed that we can all be servers and clients at the same time to the network, interconnected into a real mesh? Anyway, this is a _great_ step into the future, and let's hope that it works.

    • It was asked long ago ... (Score:4, Insightful)

      by jc42 ( 318812 ) on Monday February 24, 2003 @01:42PM (#5371240) Homepage Journal
      We should probably note that the a wireless, redundant "mesh" design was part of the ARPA project from the beginning. A lot of old-timers are somewhat disappointed that it's 40 years later, and we still don't have it.

      You can see an example in the first diagram at this historical article [cybergeography.org]. Note that the diagram dates to 1964, and the text mentions a "communications network that would survive a major enemy attacked" [sic].

      Many of the earliest diagrams of the ARPAnet showed planes, ships, plus all sorts of mobile ground vehicles, with wireless random-looking connections. Again, this was 40 years ago.

      Another interesting bit of history: The earliest ARPAnets were mostly on Ethernet. This is a curious term. Why would they use it for a length of coax cable? The reason was that the intention was that it be wireless, with packets being sent "throuh the ether". The wired version was just a temporary kludge until they could get the wireless version working. "Ethernet" was chosen as an unsubtle hint as to what was considered the real packet medium. It was clumsy, limited and kludgey, but the wires were only supposed to be a temporary medium, to be phased out in a few years.

      It's been 40 years, and we're still not there ...

  • Wires are where its at (Score:3, Funny)

    by Anonymous Coward on Monday February 24, 2003 @11:07AM (#5370231)
    Plug the male end into the female socket. Thats what connectivity is about.

    I fear it may be a foreign concept around here, but trust me, WiFi goes against God and Nature.

  • one word... MESHBOX (Score:5, Informative)

    by Anonymous Coward on Monday February 24, 2003 @11:08AM (#5370239)
    So you wanta mesh networking? I givea youa the mesha networking...

    Meshbox [www.locustworld] is a lightweight unix distro that does mesh networking over wifi and a gazillion other useful things.. ..fits in 32mb.. ..can also be bought with a an miniITX puter to run on... for just $400.. ..has potential to change the world... or at least the telco industry.. ..is cool.. ...is developed on the right side of the atlantic... :)

    • Re:one word... MESHBOX (Score:4, Informative)

      by Spruitje ( 15331 ) <ansonr.spruitje@org> on Monday February 24, 2003 @12:08PM (#5370589) Homepage
      And there is even a sourveforge project started .
      I have build five meshap units.
      The VIA-EPIA V8000 is only 109 euro including the processor and a processorcooler.
      Only thing you need next to this board is a 128 mb sdram module, a 32 CF IDE drive and a PCI-wirelesscard.
      And of course a case.
      The biggest advantage is, that it works and that is doesn't cost you an arm and a leg.
      • This is really cool stuff, but their website is a bit lite on demographic info. Where are these devices flourishing? If I buy one I'd like to know that I'm in a location where I'll find likeminded peers.

        Is there a map available? Links appreciated.
        • The MeshAP/Meshbox solution builds a backbone wireless mesh network using AODV, but also presents a standard wireless AP to client PCs (or at least that is how I understand it to work).

          Someone correct me if I am wrong!
    • Meesa very appreciating yousa advice!

  • I guess I'm slow... (Score:4, Interesting)

    by mao che minh ( 611166 ) on Monday February 24, 2003 @11:09AM (#5370245) Journal
    So they intend on doing away with the traditional hub/switch/router layout, in which someone administers the network and decides what amount of bandwidth goes where, and instead embed these functions into the wireless devices themselves? Seems a bit ambitious.

  • wow (Score:1, Funny)

    by Anonymous Coward
    thats a lot of pringles cans

  • Whats the point of that Mini-ITX cluster? (Score:5, Interesting)

    by stratjakt ( 596332 ) on Monday February 24, 2003 @11:15AM (#5370283) Journal
    I have to assume those are the 800mhz versions from the CPU fan, but still, these things have very little power from my experience with them. Cool little toys, maybe enough for a low-end workstation or terminal, but I wouldnt think of using one in a server situation.

    I actually used one to run my squid-based proxy, and it was outperformed by the P200/MMX I wanted to replace.

    Why cluster 4 of those? I'd think a 2 gig Celeron (of course P4 would be preferred) would have more power, faster DDR Ram, be as cheap (if not cheaper).

    I cant fathom why one would cluster those little Eden boards, unless they were going for redundancy; a poor mans fault tolerant server.

    Anyone?
    • Two words - power consumption.

      Those little Eden boards consume very little power. Clustering them would provide more robustness and processing power for a mobile network.
    • it was outperformed by the P200/MMX I wanted to replace.

      That seems like a rather extreme case, and probably more to do with memory than with the actual processor. On most applications, using similar memory/bus technology, the VIA will come in only a little behind an Intel or AMD processor at the same clock rate. On the measure of "MIPS per milliwatt" it will come out way ahead, and that often matters even more. This is not a platform designed for raw performance. It's designed to balance performance with other factors, and does it quite well.

      Why cluster 4 of those? I'd think a 2 gig Celeron (of course P4 would be preferred) would have more power, faster DDR Ram, be as cheap (if not cheaper).

      Also more power required, more heat, and more space. The nice thing about the Eden boards is that they do well in those three areas, which are more important in this application than raw computes, and yet they run everything that those hotter, more power-hungry processors plugged into bigger motherboards do. There are four of them because this is the sort of application where more slower processors provide benefits that fewer faster ones would not.

      My quibble is not that they went with Eden, but that they didn't get the ME6000 which can run fanless. BTW, that board supports DDR SDRAM, so for a memory-bandwidth-bound application such as your squid server it would probably do quite well (assuming that the app isn't poorly coded to use more CPU cycles than necessary).

      Disclaimer: I do have a VIA-based system (Shuttle SV24) but that's my only association with them. I also happen to know a couple of the Wifi Caravan folks.

  • Old Hat (Score:5, Interesting)

    by NimrodMCSE ( 560652 ) on Monday February 24, 2003 @11:22AM (#5370311) Homepage
    The company I work for has been doing this for over 2 years. Seems like Intel is way behind the curve on this one. You can see what we've been doing @ http://www.meshnetworks.com .

    • Mesh networking in general is the future of wireless.

      Is the protocol that enables mesh networking an open standard? The OpenAP project [instant802.com] and the Mesh AP [locustworld.com] folks use 802.1d, or MAC bridges [ieee802.org], to eliminate redundant hops.

    • Seems like you're way behind the curve. Six years ago the company I worked for teamed up with a company that had been doing this for years. That company was acquired by Nokia [nokia.com] in 1999.
      • Did you read our site? We have high-speed mobility and geo-location. Problems that Rooftop couldn't solve. Also our root technology was licensed from ITT, which developed it for a DARPA project years before Rooftop. Rooftop is a fixed wireless solution and rumor has it that TESCO has discontinued support for this product.
        • I read your site. Then I talked to your sales guy (over about a two week period when I could get my calls returned). Sounded like a bait and switch deal to me. Only interested in high volume buyers. Way overpriced. Geolocation in the highest end stuff only (if there). Now I've got a couple of MeshAP boxes from Locustworld on order.
          • I set up a few Locustworld APs in my neighborhood using old laptops. Works good for what I need, We've got about 10 folks who use it, mostly for access at the beach or on the lake. Our MeshNetworks stuff is designed for commercial use and we do need to qualify buyers. Not my choice, business types decide that stuff. I'm just glad I get to play with it.
    • What is the price of the MeshLAN routers and APs? Who retails them?

  • Wireless security IS a big issue... (Score:5, Interesting)

    by DarklordJonnyDigital ( 522978 ) on Monday February 24, 2003 @11:28AM (#5370349) Homepage Journal
    ...when the modern nerd can hack from low-flying aircraft passing over your house! Ars Technica have done it already - twice, no elss: War Flying, 1 [arstechnica.com] and War Flying, 2 [arstechnica.com]

    This is just too cool.
    • If someone is so anxious to know what traffic is on my wireless network that they are willing to charter a plane...they can have it.

      I don't think of wireless networking as the next wave for corporate america...replacing the wired office with large nework infrastructures.

      I think of wireless networking as the best way to get internet to mom and pop in the country. I think of it as a convenience for home users that don't want wiring coming out of their ears. I think of it as another way for my portable computer to be more portable.

      Do I worry about the security aspects of it? Absolutely not, because I don't use my wireless networks for anything that require security.

      I don't mean to limit the scope of wireless networking. I can see a future where it gains a solid foothold in the workplace of the large corporate network, but that is still sometime in the future.

      For the here and now there are still plenty of uses for wireless networking and advances in wireless networking that can flourish regardless of any security loopholes that might exist.

      Craenor

  • Being offline... (Score:5, Insightful)

    by MosesJones ( 55544 ) on Monday February 24, 2003 @11:30AM (#5370366) Homepage

    Is great, having those hours when no-one can contact you. Finding a hotel in a mobile blackspot. Being unable to pick up emails for days knowing that people will just have to cope.

    I like being offline, I hate being forced to be online more, with the internet on planes now there goes 8 hours of peace and quiet without an urgent request to do something minor.

    The more I'm online the less work that I do, because the more "noise" I receive. Being online all the time means more stupid IM requests, more emails to follow up and more calls asking about something they could have read in a book.

    Next year you'll have articles on how far people go to kill their net connection.
    • Is great, having those hours when no-one can contact you. Finding a hotel in a mobile blackspot. Being unable to pick up emails for days knowing that people will just have to cope.

      who says you need a blackspot? "my battery died" works just as well for just about any item these days. if anyone asks about your charger, well, gee that broke too or you forgot it at home.
    • "Is great, having those hours when no-one can contact you."

      Just like Gary Kildall, eh?

  • Battery usage? (Score:3, Insightful)

    by trikberg ( 621893 ) <trikberg.hotmail@com> on Monday February 24, 2003 @11:32AM (#5370379)
    So what they're saying is that anyone in my general vicinity can use up my battery because that's the best path for the data?

    In that case: No, thank you. This is never going to take off.

    • Re:Battery usage? (Score:2, Interesting)

      by vadim_t ( 324782 )
      Why not? You get something in return for the resources you have to give up: a network.

      It sounds like Freenet to me. In order for the network to work well people need to run nodes. Yes, they will transfer stuff for other people, something that doesn't benefit your directly. But it also keeps the network ticking, which is what you want.

      I suppose it will work this way: If you want the advantages of the network then you have to contribute with your battery.

    • Re:Battery usage? (Score:3, Informative)

      by Salamander ( 33735 )

      Actually, the people who design ad-hoc routing protocols are very much aware of this issue. If there's an alternative route through plugged-in stations, it will be preferred. If your battery power, as reported through the routing protocol, is low, traffic will be routed somewhere else if possible. Sometimes, though, you might be the only link between two network segments, and there's no choice but to route through you. You don't even know whether that's the case, but that's the risk you have to be willing to take as the cost of participating in such a network. If you want guarantees, you can always use a traditional "infrastructure mode" AP setup that's under your own complete control.

  • ./ finally listens to its users complaints about having its own category

  • Wireless Security (Score:5, Insightful)

    by Gyorg_Lavode ( 520114 ) on Monday February 24, 2003 @11:45AM (#5370444)
    It seems to me that wireless is still in the "can we do it" phase and has not progressed to "can we do it RIGHT".

  • Mobile SMP (Score:5, Funny)

    by Chocolate Teapot ( 639869 ) on Monday February 24, 2003 @11:48AM (#5370471) Homepage Journal
    My favorite is their 4-way SMP system that fits into a briefcase.
    Sounds cool, but I just know that I would leave this on the train and pick up someone else's case by mistake. What a bitch when you arrive home to find that you have a veritable beowulf of empty sandwich bags, orange peel, an odd sock and half a dozen photos of someone else's kids.
    • I would leave this on the train and pick up someone else's case by mistake.

      Ah, but at least it would be ethical [randomhouse.com]. Disagree? Many [metafilter.com] would side with you.

      Yeah, I know this is (-1, Offtopic). Mod as you wish.

  • Intelligent Wi-Fi (Score:2, Informative)

    by shamitbagchi ( 641092 )
    MORE HERE [btexact.com] AND HERE [bbc.co.uk]
  • I'm not too hot on the mesh networking idea, mostly because people who want high latency can get that via satellite.

    Don't have anything else useful to add to the discussion, except:

    now that the number of wireless devices is set to explode.

    With all the English-as-second-language writing I encounter every day, that sentence is nearly enough for me to play it safe and not buy that new 802.11b card.
  • The picture is of four Via Mini-ITX [mini-itx.com] boards epoxed together. They have no internal connection other then there ethernet interfaces. It is not a 4-way SMP machine (they are _much_ more expensive than this setup).

    Out of curiousity, does any know of a way to chain boards like this together through a fast bus like PCI or something?

    I know about blade servers and how they work but I'm talking about regular commodity motherboards.
  • Automatic Wireless Network Organisation Organization IS spelled with a 'z' not an 's'.
  • First of all wirless networks need to come into more prevalent/dominant use - unless otherwise . . . not just cell-phones but more powerful application devices with tremendous crunching power.

    The concept is in the nascent stage - the initiative by Intel and others to create hotspots is useful, but wireless long distance and cell-based networks are 2 different things.
    Carrying data over cellular networks is still not strong in developing contrie snad quality of service and bandwidth needs to be improved - probably getting a boost via these techniques of auto routing - also dynamic routing and successful techniques during travel (trains, planes) will have to be implemented.

    Wiring villages without the necessary infrastuctures will fail to generate the opportunities.
    Lot of research in terms of algorithms etc will be important - probably existing algorithms will become redundant and new concepts will have to be used.

    Is there going to something called Radio frequency pollution ???
  • My favorite is their 4-way SMP system that fits into a briefcase.

    To put it in simple terms, SMP means several processors share the same memory. I doubt that the four separate motherboards shown are capable of this.

    With Hypertransport, this little bit of fiction might become reality in the not too distant future.

  • VPN... (Score:4, Informative)

    by craenor ( 623901 ) on Monday February 24, 2003 @12:36PM (#5370731) Homepage
    If you want wireless security, there it is. Setup your access points (APs) with a DMZ. That's a small space in the networking architecture of the AP that anyone can access.

    The only thing you will find in that DMZ is a portal to sign into the VPN server. You have a VPN account, you're in there. You don't have a VPN account? Sorry. Is it perfect? Maybe not, but it's a helluva lot better then relying on WEP.

    Craenor
    • And you can find dedicated VPN servers on eBay these days for like $25. Stick it behind your AP and your problems are solved.
      • Or just install FreeS/WAN (http://www.freeswan.org) on some piece of junk computer. Maybe even on the same computer that you use as your gateway or router or firewall (or some all of the above).
  • Hey, that's a new slashdot topic icon! An event to celebrate! It's not every day we see a new topic icon.

  • Why? (Score:1)

    by t0ny ( 590331 )
    why is it that security always lags behind technology? From wireless phones and baby monitors that can be listened to with scanners, to wireless networking that has nothing preventing access, these things seem to happen ad nauseum.

    My uneducated guess would be that security is ignored in the rush to market, and also is seen as 'paranoid nonsense' until it is prevalent. Things like this are the reason I urged a ban on wireless networking at my company until the technology matures more (thankfully it is now prohibited).

  • Security in "cooperative" networks (Score:5, Interesting)

    by per unit analyzer ( 240753 ) <{EngineerZ} {at} {gmail.com}> on Monday February 24, 2003 @01:22PM (#5371077)
    The problem with security in ad hoc mesh networks built in a cooperative environment* is that you have to worry about who's running the intermediate nodes and whether or not they're doing anything bad with your traffic. Even if you design the wireless link so that non-participants can't sniff your traffic out of the air, the mesh nodes themselves must be secure so that their owners can't snoop on each other. So in the mesh environment, you'll either need to require security to be end-to-end or design a radio that switches packets at a low level and doesn't let traffic passing through to be copied higher into the node OS where it can be snooped. I would opt for the end-to-end security since I can't be sure someone hasn't built a radio that violated a privacy standard.

    --zawada

    (*) By cooperative environment, I'm talking about mesh networks that are built by many independent entities, with each node carrying the traffic of multiple participants. e.g., your laptop participates in a cloud of laptops that ultimately carries all participants' Internet traffic back to an access point somewhere.

  • Mesh Routing algorithms (Score:3, Interesting)

    by TheSync ( 5291 ) on Monday February 24, 2003 @01:39PM (#5371210) Journal
    Mesh Routing [waterloowireless.org] links.

    MeshAP/MeshBox from LocustWorld is based on AODV routing module. There are also userspace versions of AODV. Plus there are at least two other competing mesh routing algorithms, and there are other hardware mesh solutions, but MeshAP has a lot going for it.
  • ... Dont let your choice of wireless transport dictate the method and depth of the security (best is large key VPN). Some users will want to use open (unencrypted) traffic. Don't hold up the deployment of the wireless infrastructure waiting for things that should be a part of the node's app stack.
  • Didn't Apple already create a self configuring wireless network? How is this different then rendezvous? Doesn't Apple own patents to this concept, or at least have prior art?
  • This reminds me of something a friend was working on a few years back, hardware that would search for the other like wireless cards in range, and they would self-configure to form a network with all the computers in range, no need for a base station.
    Not high bandwidth, but still interesting. Of course, I haven't seen him since then.

Slashdot Top Deals

One man's constant is another man's variable. -- A.J. Perlis

Close