Forgot your password?
typodupeerror
Science

8.6 GB Internet? 382

Posted by CmdrTaco
from the sure-why-not dept.
prostoalex writes "Caltech computer scientists announced the protocol, capable of delivering 8,609 Mbps over the Internet, using 10 simultaneous flows of data. The research project was conducted in partnership with CERN, DataTAG, StarLight, Cisco, and Level 3. The practical applications, according to the press release, is ability 'to download a full-length DVD movie in less than five seconds'. There is a number of papers and scientific publications available."
This discussion has been archived. No new comments can be posted.

8.6 GB Internet?

Comments Filter:
  • watch out! (Score:5, Funny)

    by rehabdoll (221029) on Saturday March 22, 2003 @07:49PM (#5576024) Homepage
    CERN, DataTAG, StarLight & Cisco - watch out! MPAA is coming for you!
  • by Anonymous Coward on Saturday March 22, 2003 @07:50PM (#5576032)
    They've been facing a major bandwidth crunch [theregister.co.uk].
  • Argh! 8Gb (Score:5, Funny)

    by addaon (41825) <addaon+slashdot.gmail@com> on Saturday March 22, 2003 @07:50PM (#5576035)
    I have a dream. Some day the editors will learn the difference between a bit and a byte. Or I'll byte a bit of their heads off. [grumble]
    • Re:Argh! 8Gb (Score:5, Informative)

      by XaXXon (202882) <xaxxon@ g m ail.com> on Saturday March 22, 2003 @07:52PM (#5576045) Homepage
      Yes, as the original poster said, it's 8.6 giga-BITS per second. Little 'b' means bits, big 'B' means bytes.

      Saying 8.6GB is off by an order of magnitude.

      Sigh..
      • by Monkelectric (546685) <slashdot@mo[ ]lectric.com ['nke' in gap]> on Saturday March 22, 2003 @07:54PM (#5576063)
        Actually, its 8/10ths of an order of magnitude, but we're not being picky here now are we ? :)
      • So they can only move one gigabyte per second? That would 'splain why a DVD movie takes 5 seconds (4.7G on a SSSD (single sided, single density - not that anybody remembers those) DVD.)

        Hmmm. Given that I only get 100 kilobytes a second, that is ... maybe 10,000x what I get. I could live with that.

        Eight gigabit per second throughput ... nobody will need more than that! (Ghost of billg past)

        Oh yea, Monkelectric - it is off by exactly an order of magnitude if you are counting in octal :)
        • Re:Argh! 8Gb (Score:3, Informative)

          by damien_kane (519267)
          (4.7G on a SSSD (single sided, single density - not that anybody remembers those)

          Actually when talking about DVDs, the density of each layer cannot change.
          I believe you are referring to SSSL (Single-Sided, Single-Layer) DVDs, as each since on a regular red-ray DVD disc can have two layers of data.

          I'm not sure if that's the same for the famed blu-ray discs or not, I would appreciate it if someone could enlighten me.
      • Re:Argh! 8Gb (Score:5, Interesting)

        by jelle (14827) on Saturday March 22, 2003 @08:05PM (#5576123) Homepage
        Not only that, it's a different metric, because it's leaving out the 'per second'. My response to the title "8.6GB Internet" was 'the internet is much bigger than 2 DVDs, more like tera or exabytes'.

        Otherwise, who needs Internet connections if you can carry a copy of the whole Internet on 2 discs?
        • by Anonymous Coward on Saturday March 22, 2003 @11:20PM (#5576813)
          Otherwise, who needs Internet connections if you can carry a copy of the whole Internet on 2 discs?

          I recall a frame wherein Dilberts boss ordered up a printout of the internet. So, you don't need to use discs, either.
  • CalTech (Score:5, Funny)

    by Ken@WearableTech (107340) <{ken} {at} {kenwilliamsjr.com}> on Saturday March 22, 2003 @07:50PM (#5576036) Homepage Journal

    CalTech's Motto: Enabling Faster Porn and Slashdoting Through Technology

    Bless those people :-)
    • Re:CalTech (Score:5, Insightful)

      by deadsaijinx* (637410) <animemeken@hotmail.com> on Saturday March 22, 2003 @08:11PM (#5576162) Homepage
      Geek: "I'm developing a program to download porn 1 million times faster."
      Marge: "Does anyone need that much porn?"
      Homer: "MMMmmm... one million times.... (gurgle noise)"

      Okay, now to say something serious. Even with broadband, most files download painfully slow because no one can afford to constantly upgrade their servers to dish out large volume of data to the public. If you ask me, 8.6Gb ethernet would be a lot more useful. After all, huge file transfers on your ethernet are at least common place.

      • Re:CalTech (Score:5, Informative)

        by ccnull (607939) <null@@@filmcritic...com> on Saturday March 22, 2003 @10:02PM (#5576590) Homepage
        10Gbps Ethernet already exists [itworld.com].

        The problem is that the fastest hard drives on the market today are Ultra320 SCSI, which have a throughput of 320MB per sec... or about 2.5Gbps. Even that's theoretical, of course. And few people have an all Ultra320 datacenter.

        Just pointing out that the cabling is hardly the bottleneck when you reach that kind of speed, even at the LAN level. I've seen so many people upgrade their switches to gigabit ethernet then scratch their heads wondering why the network is still slow... when the server in the closet hasn't been upgraded in 5 years. Storage will continue to be the bottleneck on the LAN for a long time to come.
        • Re:CalTech (Score:5, Informative)

          by Sycraft-fu (314770) on Sunday March 23, 2003 @03:34AM (#5577466)
          Just a note that the bottleneck of drives isn't a problem at this point since for now 10Gb ethernet isn't targeted at the desktop or server. It is for links between switches. If you have a switch loaded full of Gb connections, you'll probably want something mroe than just a Gb connecting it to its neighbours. However going to ATM or POS really isn't great since you then have to route instead of just switch. Enter 10Gb ethernet to solve the problem.
      • Re:CalTech (Score:3, Insightful)

        by Llurien (658850)
        After having read the article, I'd say that perhaps the biggest achievement wasn't the huge transfer rate, but the high efficiency. Apparently standard TCP coupled with antiquated congestion control methods waste two thirds of bandwidth, and current methods to get around that cause problems for other users. The new protocol had an efficiency of around 90 percent. I'm assuming here (but I could be entirely wrong, as the article does not explain it), that the rest of the bandwidth (two thirds in the first
  • Nothing new (Score:4, Informative)

    by Billly Gates (198444) on Saturday March 22, 2003 @07:51PM (#5576040) Journal
    Fiber optics have been capable of delivering up to 200/gb a second in demonstrations for the last 15 years.

    Its just that optical routing is expensive and so would the switch at such a high speed.

    • Re:Nothing new (Score:5, Interesting)

      by fjordboy (169716) on Saturday March 22, 2003 @07:57PM (#5576083) Homepage
      But not for long! A prof at my college [gcc.edu], Dr. Shane Brower, is part of a research group that is attempting to find cheaper ways to produce easy and cheaper optical routing. Right now, he is attempting to find out why polymers have temporal problems when they're used for non-linear optics. Basically, right now, crystals are the best bet in high-speed fiber optic data transmission...this is because of their non-linear optical properties (you can shoot one color light through them and another color comes out...way faster than turning switches on and off...)...unfortunately, crystals are expensive and take a while to grow and whatnot...however, the other option, polymers are great and easy to make! But..their non-linear properties are temporal, after a little while they no longer work. Dr. Brower's research is trying to find out why that happens...and then, we can produce polymers that continue to work for years! And then...cheap fiber for everyone! Woo!
      • Re:Nothing new (Score:5, Insightful)

        by cryptochrome (303529) on Saturday March 22, 2003 @09:31PM (#5576471) Journal
        Well, I reckon it probably has something to do with the way most all plastics degrade in light, aka the inherent tendency of light to react on covalent bonds, particularly when they are absorbing and reemitting said light in this case. This is a perennial problem with flourescent dyes, by the way - they bleach. Even if you understand the problem in detail, I doubt you'll be able to overcome it cheaply.

        If I were you I'd be looking for a cheaper way to make crystals, or another non-polymeric approach. Quantum dots sound promising.
    • Re:Nothing new (Score:5, Informative)

      by Lothsahn (221388) <Lothsahn@@@SPAM_ ... u_bastardsyahocm> on Saturday March 22, 2003 @08:12PM (#5576169)
      Sure, we can deliver 200 gb/sec in fiber optics.

      This isn't talking about delivering raw speed over a point to point connection but delivering a large amount of data over a shared network. It's talking about a protocol rather than a transport medium, which must account for problems such as error, latency, bandwidth, and flow control.

    • Re:Nothing new (Score:5, Informative)

      by Anonymous Coward on Saturday March 22, 2003 @09:54PM (#5576546)

      If you read the article, you'll notice that they're talking about a new transport protocol, not a physical layer. Yes, physical layers have been able to run faster than 8 gig for quite a number of years. But if you run a TCP session across such a link, the window sizes, congestion control algorithms, ack timers, and such features keep you from getting anything like the speed of your physical link.

      To illustrate with a point from the article, TCP over the 1 Gbps link they were apparently using typically maintained a throughput of about 270 Mbps, only 27% efficient even when that one session had the whole link to itself.

      Previously, no one much cared, because you used those multi-gigabit links by multiplexing a whole bunch of different users; each user saw a much slower link. So, the old, slow TCP was adequate. (To a point, of course; people have noticed problems with TCP acks even on DSL links.)

      One of the purposes of the "Internet 2" research and other projects was to develop protocols that would allow _single connections_ to run at very high speeds.

      The announced protocol, according to the article, managed 95% efficiency and 925 Mbps with a single flow, and 88% efficiency and the 8.6 Gbps of the headline with 10 concurrent sessions over a 10 Gbps link.

      So, yes, it is something new.

    • Re:Nothing new (Score:5, Informative)

      by SiliconEntity (448450) on Saturday March 22, 2003 @10:03PM (#5576595)
      No, this really is new! It is over the regular Internet, a connection from California to Switzerland, that they achieved 8 Mbps:
      Using standard packet size that is supported throughout today's networks, the current TCP typically achieves an average throughput of 266 Mbps, averaged over an hour, with a single TCP/IP flow between Sunnyvale near SLAC and CERN in Geneva, over a distance of 10,037 kilometers. This represents an efficiency of just 27 percent. The FAST TCP sustained an average throughput of 925 Mbps and an efficiency of 95 percent, a 3.5-times improvement, under the same experimental condition. With 10 concurrent TCP/IP flows, FAST achieved an unprecedented speed of 8,609 Mbps, at 88 percent efficiency, that is 153,000 times that of today's modem and close to 6,000 times that of the common standard for ADSL (Asymmetric Digital Subscriber Line) connections.

      They achieved this by modifying the TCP protocol to be more efficient. It's a huge improvement.

      Of course you'd need a big pipe to the net to be able to handle this bandwidth; it will be quite a while before home users could see this kind of speed. But the new protocol sounds like a big win over regular TCP and hopefully it can be rolled out relatively quickly.

  • Why do we need a new protocol?

    IP can scale, can't it?
    • by cperciva (102828) on Saturday March 22, 2003 @08:16PM (#5576189) Homepage
      IP can scale, yes, but TCP (as originally designed) can't scale very well. It severely breaks under multipath routing, and tiny rates of packet loss can dramatically limit throughput, for a start.
  • MPAA Surrenders (Score:2, Interesting)

    by Fenis-Wolf (239374)
    I read this article a couple of days ago. I don't think we'll see a rollout of this anytime soon. Although it would be cool if it happaned. *sigh* and here i was looking forward to downloading DVD's as i watched them.
  • Unhandleable (Score:2, Interesting)

    by Anonymous Coward
    Even with techologies like QDR RAM, fibre channel and pci express most computers will not be able to handle the pipe for this connection.
  • Sigh (Score:3, Funny)

    by Sabbath.sCm (542240) on Saturday March 22, 2003 @07:53PM (#5576055) Homepage
    Now my lil bro will be able to fill up our HD with porn in a couple of minutes...
  • by Faust7 (314817) on Saturday March 22, 2003 @07:53PM (#5576060) Homepage
    I can't help but be amused that that was their first measurement standard for it.

    Oh, they meant legit full-length DVD movies...
  • gosh (Score:4, Funny)

    by LBArrettAnderson (655246) on Saturday March 22, 2003 @07:54PM (#5576065)
    impatient people... can't even wait 5 minutes nowadays... geesh...
  • by KilljoyAZ (412438) on Saturday March 22, 2003 @07:54PM (#5576068) Homepage
    is Jack Valenti having an aneurysm.
  • by Lieutenant_Dan (583843) on Saturday March 22, 2003 @07:55PM (#5576071) Homepage Journal
    How many Libraries of Congress per hour is that?

    • by Esion Modnar (632431) on Saturday March 22, 2003 @08:55PM (#5576358)
      ...but if you lined all the bits up, end to end, it would reach higher than 10 Olympic size swimming pools...

      (stood on end, that is...)

  • by magnum3065 (410727) on Saturday March 22, 2003 @07:57PM (#5576086)
    While this is pretty cool theoretically, current hard drives don't even come close to handling this kind of bandwidth, so there isn't much use for this until we can actually manage to store the data fast enough to keep up with the connection.
  • by millia (35740) on Saturday March 22, 2003 @07:58PM (#5576088) Homepage
    i read this when it was on fark the other day, and i had to wonder what the big deal was. the speed worked out to be slightly lower than 10 gigabits.
    bearing that in mind, isn't 10 gigabit TCP in the getting-done stages?
    i don't know, maybe i missed something 'golly-gee' about this. this just seemed superfluous.
  • by Dr. Spork (142693) on Saturday March 22, 2003 @07:58PM (#5576090)
    "...ability 'to download a full-length DVD movie in less than five seconds'



    Five seconds?? Ohhhh... but I want it NOW!

  • Bottleneck (Score:5, Insightful)

    by dalutong (260603) <djtansey @ g mail.com> on Saturday March 22, 2003 @07:59PM (#5576097)
    The problem is, what sort of mass storage device can write at 8.6 gigabits/sec?
    • by jelle (14827) on Saturday March 22, 2003 @08:07PM (#5576137) Homepage

      Well, /dev/null comes to mind.
    • Re:Bottleneck (Score:5, Interesting)

      by Billly Gates (198444) on Saturday March 22, 2003 @08:14PM (#5576180) Journal
      Also a standard pc bus can not handle the load. This makes any card that can receive the signal at such a high speed useless.

      Assumin its actually 8.6 bytes/sec and not bits like another poster suggested, the pci bus would become oversaturated since it can only transfer 3.2 gb/sec ( correct me if the transfer rate is wrong).

      I wonder if a Sun or IBM unix box could handle this. My guess is this speed will only be used as a backbone anyway so only large unix mini's or dedicated routers will send and recieve at 8.6/gbs. Sorry Johny you can not download porn at that speed.

      • I wonder if a Sun or IBM unix box could handle this.

        It all depends on how the I/O busses are laid out. For a single channel, I believe 2GB fibre channel is the fastest they can do, but if you stripe a bunch of channels together, you can probably sink that much data.

      • Re:Bottleneck (Score:5, Informative)

        by Emil S Hansen (143865) on Saturday March 22, 2003 @09:19PM (#5576428) Homepage Journal
        Assumin its actually 8.6 bytes/sec and not bits like another poster suggested, the pci bus would become oversaturated since it can only transfer 3.2 gb/sec ( correct me if the transfer rate is wrong).

        A 33 MHz/32 bit PCI bus which is standard in most PCs will transfer 133 MB/sec.
        A 66 MHz/32 bit PCI bus which is in quite a few Intel and UNIX servers will transfer 266 MB/sec.
        A 66 MHz/64 bit PCI bus which also is quite common in UNIX servers (and becomming in Intel) will transfer 532 MB/sec.
        A 133 MHz/64 bit PCI bus which is the current standard for big UNIX servers will transfer, you guessed it, 1 GB/sec.
        Mind you that these numbers are pr. PCI bus, some of the lager Intel servers, and most UNIX servers have more than one PCI bus.

    • by addaon (41825) <addaon+slashdot.gmail@com> on Saturday March 22, 2003 @08:19PM (#5576212)
      An array of card punchers. A very wide array. Or just a piezo speaker, and store it in a mercury delay line until you have time to write it to disk. Hmm... then again, room temperature would give far too much brownian motion for coherence at that bandwidth in mercury. Metallic hydrogen delay line, then.
  • Bloody repeats (Score:4, Informative)

    by blamanj (253811) on Saturday March 22, 2003 @08:03PM (#5576109)
    Ahem, this was reported here [slashdot.org] a couple weeks ago.
  • by blair1q (305137) on Saturday March 22, 2003 @08:05PM (#5576119) Journal
    Unless they're willing to pay for the $5K in equipment to wire my house up for that, I'm not going to be downloading any movies over it.
  • by SensitiveMale (155605) on Saturday March 22, 2003 @08:05PM (#5576121)
    limit everyone's connection to a single stream.
  • by Randolpho (628485) on Saturday March 22, 2003 @08:09PM (#5576150) Homepage Journal
    The protocol they used is called "FAST" (or "FAST TCP"): Fast Active (queue management) Scalable TCP.

    Looks pretty slick... is it a replacement for TCP, or an overlay of TCP? The article says that it uses 10 simultaneous TCP connections....

    I can't find on a cursory glance whether or not it can run on IP, but I assume so. Hopefully it will work with IPv6, when (if) it becomes mainstream.

    The article mentions that has an average throughput effeciency of 95% (meaning that if you have a Gigabit connection, it can send/receive stuff at around 950Mbps). Does it drop TCP's congestion handling and do something similar to UDP then?
  • by rocjoe71 (545053) on Saturday March 22, 2003 @08:11PM (#5576166) Homepage
    I'm sorry, but 8,609 Mbps means nothing to me-- how much is that in spam emails per day?
  • HDD Speeds? (Score:5, Insightful)

    by PhrostyMcByte (589271) <phrosty@gmail.com> on Saturday March 22, 2003 @08:12PM (#5576170) Homepage
    Okay, todays RAM can top 8GB/s, so there is no problem generating data and sending it through this like that. However, hard drives can't even reach 1/100th of this speed, so don't expect your p2p programs to go much faster ;) This can be great for sites that require a massive pipe and have fiber hard drives's or ISPs. Also be good defence against a slashdotting ;)
  • by glMatrixMode (631669) on Saturday March 22, 2003 @08:13PM (#5576176)
    that may be silly, but in the case this technology is actually developped, there will remain a crucial battle : the RIAA/MPAA (media lobbies) are going to be so scared by such a tech that they'll do all what they can so that it comes with some kind of DRM (digital rights managements).

    In other words, such a technology would give a boost to legal attempts to allow hard DRM - as is today illegal under the liberty-preserving legislation of a lot of countries, especially in Europe.

    Do not answer that the media lobbies aren't asked to give their opinions here. Because it is part of Microsoft's, Intel's and AMD's (to cite only 3 members of the vast TCPA alliance) strategy to maintain good relationships with the media companies in order to enlarge the computer market.

    You know what I'm talking about - Palladium. I don't think it's necessary to insist on the fact that it would be a bad thing for us.
  • by linux11 (449315) on Saturday March 22, 2003 @08:25PM (#5576234)
    I imagine that there will be a day when you can get ANY movie regardless of popularity from Blockbuster, Best Buy or Circuit City easier than filling out a prescription. You just tell them what legacy movie or TV show episodes you want and 15 minutes later your burned DVD with professional looking label printed on it is ready for pick-up for $20-$30. It may even include a difficult to replicate vendor hologram on the label side of the DVD to help distingish it from non-approved burns.
  • I choked on my 2am coffee when I read that!
  • DMSCA (Score:2, Funny)

    by Anonymous Coward


    Jack Valenti has heart failure at announcement.

    Hilary Rosen Responds by announcing DMSCA bill.

    Berman and Hollings, after campaign contributions and honorariums, announce co-sponsor the Digital Millenium Scientist Control Act, stating that the only reason scientists could possibly have for developing the technology for such fast downloads is to support porn, piracy, and terrorists.

    The Digital Millenium Scientist Control Act is written to allow scientific research, unless it can be used to deny unjust enr
  • by Anonymous Coward on Saturday March 22, 2003 @08:33PM (#5576272)
    ...CERN, DataTAG, StarLight, Cisco to release "The complete works of Jenna Jameson" in div-x format. Order now!
  • by holyrabbitear (635135) on Saturday March 22, 2003 @08:54PM (#5576352)
    From the article: The protocol is called FAST, standing for Fast Active queue management Scalable Transmission Control Protocol (TCP).
    That would be FAQMSTCP..in other words pronounced
    FAH Q MS TCP...

    as read on FARK...
  • So what? (Score:5, Insightful)

    by jeffasselin (566598) <cormacolinde@NOSpam.gmail.com> on Saturday March 22, 2003 @10:10PM (#5576627) Journal
    No really. That's too fast. A full-length movie would be 2 hours. Why would you need to download it in 5 seconds? It will take you 2 hours to watch ANYWAY. So if you can stream it in a reasonable amount of time (like 2 hours) that would still be nice.

    And I won't add the problem of hard drive speeds which can't handle it. Of course, big RAID arrays and the like can, but not consumer drives.

    Of course, eventually, when we use a better quality encoding method for video/audio, the datarate may have to increase, but right now, it's useless.

  • I see two things... (Score:5, Interesting)

    by The Master Control P (655590) <ejkeever&nerdshack,com> on Saturday March 22, 2003 @11:31PM (#5576843)
    First, they said it uses 10 parallel data streams. So any given stream is only running ~860Mbps. Could this be a resurgence of parallel commucations? For example, 10 cheap 100Mbps LAN transcievers integrated into 1 card for Gigabit Ethernet speed? Would there be any cost advantages of cramming large numbers of cheap devices onto a card VS a single fast but expensive device? Sort of like Billion-Dollar-Probes vs the smaller/faster/cheaper thing at NASA.

    And I figure that by the time this becomes mainstream, the amount of data needing to be transferred will also have increased by 1 or 2 orders of magnitude, and you'll still be stuck waiting hours for the latest HoloVideo downloads. Just like you wait hours to download Attack of the Clones over DSL and Cable, and like you once waited hours to download that 5 meg shareware program over your 56K modem.

    Seems like the amount of data being stored is always 1 step ahead of the amount that can be conveniently transferred... We need a war on program bloat.
  • by punkass (70637) on Saturday March 22, 2003 @11:41PM (#5576874)
    ...in which someone told me that there has yet to be backbone built that could go faster than a station wagon loaded with backup tapes doing 90 mph from Buffalo to Syracuse...
  • by autopr0n (534291) on Saturday March 22, 2003 @11:53PM (#5576905) Homepage Journal
    Hey, what happened to Libraries of Congress per fortnight?
  • by Transcendent (204992) on Sunday March 23, 2003 @01:42AM (#5577183)
    The practical applications, according to the press release, is ability 'to download a full-length DVD movie in less than five seconds'

    In other news, the MPAA has filed a lawsuit against Caltech for "aiding the piracy of copyrighted movies". The RIAA is expected to file a similar lawsuit as many wonder why they haven't already milked Caltech for all the money it's got.
  • Now wait a minuet! (Score:3, Interesting)

    by Nonillion (266505) on Sunday March 23, 2003 @05:02AM (#5577616)
    While having this kind of bandwidth would be nice, consumer grade computers let alone the hardware are beyond woefully inadequate. About all you could hope for would be a 100M/bit connection. This is assuming that the phone company/cable operator dosen't bend you over for the cost of said connection.

    The only machine that I know of that could even utilize a connection this fast is a Cray X1 [cray.com]
  • by Zone-MR (631588) <<slashdot> <at> <zone-mr.net>> on Sunday March 23, 2003 @08:40AM (#5577867) Homepage
    They are transmitting accross a public network, so in a sense many streams will be contended at one point or another. By splitting the data into 10 streams they are getting an advantage, as their data stream will in effect have a 10-fold priority over other internet traffic.

    But what if this was done on a mass scale, and everyone used 10 streams to increase their transfer rate? I imagine the combined bandwidth would be as bad as a single stream was. Which I find questionable if its efficient, or a good thing for the Internet.

What is wanted is not the will to believe, but the will to find out, which is the exact opposite. -- Bertrand Russell, "Skeptical Essays", 1928

Working...