Slashdot Mirror


Bittorrent To Cause Internet Meltdown

Gimble writes "Richard Bennett has an article at the Register claiming that a recent uTorrent decision to use UDP for file transfers to avoid ISP 'traffic management' restrictions will cause a meltdown of the internet reducing everybody's bandwidth to a quarter of their current value. Other folks have also expressed concern that this may not be the best thing for the internet."

872 comments

  1. 98% by Anonymous Coward · · Score: 5, Funny

    Plz seed

    1. Re:98% by Kjuib · · Score: 4, Funny

      If it melts... it should flow better and faster right? A liquid net would better than a solid one.

      --
      - Your stupidity got you into this mess, why can't it get you out? -Will Rogers
    2. Re:98% by ardor · · Score: 4, Funny

      Nah, it would melt the internet tubes.

      --
      This sig does not contain any SCO code.
    3. Re:98% by Glothar · · Score: 3, Funny

      Well, it would fit through the pipes better.

      [/required]

    4. Re:98% by Anonymous Coward · · Score: 0

      If the tube melts your liquid internetz and big trucks will fall out.

    5. Re:98% by Anonymous Coward · · Score: 1, Funny

      It should flow like a harpoon daily and nightly.

      But will it ever stop? Yo, I don't know.

    6. Re:98% by macshome · · Score: 3, Funny

      I think that's exactly what Skynet wants...

    7. Re:98% by eat+here_get+gas · · Score: 0

      especially being contained in these "tubes" i've heard so much about...yes, it sounds like this will in fact "streamline" the internet!

      --
      the significance of a signature is insignificant
    8. Re:98% by Zencyde · · Score: 2, Funny

      Shall I turn out the lights so you can glow?

      --
      What day is it? Could you please tell me?
    9. Re:98% by toriver · · Score: 3, Funny

      I vas elected to lead, not to seed!

    10. Re:98% by Anonymous Coward · · Score: 0

      Absolutely. Ted Stevens will tell you all about how liquids travel better through tubes than do solids.

    11. Re:98% by Anonymous Coward · · Score: 0

      The tubes are strong with this one.

    12. Re: 98% by Sublmnl · · Score: 1

      What happens when I have both a udp tracker and a tcp tracker listed while downloading a torrent? Do I make some connections while losing others? Is the info shared from the udp connection to the tcp connection? Or would I better off with a single tcp connection?

    13. Re: 98% by mcpkaaos · · Score: 5, Funny

      Bald kid: Do not try and manage UDP connections. That's impossible. Instead... only try to realize the truth.
      Ted: What truth?
      Bald kid: There is no connection.

      --
      It goes from God, to Jerry, to me.
    14. Re:98% by Anonymous Coward · · Score: 0

      98% should be enough for anyone.

    15. Re: 98% by defrex · · Score: 1

      I wish you could get a funny score higher then 5...

  2. Finally! by tikram · · Score: 2, Funny

    Finally, I'll have a legitimate reason to slack off and not do my job...

    On the other hand, how am I going to procastinate without the internet?

    1. Re:Finally! by psychicsword · · Score: 1

      You could always download something to do with Bittorrent :P

    2. Re:Finally! by Bob+The+Cowboy · · Score: 1

      Quick, start printing all the pr0n? ;o)

  3. Ummm by rehtonAesoohC · · Score: 1, Funny

    So what you're saying is that it may clog the tubes?

    Someone get a plumber, quick!

    1. Re:Ummm by Adriax · · Score: 5, Funny

      Call in Mr Stevens, he's unemployed and looking for work.

      --
      I don't suffer from insanity, I enjoy every minute of it!
    2. Re:Ummm by Anonymous Coward · · Score: 0

      He should be making license plates by now.

    3. Re:Ummm by LandDolphin · · Score: 3, Insightful

      He's just relaxing and waiting for Bush to Pardon him.

      --
      Spelling and Grammar errors have been added to this post for your enjoyment
    4. Re:Ummm by adpe · · Score: 1

      It's-a me..!

    5. Re:Ummm by R2.0 · · Score: 1

      Yeah - he got his travel itinerary from Mark Rich.

      --
      "As God is my witness, I thought turkeys could fly." A. Carlson
    6. Re:Ummm by Anonymous Coward · · Score: 0

      Maybe Joe the Plumber can help!

    7. Re:Ummm by Anonymous Coward · · Score: 0

      I'll call Luigi. (only because I don't have Mario's phone number)

    8. Re:Ummm by Anonymous Coward · · Score: 0

      The eighties called, they want Mario & Luigi back...

    9. Re:Ummm by Anonymous Coward · · Score: 0

      Let me call Joe the Plumber. He will unclog the tubes for us. :)

    10. Re:Ummm by akashk · · Score: 1

      Someone get a plumber, quick!

      A plumber? sure.. I know this guy called Joe.

    11. Re:Ummm by Aloisius · · Score: 1

      For the life of me I can't figure out why everyone jumps on Stevens for saying the Internet is a series of tubes especially since network service providers commonly refer to their service as "big pipe."

      Further, unless you're using a wireless service, technically speaking your internet service is delivered over a series of tubes. Well, if you ignore the fact that fiber optic cabling and copper cabling isn't really hollow...

      <blockquote>[...] They want to deliver vast amounts of information over the Internet. And again, the Internet is not something that you just dump something on. It's not a big truck. <b>It's a series of tubes.</b> And if you don't understand, those tubes can be filled and if they are filled, when you put your message in, it gets in line and it's going to be delayed by anyone that puts into that tube enormous amounts of material, enormous amounts of material.</blockquote>

      While Steven's waaaay oversimplified things, his description of networking queuing is essentially correct.

    12. Re:Ummm by Anonymous Coward · · Score: 0

      Isn't Mr Stevens dead?

    13. Re:Ummm by rtb61 · · Score: 1

      And you know the description of the real problem is just as simple. ISPs should simply stop selling something they don't fucking have. Stop over selling bandwidth, stop the deceit about the bandwidth they claim to be selling to you versus the bandwidth they actually have available to sell to you.

      More power to bit torrent to force the ISP's to either supply the bandwidth they claim to be selling and start telling the truth about what they are really selling to customers.

      --
      Chaos - everything, everywhere, everywhen
  4. fairness by seanadams.com · · Score: 5, Insightful

    If you're going to transfer files over UDP then you need to build some TCP-like protocol on top of it. The article doesn't say exactly how BT works in this respect, but he's probably right. There's no way that BT's protocol could be as sophisticated as TCP, given its 30+ years of development.

    Most people don't appreciate how amazingly well TCP's flow control works in terms of maximizing link utilization in a way that is fair to all network users. We really don't need is an arms race of new, greedier protocols.

    However, one thing to realize about P2P is that because there are often dozens of active TCP connections transmitting from one machine, fairness goes pretty much out the window anyway. An alternate protocol could conceivably improve on this by applying flow control to the aggregate throughput for the whole "bundle" of connections, rather than each connection individually. This would improve fairness and also increase efficiency because you wouldn't have a bunch of TCP streams individually trying to grow their windows, causing packet losses.

    1. Re:fairness by Ed+Avis · · Score: 5, Informative

      If you're going to transfer files over UDP then you need to build some TCP-like protocol on top of it.

      Not really. You would need that if you were transferring a file from one computer to another. But Bittorrent scrapes together little bits of file from lots of other computers. If a packet is lost here and there, that bit of file is naturally requested again, probably from a different machine. That's just a consequence of the way Bittorrent works.

      However, one thing to realize about P2P is that because there are often dozens of active TCP connections transmitting from one machine, fairness goes pretty much out the window anyway.

      There's no reason in principle for this to be the case; obviously, metering of bandwidth should be by subscriber according to money paid, not by some arbitrary and easily manipulated value like number of open TCP connections.

      --
      -- Ed Avis ed@membled.com
    2. Re:fairness by Man+On+Pink+Corner · · Score: 5, Interesting

      There's no way that BT's protocol could be as sophisticated as TCP, given its 30+ years of development. Most people don't appreciate how amazingly well TCP's flow control works in terms of maximizing link utilization in a way that is fair to all network users. We really don't need is an arms race of new, greedier protocols.

      TCP gets a lot of credit it doesn't deserve. It enforces bad design -- most client/server applications should be either stateless or session-based, rather than connection-oriented. Anything that even vaguely resembles a streaming application shouldn't even consider TCP. Finally, TCP's connection model is almost guaranteed to be suboptimal for any application that does require one.

      What are the odds that HTTP, FTP, SMTP, and BitTorrent will all work optimally over TCP? Slim to none, and none is still waiting for Nagle.

    3. Re:fairness by Anonymous Coward · · Score: 0

      MPLS Anyone (http://en.wikipedia.org/wiki/Multiprotocol_Label_Switching) ?

    4. Re:fairness by zappepcs · · Score: 4, Insightful

      That is addressing the problem from an ISP's point of view, or perhaps the "**AA's talking points for ISPs" point of view.

      If I pay for 10Mbps download speed, it should not matter to anyone how I use those bits. If you as my ISP cannot handle that traffic, you should NOT have sold it to me in the first place. Every time you throttle or shape my traffic, I want a rebate. It's that simple. I don't think we should have bailed out wall street and I don't think It's my responsibility to support an ISPs bad business model. That is what this problem is all about. Bad business decisions on the part of ISPs. They over sold their networks and now want a bailout. BS!

      If you want regulation, how's this: If you sold me 10Mbps download and can't provide it regardless of protocol, you have committed fraud and I'm allowed to sue. I don't want to hear about your problems, just provide what you sold me.

      If you sell me a parachute I expect it to work in every state, on any day of the week, and from any kind of airplane, no matter what clothes I'm wearing or not wearing. After you sold it to me, it's simply criminal to then say it only works if you are wearing green, or skydiving on a day of the week that begins with a T.

      If you don't want me to use BT, then give me a 50% discount on my bill.

    5. Re:fairness by HardCase · · Score: 4, Funny

      And all this time I thought that spam was going to cause the Internet to melt down. Maybe we need new terminology. Instead of "melt down", it should be "Global Internet Change".

    6. Re:fairness by seanadams.com · · Score: 3, Insightful

      Not really. You would need that if you were transferring a file from one computer to another. But Bittorrent scrapes together little bits of file from lots of other computers. If a packet is lost here and there, that bit of file is naturally requested again, probably from a different machine. That's just a consequence of the way Bittorrent works.

      That behavior needs to be driven by some timing and retry logic. Also, hosts need to determine how fast they can fire these UDP packets at each other. Those are the most basic fundamentals of transmitting bulk data over a packet network. You really would be reinventing some subset of TCP.

      obviously, metering of bandwidth should be by subscriber according to money paid, not by some arbitrary and easily manipulated value like number of open TCP connections.

      It's not just about metering. What about where many users share a connection to the internet, such as at a business or school? Or even in a household? What if there's a bottleneck caused by a malfunction out on the backbone? You can't have good performance in these situations unless users agree on "equally aggressive" protocols.

    7. Re:fairness by markov_chain · · Score: 1

      I suppose you have some other clever way to deal with congestion?

      --
      Tsunami -- You can't bring a good wave down!
    8. Re:fairness by Ummite · · Score: 1

      It's not because it's used since 30 years+ that TCP is so great. Does VHS was better than Beta? Making a home made TCP over UDP isn't especially complicated ; especially when you have no obligation to get packets in the right order, and that you can retry if you get a missed packet. I think the best of both world would be to use a FTP like scheme : one tcp channel to do control, and UDP packets for file content. If the TCP get throttled, this is not a big deal since there will be not so much data on it.

    9. Re:fairness by The+MAZZTer · · Score: 1

      UDP is simpler than TCP, so I don't see how switching to UDP would hurt the internet.

      Not really. You would need that if you were transferring a file from one computer to another. But Bittorrent scrapes together little bits of file from lots of other computers. If a packet is lost here and there, that bit of file is naturally requested again, probably from a different machine. That's just a consequence of the way Bittorrent works.

      If there is no compensation for lost UDP packets (TCP compensates by detecting and resending lost packets), the chunk (about 64kb IIRC) will not hash right and will need to be redownloaded, not just the packet (a packet can hold what 1-1.5kb? I think it varies from network to network, but TCP packets have a lot of metadata bundled and so can carry less data per packet... something like 512b IIRC).

      Of course lost packets don't occur as often as you might think, in my experience. I've made a program to query Valve game servers, and this uses UDP. While testing I don't recall noticing lost packets at all.

      And of course there's always the chance that uTorrent will compensate for lost packets itself anyway. Such an implementation would likely be lighter-weight than TCP anyway (otherwise why bother?) and have less metadata per packet, allowing for faster transfers (more data per packet).

    10. Re:fairness by seanadams.com · · Score: 3, Insightful

      If I pay for 10Mbps download speed, it should not matter to anyone how I use those bits. If you as my ISP cannot handle that traffic, you should NOT have sold it to me in the first place

      You have totally missed the point of my post! I wasn't even addressing ISP billing policy, I am talking about how to share a link. Maybe YOU have a dedicated 10Mbps link all to yourself, but not everyone is so lucky. Imagine a small business where 50 people are sharing a T1 line. For web browsing, this many users could all get decent performance, even if a handful of people are doing big downloads, provided they are all using TCP. But all it takes is one guy hammering the link at full throttle to ruin it for everyone else. For better or worse, the internet is designed on the assumption that applications play nicely in this regard.

    11. Re:fairness by IGnatius+T+Foobar · · Score: 1

      If you want regulation, how's this: If you sold me 10Mbps download and can't provide it regardless of protocol, you have committed fraud and I'm allowed to sue. I don't want to hear about your problems, just provide what you sold me.

      Better read that contract again. In all likelihood it very clearly said "Up to 10 Mbps." If you dig down into the fine print it probably also has some boilerplate about it being sold as an entertainment service, not an information service. Cable and phone companies have never been real ISP's.

      --
      Tired of FB/Google censorship? Visit UNCENSORED!
    12. Re:fairness by Man+On+Pink+Corner · · Score: 4, Interesting

      To say that TCP is optimal at dealing with congestion is to say that individual packets are always a good representation of the data blocks being sent and received at the application level, and that best thing that any application can do when expected data doesn't arrive is to wait on it to be retransmitted, with the network layer queuing up all subsequent intact packets.

      Once again, this behavior is guaranteed to be completely wrong for anything but toy command-line applications that fit on a single page in the back of a musty-smelling manual.

    13. Re:fairness by Adam+Hazzlebank · · Score: 4, Interesting

      Not really. You would need that if you were transferring a file from one computer to another. But Bittorrent scrapes together little bits of file from lots of other computers. If a packet is lost here and there, that bit of file is naturally requested again, probably from a different machine. That's just a consequence of the way Bittorrent works.

      That behavior needs to be driven by some timing and retry logic. Also, hosts need to determine how fast they can fire these UDP packets at each other. Those are the most basic fundamentals of transmitting bulk data over a packet network. You really would be reinventing some subset of TCP.

      I think what he's trying to say is the TCP connection often gets dropped completely, for example the host just goes offline, or is bogus and transmitting false data. Bittorrent needs to account for this anyway by re-requesting packets from the network, so they have implement the retry logic differently that TCP anyway.

    14. Re:fairness by Opportunist · · Score: 5, Insightful

      Not really, actually.

      TCP enforces and faciliates delivery certainty. You may be sure that a packet arrived. It gives you everything to make sure some packet arrives in time, if it's fragmented and arrives in the wrong order it's reassembled and all the other little bits that are quite useful when you're normally transfering data.

      This doesn't really apply to Bittorrent and the way it works. Bittorrent by its very nature transfers little parts of files. Parts in a size that can easily avoid fragmentation. Parts where it doesn't really matter whether they arrive at all. If they don't, the requesting machine will simply ask for it again. Maybe now, maybe later, maybe even from another source.

      Yes, TCP has its merits and sometimes they are even used sensibly. Don't make me start about all the cases where TCP is used without any reason because neither packet size matters nor certainty of delivery is a criterion, but it's just "easier". But BT can well work on UDP and even generate less overhead and thus actually less traffic than it does today.

      Face it. QoS, Netneutrality and traffic shaping or not: People will find a way around it. And when the choice is encryption and wrapping BT packets in even more overhead (because, say, the provider will only allow HTTP-Packets at full speed) or using UDP, it's a no brainer. For both sides.

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    15. Re:fairness by MasterOfMagic · · Score: 0

      The example you gave is not relevant in this case. On a typical DSL or Cable setup, the DSLAM or head-end is configured to limit the line speed of each subscriber. It would be like each port connected to the network connected to the T1 line being limited to 64kb/s. There's simply no way that any one user could saturate the connection in that case. Only if many people used their allotted bandwidth could the T1 uplink become saturated.

      So one person cannot "take more" than their allotted portion. They are taking their allotted portion but the uplink to the ISP is saturated. This is not the user's fault. This is the fault of the ISP overselling too much, and there is nothing that the user can do to fix this other than not use what he is paying for.

    16. Re:fairness by Kerelslied · · Score: 1

      I guess the day your 10 Mbps connection drops to 10 Kbps speeds, it will be within the service agreement. You can sue, but they don't want to hear about your problems as they provide you what you paid for.

    17. Re:fairness by M-RES · · Score: 1

      If you dig down into the fine print it probably also has some boilerplate about it being sold as an entertainment service, not an information service. Cable and phone companies have never been real ISP's.

      But for many people, information IS entertainment. ;)

    18. Re:fairness by rubycodez · · Score: 1

      nah, that's so 90s in thinking. A business can get a proper router that does traffic shaping or just blocks protocols. If one guy at your work is clogging up the tubes your networking admin is an idiot.

    19. Re:fairness by encoderer · · Score: 2, Interesting

      You're right. That's the real problem. ISPs are hacking vertically-- all BT traffic -- when they should be hacking horizontally:

      I support a greedy node algorithm. Everyone starts with their burstable line, and the more you utilize, your cap slowly lowers until you reach a guaranteed minimum bandwidth threshold.

      At the end of the day, greedy users will be greedy users. And if BT goes offline, they'll migrate to something else. And if I suck 100gb of crap off usenet in a month it's no different than 100gb of BT crap in terms of network stress.

      Burstable lines make sense. It's a concept as old as timeshare. But if somebody is constantly "bursting" they need a governor on their line.

    20. Re:fairness by Opportunist · · Score: 2, Insightful

      Easy. Be able to deal with the bandwidth or stop signing up customers 'til you can.

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    21. Re:fairness by nmg196 · · Score: 5, Informative

      Not really. You would need that if you were transferring a file from one computer to another. But Bittorrent scrapes together little bits of file from lots of other computers. If a packet is lost here and there, that bit of file is naturally requested again, probably from a different machine.

      No... you're getting confused between network packets (a kilobyte or two) and bittorrent's blocks (many kilobytes). Each bittorrent chunk is transferred using many network packets. If you're going to transfer those chunks using UDP, you need to sort out the packet order and do all the missing-packet checks and retries etc yourself. So you still DO need to build some kind of TCP-like protocol on top - even just for the error checking.

    22. Re:fairness by MikeBabcock · · Score: 1

      Assuming for a moment that BitTorrent sent individual chunks of files as single UDP packets, this wouldn't actually be true anymore.

      That would be massively inefficient, but the current protocol is too.

      For all my experience with QoS and firewalling, I still can't manage to keep my gaming sessions lag-free while downloading Fedora 10's DVD by BitTorrent (at any reasonable speed), but its fine using HTTP/FTP.

      --
      - Michael T. Babcock (Yes, I blog)
    23. Re:fairness by Wrath0fb0b · · Score: 4, Insightful

      If I pay for 10Mbps download speed

      No, you don't. A dedicated 10 Mbps link would run thousands of dollars a month (a T1, which is 1.5 each way, is ~$300 in the US) and most consumers can't swing that sort of dedicated line. Instead, you paid for a connection that is 10 Mbps maximum and you knew damn well that you would be sharing it with others in your neighborhood. How else could you rationalize paying only $60/month for faster-than-T1 level service?

      Pretending that you don't understand the difference between a dedicated line and a shared line is utterly unconvincing to me.

    24. Re:fairness by jandrese · · Score: 5, Insightful

      The problem is that TCP self regulates and throttles itself back in the face of network congestion. UDP does not, it just blasts packets out as fast as you can feed it. Without some sort of flow control, you could disproportionally hurt TCP flows (which are trying to be good and throttling themselves back when they hit a bottleneck) by your big ugly UDP stream.

      That said, the bottleneck for end users is typically the uplink on their last mile connection, so this probably won't bring the internet down or crash any ISPs, but it will make life worse for people sharing the connection.

      Fun fact: The original implementations of TCP did not have flow control (it was on a test network after all). It did not take long for it to become apparent that flow control is a necessary feature. A few network meltdowns made the case quite well.

      --

      I read the internet for the articles.
    25. Re:fairness by MasterOfMagic · · Score: 3, Insightful

      So, in other words, people complaining about BitTorrent users overutilizing the network should read their contract, see there's no minimum guarantee of service or line speed, and get stuffed instead of trying to bully other people into using the network in ways that would make life more convenient for them?

    26. Re:fairness by julian67 · · Score: 1

      That's all very reasonable but fails to state the other side of the equation, which is that you, and everybody else, *can* have and use that huge bandwidth all the time but the price is going to be massively higher than at present. ISPs work on contention ratios like banks work on debt ratios. When the ISPs find that the contention ratio is unworkable because a proportion of its customers render the model broken then the easiest course of action for them is to change the model. The most likely outcome is that we will simply pay for what we use, like we do with electricity, gas, fuel etc. This is how it works in Australia afaik. The "unlimited" model which started in the US and was adopted in Europe has probably reached the end of its workable life. I know that here in the UK the best ISPs do not offer these unsustainable "unlimited" plans. When you finally get sick of Virgin/Tiscali/Tesco/BT etc shaping your bandwidth into oblivion you migrate to a small ISP and pay for a 30GB peak time 300GB off peak monthly plan and then go to the broadband/ISP forums and announce how much better your new ISP is.....funny that....

    27. Re:fairness by Anonymous Coward · · Score: 0

      Bittorrent already checks for "lost" packets, because it verifies that they are authentics. Most bittorrent client also ban peers that constantly send "bad" data. It's actually heavier-weight than TCP, but using UDP removes some unnecessary redundancy.

    28. Re:fairness by Anonymous Coward · · Score: 0

      No, they sold you "up to 10 Mbps" service with absolutely no bandwidth guarantees. Even when they were advertising "unlimited" transfers they always mentioned this caveat both in the fine print of the commercials and in the terms of service when signing up.

      You'll never find guaranteed bandwidth except in commercial leased lines, for which you will pay a dear price. If you feel that it is your right to saturate your pipe at all times then feel free to purchase said service and use it to your hearts content. You could try to sue Comcast et al for advertising fraud but you won't succeed.

    29. Re:fairness by wift · · Score: 1

      Look at it this way. A company sells a service that can function under most normal circumstances much like cellular phone which has problems during a disaster. Everyone picks up the phone at the same time and the network grinds to a halt. Now let's say a new function will give everyone free calls if you leave it on all the time. So now we have a problem.

      --
      ....... Thus ends my attempt at wit or whatever
    30. Re:fairness by Anonymous Coward · · Score: 0

      Have you ever administrated a network before? It's a lot easier to handle a constant 10M/s over 5-6 tcp connections than it is to handle 10M/s of bittorrents 50+ connections, and udp will only complicate it further (essentially turning your download into an uncontrolled DDoS attack.)

      BT is AWFUL on the networks, and it isn't just a matter of overselling bandwidth, it's routing tables and router cpu utilization.

    31. Re:fairness by Conor+Turton · · Score: 0

      That is addressing the problem from an ISP's point of view, or perhaps the "**AA's talking points for ISPs" point of view.

      If I pay for 10Mbps download speed, it should not matter to anyone how I use those bits. If you as my ISP cannot handle that traffic, you should NOT have sold it to me in the first place. Every time you throttle or shape my traffic, I want a rebate. It's that simple.

      No problem. If you want a dedicated 10Mbps unrestricted service you can have it but you'll pay the full cost of that bandwidth supply which is $100's a month.

      --
      Conor "You're not married,you haven't got a girlfriend and you've never seen Star Trek? Good Lord!" - Patrick Stewart
    32. Re:fairness by Anonymous Coward · · Score: 0

      Easy. Be able to deal with the bandwidth or stop signing up customers 'til you can.

      Ah, yes, the "Layer-8 solution."

    33. Re:fairness by jandrese · · Score: 4, Insightful

      That's a pretty strong statement for something that works quite well in the real world. I'd argue that TCP works quite well for anything doing bulk data transfer given the constraints inherent in the system. TCP has no way of knowing for instance if packet loss is due to congestion or noisy links. It assumes the former because it is on the internet, but that's not always a good assumption (this is big on devices like mobile phones with web browsers). TCP is terrible for time sensitive data (streaming voice/video for instance), but that's why pretty much every streaming application uses UDP or something similar. Streaming applications can get away with that because they self regulate their transmit rate, whereas bulk data wants to fill up any available space in the pipe to get the data transferred as fast as possible. Slow start is a necessary evil in a world where you don't know what the link conditions are from the start and don't want to slam a bottlenecked router with a big opening dump of data.

      TCP stream oriented model is also a godsend for application developers. Networking is hard enough without having to build your own application state control systems (which is what would happen if you tried to make TCP stateless) for every single connection. It would be a nightmare.

      Those who don't understand TCP are doomed to reimplement it, badly.

      --

      I read the internet for the articles.
    34. Re:fairness by c1t1z3nk41n3 · · Score: 1

      Ok. You're right. And it doesn't matter. Remember they can change the terms of your contract at will. They'll just make using bit torrent against the TOS and then cut it off and there isn't shit you can do about it.

    35. Re:fairness by Anonymous Coward · · Score: 0

      Unfortunately our world doesn't work this way.

      IANAFE (...Financial Expert)
      Think of the basic Financial Industry. When you deposit your money in the bank, the bank w/ FDIC guarantees that your money will be available to you when you withdraw it. However, behind the scenes, the Bank actually takes your money and lends it out to your neighbors for mortgages, etc. It is about trust. You trust that your money is there at the bank. If everyone starts withdrawing all their money, that bank fails and the FDIC has to step in.

      IMO the Internet should work in a similar way. Albeit, the ISPs need to be more clear about the bandwidth you are paying for.

      On example is that the ISP should sell users "sustained bandwidth" plus an X MB of "burst bandwidth" per/hr or day.

      The ISP has to be required to maintain X amount of bandwidth free to sustain VOIP. Especially if Emergency 911-like traffic goes over that network.

    36. Re:fairness by Opportunist · · Score: 5, Insightful

      Then maybe they should be sold as such.

      Look, all I want is to get what I get sold. If a line is sold as a 10mbit line, I will expect it to be a 10mbit line.

      If I sell you a garage for 2 bucks a month, you might wonder but you will probably take the deal. Then you come around and notice that someone else is already standing in the space I sold you, and I tell you that you're allowed to use that space to park your car but only when it's free. Would you be happy? I guess not.

      People will expect to be able to use what you sell them. And some of them will even use it. They really want to use what they got allegedly sold! How dare they?

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    37. Re:fairness by Anonymous Coward · · Score: 0

      What are the odds that HTTP, FTP, SMTP, and BitTorrent will all work optimally over TCP? Slim to none, and none is still waiting for Nagle.

      So, phrasing this as something other than a flame, you would suggest that HTTP, FTP, etc. use UDP and then let each client application implement its own rate limiting, retransmission policy, and packet reordering? Or did you have some other exotic transport layer in mind to replace TCP?

    38. Re:fairness by klausboop · · Score: 1

      Wouldn't a router with QOS solve that issue?

      --
      Some of you already have those cute little shirts on that say disco sucks, right? That's not all that sucks.-Frank Zappa
    39. Re:fairness by zappepcs · · Score: 3, Interesting

      Wow, you got close to what I think is the solution. Every ISP can provide two virtual networks to each user. Where the edge of the ISP network sits; that point where end users are attached, it is possible to use routing to run BT traffic down one pipe and all else down another pipe. In this respect, BT traffic would not melt down the network or hog the connections of others in the neighborhood. If there is only 2.5GB/s available for BT et al, then only BT et al users suffer when it is full.

      OMG, network design 101. hmmmm if I were an ISP, I'd set that up and explain that is how the new service works. The new P2P network is limited in bandwidth and your neighbors are the ones to blame if it is clogged. Yes, this even applies to businesses, co-op networks, ISPs, the lot. It minimizes infrastructure upgrades, and provides service as perceived by the end user, not as shaped by central routing equipment. You might think of it as an HOV lane, to use a car analogy.

      Secondly, if networks were not oversold so much and under-designed so often, this would not be a problem. I really don't care how you slice it, this is a problem because of poor decision making by service providers. They wanted everyone's business (still do) but are not designing their networks to handle the traffic. When they build new roads these days, the build them so that extra lanes can be added in the future when needed. Why isn't that happening on ISP infrastructure?

    40. Re:fairness by 91degrees · · Score: 1

      That behavior needs to be driven by some timing and retry logic.

      I don't see why. You can usually wait quite some between retries without any negative impact since the connection will still be being used to download other pieces. BT might as well just assume that any pieces it hasn't received haven't even been requested.

      Also, hosts need to determine how fast they can fire these UDP packets at each other.

      Do they? I'm sure a request of data will be a single packet. Why not wait for a response before requesting another. Keeping network utilisation up just requires opening enough connections.

      I'm really not a networks guy so I may be missing something here.

    41. Re:fairness by anothy · · Score: 5, Insightful

      it's true that the protocol stack would need to have some method of regulating retransmission, but i think the GP's point is that it's already there, in the BT applications. sure, it's not at the layer we tend to think it belongs, but when you're dealing with untrusted sources (as anonymous seeders inherently are), you've got to do that work anyway.
      also, even if you ended up recreating a "subset" of TCP, that could still be fine. TCP is huge compared to UDP, and if you use UDP as a base for adding what you need, you can still come up with something much simpler than TCP; see, for example, RUDP. TCP's benefit is its ubiquity, but if you have the combination of a constrained enough environment and wide enough client distribution, that's less of a big deal. BT and uTorrent likely satisfy those requirements.

      --

      i speak for myself and those who like what i say.
    42. Re:fairness by Aladrin · · Score: 2, Informative

      Not true, actually. BitTorrent doesn't ask for data in packet-sized blocks. If a single packet is missing from the block, it doesn't (currently) have a way to ask for just that packet. You'd basically be re-implemented TCP to do that.

      --
      "If you make people think they're thinking, they'll love you; But if you really make them think, they'll hate you." - DM
    43. Re:fairness by Anonymous Coward · · Score: 0

      If people keep using the existing routers they have. Then yes this could be bad for the internet.

      What will happen is 'node management'. Nodes will be allocated a particular bandwidth at a particular moment. If they exceed that packets from that node are dropped. Fairness will become the routers problem. Instead of at the client level. You may be able to flood out your network segment. But the router will not let you go further than that... ISPs such as a cable company or phone companies with DSL could require smarts put into the node routers to throttle it right at the point going into their network. So you wouldnt even be able to flood the local segment you are on.

      Prioritization of a particular type of packet will be much more difficult but not impossible.

      It will become 'if there is room sure you can blast until you bleed'. 'if there isnt room well sorry I am dropping your packets you will have to send less from whatever applications you are running.'

      Another way is to wrap UDP packets into TCP packets coming out of the node routers. So UDP looks like '1 type' of TCP. Then the existing routers will just throttle it down like normal. Then you have another computer 'unbundle' and blast it along. This penalizes UDP bandwidth in favor of using a kludgy system.

    44. Re:fairness by Man+On+Pink+Corner · · Score: 4, Interesting

      TCP does work well, and certainly the axiom about those who don't understand TCP being condemned to reimplement it badly is a valid one. However, it is the wrong tool for many modern applications. If you're writing networking code and you find yourself fighting TCP's behavior, it's not necessarily your fault.

      The developers of BitTorrent have long since passed the level of play where they're better off using TCP/IP because "well, because that's what you're supposed to use." My objection was to the naive canonization of TCP as an all-purpose protocol that's somehow magically superior to any protocol that the application can implement on its own behalf.

      "Because it's the most router-friendly protocol" is also no excuse. Applications that aren't a good fit for TCP often abuse the protocol, e.g. by disabling Nagling and tinkering with other parameters in an effort to make it work more like, well, UDP.

      Those developers didn't reimplement TCP badly, but they might as well have, as their efforts are likely to have the same effect.

    45. Re:fairness by rikkards · · Score: 1

      There is one difference between Usenet and BT. How many open connections does Usenet use compared to Bittorrent? That in itself puts a load on the Router as it has to remember this.

    46. Re:fairness by Anonymous Coward · · Score: 0

      And if I suck 100gb of crap off usenet in a month it's no different than 100gb of BT crap in terms of network stress.
      seed pls

    47. Re:fairness by Belial6 · · Score: 4, Informative

      That is just not true. Telephone companies where very clear that you should go with them because you don't have to share a line. That was the benefit they claimed that DSL had over cable internet access.

    48. Re:fairness by Artifex · · Score: 4, Interesting

      Without some sort of flow control, you could disproportionally hurt TCP flows (which are trying to be good and throttling themselves back when they hit a bottleneck) by your big ugly UDP stream.

      Except that one of the cool things about UDP is that it doesn't have to get through, so your router can drop all it needs to if it starts saturating your bandwidth. UDP has no guarantee of reliability at all.

      I think going to UDP would be cool for another reason: there's not all the setup and teardown for connection. If 200 people each request the same block from me in a minute, do I really want to have to go through something like 'hi can I talk to you, what port should I use, hey here it comes, do you have it, ok, I'm done talking to you go away', or should I just shovel it out? If packets get dropped en route or mangled, do they not each already have enough hashing provided by the .torrent that should indicate they're bad, and to re-request?

      --
      Get off my launchpad!
    49. Re:fairness by melikamp · · Score: 1

      Mmmmmmm, musty smelling manuals....

    50. Re:fairness by AK+Marc · · Score: 3, Informative

      If I sell you a garage for 2 bucks a month, you might wonder but you will probably take the deal. Then you come around and notice that someone else is already standing in the space I sold you, and I tell you that you're allowed to use that space to park your car but only when it's free. Would you be happy? I guess not.

      All utilities use statistical averaging. It's not possible to allow for all users to be using 100% of what is available at the same time. Well, perhaps if the infrastruture of all utilities were completely redone it might be possible. For even 1000 people in close proximity to coordinate use of electricity, they could cause massive damage to the system from nothing other than just using what they had paid for.

      Phones everywhere in the US were useless on 9/11/2001. Where I worked, they had 2 T-1s for a little over 100 people. The T-1s were full. That's the first time that has ever happened. To have over 50% of people picking up the phone at the same time is unheard of. Sure, we could have bought a dedicated line for each person, but that's not what companies do. I live in Alaska. You have less than a 50% chance of getting a long distance line on Mother's Day. That's right, the entire state is busy. The cell phone systems crash around every large event I've ever been to. The Las Vegas Convention Center is the closest I've been to a large place that worked. It would pop up my voicemails quickly when the person was sent straight to voicemail. For other places that are much more seasonal or random in their use (like state fair grounds) I've seen horrible dial rates. Phone lines all over the US (and the world) were jammed when 9/11 happened, and people were unable to make calls because the utility wasn't able to provide. If there was something that caused similar unusual spikes in demand in any utility, it would crash. No utility designs for 100% utilization by everyone 100% of the time.

      The only way to get what you demand is to design all utilities to do that, and no one does. The only functional difference with Internet and the other utilities is that Internet is designed with more sharing. It's like when you buy a phone line, and you get a party line. Sure, you have a phone line, but you can't use it if your neighbor is on it. You had access for emergencies 100% of the time, and otherwise had to share nicely with others.

    51. Re:fairness by Ed+Avis · · Score: 4, Interesting

      Except that one of the cool things about UDP is that it doesn't have to get through, so your router can drop all it needs to if it starts saturating your bandwidth. UDP has no guarantee of reliability at all.

      You could make the opposite argument: the cool thing about TCP is it automatically retries and resends any dropped packets, so your router can drop all TCP traffic if it needs to.

      --
      -- Ed Avis ed@membled.com
    52. Re:fairness by cbiltcliffe · · Score: 2, Insightful

      It's not just about metering. What about where many users share a connection to the internet, such as at a business or school?

      Then the business or school should have usage policies. If they don't, it's not up to their ISP to regulate things for them.

      Or even in a household?

      Follow Russell Peters' advice. "White people. You need to beat your kids."

      What if there's a bottleneck caused by a malfunction out on the backbone?

      Then fix the damned backbone! Surely it takes less time to replace a screwed up router than to develop all these bandwidth restriction methods that only get circumvented anyway.

      --
      "City hall" in German is "Rathaus" Kinda explains a few things......
    53. Re:fairness by Pope · · Score: 1

      Look, all I want is to get what I get sold.

      Then you'd better go over every single line of the contract you agreed to when you signed up, as well as all subsequent updates that they sent out, and stop complaining over what the marketing copy said.

      --
      It doesn't mean much now, it's built for the future.
    54. Re:fairness by Ed+Avis · · Score: 1

      OK, fair enough. It would only be simple if a block were small enough to fit in a single UDP datagram. Still, perhaps this is what the uTorrent developers are doing?

      --
      -- Ed Avis ed@membled.com
    55. Re:fairness by poopdeville · · Score: 1

      How else could you rationalize paying only $60/month for faster-than-T1 level service?

      Poor upstream bandwidth, no guaranteed latency across the line, and no service level agreement. In any case, a digital subscription line isn't shared with your neighbors. The DSLAM is the bottleneck, and it can be alleviated the same way T-1 connected networks alleviate theirs: faster routers and more bandwidth into them on the WAN side.

      Also, DSL service isn't faster than T-1 service if you're not getting at least T-1 speed out of it. Right now, I am getting 50 kBps out of my DSL connection. A dedicated T-1 would give me four times that much.

      If my (hypothetical) bonded T-1 went down in the middle of the night before Black Friday, somebody would get an angry phone call, and it would be fixed in a few hours or else they would be sued for breaking their SLA. If my DSL line went down in the middle of the night, I wouldn't have anybody to turn to for help.

      --
      After all, I am strangely colored.
    56. Re:fairness by Courageous · · Score: 1

      Then maybe they should be sold as such.

      It is, and you knew that when you bought it. Pretending, somehow, that you were innocently unaware of that fact is a total lie.

      C//

    57. Re:fairness by Man+On+Pink+Corner · · Score: 2, Insightful

      So, phrasing this as something other than a flame, you would suggest that HTTP, FTP, etc. use UDP and then let each client application implement its own rate limiting

      Because my application is better at knowing how to adapt to a given amount of bandwidth than TCP/IP is.

      retransmission policy

      Because non-trivial applications often have better ways to deal with packet loss than TCP's acknowledgement/retransmission mechanism. ...and packet reordering?

      It often makes more sense to let your application deal with this. BitTorrent's a great example, as are most action games that do client-side prediction. Likewise, the way streaming applications have to work in the presence of TCP's reordering is by grinding to a halt waiting for the retransmission. Gee, thanks, TCP. Instead of a 16-millisecond glitch, I get a 2000-millisecond dropout.

      Or did you have some other exotic transport layer in mind to replace TCP

      No; I believe that dictating those details to application developers is counterproductive. As long as the implementation is competent, datagram transport with application-specific reliable delivery is almost always a win for everybody concerned -- clients, servers, routers. And if the implementation is incompetent, TCP can only do so much to help.

    58. Re:fairness by Anonymous Coward · · Score: 0

      No, you don't. A dedicated 10 Mbps link would run thousands of dollars a month (a T1, which is 1.5 each way, is ~$300 in the US)

      Really? Cogent claims $4 per megabit.

      http://www.cogentco.com/us/contact_sales.php

      Now Cogent has many other issues, but that is a different story.

    59. Re:fairness by DragonWriter · · Score: 1

      If you're going to transfer files over UDP then you need to build some TCP-like protocol on top of it.

      Well, no, you don't. You need an application level protocol, which only needs to be "TCP-like" if you are building a connection-oriented application. This might make sense for the client-tracker portion of a bittorent-like setup, but for the main file transfer I don't see why you'd need something much like TCP at all.

    60. Re:fairness by DreadPiratePizz · · Score: 1

      f you sell me a parachute I expect it to work in every state, on any day of the week, and from any kind of airplane, no matter what clothes I'm wearing or not wearing. After you sold it to me, it's simply criminal to then say it only works if you are wearing green, or skydiving on a day of the week that begins with a T

      Interestingly enough, parachute manufacturers do not guarantee their parachutes will work at all. You buy it as-is-you-take-the-risk-jumping-it. Otherwise, the would get sued when a malfunction occurs. That's why I believe the fine print says 'UP TO' 10Mbps from the cable company, and why they haven't been sued for false advertising.

    61. Re:fairness by Lonewolf666 · · Score: 1

      Other posters have already pointed out that the BT protocol has slightly different design goals compared to TCP.

      But in case some "homegrown" TCP is desired, I'd like to add that the developers could always pull an Apple (or Microsoft with regard to networking) and adapt some mature TCP stack from a BSD-licensed operating system. There you get the 30+ years of development ;-)

      --
      C - the footgun of programming languages
    62. Re:fairness by Anonymous Coward · · Score: 0

      I don't think downloading a torrent of the latest James Bond movie would help at all!!

    63. Re:fairness by Tragedy4u · · Score: 1

      Most routers and switches support some form of Layer 2 flow-control for environments where the TCP window scaling protocols aren't used. If Layer 2 flow-control is enabled congestion is less likely with the use of RNR frames.

    64. Re:fairness by NorQue · · Score: 1

      TBH, I don't have any idea of the inner workings of TCP and UDP, but what you described pretty much describes the status quo without that uTorrent UDP change already. If you have one client unregulated up and downloading and he's on a torrent that maximises both it effectively slows the net for everyone else and him to a crawl. You already have to throttle your own bandwidth to be able to use your own network while your using any P2P app. About 80% of actual up/download speed has proven to be a good number in the past.

      That's why I call FUD on that article, too, TBH.

    65. Re:fairness by Anonymous Coward · · Score: 0

      And there is the real issue: the telcos have not updated their tubes as they were supposed to do. We gave them significant tax advantages in the 1996 Telecom bill to do exactly that... down to the last mile.

      Every single time I see a telco complaining about bandwidth issues, I think about the lack of capitalization they've done over the last 14 years... even in the face of being paid to do exactly that by the gov't.

    66. Re:fairness by AndrewNeo · · Score: 1

      But my internet is up to 6Mb/s, with a minimum of 3Mb/s. I assume it's sold this way due to DSL being DSL, but it doesn't change the fact that there is an explicitly written 3Mb/s minimum.
      I'd expect to get that minimum consistently, if nothing else. I'm not sure about contract text, but it's not some floating 0-6Mb/s range.

    67. Re:fairness by Anonymous Coward · · Score: 0

      you're kidding right?

      I don't think fairness is one of bt's primary motivating factors when it comes to bandwidth. That and BT is not at the same layer as tcp or udp so their protocol would not be in compitition. It's still reliant on the underlying protocol. That is the advantage to switch to UDP, less ability to do traffic shaping. Just means the market will adapt.

    68. Re:fairness by Anonymous Coward · · Score: 0

      Your point does not apply to the internet, it applies to a local area network. This should be taken care of with network and computer usage policies. It would be trivial to find any source of UDP packets with a little traffic analysis. I think its fair to say that I can't torrent at work and that I would get in trouble if I did. I should be working. However it is unfair for a ISP to say that I can only use certain protocols on my internet connection at full speed.

    69. Re:fairness by gsslay · · Score: 1

      That is addressing the problem from an ISP's point of view

      I see it more a case of addressing the problem from the point of view of reality.

      No-one cares what fantasy arrangement you personally entered into with your ISP. You're both living in a dream world. Reality is bandwidth is a limited resource. Reality is that demand grows at a faster rate than supply until the buffers are hit and it's everyone for themselves.

      If your ISP sold you magic beans that turned out to be just beans, what do you think is the sensible, mature reaction to the problem? Learn the hard way that there is no such thing as magic beans, or continue to stamp your feet demanding what you paid for?

    70. Re:fairness by H0p313ss · · Score: 1

      There's no way that BT's protocol could be as sophisticated as TCP, given its 30+ years of development.

      Most people don't appreciate how amazingly well TCP's flow control works in terms of maximizing link utilization in a way that is fair to all network users. We really don't need is an arms race of new, greedier protocols.

      All you've done here is demonstrate how little you know about UDP and TCP and bittorrent. I have always been rather uncomfortable with at TCP based implementation since UDP should be far more efficient for this application. TCP is just a sign of laziness on the part of the implementor.

      --
      XML is a known as a key material required to create SMD: Software of Mass Destruction
    71. Re:fairness by jandrese · · Score: 5, Insightful

      That misses the point. UDP senders don't know when they're flooding the connection, so they just keep doing it. A TCP stream would back off to try to be fair, but your UDP stream is just going to keep on blasting at full speed.

      Think of it this way, you have a congested router that has 1mbps of available bandwidth. Normally you have 5 TCP streams sharing it at 200kbps each. Everybody is happy. Now you replace one of the TCP streams with your UDP sender which is configured to transmit at 800kbps. It will continue to pound the router with 800kbps worth of traffic while the TCP streams all throttle back to 50kbps. Now you're not playing fair, and there's nothing the other TCP guys can do about it because they're all trying to play fair still.

      --

      I read the internet for the articles.
    72. Re:fairness by TheThiefMaster · · Score: 1

      If I pay for 10Mbps download speed, it should not matter to anyone how I use those bits.

      Stop stop stop! You're not paying for "10Mbps download speed", you're paying for one of:
      "Up To" 10Mbps (may never get this due to the line or may be traffic shaped, but even if you get it you'll never have it 24/7 continuously)
      a 10Mbps line, but not 10Mbps download speed

      If you want to be able to download at 10Mbps 24/7 then pay for that! Take your business away from the ISPs that advertise "10Mbps unlimited" and actually deliver one of the above two. If your ISP does advertise "up to 10Mbps" (even if it's "unlimited") and they shape you, you're getting exactly what was advertised. Stop complaining.

    73. Re:fairness by rbarreira · · Score: 1

      You could, but then you'd be talking a different kind of coolness. Your point is that TCP makes it easier to program, the other separate point is that UDP doesn't require reliability which is good in some way.

      --

      The AACS key is NOT 0xF606EEFD628B1CA427BEA93A9CA9773F
    74. Re:fairness by Anonymous Coward · · Score: 0

      TCP self regulates and throttles itself back in the face of network congestion. UDP does not

      That's precisely why ISPs who absolutely do not want to upgrade their networks need to work on account level fairness mechanisms instead of content based throttling. Nothing beyond the IP header should ever matter in a queuing or routing decision. None of that information is reliable anyway, as can be seen here. Application developers can use all of the TCP algorithms with other protocol designations, encrypt the whole packets or split one stream into several TCP connections (hello download managers...).

    75. Re:fairness by rawler · · Score: 1

      Do they? I'm sure a request of data will be a single packet. Why not wait for a response before requesting another. Keeping network utilisation up just requires opening enough connections.

      This would mean hooorible performance in smaller swarms, especially with bad latency.

    76. Re:fairness by TheRaven64 · · Score: 1

      I wrote a bittorrent-like protocol that used UDP for my third-year undergrad project. It used exactly the same congestion-control algorithm as TCP, which took about five lines of code to implement.

      --
      I am TheRaven on Soylent News
    77. Re:fairness by Artifex · · Score: 4, Insightful

      Except that one of the cool things about UDP is that it doesn't have to get through, so your router can drop all it needs to if it starts saturating your bandwidth. UDP has no guarantee of reliability at all.

      You could make the opposite argument: the cool thing about TCP is it automatically retries and resends any dropped packets, so your router can drop all TCP traffic if it needs to.

      In the scenario where multiple hosts have the data I want, I'd rather the software decide, not the router or my PC's stack. Like you said elsewhere, it can just grab from another host. So I'd rather have the protocol with the lower overhead for my pipes/router/stack. If torrent software supports requesting the same block from multiple sources at the same time, this is even more important, because my stack will keep trying to get a good version of a mangled packet even if I really don't need it any more because someone else sent the block, whereas with UDP, the software knows it has it and won't bother.

      --
      Get off my launchpad!
    78. Re:fairness by CarpetShark · · Score: 1

      Get your facts straight. He's talking about a 10mpbs download... most likely over high-latency, home-targetted DSL, you're talking about a synchronous, low-latency leased line that probably comes with anal SLAs etc. A 10Mbps download speed costs NOTHING LIKE thousands of dollars per month. My 2Mbps download speed costs about £35/month. Yes, it's unlimited. REALLY. Yes, they have cheaper deals for 2Mbps speed, but limited downloads.

    79. Re:fairness by jthill · · Score: 1

      Nobody said TCP is optimal, just that it's had 30 years of tweaking based on real-world experience.

      --
      As always, all IMO. Insert "I think" everywhere grammatically possible.
    80. Re:fairness by Artifex · · Score: 1

      That misses the point. UDP senders don't know when they're flooding the connection, so they just keep doing it. A TCP stream would back off to try to be fair, but your UDP stream is just going to keep on blasting at full speed.

      Think of it this way, you have a congested router that has 1mbps of available bandwidth. Normally you have 5 TCP streams sharing it at 200kbps each. Everybody is happy. Now you replace one of the TCP streams with your UDP sender which is configured to transmit at 800kbps. It will continue to pound the router with 800kbps worth of traffic while the TCP streams all throttle back to 50kbps. Now you're not playing fair, and there's nothing the other TCP guys can do about it because they're all trying to play fair still.

      Ok, that's a good argument. :)

      --
      Get off my launchpad!
    81. Re:fairness by Pentium100 · · Score: 1

      What router has to remember all of my connections? My NAT router? OK, I can use one that has enough RAM. The ISPs? Why should it? If I am not sitting behind my ISPs NAT (and have an IP address that is publicly routable), no other router has to remember my connections, just that my IP is "this way".

    82. Re:fairness by wiremind · · Score: 1

      If you sold me 10Mbps download and can't provide it regardless of protocol, you have committed fraud ...

      Thankyou!!! That is exactly it.

    83. Re:fairness by Anonymous Coward · · Score: 0

      Pffttt... You probably want people to switch to the gold standard, so we can't spend money that doesn't exist, too. Or feel credit companies shouldn't be able to run at 30 to 1 leverage ratios.

      Everyone won't need all their bandwidth at the same time, just like everyone won't default on their mortgage at the same time.

      Why do you hate progress?

    84. Re:fairness by ShatteredArm · · Score: 5, Funny

      Clearly whoever invented TCP did not properly understand game theory.

    85. Re:fairness by yabos · · Score: 2

      TCP flow control scales back when it doesn't receive the ACK from the destination. They could easily do this over UDP by implementing their own ACK with a return UDP packet.

    86. Re:fairness by sexconker · · Score: 1

      TCPs flow control is trash.

      Bittorrent does automatic hash checking, any failed pieces will be re-requested. This may happen more with UDP, sure, but if it's a problem you can just break the torrent into smaller chunks instead of the default.

      UDP would not be exclusively used. Any self-respecting client would use UDP in addition to TCP to improve bandwidth in throttled scenarios. If a chunk keeps failing a hash check via UDP, switch over to TCP, just as we switch peers when a TCP chunk from one peer keeps failing a hash check.

      TCP windowing is an issue on the upload end, not the download end, in the vast majority of cases. Most Bittorrent clients by default limit the number of upload slots to only a handful, with an option to automatically add more if there's room in your upstream bandwidth. TCP windowing is also very fast when you're talking about something the size of a typical torrent chunk (connections are per chunk).

    87. Re:fairness by Anonymous Coward · · Score: 0

      obviously you never heard about the difference between a SLA and Best-efforts practices.

      Best effort means the provider will do what seems the best in the interest of everybody. (it's that vague).

      SLA gives warranties about how much defects in the service are tolerable. They include RTT, downtime and sometimes bandwidth

    88. Re:fairness by blhack · · Score: 2, Insightful

      If 200 people each request the same block from me in a minute, do I really want to have to go through something like 'hi can I talk to you, what port should I use, hey here it comes, do you have it, ok, I'm done talking to you go away',

      You NEED to do that for the same reason that you need to wait in line at the check stand when getting groceries. There NEEDS to be flow control, otherwise, with everybody just trying to bum-rush the checkout, nobody will be able to get anything done.

      Yes, this might work out okay if one person decides that they are sick of waiting and shove a few ladies out of the way. When pushing and shoving become the norm, it stops.

      This is NOT a good idea.
      Honestly, pirates, I get it; you're idealistic. Unfortunately, you're not thinking about the long term affects of doing this. Demonstrating that pirates (or people distributing linux ISOs or whatever...the media, and the ISPs see EVERYBODY that uses BT as a pirate) are willing to just shit all over the tubes in order to get what they makes a pretty good case for allowing the ISPs to start putting roadblocks in the way. It brings in legislation, more control, less freedom.

      Seriously, guys, short-term win, long-term epic failure if this goes-large scale.

      --
      NewslilySocial News. No lolcats allowed.
    89. Re:fairness by watice · · Score: 1

      It's 2008, (almost 09!!) wouldn't QOS solve these kind of issues?

    90. Re:fairness by IamTheRealMike · · Score: 2, Insightful

      The internet isn't a circuit-switched network - when you buy a 10Mbit/sec connection even assuming it's dedicated (which nobody at home can afford), you don't buy a dedicated 10Mbit/sec circuit to every possible website. You buy 10Mbit/sec to your nearest switching center, and from then on out your packets might traverse all kinds of links, some more congested than others.

      The rules of TCP ensure all the computers on the network work together to ensure that if one link bottlenecks they all back off a bit and everybody can still get through at reduced speed, instead of seeing massive packet loss, which just hoses everyone. UDP doesn't have that, and it works OK as long as UDP doesn't make up the bulk of data flows on any given link which has always been the case. The uTorrent change might break this system, and that's what the author is concerned about.

      BTW, I'd note that the author of TFA is a contributor to the WiFi and Ethernet specs, so I'd think he knows what he's talking about.

    91. Re:fairness by markov_chain · · Score: 1

      However, it is the wrong tool for many modern applications.

      Yeah, sure, anything not doing bulk or stream oriented transfers. So what?

      My objection was to the naive canonization of TCP as an all-purpose protocol that's somehow magically superior to any protocol that the application can implement on its own behalf.

      Point taken. By the same token, I defend TCP because there are good reasons for its seemingly inefficient design. There are 30 years of experience and academic research on TCP design. When evaluating any replacement protocol you have to ask yourself, would the Internet suffer a congestion meltdown if the *vast majority* of traffic switched to it? I can't take any TCP complaints seriously until I have a good answer to this question.

      The developers of BitTorrent have long since passed the level of play where they're better off using TCP/IP

      Why? BitTorrent is arguably exactly the application that should be using TCP--it does bulk, delay-insensitive transfers in enough quantity to cause congestion. Why in the world would you have BitTorrent use something else when it will turn out reimplementing TCP?

      --
      Tsunami -- You can't bring a good wave down!
    92. Re:fairness by yahooglesoft · · Score: 1

      You pay your ISP for download speeds UP TO 10mbps. that UP TO is the key part. They never say that you will always get 10mbps. If you want 10mbps all the time then it's going to cost you hundreds a month. If you want them to guarantee you will get a certain speed then fine. They'll just sell you a 500kbps line for the same price. You get 500kbps all the time, and you can blast it with UDP as much as you want. ISPs like many other companies oversell. This is because 99% of the time there will be no problem and it would cost WAY too much to make sure that bandwidth is there 100% of the time. You're a home user, you don't need 100% uptime with 100% of your available bandwidth. If you do, then as I said earlier shell out for a business account.

    93. Re:fairness by Zephyrmation · · Score: 1

      I agree that people want to use what you sell them, but they did sell you "up to" 10mb. It's your problem since you agreed to their contract, even if it wasn't exactly what you wanted.

      However, it may be the case that they mislead you by offering a "10mb line", when the fine print really said "up to". This strategy is despicable - it's akin to selling someone a car and suggesting that the car will always go 70mph when you want it to. Sure, you may reach a speed of 70mph on some days, but most of the time you'll be limited by traffic, weather, and the speed limit. It's simply irresponsible to suggest that a car/connection will always go a certain speed when the average speed is far lower. I would be extremely happy if companies started selling their connections on the basis of average speed as opposed to maximum speed.

    94. Re:fairness by AcidPenguin9873 · · Score: 1

      From what I can tell, you're arguing against "statistical multiplexing", which unfortunately for you is how the entire Internet is built. Obviously ISPs and backbones have to constantly improve capacity, but that doesn't mean they need to provide every end user with their maximum last-mile bandwidth *all the time*. That's called a circuit-switched network, and we got away from it in the late 80s for efficiency reasons.

      Besides, 10Mbps is the maximum bandwidth that your link can deliver, but it says nothing about other traffic on your ISP's network let alone the rest of the Internet. If your ISP doesn't throttle you somewhere, but the route to and from your data is congested, you're effectively going to get throttled elsewhere. Who are you going to bitch at then? The content provider? The backbone providers?

      You were sold a 10Mbps link which is statistically multiplexed *many* places upstream with other links, not a 10Mbps dedicated circuit to every server on the Internet.

    95. Re:fairness by jmorris42 · · Score: 1

      > And if I suck 100gb of crap off usenet in a month it's no different than 100gb of BT crap in terms of network stress.

      That wasn't true until quite recently when most ISPs dropped most of UseNet. Traffic to and from one of your ISPs servers puts far less load on the Internet than throwing traffic around the world on BT. So what did the ISPs do? Dropped most of Usenet under political pressure. So screw em.

      --
      Democrat delenda est
    96. Re:fairness by Anonymous Coward · · Score: 0

      If you don't want me to use BT, then give me a 50% discount on my bill.

      You already have this option: get a T1 installed instead of cheap consumer DSL. You can use all the bandwidth all the time, no problem.

      What's that, you don't want to pay $1,000 per month? Well if you'll agree not to use BT or more than a gigabyte of throughput a day, you can have a discount on your bill of not just 50%, but 95%!

    97. Re:fairness by Anonymous Coward · · Score: 0

      The power company sold you a 200A service to your home, but not every house on the street can use it.

      I have 4 toilets in my home each with a 3-inch wate pipe, but only 1 output pipe of 4-inch from the house, do you think i want to flush them all @ the same time?

      Internet is provided as an oversubscribed service. You have a peak rate to 10Mbps. The average rate is something more like 100Kbps. Use your peak whenever you want. But don't expect peak == average. You can buy such a non-oversubscribed line if u wish. cost it out.

    98. Re:fairness by Jose · · Score: 0, Redundant

      If I sell you a garage for 2 bucks a month, you might wonder but you will probably take the deal. Then you come around and notice that someone else is already standing in the space I sold you, and I tell you that you're allowed to use that space to park your car but only when it's free. Would you be happy? I guess not.

      thats a great way to highlight how you should read the contract you sign when purchasing a service. Apparently, the garage you are operating is only for people to stand in, not park cars. I tells ya, I would be some ticked if I rolled into your garage with this huge smile on face because I just found the best deal in the world..monthly parking for 2 bucks!! wooohoo! then as I go to pull into my new spot.. I see that there is a guy standing there. I honk the horn and try to wave him threw..but he just stays..sipping on his coffee and shoots me a dirty look. so I honk again..and he yells 'this spot is taken..find another!'.

      (I realize that you probably meant that there is another car parked in my brand new spot..but I just couldn't get that picture out of my head. a guy just standing in a car-sized space in garage. haha)

      --
      The basic sleazeware produced in a drunken fury by a bunch of UCBerkeley grad students was still the core of BIND. --PV
    99. Re:fairness by Grashnak · · Score: 1

      For all of the ridiculous people saying "I paid for 10Mbp download and I should get it", I have to ask, have you ever, even once, downloaded anything at 10Mbp? No, you haven't. I have had 10Mbp service for ages, and it is nice and fast, but I have never approached 10Mbp at any time.

      Engage your brains please.

      --
      Life needs more saving throws.
    100. Re:fairness by Bill_the_Engineer · · Score: 1

      Except that one of the cool things about UDP is that it doesn't have to get through, so your router can drop all it needs to if it starts saturating your bandwidth. UDP has no guarantee of reliability at all.

      Not taking TCP's congestion mitigation in consideration, a TCP packet has an equal chance of being dropped as a UDP packet. The difference being that TCP uses ACKs to see what was the last packet that was successfully received and retransmits as necessary, while UDP leaves the reliability issues up to the application. In most cases where UDP is chosen as the protocol, the application cares more about trying to deliver the current packet than trying to redeliver old packets. The effect being that UDP packets are allowed to quietly die during the delivery attempt.

      I think going to UDP would be cool for another reason: there's not all the setup and teardown for connection.

      This is where you "hit the nail on the head" so to speak. The lack of connection overhead makes UDP appealing on the application level and why I use UDP a lot in my control programs. However this low overhead comes at a price of flow control. So the issue isn't really how reliable the packet transmission is (remember bittorrent does an adequate job of guarantying that the file makes it to its destination complete, in-order, and without errors), instead it's about congestion control which TCP provides and bittorrent apparently doesn't do well enough.

      --
      These comments are my own and do not necessarily reflect the views or opinions of my employer or colleagues...
    101. Re:fairness by Anonymous Coward · · Score: 0

      It's pretty clear that you don't have the faintest idea how bittorrent works...

    102. Re:fairness by TooMuchToDo · · Score: 1

      Doesn't Verizon offer fiber to the home for ~$60/month and they give you 35Mb/s up and down?

    103. Re:fairness by Bill_the_Engineer · · Score: 1

      I think you may need to reacquaint yourself with RFC 2581. There are actually four methods being used to mitigate congestion.

      Thinking only in terms of retransmitting failed packets is probably why most UDP based applications, using some developer's idea of a better way to send data, actually cause more network congestion.

      --
      These comments are my own and do not necessarily reflect the views or opinions of my employer or colleagues...
    104. Re:fairness by Anonymous Coward · · Score: 0

      To bad when you bought 10Mbps for your broadband package you really bought "up to" 10Mbps.

    105. Re:fairness by mpe · · Score: 1

      That wasn't true until quite recently when most ISPs dropped most of UseNet. Traffic to and from one of your ISPs servers puts far less load on the Internet than throwing traffic around the world on BT. So what did the ISPs do? Dropped most of Usenet under political pressure. So screw em.

      It's probably rather more complex than that since it's likely to depend on a lot of factors, including the actual structure of the networks and exactly where Bit Torrent is able to find peers.

    106. Re:fairness by quarterbuck · · Score: 1

      Many Video/Audio applications run on UDP, so does SNMP (after all these years still used for monitoring network devices). If the router and network starts dropping UDP packets, the effect on non-P2P users is going to be worse than them throttling TCP packets.
      For some reason, the author of the article seems to think (or imply) that Audio/Video runs on TCP - It mostly does not (or should not).
      I think the solution would be for the ISP's to use "pay for data" schemes rather than "pay for TCP connections".

      --
      http://slashdot.org/submission/1062723/Cheap-mobile-data-plan?art_pos=2
    107. Re:fairness by darkfire5252 · · Score: 1

      Imagine a small business where 50 people are sharing a T1 line. For web browsing, this many users could all get decent performance, even if a handful of people are doing big downloads, provided they are all using TCP. But all it takes is one guy hammering the link at full throttle to ruin it for everyone else.

      That analogy broke down right after the words 'small business.' Any private shared internet connection has someone who is in charge of it. If the employee is hammering the router with BT traffic, they need to be disciplined or cut off from the internet. My ISP should ensure that I get the bandwidth I paid for; their IT guy should ensure that their private network works acceptably.

    108. Re:fairness by Puls4r · · Score: 1

      This argument strikes me as incredibly naive. If the ISP's were to guarantee that you had that bandwidth, they would have to massively over-structure themselves to ensure that they always had enough bandwidth if every single one of their users logged on at once.That is equivalent to engineering a road with the expectation of every single person in that area getting on it all at once. It would be a collosal waste of money and time. In addition, they have no way of guaranteeing your bandwidth once you get off their network. Bandwidth is priced based on shared - equipment. The ISP uses some model to predict usage and scales their hardware to that model. If they didn't do that, your current prices wouldn't be anything like what you're looking at today. Throttling is just fine. However, it needs to be throttled evenly - everyone's bandwidth needs to drop by a given amount. You can't (or shouldn't at least) single out a given user because he's using a certain program. However, I think if you investigate your terms of service you will find that they reserve the right to handle this any way they see fit. After all, they ARE a business, and they don't HAVE to do business with you. The internet is not some right.

    109. Re:fairness by Golddess · · Score: 1

      Except you did still share a line, it's just that the point at which it split off to individual users was either further up or further down. It's been a few years so I forget which exactly.

      --
      "I'm not sure I like the fugnutish tone you used in your post!" -RogL (608926)-
    110. Re:fairness by Bill_the_Engineer · · Score: 2, Informative

      Telephone companies where very clear that you should go with them because you don't have to share a line.

      Marketing half-truth. True you don't share the connection with the ISP with any other customer (thank goodness, the connection is crappy enough), however once it is in the PBX you share the available bandwidth with others in your neighborhood.

      So the only difference between cable and telephone (besides the transmission medium) is the point where sharing occurs (cable trunk vs. PBX).

      --
      These comments are my own and do not necessarily reflect the views or opinions of my employer or colleagues...
    111. Re:fairness by Anonymous Coward · · Score: 0

      at the same time it is unrealistic to assume they can provide you an unlimited amount of connection at 10 mbps. I understand that its BS that they sold it to you in the first place and I am not even about to argue that.

      What needs to happen is ISPs need to do their billing on the 95% rule. You take the top 5% of traffic in the billing period and average it and charge to how many mbits or kbits are in the average. This way when their networks get way overused it becomes a good thing for them as the only thing they will regret was not building a better network connection out to your location. Everybody wins, and those that dont use their connection too much don't pay as much.

    112. Re:fairness by mpe · · Score: 1

      All utilities use statistical averaging. It's not possible to allow for all users to be using 100% of what is available at the same time. Well, perhaps if the infrastruture of all utilities were completely redone it might be possible. For even 1000 people in close proximity to coordinate use of electricity, they could cause massive damage to the system from nothing other than just using what they had paid for.

      However it really isn't the customer's fault if the supplier gets their sums wrong. Anyway electricity supply is rather different from telecommunications, generating capacity can be turned on and off using both predictive models and monitoring of actual demand.

      Phones everywhere in the US were useless on 9/11/2001. Where I worked, they had 2 T-1s for a little over 100 people. The T-1s were full. That's the first time that has ever happened.

      Has this happened since?

      To have over 50% of people picking up the phone at the same time is unheard of. Sure, we could have bought a dedicated line for each person, but that's not what companies do. I live in Alaska. You have less than a 50% chance of getting a long distance line on Mother's Day.

      So long as this dosn't happen that frequently then customers won't be too upset. Especially if there's an obvious reason why this is happening. However if people experienced this every few days, especially at random, they'd be demanding their money back.

    113. Re:fairness by compro01 · · Score: 1

      The difference being is that it is being oversold to the point where your "disaster" scenario is happening on a regular basis.

      --
      upon the advice of my lawyer, i have no sig at this time
    114. Re:fairness by zappepcs · · Score: 1

      Perfect. This description works well for telephones, but even telcos increase capacity to handle increasing call volumes. When the argument that the service I pay for is 'up to 10Mbps' and not 10Mbps 100% of the time, I will ask you this: Should I expect that only 25% of my voice calls will get through some times, or that only 25% of my words will get sent to the other end? Or should I expect that every time I pick up the phone and dial, it will go through the network to the distant end. Did phone companies bitch to Congress because people were staying on their dial-up lines 24/7?

      No matter what you counter with, the problem is still that ISPs over-sold and poorly designed their network infrastructure.

      You can argue that 'oh, P2P is bad and UDP P2P will kill the network' but when it's all said and done, if you make P2P illegal all those HTTP and FTP downloads (and probably other protocols will be implemented) are still going to suck the life out of a poorly designed and over-sold networks.

      While you are at it, please explain how in the fuck large ISPs intend to provide triple-play and quadruple-play services if their network infrastructure can't handle current Internet bandwidth requirements? Perhaps this is where the money that might be used for expanding capacity is going? Can't build out for customers

    115. Re:fairness by compro01 · · Score: 1

      Obvious difference being that this system is working fine in many other countries and I fail to see their ISPs wailing about the "intertubes melting", despite having far higher bandwidth provided to customers which actually take advantage of said bandwidth.

      --
      upon the advice of my lawyer, i have no sig at this time
    116. Re:fairness by Khyber · · Score: 1

      "UDP senders don't know when they're flooding the connection, so they just keep doing it"

      Well, in all fairness, the little uplink light on my router would go absolutely nuts if I had a UDP stream (Oh, say, like a Camfrog Video Chat) happening. So I'm sure I'd notice fairly quickly.

      --
      Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
    117. Re:fairness by Raenex · · Score: 1

      Applications that aren't a good fit for TCP often abuse the protocol, e.g. by disabling Nagling and tinkering with other parameters in an effort to make it work more like, well, UDP.

      People disable Nagle because it's a common source of performance problems because of ACK delays.

    118. Re:fairness by T.E.D. · · Score: 1

      Each bittorrent chunk is transferred using many network packets. If you're going to transfer those chunks using UDP, you need to sort out the packet order and do all the missing-packet checks and retries etc yourself.

      Not nessecarily. You could just let the packets fragment. That gives you 64K to work with.

      The problem there of course is that if there is a bad (or missing) fragment is that the entire datagram (all fragments) get thrown away, where TCP would just ditch the one bad packet. Net result is even more traffic.

      Still, they could get around this by defining the "bittorrent chunk" size to be 1.5k (UDP payload size). Everything else would probably work fine.

      In many ways, UDP is probably more appropriate for a situation where the information is naturally distributed like this. Bittorrent *already* has to deal with assembling all the pieces of the file from out of order discrete transmissions. Individual connections aren't all that important to maintain as there are plenty of other servers out there. So all the overhead of TCP maintaining connection and packet integrity really isn't buying Bittorrent much.

    119. Re:fairness by Man+On+Pink+Corner · · Score: 1

      I'm obviously not going to write a treatise on RFC 2581 in a Slashdot comment. :-P Suffice it to say that the decision to employ most of those methods -- slow start, congestion avoidance, fast retransmit and fast recovery -- belongs in the app because it simply cannot be optimally implemented by a content-agnostic layer. (If your network depends on well-defined slow start behavior... well, that's a shame, isn't it. Light up some more fiber and send Cisco some more bucks.)

      And yes, most of that RFC discusses how, when, and how often to naively retransmit data that the application probably doesn't care about anymore.

    120. Re:fairness by ACMENEWSLLC · · Score: 1

      This is actually cool from the aspect that if they implement it well, they can bypass the entire poking holes in firewall's issue. Are you behind a really restrictive motel firewall? Doesn't matter.

      Take a look at how Skype does it;
      http://www.heise-online.co.uk/security/How-Skype-Co-get-round-firewalls--/features/82481

      Basically they can bypass the firewall's restrictions on incoming connections by fooling the firewall into thinking it's already established a UDP connection to a computer for which it really hasn't.

      This works because of the way firewall's handle UDP. Switching P2P to UDP would be excellent for those of us who don't like teared Internet speeds.

    121. Re:fairness by mybecq · · Score: 1

      It enforces bad design -- most client/server applications should be either stateless or session-based, rather than connection-oriented

      Don't blame the transport layer for not including session layer functionality (because it shouldn't).

      Anything that even vaguely resembles a streaming application shouldn't even consider TCP.

      And I suppose you carry all your water from the well in buckets.

      If you meant "real-time streaming", then you should have said that; none of the protocols you listed are even close.

    122. Re:fairness by powerlord · · Score: 1

      Still, they could get around this by defining the "bittorrent chunk" size to be 1.5k (UDP payload size). Everything else would probably work fine.

      They'd lose some space for the "necessary" header. At the very least they'd need to reserve enough bytes to toss in a block number, a length and a checksum of some sort.

      They could probably compact things a bit by arbitrarily deciding:

      1) we'll ask for "block X - Y from user Z" so that at any given time given the source IP tied to the file name, you have a limited # of outstanding blocks (so you don't need your block number space to be unique for the whole system.

      2) instead of TCPs Send/Ack they could implement a "RETRANS" message that stated the blocks missing X time after the last block from a given host was received.

      You're right, the lack of TCPs complexity might be better suited, since BitTorrent isn't really tied to a specific connection, but if it isn't done correctly, there are lots of places this could come back to bite you in the but (since some of the error correction and retransmission pieces DO need to be re-implemented).

      --
      This space for rent. All reasonable inquiries will be entertained at proprietors discretion.
    123. Re:fairness by powerlord · · Score: 1

      Now you're not playing fair, and there's nothing the other TCP guys can do about it because they're all trying to play fair still.

      No, there isn't, and if it really DOES effect people, then more ISPs are going to try to switch to a pricing model (and tiered pricing), which is going to kill slow down a lot of P2P users.

      Alternatively, the ISPs are going to start disconnecting people who don't play nicely. Okay, the courts say we can't filter their traffic based on application? Fine, cut their service.

      --
      This space for rent. All reasonable inquiries will be entertained at proprietors discretion.
    124. Re:fairness by AK+Marc · · Score: 1

      Anyway electricity supply is rather different from telecommunications, generating capacity can be turned on and off using both predictive models and monitoring of actual demand.

      Electrical generation has an upper bound. Turning anything down is a cost savings (and technical requirement) and not related to capacity of the system. The capacity is fixed, just like water, phone, and Internet.

      Has this happened since?

      Yes. Why? Are you going to dismiss the reality that all other utilities run out of capacity as well? Because every utility has run out of capacity at some point. And, they will again. The Internet is no different, other than running out of capacity is less urgent of a problem.

      So long as this dosn't happen that frequently then customers won't be too upset. Especially if there's an obvious reason why this is happening. However if people experienced this every few days, especially at random, they'd be demanding their money back.

      Unless they were used to it. The wired phones were built with great reliability in mind. Why? Well, one reason was that the more they spent, the more profit they made, so they spent all they were able to justify. But cell phones are a different story. They have dropped calls. I seem to have more calls that go straight to voicemail than most. I have blocked calls (outgoing calls that don't dial), and all sorts of problems. They claim they are "phone service" just like my landline. However, the service is not the same. People put up with it and even expect it. Why shouldn't they also have a service expectation with Internet where you may get high speeds, but that you shouldn't always expect them unless you pay extra for business, dedicated, or other extra-priced service?

    125. Re:fairness by powerlord · · Score: 1

      And all this time I thought that spam was going to cause the Internet to melt down. Maybe we need new terminology. Instead of "melt down", it should be "Global Internet Change".

      True ... "Change" would be better, since some of the Internet won't "Melt Down", it will "Freeze".

      --
      This space for rent. All reasonable inquiries will be entertained at proprietors discretion.
    126. Re:fairness by Belial6 · · Score: 2, Insightful

      You know this, and I know this, but the OP claimed that the other person "knew damn well" that they were using a shared line. The telephone companies sold DSL as a dedicated line, and thus the argument of "dedicated lines cost way more" and "you knew damn well that it was a shared line" hold no water.

    127. Re:fairness by AcidPenguin9873 · · Score: 1

      I don't know how to say this differently. You're arguing for a circuit-switched 10Mbps network. (Your telco/analog phone argument uses...what do you know...circuit switched links). The Internet gives you a statistically-multiplexed 10Mbps network, which works great most of the time. The only reason you ever get anywhere near 10Mbps is because all the subscribers' traffic can be statistically multiplexed over backbone links which can't handle anywhere near the maximum bandwidth of all the pipes they feed. But you still get 10Mbps most of the time, which is why they can sell it to you at 10Mbps and charge you for it.

      Every subscriber using 10Mbps all the time (not 56k all the time as in your dial-up example) would break the network, and bumping up capacity to handle full 10Mbps at this point is too expensive. As for your triple play argument: 1) VOIP is low bandwidth. 2) Television is, multicast, mostly unidirectional, they're already moving to switched digital video because they're running out of bandwidth and can't compete with satellite for HD services.

    128. Re:fairness by Inda · · Score: 1

      I use exactly 30 connections on usenet. 20 would do. A few sites are saying I need 250 connections on BT. It's a massive difference.

      --
      This post contains benzene, nitrosamines, formaldehyde and hydrogen cyanide.
    129. Re:fairness by Belial6 · · Score: 0, Redundant

      You know this, and I know this, but the OP claimed that the other person "knew damn well" that they were using a shared line. The telephone companies sold DSL as a dedicated line, and thus the argument of "dedicated lines cost way more" and "you knew damn well that it was a shared line" is invalid.

    130. Re:fairness by legirons · · Score: 1

      The problem is that TCP self regulates and throttles itself back in the face of network congestion. UDP does not, it just blasts packets out as fast as you can feed it. Without some sort of flow control, you could disproportionally hurt TCP flows (which are trying to be good and throttling themselves back when they hit a bottleneck) by your big ugly UDP stream.

      Maybe now the ISPs will realise the consequences of interfering with network protocols. (it was originally the ISPs which sabotaged the polite flow-controlled TCP with fraudulent RST packets, thus abandoning any expectation of fairness or standards-compliance between them and their customers)

    131. Re:fairness by BronsCon · · Score: 1

      Service level agreement. If my T1 goes down for an hour, I don't pay that month. That's in my contract.

      If I can make it go down for an hour 4 our of every 5 months, I'm paying $60/mo for that T1. Why would I do that, though, when I can have a steady, stable line 24x7?

      Bandwidth is, in reality, very cheap. I consult for a hosting company, the owner of which I have known for many years before the company existed. My company and his are very tightly integrated and I know what bandwidth costs.

      Service quality and reliability are what costs. One of the datacenters housing their servers offers, amongst other connectivity options, 100mbit unmetered bandwidth for $50/mo with no SLA, 100mbit unmetered bandwidth for $150/mo with a 99.9% uptime SLA, and 100mbit unmetered bandwidth for $300/mo with a zero-downtime SLA.

      Know where that DC makes the most money? Honestly, the $150 option, although most of their customer base, according to them directly, are using the $50 and $300 options.

      For $300/mo, if their server can't see the net just once during a month, they pay only $150. If there's another incident any other day that month, they don't pay for bandwidth AT ALL. Anyone care to guess how many "incidents" are reported by those customers each month? Right. more than two.

      Only the too-broke-for-cheap-coke customers choose the $50 option. Why? Because it's all they can afford. When they pay.

      So, now, you have the majority of users finding ways to not pay, or to pay substantially less.

      Then, they have the $150 option. In a 28-day billing cycle, 99.9% uptime means 67m12s of downtime is allowed. That allows for a LOT of service interruption, at minimal expense to both the DC and the client. It's very hard, short of complete failure to pay the bill, to weasel out of paying that unless the DC majorly fucks up. Thus, though only roughly 1/4 of their customers (considering only the 100mbit unmetered bandwidth customers) use that option, roughly 1/2 the income generated by their 100mbit unmetered options comes from an option with a less than average cost.

      Who would have thought, people are willing to pay for reasonable service, less willing to pay for lower quality service, and more apt to find ways around paying for absurd levels of service?

      The cost of that T1 is all service. Maybe $1 of that is bandwidth. Period.

      That puts a 10Mbit symmetrical connection with no SLA at, let's see... $1 / 1.54Mbps = $0.649350649/Mbps. $3.25 * 10Mbps = $6.49. That's the true bandwidth cost of a 10Mbit symmetrical line.

      Let's figure for a 10/1 line real quick. Oh, halve that figure (downstream only is 10Mbps) and add 65 cents (upstream is 1Mbps). so $3.90 for a typical residential 10mbit line. That leaves plenty for infrastructure improvements, on top of payroll, maintenance and other business costs, allowing for a bit of profit, as well, after my $59.95 monthly payment.

      That holds true for the datacenter, as well. $64.94 is the base cost of a symmetrical 100Mbps line for them. That's a $14.94 loss on the $50/mo customers, until you realize that these customers, having no SLA, are using pooled bandwidth, enough to support 75% of what is sold. Now, the DC's cost is closer to $48.70 for each line. That leaves only $1.30 over bandwidth cost, leaving less than nothing after other expenses.

      The $300/mo plan costs the DC $64.94 per customer. If 75% of those customers weasel out of paying (that's close to accurate last time I spoke with them), they're averaging $75/mo per customer. That's only $10.06 over cost, leaving very little after other expenses.

      The $150/mo plan costs the DC the same $64.94 per customer that the $300/mo plan costs. Very few customers (less than 1%) see enough downtime to have their bandwidth costs waived. We'll be fair and call it 1%. They're still averaging $83.56 per customer after cost.

      See where this is going? Fewer people are willing to pay for an SLA, though a well-balanced SLA is benificial to both the customer and the provider

      --
      APK quotes people (including myself) without context and should not be trusted. Just thought you should know.
    132. Re:fairness by bit01 · · Score: 1

      Because my application is better at knowing how to adapt to a given amount of bandwidth than TCP/IP is.

      No it isn't. You are implicitly assuming your application is running in isolation, unfortunately a common naive programmer mistake.

      All running applications using the link together know better than TCP/IP how to allocate bandwidth but no one application does. Most of your complaints about TCP/IP are due to the intrinsic problem of getting different applications with no knowledge of each other to cooperate, not TCP/IP as such.

      To put it another way: TCP/IP's algorithm for bandwidth sharing can never be optimal because it doesn't have the high level knowledge that the application does, but then, neither does each application.

      ---

      WGA. Guilty until proven innocent. For millions. Again and again.

    133. Re:fairness by BronsCon · · Score: 1

      The difference here is that these utilities are designed to provide for average, even moderately above average, usage.

      ISPs, on the other hand, are complaining about this average usage, moderately above average usage be damned.

      Nobody's asking for 100% of the internet bandwidth (as per your using all the electricity example), just 100% of the bandwidth they were sold (whether what they were billed for it is enough to pay for it is a matter to be dealt with by the ISP's accountants). If I have 100 amp service to my home, I damned well better be able to draw 100 amps from it. If I plug in and turn on enough appliances to draw 101 amps (forget branch circuits for a moment, this is hypothetical) and something doesn't work, it had damned well better be because the main breaker has tripped and not because the electric company can't provide the 100 amp service they are selling me.

      We'll also ignore the fact that, with most utilities, you are billed for what you use because it is simple and straightforward to meter and control your usage.

      This doesn't apply to bandwidth. Period.

      --
      APK quotes people (including myself) without context and should not be trusted. Just thought you should know.
    134. Re:fairness by bit01 · · Score: 1

      ... and stop complaining over what the marketing copy said.

      No, if the marketing copy was dishonest he has every right to complain. A lot of marketing parasites like to pretend they're allowed to commit fraud. No actually, they're not.

      ---

      "Advertising supported" just means you're paying twice over, once in time to watch/avoid the ad and twice in the increased price of the product to pay for the ad.

    135. Re:fairness by Ungrounded+Lightning · · Score: 1

      Each bittorrent chunk is transferred using many network packets. If you're going to transfer those chunks using UDP, you need to sort out the packet order and do all the missing-packet checks and retries etc yourself. So you still DO need to build some kind of TCP-like protocol on top - even just for the error checking.

      But TCP implementations are public, while UDP just provides access to the underlying unreliable IP transport layer. So implementers can trivially clone whatever TCP functionality they want (including ALL OF IT) into the data portion of UDP packets. Then they can cut out what they don't need, adjust the tuning to play as fair or UNfair as they want (or even extend the fairness over multiple psdueo-TCP connections), add games to disguise the nature of the connection, etc.

      --
      Bantam Dominique roosters crow a four-note song. Once you've heard it as "Happy BIRTHday" you can't NOT hear it that way
    136. Re:fairness by swillden · · Score: 1

      Why? BitTorrent is arguably exactly the application that should be using TCP--it does bulk, delay-insensitive transfers in enough quantity to cause congestion. Why in the world would you have BitTorrent use something else when it will turn out reimplementing TCP?

      Because TCP is well-designed for bulk, delay-insensitive, point-to-point, in-order transfers. It's design doesn't consider a situation where the data is available from any of many hosts on the network. Bittorrent clients have to implement logic to work around this limitation of TCP, to decide when to give up on a peer that's non-responsive or slow and re-request from somewhere else. Also, TCP assumes that in-order delivery is important and its whole flow control architecture is designed around facilitation of that goal, as well as minimization of per-session state. Bittorrent doesn't care at all about packet order, and runs on peers with gigabytes of main memory, so removing those constraints opens up the opportunities for much more efficient congestion control.

      For example, rather than a window, Bittorrent clients should regulate traffic flow with an un-ACKed packet limit, which should change in size in roughly the same way that window sizes change (slow start and all), but shouldn't care at all about what position in the (nonexistent) "stream" those un-ACKed packets come from.

      Bottom line: Bittorrent only needs a portion of what TCP provides, and a portion of TCP's design works against it. Therefore, there's a strong argument for using UDP and implementing the necessary flow control mechanisms on top of that. And it's completely inaccurate to say that Bittorrent UDP-based implementations will be starting from zero, without the benefit of 30 years of TCP tuning experience. The fact is that network congestion control is much better understood than it was when TCP was designed, and most of those TCP lessons can and will be applied.

      --
      Note to ACs: I usually delete AC replies without reading them. If you want to talk to me, log in.
    137. Re:fairness by Anonymous Coward · · Score: 0

      That is just not true. Telephone companies where very clear that you should go with them because you don't have to share a line. That was the benefit they claimed that DSL had over cable internet access.

      Once again, don't believe anything that comes out of a marketing department.

      What they meant was, since a DSL line is a single line from the customer premise to the head-end, they call it a single line.
      With cable, the ISP runs a line to what is called a node, which then combines them to run back to the head-end.

      Couple of things here-
      First, the DSL lines have a distance limit. This usually ends up being roughly the same as the span from a cable customer house to node. This is why you see high-speed cable much faster and further from the head office than with DSL.
      Second, what happens to your DSL line when it reaches the headquarters? That's right, it gets bundled onto some type of shared data line.

      So really there is no difference to the end user- both services will hit a chokepoint, and if the ISP does not properly support their infrastructure you will share bandwidth at the chokepoint.

      Now you can buy a dedicated line. This means that you get a reserved amount of bandwidth- and it doesn't matter if it's cable/dsl/fiber, the ISP is reserving that much bandwidth just for you.

      If you really want to have guaranteed 100% unmolested internet traffic, get your own dedicated T1 or fiber line. Have fun trying to find someone to sell you a 5x5mbps dedicated line for under $100 a month- most areas you'll be paying at least a grand, in more rural areas it'll be 3 or 4 thousand at least if you can even get it built.

      It's all about the fine print- your service was sold as UP TO xxxx mbps MAXIMUM . While somewhat deceptive, it's no more so than the credit card companies offering you "up to $5,000 credit line" and only actually giving you $300 worth.

      It still does not excuse the overselling of bandwidth. Basically it's like the ISP saying "hey, buy a ticket to the concert & we'll let you bring in UP TO 50 extra people" and then only letting you bring in 2 or 3 people because they are out of room.
      The solution is two part- first of all, instead of assuming that each user will only "bring 1 friend" they need to realize that "concerts" are more popular & expect most people to "bring 10 or 12". They also need to update their pricing structures. Bandwidth caps are ok, but users should be able to pick a flexible plan that will give them a good transfer rate. If someone wants to pay for uncapped, sell it- but don't sell too much uncapped service, and expect uncapped users to be filling most of that pipe.

    138. Re:fairness by Kalriath · · Score: 1

      Contrary to popular belief, not every ISP did this. A lot of them simply said "meh, pretty much what we expected". My own ISP just set rules saying "we'll QoS your P2P connections during peak time if you're on an unmetered data plan, and just leave them alone if you're paying by the GB".

      Besides, what will really happen is that every ISP is going to install Layer 7 QoS hardware, and they'll just chomp BT UDP packets too.

      --
      For a site about things like basic rights, Slashdot users sure do like to censor "dissent".
    139. Re:fairness by Alarash · · Score: 1

      You can put UDP on a lower QoS priority than TCP. You can even make it so that 'fair' UDP traffic (VoIP, RTSP, etc..) is not impacted by this. The only thing preventing this are ISP not willing to spend millions of dollars on upgrading their core networks to manage this, and also because it would be complex to configure. They could also increase their own bandwidth - the technology exists, it's just a matter of adding more 10G ports in the mix. Or even upgrade to 40G ports. I wouldn't count on that since carriers and operators and content providers just barely moved to 10G cores.

      It's also worth mentionning that UDP has a much smaller overhead than TCP. In one UDP packet you can send more data than using a TCP packet. In theory it would then take less time to download a file, so in theory you would have less concurrent downloads on Internet. The bandwidth usage could be more "bursty" instead of longer, steady phases. But that's from one user perspective, I'm not sure about the effects on a large scale - besides that you would have more goodput for the same throughput.

    140. Re:fairness by jonaskoelker · · Score: 3, Informative

      But BT can well work on UDP and even generate less overhead and thus actually less traffic than it does today.

      Only if it adds its own layer of TCPness on top.

      Here's the deal. You have one gigabyte of data to download. It's been split into one megabyte chunks, and you know the sha1 hash of every 1-meg chunk.

      You go ask a peer for a 1-meg chunk. You get 1024 little 1k-chunks in return. There are 1024! permutations of them. Please put them in the right order.

      You could, you know, number them. If you want men outside the middle to not be able to spoof a connection from you, you need to start numbering from a random place, and tell the other endpoint from where you start your numbering.

      Presumably, you want to make outgoing connections to several peers at the same time. Hmm... I know, let's number each of the connections, and send the number to the receiving end.

      Boy, this sounds a lot like port and sequence numbers...

      If you do a 20-byte hash (say, sha1) of every 1k block, you end up with a 1-to-50 reduction. For a 1G torrent, the .torrent file is 20 meg. Presumably you could use a somewhat smaller hash function for each packet and then use a bigger hash for a chunk of packets...

      I'm not saying it can't be done. But I don't see what compelling features UDP offers that you can't get almost as effectively with TCP. Care to enlighten me?

    141. Re:fairness by djcapelis · · Score: 1

      No, the size of the block is determined by the torrent, not by an individual client. You need to map individual blocks to series of UDP datagrams and determine which one it is you're getting. It's certainly doable and not terribly bad and you save a lot of overhead from TCP, but the only thing you get is consistent sorting with that scheme. You have to generally build at least a couple features of TCP on top of UDP whenever you use it.

      --
      I touch computers in naughty places
    142. Re:fairness by Man+On+Pink+Corner · · Score: 1

      All running applications using the link together know better than TCP/IP how to allocate bandwidth but no one application does.

      Gee. <scratches head> If only there were a way for multiple clients to optimize their traffic patterns on a cooperative basis. Something like, perhaps, a network of some sort.

      It could be made out of, like, tubes.

    143. Re:fairness by windex82 · · Score: 1

      No, you don't. A dedicated 10 Mbps link would run thousands of dollars a month (a T1, which is 1.5 each way, is ~$300 in the US) and most consumers can't swing that sort of dedicated line. Instead, you paid for a connection that is 10 Mbps maximum and you knew damn well that you would be sharing it with others in your neighborhood. How else could you rationalize paying only $60/month for faster-than-T1 level service?

      Pretending that you don't understand the difference between a dedicated line and a shared line is utterly unconvincing to me.

      You've never talked to anyone outside your field about anything regarding the internet have you?

    144. Re:fairness by Man+On+Pink+Corner · · Score: 1

      Don't blame the transport layer for not including session layer functionality (because it shouldn't).

      I'm blaming it for including too much of that functionality, in the form of stateful connections.

      And I suppose you carry all your water from the well in buckets.

      Well, you're already in a state of sin when you treat a packet-switched network like a circuit-switched one. :-P

    145. Re:fairness by Firethorn · · Score: 1

      Just what I was thinking - how difficult would it be to develop the capacity to transfer sub-chunks, each sub-chunk capable of fitting in a single UDP packet?

      I think I've noticed something at least a little like this with Azureus.

      Using larger sections for overall data integrity checks(with checksums in the torrent file) is fine, all you need to impliment is the ability to request and recieve sub-sections.

      --
      I don't read AC A human right
    146. Re:fairness by windex82 · · Score: 1

      At home (NW Indiana) I have 16mbit most of my downloads run their course at around 25 (not bursting sustained through 4-8GB downloads from news.giganews.com)

      Our backup wireless connection at work is 6mbit and I more-often-than-not (hopefully a grammar nazi can educate me as to when you're supposed to hyphenate a phrase) get ~13 from it.

      I had to upgrade to the SSL account at giganews because comcast was throttling usenet connections as well. Even though my speeds for most things are great and above average it still pisses me off to no end when something is throttled. Why is it OK for me to saturate the connection with one protocol but not the other?

      (In my case I'm speaking about Usenet. Not sure why I'm even here I despise bit torrent and wish it would just go away... )

    147. Re:fairness by Bill_the_Engineer · · Score: 1

      So true. However the ISP favorite two words are "up to". As in experience data rate up to 6mbps. Technically this makes the range of valid values from 0 to 6mbps.

      Damn those weasel words...

      --
      These comments are my own and do not necessarily reflect the views or opinions of my employer or colleagues...
    148. Re:fairness by windex82 · · Score: 1

      Yes. Why? Are you going to dismiss the reality that all other utilities run out of capacity as well? Because every utility has run out of capacity at some point. And, they will again. The Internet is no different, other than running out of capacity is less urgent of a problem.

      Because if it has happened since perhaps part of the original problem was that there weren't enough resources to begin with. If its continuing to happen perhaps its time to invest in more resources? Will you do as the ISP's have done and wait till you have maxed out your capacity several times a day then come up with an over elaborate line sharing plan for those at your office or will you increase capacity?

      I'm betting on option 2, but the ISP's seem to have adopted option 1 while continuing to sell! sell! sell!

    149. Re:fairness by Anonymous Coward · · Score: 0

      Correct me if I'm wrong, but I thought what you were paying for in a T1 is the SLA, and fully symmetric bandwidth.

    150. Re:fairness by Anonymous Coward · · Score: 0

      And you confuse network datagrams with UDP packets. UDP packets can be up to nearly 64k (minus a little header information). UDP packets are split up into datagrams (fragmented) depending on the actual network technologies used (usually the 48 bytes used for ATM cells, really) and re-assembled. Then a checksum is calculated and if any of the datagrams were missing or damaged, the entire UDP packets is discarded.

      Often, one designs apps using UDP to use a packet size of a little less than 1500 bytes so the entire UDP packet, including IP information, fits into one 1536 byte ethernet datagram, which improves performance on LANs. This is actually quite arbitrary (cf. the ATM example), and IP takes care of splitting packets and reassembling. Actually, this is one of the points where IPv4 and IPv6 differ; on IPv4 splitting is taken care of on all intermediate hops whereas IPv6 requires that the endpoints take care of fragmentation. IPv6 requires that it is possible to transmit datagrams with a certain size (I think it's 1536 bytes, but I'm too lazy to look it up).

      Concerning error-checking: IPv4 has IP-level checksums, UDPv4 and UDPv6 has check-sums (check-summing is removed from IPv6 because all layers above has check-sums).

    151. Re:fairness by jandrese · · Score: 2, Insightful

      If ISPs started setting the QoS bits to favor voice traffic and send Bittorrent into the lowest priority queue, I guarantee that it won't take long for a BitTorrent client to start disguising itself as voice traffic.

      Setting and honoring QoS bits won't help IMHO. The biggest problem is that they're not honored on the internet at large, so they'll basically only work for your organization, and won't work at all at keeping your users from clogging the last mile uplinks unless you make every single home router smart enough to set and honor the bits on their own. DSL and Fiber should be ok (although it would likely require upgrade of a LOT of COs), but Cable and Wireless are hosed since they're shared at the last mile.

      Also, people seem to think that having Bittorrent work at the packet level is somehow a bad thing, which seems crazy to me since that's how the internet works. It would be a bad idea to plop an 8k UDP packet on the wire (or whatever your BT block size is) and expect it to make it through the network intact (IP fragmentation is going to murder your data transfer if you're congested anywhere, since losing any fragment will cause the stack to drop your whole packet on the floor).

      I'm also not sold on implementing your own flow control in BT over UDP (it's not as easy as it looks) just because you don't want to incur the queuing penalty to reorder packets (which on the internet is not typically a problem anyway!). People may not like the 3-way handshake, but it's extremely useful for preventing you from spewing data a host that no longer exists. Frankly, TCP is pretty good at bulk data transfer and that's exactly what BT is doing (granted, the data is chunked up, but you're still sending it in bulk to and from many hosts).

      It's such a shame Multicast doesn't work on the internet. This is one area where it could really do some good.

      --

      I read the internet for the articles.
    152. Re:fairness by vux984 · · Score: 1

      Nobody's asking for 100% of the internet bandwidth (as per your using all the electricity example), just 100% of the bandwidth they were sold (whether what they were billed for it is enough to pay for it is a matter to be dealt with by the ISP's accountants).

      You weren't sold a 24x7 10Mbps line. You might think you were, and you might have a valid argument that the ISP was a bit deceptive about what they sold you, but you weren't sold a 24x7 10Mbps line.

      You were sold access to a line that can do 10Mbps in bursts, that you have 24x7 access to.

      That's not the same as a line that can do 10Mbps 24x7.

      If you'd like one of those, you can get a quarter T3, they run around $5000/month.

      We'll also ignore the fact that, with most utilities, you are billed for what you use because it is simple and straightforward to meter and control your usage. This doesn't apply to bandwidth. Period.

      It is very simple and straightforward to meter and control your bandwidth usage. Up until relatively recently it wasn't really much of a problem. We used to have 'unlimited water service' for a low flat annual rate, but as the population grew and the demand on the supply increased, they've been gradually raising the price and adding metering to the system. This will happen with bandwidth too.

      Soon enough you'll be paying for "10GB at 10Mbps and unlimited at 1MBps with SmartBurst(tm) service" and a thousand variations on the theme. And yes, unlimited at 40Mbps will be available... for $18000/mo. And the prices may drop if technology advances capacity faster than demand increases.

      Indeed this is precisely why we're in the mess we're in... the shift from dial-up to dsl/cable was such a boost to capacity that for a while, they really could offer unlimited data... few users would even try to max it out, and most of the internet itself was a just low res images and text, so the average user really couldn't use 'too much'. So, 10 years later we have torrents and youtube and netflix and hula and the capacity hasn't really increased to keep up... so ISPs are starting to add caps, throttle, and so on.

    153. Re:fairness by Cramer · · Score: 1

      ... or the network admin is the guy clogging the tubes :-)

    154. Re:fairness by arthurp · · Score: 1
      I think that a UDP bulk transfer protocol would be cool for a very different reason: Multicast

      Wouldn't it be cool if a seeder could queue up lists of people who want a specific small hunk of a block and then send it out to all at once using multicast? It seems like that could actually have a pretty big band-width advantage over TCP. It would be hard to design. Since it would need to implement traffic shaping and all that, but I think it could actually produce a net reduction in bandwidth usage especially at the seed.

      In fact it might be able to allow a single seed to appear to upload at many times its real bandwidth.

      -Arthur

    155. Re:fairness by wiremind · · Score: 1

      I've purchased a business account guaranteeing 3Mbps Down, 1Mbps Up. And I get those speeds easily, all the time. Often, i'll even go over that. But when i've wanted to use the bandwidth, that base amount 3/1 is ALWAYS available.

    156. Re:fairness by Cramer · · Score: 1

      Is that throughput (i.e. beyond the ISP) or just the DSL sync rate? My DSL contract says the same sort of thing... up to X Mbps (sync), speed beyond the ISP is not covered.

      (Even with the expensive DS3 at the office, SLAs do not extend beyond the ISP's network. That's why all the offices use the same ISP.)

    157. Re:fairness by Bane1998 · · Score: 1

      People should stop saying TCP forces packets to arrive. It doesn't, really. To a naive app developer it may appear that way, but the truth is the IP transport is unreliable. TCP packets may be dropped just like UDP packets. TCP just hides the resends and ACKs and all those goodies. If people understood the layering better instead of being fed half truths they'd be smarter. Not saying you are wrong and 'calling you out' or anything, but I think we should be concise in our language when describing how this stuff works.

    158. Re:fairness by Alarash · · Score: 2, Insightful

      If ISPs started setting the QoS bits to favor voice traffic and send Bittorrent into the lowest priority queue, I guarantee that it won't take long for a BitTorrent client to start disguising itself as voice traffic.

      Fair point. But Deep Packet Inspection-enabled devices can identify protocols disguising themselves as other protocols. Stateful analysis of that kind of traffic (10Gbps+) is possible, but the performance hit could be pretty big. Not huge though, and it's definitively something doable if you spend enough money on network devices to scale up the performances. I'm starting to see 10G line rate probes that can detect Layer 7 attacks, I'm sure they can determine as quickly, if not quicker, a forged protocol.

      Whatever the technical problem is, somebody at Cisco, Juniper, F5, Foundy, and others already found the solution. It's just a matter of paying for the technology, and ISPs don't want to spend one dime too many, obviously, because they need to maximize the profitability for you know whom.

    159. Re:fairness by cfulmer · · Score: 1

      Ehh... TCP has no "guarantee" of reliability, either. It only has a guarantee that information will arrive at the receiver in the same order that they're sent from the sender. But, there is no guarantee that it will be possible to send any packet. For that, you either need to deal with the ability to reserve bandwidth or otherwise differentiate traffic at a low-level.

      UPD is the basis of the Real-Time Protocol (RTP), which is used for VoIP and various video applications. If you're going to drop UDP packets willy-nilly, you're seriously going to impact call quality.

      If uTorrent wants to do this, fine. But, they should also figure out how to throttle back if packets start getting lost. Otherwise, they'll drown out all the other traffic on the 'net.
       

    160. Re:fairness by Cramer · · Score: 1

      Actually, you are both incorrect. One connection, or even a dozen, to a USENET server farm is very different than the hundreds to thousands of connections opened and closed by bittorrent applications. For USENET, the router has a dozen, more-or-less persistent connections to remember. For BT, it has hundreds of transient connections to remember and forget. Conclusion... BT is a lot more work for routers.

      It has been common practice for ISPs to outsource USENET service for a long time now. The expense of maintaining their own hardware became too high nearly a decade ago. Add to that the decline in use, and usefulness, with the rise of "blogs" and web forums (and p2p), it didn't take any "political pressure" to kill it... it wasn't anything their customers wanted or used, so there's no point spending the money to offer USENET anymore. (If you wanted good USENET access, you were already buying it from someone else.)

    161. Re:fairness by cfulmer · · Score: 1

      What does it mean that a line is "sold as a 10mbit line"? Why do you choose to read the word "dedicated" into that instead of the word "shared" like most educated people do?

      Every utility in the world is oversold. You probably have a 200amp connection from the power company. But, guess what happens if everybody in your town decides to turn on their air conditioners at the same time? You probably have something like 50psi water service. But, guess what happens if everybody turns on the sprinklers at once. Natural gas, cell phones and landline phones all work the same way.

      Read your terms of service -- I'm guessing they spell out *exactly* what you're buying.

    162. Re:fairness by Barny · · Score: 1

      And if the router is set up right it will simply drop 600kb/s of the UDP traffic.

      The only point that will become congested is your outgoing pipe, it will be flooded heavily, but of course your ISP has well configured routing equipment that will handle an over-abundance of UDP as its supposed to and drop it right?

      This will ultimately hurt gaming a fair bit, since atm UDP is used rarely enough (volume wise) that it can be prioritised, that's likely what the uTorrent people are counting on.

      --
      ...
      /me sighs
    163. Re:fairness by Cramer · · Score: 1

      And they are technically, and legally, correct. Your LINE is not shared. Once it gets to the DSLAM, it's no longer "your line" and very much is shared bandwidth with all the other lines coming in. So, you are always getting your full line rate to the DSLAM, but not necessarily anywhere beyond it. Cable, on the other hand, is shared with everyone else in the neighborhood, so you don't always get your full line rate. (if they're selling 10M service, then only about 4 people at a time can get there, per channel.)

    164. Re:fairness by Eil · · Score: 1

      No, you don't. A dedicated 10 Mbps link would run thousands of dollars a month (a T1, which is 1.5 each way, is ~$300 in the US)

      A T1 is expensive because of the equipment that it uses and the effort involved in hooking it up. Not because a T1 is some magical guarantee of bandwidth or reliability.

      I worked in telecom for ISPs. There's no technical reason that every DSL, cable internet, or wireless ISP can't provide each customer their share of paid-for bandwidth and still oversell. It all comes down to where they keep their oversell threshold and how much they care about pissing off their customers.

      I have indeed seen ISPs that keep a close eye on their infrastructure, have happy customers, and still manage to turn a profit.

      you knew damn well that you would be sharing it with others in your neighborhood.

      If it's a cable connection you speak of, maybe a slashdotter knows but Average Joe does not. Please tell me which cable company puts on all of their advertisements, "10Mbps Unlimited Bandwidth (That you share with everyone in your subdivision and isn't really unlimited either)" because I've never seen it.

    165. Re:fairness by TikiTDO · · Score: 1

      The scenario you described is using a somewhat archaic approach. What is more likely to happen at this point is the router will be configured to begin dropping UDP traffic once it reaches a certain ratio of TCP traffic. Now this means that the total traffic on the network is slowed, but probably not as much as you are suggesting.

      The affected applications, which are in fact addressed in the articles, are those applications that also rely on UDP. If your BT client is spamming UDP packets at 800kbps, and the router is allowing those packets through at a rate of 400kbps then your VoIP and games are also losing half of their data. Similarly, your BT data is also getting through at a rate of 1 packet for ever 2, thus the people receiving your packets are seeing some rather strange results.

    166. Re:fairness by Bill_the_Engineer · · Score: 1

      First of all I was addressing your over simplification of TCP.

      Anyway, BT seems to counter your view of congestion mitigation belongs in the app layer. The premise being that since BT moved to UDP, network congestion has actually risen.

      TCP was never meant to be a catch-all for all congestion/error free transmission. However if you intend to replace it with UDP, you better at least come up with a better method to manage the connection. Which BT has seemed to fail at doing.

      The problem most (if not all) applications is focused at solving is "How do I send my data that suits my needs", where TCP is designed for "How do I send my data reliably AND without using too much of a shared resource". That is a huge different in philosophy. Of course we could simply allow the network mitigate the congestion for us, oh wait that's what BT is trying to circumvent now...

      If your network depends on well-defined slow start behavior... well, that's a shame, isn't it. Light up some more fiber and send Cisco some more bucks.

      Amateurs throw money at the problem, while the pro's make good use of the resources readily available...

      --
      These comments are my own and do not necessarily reflect the views or opinions of my employer or colleagues...
    167. Re:fairness by Anonymous Coward · · Score: 0

      Yes, I have. I quite often get the full 10 Mbps.

      I don't realistically expect to download at that rate round the clock though.

    168. Re:fairness by An+Ominous+Cow+Erred · · Score: 1

      Still, they could get around this by defining the "bittorrent chunk" size to be 1.5k (UDP payload size). Everything else would probably work fine.

      This is a really dumb idea, considering that the torrent file carries a 160-bit hash for all the chunks. You'd wind up with your torrent file being over 1/10th of the size of the file you're trying to get in the first place.

      Then you'd need a torrent for your torrent.

      (Although, this itself isn't that bad an idea now that I think about it for an advanced version of the protocol... Have peers share hashing/parity information as well as the file. You'd be protected against bad hashes by the overall torrent file having hashes of the hashes. =D)

    169. Re:fairness by BagMan2 · · Score: 1

      Having written protocol stacks on top of UDP before, I can tell you that original poster is spot on. The reason the internet works is because the vast majority of the traffic is all sharing a common protocol (in this case TCP) for the reliable transport. TCP as a protocol is well proven to be fair to other TCP connections on the network. I wrote a TCP Reno like algorithm on top of UDP once that had a few enhancements over TCP to make it even better. TCP can't do these enhancements because it needs to remain compatible. Once I had that proprietary protocol stack in place, it was super-easy for me to tweak the parameters to the protocol to make it as friendly or unfriendly to TCP as I wanted.

      The basis for sharing bandwidth is that if both connections employ the same algorithm for exploring and scaling to available bandwidth, then the competing connections will each settle in on a fair-share of the bandwidth. If however, one of the connections is using a different algorithm, then it's entirely possible that it will either get starved out by the other connections, or squash the other connections, taking more than its fair share. For example, if I simply change my protocol to tolerate moderate packetloss without scaling back the flow-control window size, I can effectively starve out any TCP connections on the same pipe in favor of me stealing all the bandwdith.

      No matter how careful they are with their proprietary protocol, it is quite unlikely that they are going to be able to continue to be fair relative to TCP connections. And that reality is what is going to mess up the internet.

      Now, the truth is that they are probably actually doing themselves a disservice. When routers get busy, they have a tendency to drop UDP traffic instead of TCP traffic. The reason for this is dropping TCP traffic does them little good, since they know for a fact that the packet will just get sent again. Dropping UDP traffic on the other hand often doesn't follow this rule, since UDP is often used for unreliable transfers, whereby the lost data is not resent (usually because it would be too out of date to have value by the time it is resent). If they switch these file-sharing networks to UDP, while it may seem to work well in the short term, it makes it very easy for the ISP's to simply dump UDP traffic in bulk if the pipe is getting full.

      Short term the UDP may force out the TCP connections, but the ISP's won't tolerate that for long and it is really quite easy to just prioritize TCP over all UDP.

    170. Re:fairness by BronsCon · · Score: 1

      And when YouTube and Netflix and Hula are impacted by these caps, they will lobby to make them illegal.

      We'll have our internet back, someday.

      --
      APK quotes people (including myself) without context and should not be trusted. Just thought you should know.
    171. Re:fairness by enoz · · Score: 1

      Am I mistaken in believing that UDP has been around for 24 years?

    172. Re:fairness by BronsCon · · Score: 1

      Oops, I forgot to say the following: My ISP offers 1500/256k, 12/1m and 20/2m service and is averse to the idea of throttling or capping. These issues don't affect me as long as I am with this ISP, who, by the way, has very reasonable prices for what they offer. I'd say $45 for a 12/2 line that I can't tell shared at the node is a pretty damn good deal; given that I can burst it to over 30Mbps when I really need (want) to.

      I, honestly, have my internet. I love it; and I will continue to give this ISP (cable provider) as much of my hard earned money as I can afford to, so long as they remain as morally strong on these issues as they have been in the past and are currently. That's right, I'm voting with my wallet. I've written (and hand-delivered, they're 5min from me) their CEO a letter to this effect, as well and was assured by him directly that they were prepared to take as much of my money as I could afford to give them.

      I love his sense of humor, as well as his business savvy. That's why I'm his customer and will be for the foreseeable future. It's nice to hear, directly from the man at the top, that my service will only get better.

      Then I wrote the letter, my $45 was netting me 6000/512. The same $45 now pays for the line mentioned above. I can even run a server (forbidden by TOS, yes), provided that I don't let things get out of control. Again, per the CEO, this is how they enforce their TOS; they'll block the port it's running on and give me a phone call if it becomes an issue.

      This is how an ISP should be run. Period.

      I pay for 12/1, I get 12/1, burstable to faster than 30/2 (I've seen 33/2.2). There's a no servers clause in the TOS only to cover them if they NEED to block a port because a server is using too much BW; then they call and let you know they did it. Speeds and reliability are awesome and always improving.

      Power dropped for a few hours for an area covering 3 cities (including the cable plant). My modem and router are on a UPS, I was online the whole time. I powered up a portable TV; yup, cable was still up.

      I'll say it again: This is how an ISP should be run. Period.

      --
      APK quotes people (including myself) without context and should not be trusted. Just thought you should know.
    173. Re:fairness by Mista2 · · Score: 1

      What if the ISPs became massive seeds for the content. They could deliver packets to their local subscibers very easily, and reduce the load on the international data channels 8)
      Oh, That would be "bad" I guess 8(

    174. Re:fairness by sudog · · Score: 1

      Actually, much of what TCP guarantees (in-order data delivery) can simply be thrown right out the window. It doesn't actually matter whether it arrives in order if you have a finite, defined chunk of data that needs to be delivered from one machine to another. Therefore, things like Windows sizes can disappear, in-order reassembly can disappear, and all this extra overhead can simply go away. (Other stuff needs to remain, but you get the idea.)

      However, BT users beware: if you don't have an exponential back-off, the core routers themselves will simply QoS you. They already have these algorithms built-in. Non-responsive protocols that don't behave well in the face of dropped packets WILL BE DROPPED HARDER.

      There're lots of interesting academic papers written about this.

    175. Re:fairness by sudog · · Score: 1

      Incorrect. ANY BT implementation over UDP will have flow control built-in. And without an exponential back-off, the core routers WILL drop the connection right on the floor. They already have this logic built-in. BT users, you've been warned.

    176. Re:fairness by sudog · · Score: 1

      Incorrect. TCP guarantees in-order delivery of DATA. *Packet* retransmission could include additional data and thus the same packet need not be the one that is retransmitted until ACK'd at the other end. It could change, grow larger, whatever.

    177. Re:fairness by quenda · · Score: 1

      UDP senders don't know when they're flooding the connection

      Nonsense. All UDP app's have flow control - its just done at the application level instead of in the OS. Which is often the whole point of using UDP.

    178. Re:fairness by HeronBlademaster · · Score: 1

      Companies shouldn't be allowed to misrepresent their services in their marketing material, regardless of what the contract actually says. If I say in my commercial "I'll sell you up to 1 Gbps for $100/month" but the service contract says that you can only get 1 Gbps on days when there's both a full moon and a solar flare, and you only get 3Mbps on all other days, should I be allowed to get away with it? Sure, it's an extreme and highly unlikely example, but it effectively portrays my point.

    179. Re:fairness by HeronBlademaster · · Score: 1

      I haven't once gotten full speed on my fiber connection, no matter the time of day.

      My ISP's advertising material doesn't say "up to 15Mbps", it says "15Mbps [down] / 15Mbps [up], 60Mbps within our fiber network".

      There's a speedtest.net server within their fiber network. I've never even hit 10Mbps on it, let alone 60Mbps.

    180. Re:fairness by HeronBlademaster · · Score: 1

      I choose option three - Sue them for falsely advertising regular beans as magic beans.

    181. Re:fairness by HeronBlademaster · · Score: 1

      TCPs flow control is trash.

      ... despite continual demonstrations to the contrary? TCP isn't right for every situation, but when it is, its flow control is superb.

    182. Re:fairness by TopSpin · · Score: 1

      If you're going to transfer files over UDP then you need to build some TCP-like protocol on top of it.

      No. TCP guarantees sequence, among other things, a property responsible of much of its complexity and overhead. BT should (and does) function well in the absence of transport layer enforced sequencing, automatic packet loss recovery, inadequate (16 bit) checksums, etc.

      We really don't need is an arms race of new, greedier protocols

      No, we don't, but we're getting one anyhow. BT is doing what it must in this arms race to remain relevant; if it did any less the greedy would abandon it for whatever weapon delivered more bandwidth. BT isn't actually at fault here. Try to remember that as you're knocking back the MSM kool-aid on the evils of BT.

      An alternate protocol could conceivably improve on this by applying flow control to the aggregate throughput for the whole "bundle" of connections, rather than each connection individually.

      Although it is possible to bake congestion control into an application layer above UDP, is not possible for BT to utilize such a design. Again, if it tried the downloaders would go elsewhere to avoid the congestion control.

      This isn't about some technical inadequacy and there is no silver bullet solution. This is about fuckwits that will not stop until The Powers that Be step on them and their nonsense. Naturally we're all going under the boot lest there be some 'unfairness.'

      --
      Lurking at the bottom of the gravity well, getting old
    183. Re:fairness by Anonymous Coward · · Score: 0

      UDP senders don't know when they're flooding the connection, so they just keep doing it.

      I don't know about that, I have good faith in my bots.

    184. Re:fairness by Anonymous Coward · · Score: 0

      Thats exactly what I don't get. If you put a cap on it fine by me just don't tell me how I am going to use it.

      http://www.bell.ca/shopping/internet.portal?_nfpb=true&_windowLabel=PrsShpInt_Access_internetBrowse_portlet&PrsShpInt_Access_internetBrowse_portlet_actionOverride=/portlets/personal/internet/browse/getDetailPage&_pageLabel=PrsShpInt_Access

      They say you get 2 down and .8 up, but that never materializes. Don't advertise what you can't deliver. I don't get why everyone freaks about the cap. They are already screwing us to use their networks. It is almost like they are laughing at us and know we won't get better service somewhere else.

    185. Re:fairness by mandelbr0t · · Score: 1

      An alternate protocol could conceivably improve on this by applying flow control to the aggregate throughput for the whole "bundle" of connections, rather than each connection individually.

      Or you could just do flow control at the firewall where it's intended to be done. I find it works quite well, keeping latency of other protocols low even though the number of bittorrent connections dominates the total number of active TCP connections.

      --
      "Please describe the scientific nature of the 'whammy'" - Agent Scully
    186. Re:fairness by vux984 · · Score: 1

      I pay for 12/1, I get 12/1, burstable to faster than 30/2 (I've seen 33/2.2). There's a no servers clause in the TOS only to cover them if they NEED to block a port because a server is using too much BW; then they call and let you know they did it. Speeds and reliability are awesome and always improving.

      If you pay for 12/1 and get 12/1, then how you could your server ever use too much bandwidth? Why exactly would they EVER "need" to block a port? How can you use to much bandwidth if they are providing you only the 12/1 you are paying for?

      Unless, you maybe aren't really getting 12/1 after all... but some sort of shared 12/1 that where they'll block ports and call you if you use too much...

      I'll say it again: This is how an ISP should be run. Period.

      It sounds like you've got a good ISP overall, and they have managed their capacity and network better than some others, and adapted to growing B/W demands better than others... but bottom line... they aren't any different than other ISPs... maybe less oversold than some, but they are still oversold -- otherwise they wouldn't need a no servers TOS, for example.

    187. Re:fairness by Opportunist · · Score: 1

      The perpetual argument seems to be that it costs oh so much to actually provide what ISPs sell. Ok. Why doesn't anyone argue the other way around? What can be provided for the 50ish bucks we pay a month for our internet connection? Maybe because people would realize the whole broadband hype isn't even close to being able to provide what it promised and we're basically still in the ages of 64k lines, just for about twice the price?

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    188. Re:fairness by Opportunist · · Score: 1

      Me? Maybe. The average customer that buys into the marketing lie? Maybe not.

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    189. Re:fairness by Opportunist · · Score: 1

      Again, you, me, and maybe everyone here on /. knows that it is certainly economically impossible and most likely even technically impossible for an ISP to offer 10+ mbit lines to every single customer. A sizable ISP would have to be able to provide more bandwidth to his customers to offer those 10+ mbit as dedicated lines than most internet backbones can offer.

      We are the minority on the internet by now, though. 99% of the internet users don't have a clue about this. They don't know that it is impossible to really provide them with a dedicated 10mbit line for the 50 bucks they pay. Hell, they most likely don't even know what "dedicated" means or how it's different from shared. Selling a line with this promise is simply dubious. If not fraudulent.

      We actually have laws that make contracts void if you can claim credibly that you (as in "an average educated person able to read the language") were unable to actually understand the terms of the contract. It's a pretty new law, so I'm sure we'll soon see some funny lawsuits and rewording of contracts due to it. Let's hope foe the best.

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    190. Re:fairness by Opportunist · · Score: 1

      Why do you hate progress?

      When did "progress" start to mean "make matters worse"?

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    191. Re:fairness by Opportunist · · Score: 1

      If "exactly" means "wrapped in enough legalese to make an encrypted bittorrent packet, tunnelled through HTTP, look like plaintext", then yes.

      In other words, when you know what to look for, and when you know a fair lot about networking, then you might be able to decipher something that could resemble something that could look like it might mean something like this.

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    192. Re:fairness by Anonymous Coward · · Score: 0

      ...unless, of course, it *is* the admin...

      Uh, for legitimate things....like linux ISOs.....

    193. Re:fairness by vux984 · · Score: 1

      The perpetual argument seems to be that it costs oh so much to actually provide what ISPs sell.

      ISPs don't sell 10Mbps 24x7 bandwidth. They sell 24x7 access to lines that deliver burst bandwidth at 10Mbps. See the difference? The reality is not just that ISPs are 'grossly overselling' its that a certain subset of users are grossly mis-interpreting what the ISP actually IS selling.

      Ask ANY ISP upfront whether you will be allowed to download and upload at your caps 24x7. Everyone of them will say NO this isn't what they are offering, and that if you want THAT you need to upgrade to their commercial grade T1/T3/and beyond stuff.

      Ok. Why doesn't anyone argue the other way around? What can be provided for the 50ish bucks we pay a month for our internet connection?

      They can provide 24x7 access to lines capable of delivering all multiple GB of data, more than an average non-commercial susbscriber needs at 10Mbps burst speeds, usually to 'soft caps' that are defined by localized network load/infrastructure limitations.

    194. Re:fairness by Estanislao+Mart�nez · · Score: 1

      Because if it has happened since perhaps part of the original problem was that there weren't enough resources to begin with. If its continuing to happen perhaps its time to invest in more resources?

      I think you are confusing two issues here:

      1. Whether a 10 Mbit/s line from an ISP should provide a guaranteed 10Mbit/s throughput 24/7.
      2. Whether the ISPs are investing in enough infrastructure.

      Basically, GP is arguing that the answer to (1) is "no." You're responding that the answer to (2) is "no." Well, (2) is a different issue than (1).

      Yes, ISPs are acting like weasels, and we should press them to build more infrastructure, to price their offerings better, to market them honestly, etc. But the endless Slashdot choir that "when I pay for a 10 Mbit/s line I should get a guaranteed 10 Mbit/s every time" is completely wrong, and doesn't help the issue at all. The shared resource model that the ISPs (and all other utlities) are using is really the correct one.

    195. Re:fairness by Salamander · · Score: 1

      think going to UDP would be cool for another reason: there's not all the setup and teardown for connection. If 200 people each request the same block from me in a minute, do I really want to have to go through something like 'hi can I talk to you, what port should I use, hey here it comes, do you have it, ok, I'm done talking to you go away', or should I just shovel it out?

      The setup and teardown in TCP itself isn't all that expensive. What's expensive is usually the setup and teardown to deal with NAT, a problem that's at least as bad with UDP as with TCP. In particular, with a UDP-based protocol that it doesn't understand the NAT box won't know when the conversation ended, so it'll just keep state around until some long-ish timeout, so you're going to be stressing it even more than you would have been with TCP.

      It's possible to improve on TCP. Many have done it, and the result is . . . TCP. Watch any modern Linux box boot and you'll see a bunch of congestion-control modules being loaded, none of which were dreamed of in the early days of Nagle and Van Jacobson, but they're all TCP. This being slashdot, a whole bunch of people are talking about how they can do better than TCP because "TCP hasn't changed in twenty years" - and then they wonder why people who've actually worked on this stuff roll their eyes. The way to improve something is to understand what has been already tried, and then try something new.

      I don't know if the BitTorrent guys are really improving on TCP or just offering the millionth painful re-learning of its lessons (with us as their guinea pigs) but some of the comments e.g. about using latency to measure congestion suggest it's the latter. I hope I'm wrong.

      --
      Slashdot - News for Herds. Stuff that Splatters.
    196. Re:fairness by jthill · · Score: 1

      Yes.

      --
      As always, all IMO. Insert "I think" everywhere grammatically possible.
    197. Re:fairness by sarkeizen · · Score: 1

      The problem is that TCP self regulates and throttles itself back in the face of network congestion. UDP does not, it just blasts packets out as fast as you can feed it.

      I think you are conflating congestion avoidance with flow control as well as mischaracterizing both what would happen on a UDP link in network congestion AND what kind of congestion that TCP is trying to avoid.

      In a highly congested long link, assuming no other programmed network behavior is in place (i.e. you could implement TCP in UDP which would make your argument moot). Both TCP and UDP would experience packet loss. The difference is that TCP would retransmit packets. This behavior, in itself contributes to congestion collapse and that is what most of the TCP congestion protocols are trying to avoid. (i.e. by tracking unacknowledged packets).

      UDP doesn't require complex congestion avoidance because, by itself it doesn't care if the packets got there or not.

      Now you can assume that in a given implementation of some protocol a developer may implement some similar kind of packet retransmission but as I alluded to above there's little reason to assume that this uTorrent implementation is being done in a way that works worse than TCP does.

      Without some sort of flow control, you could disproportionally hurt TCP flows (which are trying to be good and throttling themselves back when they hit a bottleneck) by your big ugly UDP stream.

      Flow-control in TCP parlance isn't about congestion but rather the amount of data that the receiving application can buffer. Your example doesn't appear to apply well since as I mentioned above TCP applications aren't throttling back their data rate (TCP in one sense just 'blasts' packets too. It doesn't know what rate it's sending at). The TCP application is managing it's packet resends.

    198. Re:fairness by sarkeizen · · Score: 1

      No, you don't. A dedicated 10 Mbps link would run thousands of dollars a month (a T1, which is 1.5 each way, is ~$300 in the US) and most consumers can't swing that sort of dedicated line.

      The OP starts with the following:

      "If I pay for 10Mbps download speed, it should not matter to anyone how I use those bits."

      To me this says that the person is decrying someone changing the agreement based on usage. That is the crux of the complaints against ISP's IMHO. In that light your comment is irrelevant.

      "Instead, you paid for a connection that is 10 Mbps maximum"

      Most of us in NA aren't even getting that. We are getting X Mbps maximum under certain protocols or only at certain times regardless of network congestion. I would agree with the thought of the OP that my ISP has no business whatsoever taking issue with the kind of protocols I'm using.

      If my provider wants to cap me. I'm cool with that - caps have peaceably existed for years with bandwidth providers and their users . Shaping and throttling are needlessly preemptive and annoying.

    199. Re:fairness by Ed+Avis · · Score: 1

      I suppose the sweet spot is somewhere between just under 1500 bytes, which always fits in a single packet in practice, and 64K, which gives you less overhead but more chance that a single packet will be lost somewhere and your chunk will be incomplete. It depends on the expected packet loss rate and the per-packet overhead. Or use big chunks by default, but if packet loss occurs step down to half the size adaptively. I guess the original poster was right: you do end up reinventing at least some higher-level protocol features on top of UDP.

      --
      -- Ed Avis ed@membled.com
    200. Re:fairness by Anonymous Coward · · Score: 0

      You know not every place in the world has the same deprecated understanding of what you get when you pay for something as America does. Too bad really, cause you people are really missing out on what it's like to have more than 56k guaranteed.

    201. Re:fairness by fan+of+lem · · Score: 1

      Random Early Detection sort of fixes this, for TCP and UDP both.

    202. Re:fairness by fatphil · · Score: 1

      How on earth does TCP, when it detects an expected packet hasn't arrived long after it was requested, attempt to get the packet from another different machine instead?

      Clue: It doesn't. Yet that's the kind of retry logic that BitTorrent needs. TCP connections are mostly unnecessary for torrenting, it's really not a connection-based protocol at all, it's already designed with failure (to receive packets) in mind, and doesn't need the overhead of TCP to operate.

      --
      Also FatPhil on SoylentNews, id 863
    203. Re:fairness by fatphil · · Score: 1

      It's easier for the client (recipient) to simply realise that if it's repeatedly getting fragmented blocks due to dropped packets from a particular server, then it might as well _stop requesting blocks_ from that server, and request them from a different server instead. No need for ACKs, that's just more packets to clog things up. To get less, simply make fewer requests. The client is already maintaining state, there's no need for the protocol stack to do a poor approximation of the same job with an unnecessary overhead that, in order to get *less* data transmitted, sends *more* control.

      --
      Also FatPhil on SoylentNews, id 863
    204. Re:fairness by fatphil · · Score: 1

      "And I suppose you carry all your water from the well in buckets."

      Well, I get all my bottled water from whichever shop happens to be open. I certainly don't have it piped from a single supplier to my flat.

      And curiously enough, I want my BT packets to come from whoever can most conveniently supply them at the time, I certainly don't want to be tied to one peer.

      --
      Also FatPhil on SoylentNews, id 863
    205. Re:fairness by fatphil · · Score: 1

      With all this talk of "connections" being a problem, why hasn't anyone thought of moving BT to a connectionless protocol, like UDP? ;-)

      --
      Also FatPhil on SoylentNews, id 863
    206. Re:fairness by richlv · · Score: 1

      pretending that there's something in the agreement that actually isn't there wouldn't work quite well in courts or something...

      if the isp sells 10 mbps, you can't blame user for using that. if isp can't handle that, they should sell 6 or whatever mbps connections.

      they could specify in the agreement "we provide you 10mbps line, but you may only use half that bandwidth", but that would only lead to conflicts... hey, that's what is happening right now, except they don't have such things in agreements (and that would be a stupid idea anyway).

      --
      Rich
    207. Re:fairness by BronsCon · · Score: 1

      As long as I can't tell they're oversold, that's fine with me, they may as well not be oversold. I've run tests every time of day, on holidays, on work days, on weekends, anytime a service or site feels slow to me. I'm always getting what I should be getting.

      It is possible to use more bandwidth than is available to you; I can do this in two ways with my ISP, actually. First of all, I can burst my line above 1Mbps upstream for a longer than reasonable period of time (which I've come to find is only an issue if there are connections to or from multiple addresses), which causes me to use more than my fair share of bandwidth. I can also take on more requests than my connection can handle. Rest assured that, if the level of incoming requests were burst my connection to full capacity (over 30Mbps), for a long period of time, somebody would take notice.

      Were I to rate-limit my upstream, at the router, to 1Mbps and my downstream to 12Mbps (QoS allows for this) to avoid bursting, I could run my connection maxed out 24x7 and my ISP wouldn't give a damn.

      That is how it should be done; grow to meet demands. If you become unprofitable, you should have had more foresight. Just never, EVER, screw the customer because you made a bad decision. going out of business is not a form of screwing the customer, they can always find another provider.

      --
      APK quotes people (including myself) without context and should not be trusted. Just thought you should know.
    208. Re:fairness by markov_chain · · Score: 1

      Because TCP is well-designed for bulk, delay-insensitive, point-to-point, in-order transfers.

      The in-order delivery is so far the only extraneous feature mentioned in the discussion, so points for that :)

      It's design doesn't consider a situation where the data is available from any of many hosts on the network.

      Neither does UDP's. IP provides best-effort point-to-point service. What, are you going to use IP multicast? No, applications are going to do their own, TCP or not.

      I still don't see a real, compelling reason to abandon TCP for BitTorrent; so far these are all just philosophical arguments without real gain. The only potential saving I can see is the 20% or so penalty due to the seesaw behavior of TCP during its congestion control stage.

      --
      Tsunami -- You can't bring a good wave down!
    209. Re:fairness by swillden · · Score: 1

      It's design doesn't consider a situation where the data is available from any of many hosts on the network.

      Neither does UDP's. IP provides best-effort point-to-point service.

      UDP (and IP) is point-to-point for a single packet but TCP wants to deliver a whole stream point-to-point. On top of UDP you can build a protocol that uses point-to-point delivery for individual packets, but multipoint-to-point for retrieving data. If a request for a given piece of data from one peer times out, there's no reason to re-request the data from that same peer, and perhaps good reason not to.

      Consider that current bittorrent clients, when faced with torrents with thousands of peers, can only download from a few hundred of them because of the overhead of setting up and managing thousands of TCP connections. A UDP-based mechanism doesn't have that limitation. Also, consider that a UDP-based Bittorrent protocol has no real need of ACKs, except as required for congestion control, not to mention no need of all the overhead of the TCP three-packet handshake or the two-packet teardown.

      I can't see how anyone can't see that Bittorrent is fundamentally different than point-to-point data delivery protocols, and that there are lots of opportunities to exploit those differences to make a protocol that is more efficient AND better addresses congestion control.

      It's also clear that naive implementations that don't make use of our understanding of network congestion detection and avoidance could really suck. I have confidence that Bram Cohen et al, after years of working with Bittorrent -- much of that effort related to managing congestion -- are well-equipped to do a good job. I wouldn't be surprised if there are a few tweaks to the protocol after real-world experience is gained, but I will be surprised if there are significant problems.

      --
      Note to ACs: I usually delete AC replies without reading them. If you want to talk to me, log in.
    210. Re:fairness by hr+raattgift · · Score: 1

      However, one thing to realize about P2P is that because there are often dozens of active TCP connections transmitting from one machine, fairness goes pretty much out the window anyway

      TCP (and any RFC 2001 congestion avoidance) fairness is on a per bulk transfer basis. Multiple bulk transfers for the same application is fair for all the bulk transfers, but unfair from the perspective of an application that runs only one bulk transfer. In the limit of low numbers of flows, with two data-moving applications sharing the same bottleneck with one bulk transfer each, "A" and "B" both get half of the bottleneck bandwidth; with four flows for "A" and one for "B", the former gets 4/5 of the bottleneck bandwidth and the latter 1/5, once the flows reach equilibrium.

      This is still fair in the technical sense, because the bulk transfers find equilibrium. In the limit of large numbers of flows -- tens of thousands seen over a one second interval -- this works very well for sharing bottleneck bandwidths. This is important in places where congestion is most noticeable by the largest number of users: inter-provider gateways (like at internet exchange points) and in front of very long haul links (like across oceans). Individual users are unlikely to be able to gain a significantly larger share of that sort of bottleneck bandwidth just by opening lots of flows, because they will saturate a bottleneck somewhere else along the end to end path.

      So a technical definition of fairness (bulk transfers find equilibrium and roughly equally distributes bottleneck bandwidth among the bulk transfers) is hugely useful in the most expensive parts of the Internet infrastructure.

      However, at smaller, cheaper bottlenecks where opening multiple parallel bulk transfers gains a much larger share of the bottleneck, *and* where it causes adverse interference for the users of applications that open single bulk transfers, there are two answers: one is simply to expect that other apps that traditionally use a single TCP bulk transfer to parallelize the transfers. This will reduce goodput per packet transmitted because the probing of the bottleneck bandwidth will always incur packet, and that is likely to synchronize at FIFO bottlenecks. Another approach is to do smarter-than-FIFO queueing at bottlenecks, especially ones which carry small numbers of bulk transfers.

      Ultimately, routers can only forward, delay or drop packets. FIFO forwards a packet immediately if there is nothing in the queue (no bottleneck), otherwise it delays a packet in a queue; if the queue is full, FIFO drops the packet. One can probabilistically impose an early delay or drop on packets easily (in terms of the amount of computation needed in the router), in a way which is more likely to punish the least congestion avoiding users (i.e., the ones with aggressive timers, or which open multiple parallel bulk transfers to try to dominate the bottleneck).

      One approach is to look at the actual queue regularly, and preferentially drop from the largest occupant of the queue, where an occupant is identified by a tuple such as (src, dst) address 2-tuples. This requires lots of state and computation. random early drop (RED) is a very close approximation -- the liklihood of a drop increases in proportion to the queue depth, and it is very likely that an increasing drop probability will hit the largest user (as in src,dst) of the bottleneck when the queue depth is non-zero. A large user who does not increase queue pressure will not be penalized; a small user whose traffic is synchronized with queue growth will be signalled to avoid the congestion, and will probably spread out its use. RED works very well, and is cheap and easy. It is also counter-intuitive -- sadly, many network operating people don't like the idea of a random early packet drop, and don't understand that it does help, even when confronted with before and after graphs of real traffic; RED with ECN marking is an attempt to appeal to t

    211. Re:fairness by Anonymous Coward · · Score: 0

      Clearly whoever invented TCP did not properly understand game theory.

      That's very funny! Perhaps you should look up the biographies of Leonard Kleinrock (pay attention to his early work), Van Jacobson (pay attention to his early work) and the authors of the documents in the footnotes of RFC 2581.

      You might even try a google search like "TCP game theory".

      Most game theoretical analyses realize the network congestion problem is akin to the prisoner's dilemma, where good outcomes are maximized when everyone refuses to try to claim a larger share of the bottleneck at the others' expense. (Some go so far as to argue that the pricing of congestion in standard TCP implementations leads to a Nash equilibrium).

    212. Re:fairness by T.E.D. · · Score: 1

      Errr...according to my math, that's 20 bytes for every 1.5K, which would work out to about 13K for a 1 Gigabyte file. That hardly seems unreasonable.

    213. Re:fairness by Anonymous Coward · · Score: 0

      Single-source multicast works just fine on the Intardnet. (see for example Sprint's multicast page. Sprintlink has several heavy (hundreds of Mbps average) native multicast users.

      The only thing in the way SSM deployment is that most home routers simply do not talk native multicast on the WAN side.

      What does not work well is (S,G) state in routers for large numbers of sources and groups. So a fan-out mode from a small number of sources (which is one popular usage mode for BitTorrent) to an arbitrarily large group is a reasonable fit for SSM; if the group size is zero, the outgoing packets are dropped very close to the source. If the group size is one or greater, the source simply transmits a single copy and the network maintains the fan-out tree. Lost packets towards the leaves of the fan-out tree can be recovered later (on a repeat broadcast) or via an out of bound protocol.

      This works, but is inefficient for the recipients of the data compared to a CDN or a substantial set of local caches, and is also inefficient for the single source compared to that of BitTorrent and other P2P distribution mechanism if there are often relatively small numbers of users.

      However, SSM is more efficient for "live" content to a variable audience, but there is no obvious way to make it particularly competitive with other means of distributing recorded/regeneratable/static content.

      Substituting a full-blown use of multiple-sender/multiple-group multicast for P2P applications would drown all parties in control traffic and state. Remember that for unicast routers (even household routers) only have to know about the direction in which to foward a packet based on its destination IP address, and these can be summarized into e.g. a default address. For multicast, per-interface group membership must be tracked, as must the arrival direction of traffic; the arrival and departure of sources must be distributed globally to facilitate this. The "exactly one copy" fan-out model is computationally intensive for large numbers of sources and nontrivial sets of sources.

      Finally, as you note, TCP is good at bulk data transfer. It is also good at avoiding congestion. Streaming multicast is not. Either you send very slowly so as not to cause congestion at the slowest bottleneck, or you are pretty much guaranteed to be increasing congestion somewhere. Slowing down the whole pool of users just because someone on a dial up modem talking SLIP or PPP joins a tree is not a great idea. Neither is sending at 100Mbps if you expect users to join across normal DSL lines.

    214. Re:fairness by cfulmer · · Score: 1

      I'm unaware of the "law" you're talking about. In the US, the law of contracts is pretty well-settled (a lot of people depend on it not changing, so state legislatures and courts don't like to change the rules.)

      In any case, the problem is usually that people don't bother reading these agreements. They're not really that hard to read. If you don't read the agreement, that's your own fault. Unconscionable provisions will get struck, but if you agree to something knowing that you don't understand it, then you've taken that risk. (You can always consult a lawyer.)

      In any case, if you're right that 99% of users don't understand overselling, then how do you propose that ISPs sell their services -- it's already advertised as "up to 6mbps"?

    215. Re:fairness by T.E.D. · · Score: 1

      My point to OP was that Bittorrent is *already* having to reimplement the parts of TCP that it needs because of the way Bittorrent works. It is essentially already a UDP-style application.

      It already keeps track of what pieces of its overall file is missing, and handles handshaking with a multitude of external servers that may have and be able to provide each individual chunk. It is already (as someone else pointed out) keeping a 160bit hash of every chunk of the file. On top of that, TCP's paltry handshaking and packet integrity checking is really just getting in the way.

    216. Re:fairness by Anonymous Coward · · Score: 0

      If I pay for 10Mbps download speed

      No, you don't.

      Bullshit.

      If 10Mbps is what the deal said then that's what he pays for. The lesser price is due to worse service and worse guarantees of availability. Note: It may well be that the company imagines it's selling something less than 10Mbps, but the buyer is buying 10Mbps, as long as that's what the contract stipulates. If the company wants to ensure that the buyer buys what the company wants him/her to buy, then they should damn well be upfront with the details in the contract before the deal is made. (And yes, that includes your shared / dedicated line example.)

      I'm tired of that crap, so go shove it somewhere else.

      In simpler terms: Don't want to sell actual 10Mbps lines? Then don't fucking market them as such.

    217. Re:fairness by Anonymous Coward · · Score: 0

      The absence of a standard session protocol in the Intardnet protocol stack is annoying, but has nothing to do with the choice of the transmission protocol. Indeed, the whole point of having a layered protocol stack is to maximize independence from layer to layer, so that e.g. a session layer can choose whatever transmission layer protocol it likes, the transmission layer protocol can run over its choice of network layer, and the network layer can run over whatever link layer protocol it wants...

      Layer violation is not a high crime in the Intardnet protocol stack, which has led to all sorts of problems, and has forever pushed back standardization of a session layer.

      Among the things a session layer should provide is efficient recovery after disconnections of the transport layer connection or transient network failures interrupting the flow of connectionless transport layer protocols. It is silly how often large fractions of static data are re-retrieved after the initial retrieval stalls, times-out or otherwise fails because of a short (few minute) network partition. This should also generalize to recovering when migrating a mobile client from one network to another while in the middle of a session.

      What are the odds that HTTP, FTP, SMTP, and BitTorrent will all work optimally over TCP

      I would suggest that the odds are very good, since they were all designed with TCP specifically in mind. Can you suggest an alternative transport layer they would prefer? I'm honestly curious.

      Remember that most of these have a very strong bulk transfer mode in their usage distribution; HTTP serves up multimegabyte images and datasets, FTP is much more about moving files than about creating directories or changing permissions, SMTP carries large attachments often these days, and BitTorrent is all about moving multimegabyte file chunks.

      [TCP] enforces bad design

      It may make bad design easier; it doesn't enforce it, since it does not have a monopoly on the IP network layer, and routers generally don't care about the transport layer payload of IP datagrams.

      Client/server state is not closely tied to transport layer connection-orientedness. NFS, for example, works over TCP. It has its own session layer which can cope with both TCP and UDP, typically chosen by the client for its own reasons (lossy paths, high delay*bandwidth product paths, etc.); the overlying NFS protocol remains stateless in either case. AFP (Apple's) is session-oriented and will happily migrate a session from AFP over TCP to AFP over AppleTalk-on-the-wire and back; TCP is preferred mainly because the fundamental bulk transfer dominance of file service being a good fit for TCP.

      However, all that said, you are right that TCP is not a good choice for live streaming content where upper layer protocols are loss-tolerant but not very delay-tolerant. Such applications generally work out their own session layer and a pseudo transport layer managing UDP.

      Live streaming content is, however, fairly rare. Most content is recorded or readily regenerated.

    218. Re:fairness by markov_chain · · Score: 1

      I can't see how anyone can't see that Bittorrent is fundamentally different than point-to-point data delivery protocols, and that there are lots of opportunities to exploit those differences to make a protocol that is more efficient AND better addresses congestion control.

      This I would like to see. The fact that TCP sends around streams of data point-to-point is not much different from UDP, because each chunk (which is small relative to the whole file) can be viewed as a packet. Of course a multipoint-to-point protocol is different from a p2p one, but it must be built on a point-to-point primitive, be it IP, UDP or TCP. The TCP option is not that inefficient, because the three-way handshakes have negligible performance impact with large chunks.

      So again, the efficiency gain won't come from some fuzzy "this protocol is designed from the start to be multipoint-to-point" philosophy, but from doing a better congestion control than TCP's, which loses during the slow-start ramp-up and the seesaw steady state phase with the 20% or so loss.

      --
      Tsunami -- You can't bring a good wave down!
    219. Re:fairness by vux984 · · Score: 1

      Were I to rate-limit my upstream, at the router, to 1Mbps and my downstream to 12Mbps (QoS allows for this) to avoid bursting

      Your ISP is already be doing this -at their end- plus rules for burst traffic. It shouldn't be possible for you to exceed the amount of bandwidth they want you to have.

      I could run my connection maxed out 24x7 and my ISP wouldn't give a damn.

      Maybe =you= can. Not all internet connections are created equally even on the same ISP. I've got friends where one gets throttled right away, while others don't... all on the same package of the same ISP in the same city. Their official policy is that they throttle and have soft caps. The reality is some parts of underlying network have a lot more capacity than others, and they only throttle on the parts that are older and congested. If you are in a more modern neighborhood where there is more fiber etc, and they don't need to throttle, then they don't.

      In my experience the "what's the best ISP" question is usually answered by "it depends on your address" - go with who ever has the best network in your neighborhood.

    220. Re:fairness by Anonymous Coward · · Score: 0

      I'm suprised there are so many people spouting crap without making a legitimate argument for either side.

      Go back and look at the history of TCP and why its congestion controls were put in place. Routers were getting overloaded because everyone was using a greedy method to send their data through the internet. TCP's congestion control assumes that packet loss is due to congestion on a router and aggressively backs off in that case in order to avoid abusing the internet's routers. This is not why it is bad for a RealTime protocol or high throughput protocol like BT.

      It is bad for a RT protocol because most RT protocols are lossy and don't care about losing a frame here or there. It is less optimal for BT, because you don't need to preserve order immediately in BT, and thus the error checking part of the protocol becomes inefficient around waiting for data that is lost, rather than eventually retransmitting it later.

      That is completely besides the point though, because the more UDP is used, the more taxed the network will be. Either way, the ISPs will eventually have to figure out how to throttle the UDP traffic since it does have the potential to overly congest the internet.

    221. Re:fairness by BuildMonkey · · Score: 1

      No. TCP does NOT guarantee delivery... that's impossible. TCP is a *reliable* protocol, which means that it tells you when it fails, not that it never fails.

    222. Re:fairness by mzs · · Score: 1

      Every ISP can provide two virtual networks to each user. Where the edge of the ISP network sits; that point where end users are attached, it is possible to use routing to run BT traffic down one pipe and all else down another pipe.

      OMG, network design 101.

      How do you propose to do this? Ponies? It's not like BT only uses certain ports or a subset of IP addresses. Plus the congestion can be some arbitrary router or point to point link along the way and not simply at the ISP. Many people do use the internet in Australia and South Africa.

    223. Re:fairness by mzs · · Score: 1

      TCP enforces and faciliates delivery certainty.

      No, it's just that your app can pretend that it does. It does not need to resend anything, the TCP stack will keep retrying until it times-out. Try it for yourself, ssh into a box, then turn off said box. After a while you will get a connection timed-out. TCP does not guarantee delivery. Instead it will try hard to send and receive everything without your intervention and if you do run into real trouble, you'll find-out about it.

      It gives you everything to make sure some packet arrives in time, if it's fragmented and arrives in the wrong order it's reassembled and all the other little bits that are quite useful when you're normally transfering data.

      TCP does nothing to guarantee any timing worth a damn. In the case you mentioned (a dropped fragment) everything on that socket is likely to hold-up for 25 seconds. Also all that fragment handling stuff, it's in the IP layer. You get that in UDP as well

    224. Re:fairness by BronsCon · · Score: 1

      I suppose it helps that I'm a mere 5 minute drive (10 minute walk, traffic's a bitch) from the plant. It's my understanding, however, form friends and colleagues much farther away from the plant than myself that my experience is par for the course.

      It helps that Cox is a franchise and my local franchise is actually locally owned and operated. Each Cox franchise is its own private company, with its own infrastructure; I guess it must just be easier to maintain a lot of smaller networks than it is to keep track of one large one.

      Again, how an ISP should be run.

      --
      APK quotes people (including myself) without context and should not be trusted. Just thought you should know.
    225. Re:fairness by swillden · · Score: 1

      So again, the efficiency gain won't come from some fuzzy "this protocol is designed from the start to be multipoint-to-point" philosophy

      Go back and reread my posts, I've given several concrete examples of how efficiencies can be gained. There's nothing fuzzy about it.

      but from doing a better congestion control than TCP's, which loses during the slow-start ramp-up and the seesaw steady state phase with the 20% or so loss

      In addition to the other opportunities for efficiency gains that I've already mentioned, I see a couple here, too.

      Look at the slow startup issue. That's unavoidable in the purely point to point case, because in general the available bandwidth between client and server is unknowable, and starting too fast means throwing large numbers of packets on the floor.

      In practice, the bottlenecks are the "last mile" connections at each end of the virtual circuit. It's relatively easy for an application to measure its own last-mile bandwidth, but it can't know the bandwidth available to the other end, so slow start is necessary.

      But that's not true for torrents with many peers and a connectionless protocol. The client can spread its requests broadly enough that the outgoing bandwidth of any of the peers is nearly irrelevant, and can tune the request volume to its known inbound bandwidth, to achieve a fast start.

      Of course, care must be taken not to overwhelm the inbound bandwidth of the peers with block requests. At present, most peers have asymmetric connections with significantly more inbound than outbound bandwidth, but it's probably not wise to depend on that. However, clients should be able to estimate the inbound request load on a given peer by looking at the seeder/leecher ratio, and then can adjust their requests accordingly. Also, peers that do not respond to a request should generally not be sent another, not quickly, at least. That should help to ensure that if peers are flooded with inbound requests, the flood is brief. Except during times when large numbers of new leechers are joining all at once, it would probably also provide an adequate primary flow control mechanism; peers respond to incoming requests as much as they want to, based on their measured outbound bandwidth, trusting that ignored requestors will take their queries elsewhere.

      The more I think about it, the more I believe that a BT protocol should be completely ACKless, with no attempt to retry or even track failed deliveries. Definitely not how TCP works.

      I'm typing off the top of my head here, so I'm sure there's a lot more that needs to be considered, but the key is that a bittorrent protocol has a lot of options that a point to point stream protocol like TCP does not. The ability to pull pieces of the data from any of a large number of places, and the irrelevance of order, change the requirements dramatically. The existence of the tracker as a central coordinator also adds a lot of options (which have to be weighed against tracker traffic, obviously).

      --
      Note to ACs: I usually delete AC replies without reading them. If you want to talk to me, log in.
    226. Re:fairness by markov_chain · · Score: 1

      Go back and reread my posts, I've given several concrete examples of how efficiencies can be gained. There's nothing fuzzy about it.

      I did, the gains you mention are superficial. For example: peers can open more connections; clients don't have to deal with connection state; no three-way handshake; etc.

      I don't believe you have a good case here :) I want to see something like a 20% improvement in, say, download time given the same network topology conditions, while still being able to avoid congestion well.

      I'll give you that this is a tall order, and that we should probably be reading BT and TCP research papers to see what the state of the art does.

      Of course, care must be taken not to overwhelm the inbound bandwidth of the peers with block requests. At present, most peers...

      This seems like a lot of specialized little tricks and rules of thumb that aren't really simpler than what standard TCP-based clients do... again, I'm not convinced by the argument :)

      The more I think about it, the more I believe that a BT protocol should be completely ACKless, with no attempt to retry or even track failed deliveries. Definitely not how TCP works.

      That depends. I could view each TCP connection transferring one chunk as one packet. Then there is no ACK; if the connection breaks in the middle it times out just like the other method. I can also apply all the other connectionless tricks.

      --
      Tsunami -- You can't bring a good wave down!
    227. Re:fairness by markov_chain · · Score: 1

      UDP is simpler than TCP, so I don't see how switching to UDP would hurt the internet.

      Ye Gods! Jon Postel must be spinning in his grave. It seems we are not doing enough to teach kids TCP/IP.

      --
      Tsunami -- You can't bring a good wave down!
    228. Re:fairness by markov_chain · · Score: 1

      I know, we could use a bandwidth reservation protocol! Maybe you can be the first to donate some money to get the backbone providers to turn on RSVP :)

      --
      Tsunami -- You can't bring a good wave down!
    229. Re:fairness by Anonymous Coward · · Score: 0

      > Telephone companies where very clear that you should go with them because you don't have to share a line.

      And you don't. The fact that you didn't understand what that meant isn't purely their fault.

      They claimed that you don't have to share a line: since every subscriber gets a dedicated line to the DSLAM, this is demonstrably true (with cable, you really are sharing the line with 100s of your neighbors). They further claimed that DSL is inherently better able to accomodate large numbers of users, because they can increase the available bandwidth easily by adding or upgrading DSLAMs and trunk capacity: this is also demonstrably true, due to the architecture of DSL (with cable, the bandwidth of the loop is fixed; when you exceed that, you've got expensive recabling ahead).

      On the other hand, they *never* claimed that you would get guaranteed bandwidth. DSL is a shared connection architecture, limited at the DSLAM (usually), designed around "average" bandwidth usage. The more users on a particular DSLAM, the less likely you are to get your maximum bandwidth. That's a shared medium for you. That's why shared mediums (like wireless, BTW) suck, but also why it's so much cheaper than a dedicated line--they can amortize the cost of the bandwidth across more than one user.

      The problem with DSL isn't what the telcos can't do, it's what they won't do. They can upgrade back end capacity to match demand--they just won't because they claim it isn't cost effective.

      Capitalism only requires DSL to be better than cable, not as good as possible--and even then only on average.

    230. Re:fairness by Anonymous Coward · · Score: 0

      > Then maybe they should be sold as such.

      They are. Try reading your service agreement. Seriously, they aren't even trying to hide the fact that the bandwidth is not guaranteed.

      > If a line is sold as a 10mbit line, I will expect it to be a 10mbit line.

      And if it is sold as a 10mbit maximum line (which it is), you should expect that it could be less. If you want 10mbit guaranteed, be prepared to pony up for it.

      Where I start disagreeing with the telcos is when the average availability is much less than the advertised maximum. For example, my local DSLAM is so overloaded that I routinely get 300 kb/s or less on my supposed 1.5 Mb/s link. My burst rate can actually exceed 1.5 Mb/s, but those bursts are pretty infrequent.

    231. Re:fairness by Cramer · · Score: 1

      Because from a router's perspective, there's no such thing as "connectionless".

    232. Re:fairness by Courageous · · Score: 1

      The average customer doesn't know what a byte is, so they probably don't know what MB/s is, not really. The average customer updates their computer when their internet is slow.

      Just sayin' man.

    233. Re:fairness by swillden · · Score: 1

      I don't believe you have a good case here :) I want to see something like a 20% improvement in, say, download time given the same network topology conditions, while still being able to avoid congestion well.

      I don't think anything like a 20% improvement is possible, given the fact that the present protocol is capable of pretty much saturating any given network link. However, when it saturates the network link it tends to force out all other traffic, and that is why the BT guys say they are switching to UDP -- maintaining efficiency while being a nicer network citizen.

      I think the achievable benefits are:

      • Small efficiency gains, due to avoidance of handshaking packets, ACKs, and similar overheard. These aren't going to amount to more than a fraction of a percent on a per-peer basis, but they are more significant if you use larger numbers of peers and smaller chunks.
      • Fast start should be achievable, which will provide a significant net performance improvement for small torrents. Connection-oriented BT tends to have a very slow start, since it starts up dozens of TCP connections, each of which does the normal TCP slow-start.
      • Better peer selection. Timestamping the UDP packets will allowing accurate round-trip timing to specific peers, without adding extra ICMP ECHOs just for latency measurement the way some BT clients do. Insofar as low latency corresponds to network locality, that's a good way to pick closer peers and reduce the load on the network. A UDP-based protocol would allow the client to use a wider set of peers at first, and then settle down to a near, fast subset.

      This seems like a lot of specialized little tricks and rules of thumb that aren't really simpler than what standard TCP-based clients do... again, I'm not convinced by the argument :)

      I think you're missing the forest for the trees. Each of the individual opportunities for improvement that I mention is small, but the fact that there are so MANY of them -- and don't forget that I'm no expert here, and I haven't spent a significant amount of time thinking about this, those who are experts undoubtedly have more and better ideas -- makes very clear to me that TCP is simply too limiting.

      That depends. I could view each TCP connection transferring one chunk as one packet. Then there is no ACK; if the connection breaks in the middle it times out just like the other method. I can also apply all the other connectionless tricks.

      Not all of them. In particular, you can't talk to nearly as many peers at once, due to OS and libc implementation issues. How many TCP sockets can you open at once? It's been a few years since I had reason to test this, but when I did no platform around allowed more than 1024, and most were far less than that.

      Even if that's no longer true, there's the question of why you would bother using TCP in that manner. If you want a connectionless protocol, then use one.

      --
      Note to ACs: I usually delete AC replies without reading them. If you want to talk to me, log in.
    234. Re:fairness by anothy · · Score: 1

      there's a lot in here i'm skeptical of.
      you assert that existing routers tend to favor TCP over UDP. can you support this? clearly it would be easy to do%2

      --

      i speak for myself and those who like what i say.
    235. Re:fairness by GuloGulo · · Score: 1

      "You've never talked to anyone outside your field about anything regarding the internet have you?"

      You've never accepted the diagnosis that you're mentally retarded despite proving it daily, have you?

      --
      "The government grants you rights, not the other way around."-- beav007. Yes, these people really exist...
    236. Re:fairness by fatphil · · Score: 1

      It'll have a cache. Let's not pretend it's something it's not.

      --
      Also FatPhil on SoylentNews, id 863
  5. This is a good thing by Gotung · · Score: 5, Insightful

    In the end this will be a good thing for the internet.

    Forcing ISPs to treat all traffic the same, because they can't tell what is what, will be good for net neutrality.

    You should get the bandwidth you pay for, regardless of what actually travels over it.

    1. Re:This is a good thing by michaelhood · · Score: 4, Insightful

      Except that probably isn't what will happen.

      Let's use Comcast as an example.

      Their target customer "surfs the web", and checks their email.

      Their high-maintenance customers, who complain about latency issues, throughput, etc. are the ones who use UDP in any significant volume.

      UDP is used for online gaming, VoIP, etc. They will just start to deprioritize UDP, which is bad. 99% of customers won't notice the difference, but we will.

    2. Re:This is a good thing by ThaReetLad · · Score: 1

      Maybe, but few of us have been actually paying enough to actually cover the cost of providing that full bandwidth 24/7.

      The ISPs assume that their customers will only use the peak bandwidth very occasionally, so that upstream they only have to provide enough bandwidth so that, on average, they are able to meet the minimum service levels. If the amount of bandwidth customers actually use rises dramatically the ISP will have to add a lot of extra capacity (and charge people for it) or introduce bandwidth caps.

      --
      You can't win Darth. If you mod me down, I shall become more powerful than you could possibly imagine
    3. Re:This is a good thing by markov_chain · · Score: 1

      Next step: switch to raw sockets, and implement a TCP without congestion control. Filter that!

      --
      Tsunami -- You can't bring a good wave down!
    4. Re:This is a good thing by Andr+T. · · Score: 1
      So, you think 1% of the internet users are online gamers? I don't have numbers, but I guess it's much more than that. And these people will notice bandwith problems.

      I completely agree with Gotung when he says you should get what you pay for. And if the ISPs don't like what is happening with p2p now, they should work out a way to bill the users according to the internet usage. I can't see why not.

      --

      Any life is made up of a single moment, the moment in which a man finds out, once and for all, who he is.

    5. Re:This is a good thing by c0y · · Score: 1

      You should get the bandwidth you pay for, regardless of what actually travels over it.

      It is time for an end to flat-rate pricing then. As long as my neighborhood hogs are actually paying their fair share, and my provider uses that revenue to increase our infrastructure so that I don't suffer his piggishness then everything would work out.

    6. Re:This is a good thing by Anonymous Coward · · Score: 0

      | The ISPs assume

      I see the problem right there. And you know what? it's not MY problem.

    7. Re:This is a good thing by kvezach · · Score: 2, Funny

      The real next step: file transfers over HTTP. Or go right out and tunnel IP over HTTP!

    8. Re:This is a good thing by maxume · · Score: 1

      If only a small group of people did this, they would simply engage the physical filter.

      --
      Nerd rage is the funniest rage.
    9. Re:This is a good thing by M-RES · · Score: 1

      No way - that's a return to the bad old days of having to keep an eye on how long you're online for! The ISPs aren't just moaning about P2P, they're having a good old whinge at TV companies hosting on-demand services too. The BBC's iPlayer is one such target for UK ISPs. That's not filesharing, but traffic over a normal http connection and people watching TV shows on bandwidth that should easily handle the traffic aren't being a 'hogs'. They're just 'surfing' in it's traditional sense - visiting websites and viewing the content on those sites. Legitimate use (even under acceptable usage policies) for the bandwidth they're paying for - it's the ISPs who have oversold their capacity.

    10. Re:This is a good thing by Chyeld · · Score: 1

      And that would have worked for them back in the 90's when the average customer "only used web and email".

      But in case you haven't noticed, that's not been true for a while. Guess who has a lower tolerance for BS? Sterotypical Little Red Riding Hood's "Grandma" who only uses email and web, and doesn't have any real expectations on how fast it should be, or Sterotypical power mom "Lynette" whose children are screaming at her because their Wbox 3 is 'broken'?

    11. Re:This is a good thing by rickb928 · · Score: 1

      How would this 'deprioritizing UDP' affect DNS?

      There's no way out of this without pain. Either the ISPs fix their interconnects so they can actually provide the bandwidth they claim to sell, or be honest and tell you that you will be throttled to a fraction of that when you saturate your link, or perhaps they fix the problem and make some form of hi-speed file transfer work. Since, after all, much of what we call 'Broadband' is intended to be, you know, 'high-speed'.

      Be aware that most if not all ISPs are trying to monetize their business by selling us lots of data, such as video. They see other large data providers suchg as BT as competitors. YouTube, if it nails HDTV, will also be a competitor, and Apple of course if iTunes does video right will also be their 'enemy'.

      Then we will be ready for an agnostic ISP. And none are on the horizon.

      feh.

      --
      deleting the extra space after periods so i can stay relevant, yeah.
    12. Re:This is a good thing by Anonymous Coward · · Score: 0

      or open your fucking wallet and stop stealing?

    13. Re:This is a good thing by pete-classic · · Score: 1

      I pay a premium for a faster tier of service from Comcast. They marketed this feature to me, and have collected hundreds of dollars from me for this upgrade.

      And somehow I'm doing them wrong by using it?

      They already have tiered service. I see no reason they shouldn't deliver on what they have marketed and sold.

      -Peter

    14. Re:This is a good thing by Opportunist · · Score: 1

      ...and THEN watch the internet grind to a halt with the insane overhead.

      Quite frankly, anything but a neutral net will lead to congestation.

      ISPs throttle Bittorent packets.
      BT packets get encrypted.
      ISPs throttle everything but HTTP traffic.
      BT packets get a HTTP wrapper.
      ISPs inspect HTTP packets and throttle everything but text
      BT packets get MIME/Base64 encoded. ...

      And with every iteration packets get larger and larger, the overhead grows, the intended effect, i.e. elimination of BT traffic and reducing bandwidth use, is never reached. Quite the opposite.

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    15. Re:This is a good thing by ajs · · Score: 1

      UDP is used for online gaming, VoIP, etc. They will just start to deprioritize UDP, which is bad. 99% of customers won't notice the difference, but we will.

      99% of customers are made up statistics ;-)

      A couple of things on this: 1) I don't know of any games (not saying they don't exist) that use UDP. The largest Internet-connected player base out there right now is World of Warcraft, and I know for a fact that that traffic is TCP-based.

      VOIP is easy enough to recognize and prioritize.

      The real issue that will be hitting ISPs (actually, already is) is the fact that they've been selling pipe to users that the users can't use ... and suddenly everyone and his brother Skippy is selling an Internet-connected video device. This means that customers will not only be using all of their allotted bandwidth, but they will be doing so during an ever-increasing percentage of the day (as their video devices automatically download subscription programming). I can already subscribe to a "season pass" for programming on my TiVo that is downloaded from Amazon, and sometime this month, Netflix is claiming they'll have the same TiVo integration. Sling, Blockbuster and many others are also sucking up your ISP's bandwidth.

      Simply put, these networks were never provisioned for this much usage, and I'll be surprised if there aren't massive growing pains along the way. Complaining about P2P traffic is a random thing that they feel they can control, not the core of their concerns.

    16. Re:This is a good thing by Opportunist · · Score: 1

      Actually that has been in place for a while now in some places in Europe, you get a certain useage (e.g. 10 GB/Month) and everything above costs you.

      Funny enough, we're moving away from that. More and more ISPs offer "unlimited" contracts for a nominal fee (about 5 or 10 bucks extra a month), and appearantly bandwidth usage isn't really a big deal, as long as you pay the equivalent of a pizza.

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    17. Re:This is a good thing by MaxwellEdison · · Score: 1

      As long as my neighborhood hogs are actually paying their fair share, and my provider uses that revenue to increase our infrastructure

      Oh that last part tickled me...what color is the sky where you come from?

      --
      -=Bang Bang=-
    18. Re:This is a good thing by brdsutte · · Score: 1

      The problem is not bandwidth. It's latency. You pay only for bandwidth, but for many applications you also care about low latency. And no single provider can ensure that you get some latency to every other corner of the world. Unless of course, everyone behaves as gentlemen. Then there are still no guarantees, but it seems to work pretty well in practice... let's keep it that way.

    19. Re:This is a good thing by Anonymous Coward · · Score: 0

      UDP is used for online gaming, VoIP, etc. They will just start to deprioritize UDP, which is bad. 99% of customers won't notice the difference, but we will.

      UDP is also used for DNS queries.

      The ISPs should be careful - I don't think they BitTorrent to run on port 53 by default and use DNS as a base for the protocol (which, make no mistake, would not only be possible but also quite easy to pull off).

    20. Re:This is a good thing by ThaReetLad · · Score: 1

      It will be when they charge you more, or they start charging based upon how much data you use, instead of the maximum peak bandwidth of your connection. You could argue that data volume charging is fairer anyway.

      --
      You can't win Darth. If you mod me down, I shall become more powerful than you could possibly imagine
    21. Re:This is a good thing by Forge27 · · Score: 1

      That would work for 75% of people for inbound only. Most ISPs I know of block port 80 servers. That and the overhead would probably suck.

    22. Re:This is a good thing by Real1tyCzech · · Score: 1

      And things like VOIP and RDP go the way of the donosaur.

      Sorry. Without QoS/p2p throttling, applications such as VOIP become unusable.

      What's your solution for that one?

    23. Re:This is a good thing by cobaltnova · · Score: 1

      This is modded funny, but it is the obvious next step in this ridiculous arms race.

      Its ridiculous because both sides are trying to solve a social (economic) problem with a technical measure.

    24. Re:This is a good thing by Real1tyCzech · · Score: 1

      *dinosaur. (note to self: proofread before posting...)

    25. Re:This is a good thing by Anonymous Coward · · Score: 0

      You assume you are actually PAYING for whatever bandwidth you "pay for". You don't. You pay for, usually, 10% of the bandwidth they tell you you're paying for, if that much.

      What you should be fighting for was for the ISPs to stop lying to people and to actually tell you that their "2Mbit/s ADSL" is actually a 256kbit/s connection burstable up to 2MBit/s for type of traffic, with all metering, filters and limits disclosed.

      Just don't expect to pay for 2MB/s of BACKBONE bandwidth left aside for you and delivered to your house, unmettered and unfiltered (which is what people are asking for when they complain about these things) for anything less than 10 times whatever you currently pay for your ADSL link.

    26. Re:This is a good thing by Anonymous Coward · · Score: 0

      I highly doubt that only 1% of comcast customers do anything beside surf the web. No need to be like the copyright regimes and just make up obviously bullshit number to support your theory. All that does is destroy your creditability and invalidate your argument.

    27. Re:This is a good thing by Tony+Hoyle · · Score: 1

      Well.. for certain values of "unlimited".

      It's a marketing trick that ISPs have been playing for years.. One of my phonea has "unlimited" internet with a 1GB cap!

      They're more subtle these days.. after they were well and truly caught lying by saying unlimited and putting caps in their FUP, they took the numbers out.. now it says something like "if your usage is excessive we reserve the right to throttle and/or cancel your account" without actually telling you what excessive actually is.

      There are one or two ISPs who are truly unlimited but they're very hard to find.

    28. Re:This is a good thing by DigitAl56K · · Score: 1

      Exactly.

      The Internet would not be melting down if the ISPs actually improved their capacity over time. I still get the same bandwidth today from my cable ISP that I got when I subscribed 3 years ago and to deal with increasing demand rather than improving capacity and speed instead we hear about bandwidth caps and throttling.

      Internet service in this country is failing to grow in line with demand and the finger is being pointed squarely at "abusive" customers while providers try to hold a price point and a revenue line with as little investment as possible. It's quite incredible really.

    29. Re:This is a good thing by StikyPad · · Score: 1

      Maybe Stereotypical power mom "Lynette" should stop spoiling her progeny and covering up their crimes, stop micromanaging her husband, and stop being an overall bitch. Just because you had cancer doesn't give you a license to screw up everyone else's life too.

      I mean, uh.. wait, what? Lynette who?

    30. Re:This is a good thing by Tony+Hoyle · · Score: 2, Insightful

      Most games are UDP based because TCP introduces latency. All the Doom/Quake/Unreal type games are UDP, as latency is important in those sorts of games.

      PS3 uses UDP. XBox360 uses UDP.

      Even WoW uses UDP for in-game voice chat.

      As far as the future goes, there are already ISPs that offer video services and it's only a short step to them *only* allowing video downloads off their servers. I expect the likes of Amazon and Netflix will be doing deals to ensure they get a piece of that pie.

    31. Re:This is a good thing by deroby · · Score: 1

      Depends,

      the question will quickly become : can you afford what you want ?

      (Not sure what you pay now for a x-Mbit line, but expect that price to go through the roof if you insist on it being 'constant speed' instead of the 'burst speed' that they sell right now, be it with 'dubious wording'...)

      --
      If there is one thing to be learned on slashdot, it has to be sarcasm.
    32. Re:This is a good thing by javilon · · Score: 3, Insightful

      Everyone here seems to work under the assumption that heavy bittorrent users would be worse off in a world with download caps or metered bandwidth. I don't think so. It would force companies to compete to give good service with clear contracts where they actually tell you what they are really selling. This is bound to increase, not decrease, the availability of real bandwidth per dollar for most users, included us computer geeks.

      --


      When his defense asked, "Which computer has Jon Johansen trespassed upon?" the answer was: "His own."
    33. Re:This is a good thing by Anonymous Coward · · Score: 0

      There are many gamers who have a cable-modem/dsl and their xbox 360, Playstation 3, Wii, etc. How about voip phones do they use UDP? Deprioritize UDP and I think the masses might complain.

    34. Re:This is a good thing by Tony+Hoyle · · Score: 1

      Of course they oversold their capacity, and they even told you by how much - in the UK the consumer lines are up to a 50:1 ratio. My own ISP keeps under 15:1 which pretty much means no slowdowns even during busy times... but I pay for the privilege.

      If they'd gone for 1:1 they wouldn't have sold many connections at £1000/month.

    35. Re:This is a good thing by Anonymous Coward · · Score: 0

      Personally I don't care when my downloads have a high latency. But a low latency is quite useful if you try to communicate with others.

      I would say it is a good thing to treat the traffic differently.

    36. Re:This is a good thing by Klaus_1250 · · Score: 1

      QoS and Throttling is not the same. Threating VOIP with a higher priority as BitTorrent is not a problem and noone could care less if you do (I do that myself). Dropping BitTorrent-packets in order to make room for VOIP is another ballgame and only (needs to) happen when your ISP has overbooked its network to such a degree that bandwidth is scarce. Overbooking is not a problem, unless you do to such an extent that your pipes become clogged.

      The whole issue with melting internet and smoking routers has nothing to do with BitTorrent, Youtube or whatever protocol/app you prefer. It is bad management, poor investment and limited competition of ISP's. Which is why this is not a global problem, but only affects certain markets and ISP's.

      --
      It only takes one man to change the Wisdom of the Crowd to Tyranny of the Masses.
    37. Re:This is a good thing by nurb432 · · Score: 1

      I second that.

      Except the true outcome is they will just raise prices and throttle us even more.

      --
      ---- Booth was a patriot ----
    38. Re:This is a good thing by Glendale2x · · Score: 1

      One can also pay for a T1 and nobody will say a damn thing utilization. You'll get awesome customer service, unfiltered, unshaped access to the internet, and you can peg it to 100% 24/7 and nobody will care. Also costs more. Using commodity circuits that 99% of the users only use 1% of the capacity is going to be a problem for the ISP. I'm not defending their business model, merely stating how it is. They're trying to oversubscribe as much as they can get away with to maximize profit; being able to get online is merely a byproduct.

      --
      this is my sig
    39. Re:This is a good thing by Anonymous Coward · · Score: 0

      This is modded funny, but it is the obvious next step in this ridiculous arms race.

      No. It's an OLD step in the arms race.

      REALLY old.

      Like. Gnutella 0.4 old. Remember Gnutella? Yeah. It's still around. And its backbone protocol is HTTP.

    40. Re:This is a good thing by Real1tyCzech · · Score: 1

      Sorry:

      QoS (or) Throttling. ...and I didn't necessarily include dropping packets in either of those.

      Perhaps I should have just stated "prioritizing". All the data needs to get where it's going, but some data is more important than others.

    41. Re:This is a good thing by qmaqdk · · Score: 1

      You may be joking, but this may happen. Let's see what Comcast's next move is.

      --
      My UID is prime. Hah!
    42. Re:This is a good thing by jmorris42 · · Score: 1

      > Simply put, these networks were never provisioned for this much usage, and I'll be surprised if there aren't massive growing pains along the way.

      The Internet was designed for video. Multicast would be the perfect way to allow dumping video into everyone's Tivo. Too bad the ISP are dead set against the notion of anybody but them doing it.

      --
      Democrat delenda est
    43. Re:This is a good thing by whoever57 · · Score: 1

      Everyone here seems to work under the assumption that heavy bittorrent users would be worse off in a world with download caps or metered bandwidth. I don't think so. It would force companies to compete

      And there is the propblem in the USA. For most USAans, there is no real competiton amongst Internet Service providers -- there is a duopoly. It's either the "Big Phone Company" (with its history of bad customer service) or the "big Cable Company" (rapidly expanding the scope of its bad customer service).

      --
      The real "Libtards" are the Libertarians!
    44. Re:This is a good thing by M-RES · · Score: 1

      Yes, but the slowdowns I personally experienced through traffic shaping were over a fibre-optic connection with 2mb package. You're not seriously telling me that a 2mb connection using perhaps three quarters of it's maximum throughput at most to stream video from a website is breaking the ISPs networks? Before traffic shaping, even WITH a huge number of subscribers, there was never any slowdown.

      I should imagine it may have been hitting some of the guys on the higher bandwidth packages even harder, but there was a blanket rule across all users - not even capping at a particular reasonable speed as max available at certain times (but what is a 'reasonable' speed anyway when you're paying for 20mb+?), just a cut-off point after 20 minutes of using a percentage of bandwidth on your package. The connection could drop as low as 56kb for as much as 6 hours as a 'punishment', regardless of how congested the network was at the time you were using your bandwidth.

      I switched to another ISP on ADSL2 (8mb) and even with network congestion evident from oversubscription, it rarely dropped below 2mb, but when it did I could understand the reasons why (too many people online at once) and the ISP had acknowledged the problem and expanded their capacity to take account of all their recent oversubscription. No traffic shaping, just natural network flow and suitable response by the ISP.

      Blocking people's usage is not a good idea - you just lose customers to competitors who don't do it. Using the money from the extra subscriptions you've taken to expand your service to keep everyone happy leads to more customers through recommendation, thus more income to expand the network and on and on - it's simple economics really. But rather than face this simple truism, most ISPs are trying to fight against spending the money or perhaps purposely trying to shed subscribers (by pissing them off) to get back to a level they can suitably maintain without having to spend money on extra infrastructure.

      Maybe I'm just lucky to have found an ISP who is orienting their business model to be customer-centric, but their willingness to invest in their infrastructure to cater for recent boosts in subscription after a wide advertising campaign looks promising. They had a month or so of moaning customers as there was a network-wide slow down due to the sudden influx of new users, but they publicised their work to expand throughput and resolve this issue including giving people a date when work would be complete, which they stuck to rigidly in practice.

      Other ISPs could learn from this approach. Don't alienate your users, treat them like people and they'll bear with you if you're reasonable. For the month or so of disruption, most users just modified their net use to get around the problem and then once the dust settled they went back to normal. Now it's back to great speed again, proof that investment works as I'd recommend them to other people.

    45. Re:This is a good thing by Trojan35 · · Score: 1
      UDP is used for online gaming, VoIP, etc. They will just start to deprioritize UDP, which is bad. 99% of customers won't notice the difference, but we will.

      I submit that the gaming industry is big enough (Sony, EA, Microsoft, etc) that gaming connections will not be de-prioritized.

    46. Re:This is a good thing by Kalriath · · Score: 1

      EA's old hat now. Activision-Blizzard is larger.

      --
      For a site about things like basic rights, Slashdot users sure do like to censor "dissent".
    47. Re:This is a good thing by Cramer · · Score: 1

      How would this 'deprioritizing UDP' affect DNS?

      From a consumer level, very little. 99% of consumers use their ISP's DNS servers so there would be very little need to throttle internal traffic. Plus, DNS amounts to effectively zero percent of network traffic. On my router, DNS is 0.22% of input packets and 0.13% of output packets (with no BT traffic on that network.) (83% for the link that has a DNS server on it :-))

    48. Re:This is a good thing by HeronBlademaster · · Score: 1

      Comcast used to say "there's no limit, but if you go over it we'll cut you off." I actually spent twenty minutes trying to get a Comcast sales rep to explain this logical inconsistency to me. (He eventually went off on some story about some customer sending 5000 e-mails per day... I don't think the CSR realized that 5000 e-mails per day couldn't be more than 50MB, if every e-mail were 10KB...)

      Now, though, they've taken their previously undisclosed limit and made it public knowledge. (What is it, 250GB per month?)

    49. Re:This is a good thing by HeronBlademaster · · Score: 1

      IIRC DNS queries are sent over UDP, but someone correct me if I'm wrong.

      So if this is true (a quick google search seems to indicate that it is), deprioritizing UDP packets would result in DNS queries getting deprioritized as well. On a congested link, that would result in DNS queries getting dropped or at least delayed, which could cause all sorts of issues on the client end. Anyone else here ever had Windows time out on a DNS query? It's kind of annoying.

    50. Re:This is a good thing by rickb928 · · Score: 1

      Someone out there, right now, is thinking how they can explain that this won't affect DNS. After all, UDP is a 'best-effort' protocol, intended to survive packet loss, delays, etc. by trying again and again.

      I'm much more interested in how many ISPs will use UDP manipulation to both hammer BT and possibly selectively deny or frustrate DNS to various services or hosts they find 'harmful'.

      We are well on our way to a seriously degraded Internet, if U.S. ISPs continue to modify traffic for *whatever* reason.

      This is getting to the crux of Internet service as a utility. Imagine some power generators, say the TVA or similar, denying other providers from using their grids to deliver power from one region to another. Not helpful to the overall grid, and could end up in a retaliatory environment with bad consequences.

      Then again, the Internet based on NAPs and peering in the U.S. is a mess already and we sort of don't know it. See the Sprint/Cogent tiff for an example of how fun it can be.

      Whne the ISPs start BGP poisoning, then we will have to sanction them somehow.

      Yeah, right.

      --
      deleting the extra space after periods so i can stay relevant, yeah.
    51. Re:This is a good thing by hany · · Score: 1

      And there is the propblem in the USA. For most USAans, there is no real competiton amongst Internet Service providers -- there is a duopoly. It's either the "Big Phone Company" (with its history of bad customer service) or the "big Cable Company" (rapidly expanding the scope of its bad customer service).

      ... And this problem wont be solved by any "packet shaping" ever no matter which of those two will be doing it. :)

      It still boils down to (some) ISPs overselling their network to the point where "last mile" capacities greatly overwhelm the capacity of ISP's backbone and uplinks. Overselling is good for ISP - more profit. But overselling is bad for consumers - they do pay for X megabits per second but in reality get only fraction of that.

      Of course such ISPs usually do not wont to either admit they are ripping the customers off nor to lower their profit by investing into the infrastructure. What's worse, quite a lot of ISP have a bussiness model so tuned to "oversell" that they can't start providing decent service without rising prices significantly.

      And that usually leads to such nonsense as "users of BT are declaring war against users of VoIP" etc.

      People please - if you hear any such nonsense from your ISP, switch the ISP.
      And if you are unable to switch then its a good indication that the "market with Internet connectivity" you live in is not "healthy" and is most probably not able to provide you with good service for good price. So then take propers steps to fix that (like complain to FCC? or anti-monopoly office?)

      --
      hany
    52. Re:This is a good thing by 3p1ph4ny · · Score: 1

      HTTP != port 80

    53. Re:This is a good thing by Anonymous Coward · · Score: 0

      Actually, Markov Chain, it's pretty easy to filter that.

      Sorry that this is a little disorganized, I was distracted when writing it, and well, it's just an anonymous coward slashdot comment, so the motivation to edit is low. :-)

      Let's assume first that the "raw socket ... TCP without congestion [avoidance]" is done naively, thinking that it might help get all the bits of a particular chunk of data from source to destination faster than TCP would. That is, rather than a smart game theoretical analysis of the bottleneck bandwidth distribution dynamics, the designer of the protocol honestly believes a firehose of duplicate data will win over a patient congestion avoider who aims to minimize packet loss and duplicate transmission.

      We know one important thing about the packets, and that is that they all have a common destination network layer address (or for ipvsux, possibly a substantial range of dst nl addresses, so we might want to consider a common but reasonably long prefix, to catch dst addr hopping done at the source towards a destination that listens to a large range of addresses).

      Next we know that TCP style congestion avoidance is a good thing for reasonable sharing of bottleneck bandwidths. We know a good deal about TCP dynamics, in particular, we know that if we randomly drop packets from our chosen class (packets towards the range of destination addresses) we should see a significant drop off in traffic.

      We don't care when there is no queue; if we are not a bottleneck, why police traffic? Let the bottleneck on any given path do that. (It *will*, even if "policing" is simple FIFO with a finite queue length).

      We do care if we have an average queue length longer than zero over even a relatively short time. If we're delaying packets in a queue, we're a bottleneck. Our job is to share the bottleneck bandwidth reasonably fairly among the *users*.

      A nice user can be spotted because there is a stable 5-tuple: network layer src, nl dst, transport layer protocol, transport layer source, tl dst. For instance: (10.1.1.1,192.168.1.1,tcp,80,41061). Nice users back off when signalled, so if we randomly choose to drop a packet from that 5 tuple, we would expect not to randomly select that 5-tuple again for a substantial amount of time, because it's either transient traffic, or because it engages in AIMD. If what we think is a nice user keeps being selected randomly, it's misbehaving and should be stuffed into a penalty box where we drop against it aggressively even if we have no queue.

      That is, punish users who do not back off when we are a bottleneck.

      The problem here is that at a busy interface, we could be seeing many thousands of these 5-tuples a second. That may or may not be a problem; in some routers we can easily tweak the forwarding ultimate directive (or node in the m-way routing tree) to aim at a penalty box or to indicate that we have recently dropped from the 5-tuple, provided we have 5-tuple granularity.

      If (very likely) we lack 5-tuple granularity and only know about fairly coarse-grained prefixes (/29s, and shorter, for example, for the IP case; possibly /48s and shorter for the vsux case, who knows?) we can at least deaggregate down to a /32 or /48 temporarily.

      That is, if we have a queue, and we randomly drop from the queue, and we can remember which of the routes learned from e.g. BGP we have done this to recently, we can probably temproarily do a binary deaggregation of the routes to avoid penalizing a whole class of destination addresses just because there is one bad actor in that prefix/mask combination.

      So we might have:

      4.0.0.0/8 --> forward normally [4/8 learned from bgp]
      4.0.1.26/32 --> put in penalty box [packets towards 4.0.1.26 have been in a random selection from the nonzero average queue length recently]

      penalty box could be a nonzero chance of drop, or a delay using some sort of fancy qu

  6. I blame ... by Krneki · · Score: 0, Flamebait

    The terrorists, it's all their fault.

    --
    Love many, trust a few, do harm to none.
  7. File Service Protocol by FriendlyLurker · · Score: 2, Interesting

    "They" said the same thing about once popular File Service Protocol (http://fsp.sourceforge.net/) way back when the net was young, pre-Napster, and before any massive internet infrastructure investment was made...

    1. Re:File Service Protocol by electrosoccertux · · Score: 4, Insightful

      They also said the same thing when UDP streaming internet video became a hit-- their servers couldn't keep up.
      They just had to upgrade.

      Hopefully the same thing will happen now.

    2. Re:File Service Protocol by MBGMorden · · Score: 4, Insightful

      I think this whole thing is just hinging on them upgrading the darned infrastructure. The ISP's have sat fat and lazy for too long just selling you a "faster pipe" as the last mile of cable got faster. All that while though the baseline infrastructure has been receiving upgrades as a snail's pace, while at the same time more and more users are jumping onto the net in droves.

      They pocketed far too much money that should have been allocated to network upgrades to actually support increasing TRUE capacity - not just a theoretical burst speed that you might maybe be able to get for 3 or 4 minutes back home.

      It's like that lazy employee who has 3 months to do 1 week's worth of work. He puts it all off until he has 2 days left, and then starts to moan about how he doesn't have enough time to do all this work. Well, at this point, he's right. It's his own fault though. My boss has a nice poster in her office that I think applies here: "Lack of planning on your part does not constitute an emergency on my part."

      --
      "People who think they know everything are very annoying to those of us who do."-Mark Twain
    3. Re:File Service Protocol by LS · · Score: 1

      I don't discount your logic, but the difference between now and then is that the massive internet infrastructure investment has already been made, and a massive economic downturn is in our face, causing everyone to cut spending for new infrastructure, thus stopping the growth in bandwidth while the growth in bittorrent traffic continuously grows.

      To be honest I have no idea how this change will affect internet traffic or ISP policies. I don't know all the technical and business factors involved and won't pretend to know the future.

      LS

      --
      There is a fine line between being a cultivated citizen and being someone else's crop. - A. J. Patrick Liszkie
    4. Re:File Service Protocol by IamTheRealMike · · Score: 2, Insightful

      The problem is that P2P traffic is notorious for expanding to fill whatever capacity is thrown at it, which is why it now takes up such a giant amount of backbone capacity. So your "lazy ISPs should upgrade the darn infrastructure" argument isn't that convincing, I expect them to do so and then I expect BitTorrent users to fill those links immediately with more crap that they download and then never watch/install/use.

    5. Re:File Service Protocol by Anonymous Coward · · Score: 0

      They should have included guaranteed and maximum bandwidth provided, as often in businnes connections.
      Then if I get 10Mbps max and will be told when signing the contract that guaranteed is let's say 1Mbps, then I will have a speed of 10Mbps most of the time and only during peaktimes it will go down eventually, but it will be guaranteed to 1Mbps.
      Guaranteed up to their border routers.
      'nuff said.

    6. Re:File Service Protocol by bit01 · · Score: 1

      The ISP's have sat fat and lazy for too long just selling you a "faster pipe" as the last mile of cable got faster.

      True. One thing that bugs me is the lack of support for multicast. This has the potential to significantly and cheaply improve network efficiency with almost no change in network hardware at all and yet, with a few honorable exceptions, ISP's have been too slack to consistently implement it.

      ---

      Windows and closed source software. The US intelligence agencies back door to every network connected country and business on earth.

    7. Re:File Service Protocol by electrosoccertux · · Score: 1

      My subscription plan is capped at 8megabits/second.

      I'm not getting that speed even on the best torrents.

      Complain to your ISP, not to other bittorrent users.

    8. Re:File Service Protocol by Anonymous Coward · · Score: 0

      Except of course, when the company is depending on the work being done by the deadline. Then it's an emergency on the manager's part: the solution will include replacing the employee.

    9. Re:File Service Protocol by Iced_Eagle · · Score: 1

      They also said the same thing when UDP streaming internet video became a hit-- their servers couldn't keep up. They just had to upgrade.

      I wonder if the worse economy will affect that decision at all.

      If Comcast had the option of upgrading their servers for X amount of dollars (which perhaps could have been an unplanned upgrade due to the possible stress of their network brought on fairly suddenly) or rather limit all UDP traffic to reduce stress for a hell of a lot less, what do you think they will do (and remember this is Comcast, the master of throttling)?

    10. Re:File Service Protocol by im_thatoneguy · · Score: 1

      There's a viscious cycle at work here.

      1) Lack of streaming options leads people to pirate.
      2) Pirates slow down internet.
      3) Media offers better streaming options but connections are too slow becaue of piracy. Even though both are free.
      4) People turn to piracy instead of legal streaming because of skipping and lag.
      5) Piracy slows down streaming drivng people to download and watch instead of streaming.
      6) And so on and so forth.

      I pirate shows that I forget to DVR even if they're available on Hulu because my internet connection is only 3mbps on average over an hour... it fluctuates wildly between .5mbps and 5mbps. Watching Hulu takes longer than watching it with commercials... so I download it.

      Netflix and Hulu need to get some deals with Comcast, Qwest etc and setup summer olympics style caches of their libraries. Netflix + 360/settop is a potent combination. Qwest could easily sell me on a $1 a month netflix hosting fee to give me a short loop to 6mbps Netflix HD above and beyond my normal internet connection.

      ISPs should also be encouraging MANs. If I had 50mbps across town connection I would imagine a lot of bittorrent traffic would be pulled from the backbones. It would also be great for VPN work.

  8. Comcast by CDOS_CDOS+run · · Score: 1

    Comcast will just block UDP completely... duh it's not like they care if you can use 'your internets'

    1. Re:Comcast by Anonymous Coward · · Score: 0

      Once your modem says it's connected, Comcast is satisfied that they have done their job.

    2. Re:Comcast by Anonymous Coward · · Score: 0

      Ya because nothing relies on UDP at all...

    3. Re:Comcast by Anonymous Coward · · Score: 0

      Nothing important. As long as users can reach Google, Facebook, and Hotmail they are providing the services 95% of the users use.

    4. Re:Comcast by Opportunist · · Score: 1

      Hmm... let's see...

      Does "the internet" work (read: Browsing pages with internet explorer)? Check.
      Can people download and look at pr0n? Check.
      Can you use YouTube? Check.
      Can you play WoW? Check.

      Should keep us 99% of our customer base and we cut the high bandwidth users? John, throw the switch!

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    5. Re:Comcast by Piranhaa · · Score: 1

      You would theoretically breaking DHCP, DNS, NTP, VOIP/skype/MSN video&voice. Heck, why don't we block icmp while we're at it. Who really needs to ping and traceroute on the internet anyways? Sounds they're use for (D)DoS'ing anyways.

    6. Re:Comcast by shawb · · Score: 1

      Nothing important, indeed. I think you'd have a lot of annoyed customers if they had to go to 69.63.176.140 rather than www.facebook.com

      --
      I'll never make that mistake again, reading the experts' opinions. - Feynman
    7. Re:Comcast by Grandim · · Score: 1

      You forgot gaming, sacrilegious.

    8. Re:Comcast by Kalriath · · Score: 1

      So are they going to push out a firmware upgrade that makes the connected light come on whether you have connectivity or not?

      --
      For a site about things like basic rights, Slashdot users sure do like to censor "dissent".
  9. Just around the corner by Yaur · · Score: 1

    The net has been about to melt down any day now for at least 10 years.

    1. Re:Just around the corner by Skater · · Score: 1

      Yeah. I remember reading something similar when the "secret" of adjusting your MTU came out in the days of 56K modems.

  10. Re:A little extreme there, don't you think? by FredFredrickson · · Score: 5, Insightful

    The problem is, that it could be ligitimate. Are you the judge and jury? Don't let something set a precedent that could affect our legal freedoms as well.

    --
    Belief? Hope? Preference?The Existential Vortex
  11. Re:Well Duh by stonecypher · · Score: 2, Insightful

    That ISPs will start shutting BitTorrent users down, including legitimate ones, when they realize that BitTorrent users have forced them into a 95/5 choice. It isn't appropriate for legitimate bittorrent users to be driving other TCP off the network, let alone the vast bulk of what BitTorrent is really used for. You're not backed into a corner, getting stabbed in the face, or being locked in the bedroom; you just want to bully other people out of their bandwidth so you get more. It's about to explode in your face. There's no need or reason for this switch to UDP. This will, however, create a serious reason for ISPs to want rid of BitTorrent.

    BitTorrent is going to find out, very soon, that it shouldn't try to be a bully; it's making other customers vote with their wallets, and if you force the point, there are actually a ton of ways to stop this cold (which unfortunately hurt the rest of us too, like caps). Unfortunately, BitTorrent fascinated mods are about to call me a troll or say I'm promoting flamebait, when I'm doing neither, because I'm telling them something they don't want to hear, but whatever.

    This isn't the right way for BitTorrent to move forward, even when you only look at it as a collection of people using a protocol for legitimate purposes. You're just being greedy.

    --
    StoneCypher is Full of BS
  12. Daft by symes · · Score: 1

    Gamers, VoIP and video conference users beware. The leading BitTorrent software authors have declared war on you - and any users wanting to wring high performance out of their networks.

    What a load of nonsense. The best solution (if there's a problem here in the first place) is for ISPs to drop any bandwidth allocation.

    1. Re:Daft by abigor · · Score: 1

      Not mention have them start metering bandwidth. Then the "average" user (internet surfing, email, etc.) would end up paying little, while the BT hogs would pay thousands of dollars a month, which is fair enough.

  13. excuses... by Oceanplexian · · Score: 1

    Obviously, isps aren't going to lay down and die. They'll simply throttle the offending users and throttle udp for residential customers. The problem with this is that legitimate applications like voip will be blocked or throttled with the excuse of "fighting the thieving pirates". I hate packet tampering as much as anyone else here, but without qos rules everyone loses.

    1. Re:excuses... by Opportunist · · Score: 1

      The problem is that people will fight that QoS, by encrypting and tunnelling, increasing overhead by packet masquerading and thus everyone loses even worse. Becaue people will try what they can to keep doing what they want to do.

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    2. Re:excuses... by Terrasque · · Score: 1

      I've worked in 2 norwegian isp's. The first one, one of the bigger ones in norway have an average network usage of around 40-50%, with no link over 80% used, even in peak times.

      The second, a smaller one more centered on business customers (but also sell to private), the numbers are more around 30% and 50%.

      Do you see a difference from US isp's? There's no need to do QoS, because there is no bottleneck in the network. And 15-20 mbit/s download speed is the norm around here.

      In fact, around 5-6 years ago my isp did a test of their infrastructure. Want to know how they did it? They sent a mail to all customers saying "Hello, this weekend we're going to test our infrastructure, and we'll set everyone's line to the maximum it can handle. Please try to download as much as you can." - This was when 1mbit was considered fast, and everyone got their line set to max (mostly 8mbit). After that they went out with some very agressive pricing, so I guess the test was a success.

      I know there are many differences between usa and norway, especially the number of people, but still.. Quite some contrast, don't you think?

      --
      It's The Golden Rule: "He who has the gold makes the rules."
  14. don't see it myself by myxiplx · · Score: 5, Insightful

    Well, since The Register don't seem to want to print my comment*, I'll repeat it here:

    "I think this is a bit of scaremongering that's missing one vital point:

    When an ISP throttles UDP packets because somebody is using excessive bandwidth, they'll be dropping packets *from that source*.

    So while .torrent moving to UDP is going to affect VOiP and games, the effects of that will be *restricted to the person using excessive bandwidth* via bittorrent. There's no reason it would affect anybody else, and I doubt ISP's are going to be dumb enough to block packets at random.

    Unfortunately that kind of blows the articles entire premise out of the water."

    Myx

    * Posted at 12:40pm, ten minutes after the article appeared, at a point where there were no other comments on the article. 3 hours later there are 37 comments, but no sign of mine. Now it may be that they've just been overwhelmed with comments, but I'm a suspicious soul at times...

    1. Re:don't see it myself by Anonymous Coward · · Score: 0

      ISPs which are meddling with traffic shaping love to drop every X packets within one TCP session. Such filtering is impossible to prove without whistleblowers, and it works by exploiting TCP window scaling which directly affect effective bandwidth. IP packets do get lost, and losing every X of them is hardly unique or suspicios.

      So, every TCP connection, that gets classified as a BT or BT suspect connection gets ever 1000th TCP packet dropped. Effectively limiting bandwidth of single TCP connection. If some other TCP connection gets misclassified, nothing tragic happens. The mail might be delayed a little, but certainly not noticable.

      UDP has no such traffic shaping protocols or assurances, so this kind of "traffic shaping" done by ISPs will have no effect. They will have to invest heavily into new DPI engines that can really inspect each and every packet without any more delay than store-and-forward switch creates. I.e. wire-speed inspection of each and every UDP packet.

      BTW: Most DPI engines, even some that are so-called "cutting-edge", still cheat in a way, as they make SW decision on first couple of TCP packets in flow and then relegating the logic to couple of predefined actions in HW, based on ACL lists. Make them check each passing UDP packet on a 1Gbit/s link in SW, and see them melt down and die in horrible pains. Nice.

      Certain unnamed (no commercials here, thos who have it, know it) monster of an DPI engine, which in reallity even isn't a DPI engine, but rather a quite generic network CPU programming platform, might chew 2 or 3Gbit/s, but anything above that simply isn't available on the market. Yet.

      Where does this leave us? ISPs will adapt, just as BT was/is adapting. I think this was inevitable and long time in coming. I also think that one of two things will happen: move back to walled gardens - i.e. end of the internet as we know it; or, alternatively, weeding out of the providers that are not capable of affording either expensive DPI solutions, nor high-capacity uplinks - i.e. less competition and higher prices.

      I know which option I prefer... and it certainly isn't walled.

    2. Re:don't see it myself by melikamp · · Score: 4, Funny

      Your post might have been dropped, probably due to the excessive amount of posting from your end.

    3. Re:don't see it myself by myxiplx · · Score: 1

      Hahahaha. Mods, this needs to be +1 funny. :-D

    4. Re:don't see it myself by BobSixtyFour · · Score: 1

      I think your ISP blocked your post at random, because your an excessive poster XD. (This is an attempt at an joke - for those of you without a humor chip)

    5. Re:don't see it myself by AndrewNeo · · Score: 1

      Your lowercase letter in VoIP got moved over one. Voice over IP.
      When you write it like VOiP it reminds me of the robot from Homestar Runner.

    6. Re:don't see it myself by Anonymous Coward · · Score: 0

      You probably just Previewed without Sending you paranoid fellow :) El Reg simply don't censor comments like this.

    7. Re:don't see it myself by zdzichu · · Score: 1

      Is anyone really expecting to have great experience with VoIP and games while having some heavy torrents running? No matter TCP or UDP, it's not going to work.

      --
      :wq
    8. Re:don't see it myself by Anonymous Coward · · Score: 0

      I don't think I've ever read an article on The Register that wasn't scaremongering.

    9. Re:don't see it myself by Anonymous Coward · · Score: 0

      Perhaps your precious packet got blocked by the ISP?

    10. Re:don't see it myself by jonaskoelker · · Score: 1

      When an ISP throttles UDP packets because somebody is using excessive bandwidth

      I assume good nature on behalf of the ISPs, meaning that "excessive bandwidth" is understood to exactly mean "more than you paid for".

      I would assume the ISPs to drop IP datagrams to matter what protocol is used inside them; TCP, UDP, RTP, whatever. You used more than you paid for; away goes the packet.

    11. Re:don't see it myself by sudog · · Score: 1

      Yes they do. ISP and core routers already do drop packets. But it's not at random. They drop it when dropped packets don't halt the incoming flood of other packets which are all part of the same connection or even connection class.

  15. ISPs will love UDP by Anonymous Coward · · Score: 0

    If they drop TCP packets or try to fake reset the connection, it's obvious and provable. If they silently discard UDP packets, that's just normal network behavior.

    1. Re:ISPs will love UDP by Anonymous Coward · · Score: 0

      It's not at all obvious and provable, especially they're doing it less often than Comcast was, considering that RST resets happen anyhow!

  16. bittorrent is THE mesh networking application! by Anonymous Coward · · Score: 0

    I was thinking. The people doing Skype have a point. I don't care if my packets take three, four, or five times as long to get to me. I ONLY care about the total time to get the 700 MB (or whatever). It could take a path five times as long as the voice communication, I don't care.

    Then it hit me. A CD-ROM. They're always falling off the shelf above me.

    As I lay there rubbing my head I thought: if my roommates voice call is so important, he wont mind peering into a mesh network at the same time, to keep me from using his bandwidth with his ISP. The thing about mesh networks is, they're nowhere near as direct as your ISP. But with bittorrent it just and simply DOESN'T MATTER. It literally doesn't matter if it it take 8 seconds to get from me to my roommate to his neighbor to their roommate to their son downstairs in the basement to their neighbor across the lawn who is one of my seeds. ALL that matters is not getting throttled.

    Folks: Bittorrent is the killer mesh application, and we need to get people who want their precious skype to realize that just by joining the mesh, they can improve their voice quality! It's the perfect trade-off.

  17. Total bullshit by Idaho · · Score: 3, Interesting

    UDP does not guarantee delivery. If ISP's want to, they can simply start dropping UDP packets once the total amount exceeds a certain threshold. This should be almost trivial to implement.

    Sure, just blindly dropping all types of UDP packets will also degrade VoIP services etc, but certainly this does not need to impact "the entire speed of the internet".

    Since VoIP and other "normal" uses of UDP do not need terribly high bandwidth, the problem can be easily solved by imposing a maximum UDP throughput per IP and simply dropping any UDP packets past that limit. That way, VoIP will still work just fine but other services "abusing" UDP will just be effectively capped by the unguaranteed delivery.

    I'd love to see lawsuits about this as well, as UDP does not guarantee delivery so you would hardly have a basis to complain when ISP's drop such packets, especially as long as they deliver *most*, but not necessarily all such packets.

    --
    Every expression is true, for a given value of 'true'
    1. Re:Total bullshit by michaelhood · · Score: 1

      I think you're probably spot on here about what will actually happen if BT/uTorrent goes forward with this.

      VoIP streams only use up a few kBps, even 4 lines going simultaneously will only use about 12 kB/s. I suspect it will be pretty easy for them to implement shaping to handle these issues.

      Some net appliance vendor (Sandvine?) is going to make a killing in the next year.

      I thought it would be a bit longer before we saw some real world tests of net neutrality issues, perhaps not.

    2. Re:Total bullshit by Spatial · · Score: 1

      as UDP does not guarantee delivery so you would hardly have a basis to complain when ISP's drop such packets

      You'd have exactly the same basis as you would in any other situation: they're actively interfering with your connection. A protocol specification isn't a law. It doesn't matter a damn what it says.

    3. Re:Total bullshit by Opportunist · · Score: 1

      Sometimes it seems my ISP is already using that "dropping random packets" kind of traffic shaping...

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    4. Re:Total bullshit by AK+Marc · · Score: 1

      You'd have exactly the same basis as you would in any other situation: they're actively interfering with your connection.

      I don't think we are talking about the same thing. The way networks work, slowing things down to make sure things that are being sent will fit is an important part of reducing congestion. If whatever bandwidth management tool is acting, that does not mean they are "actively" interfering with the connection. When too much traffic is going through, something is dropped. If they expect everything to be over UDP and throttle according to the protocol specifications, I would assert that it isn't "active" interference, but automated backgrougd interference done to make the whole system better. If they choose to select UDP packets, sorted descending by size, and drop them to make room for everything to fit, that would be one way of doing it.

      A protocol specification isn't a law. It doesn't matter a damn what it says.

      Just because a service is provided doesn't mean that the service will have no restrictions. They aren't doing a man-in-the-middle attack to reset connections with fabricated packets impersonating servers. I can't think of any hacking law that doesn't break. But to drop packets because the network is full, as long as you aren't singling out a specific person or company, I don't see how it could be illegal. What specific law is broken by TCP throttling? If none, then why do you think that a similar throttling measure employed by a 3rd party to enforce similar rules on UDP would be illegal?

    5. Re:Total bullshit by CarpetShark · · Score: 2, Insightful

      UDP does not guarantee delivery, but you can still run a packet loss test and take your ISP to court for selling a service of unmerchantable quality if it's that unreliable.

    6. Re:Total bullshit by Spatial · · Score: 1

      I don't think we are talking about the same thing.

      You're right, I got the wrong idea of what you were saying. I had thought your reasoning was based on the specification determining what the ISP could do from a legal perspective, but obviously I was mistaken. I'm in agreement.

    7. Re:Total bullshit by JesseMcDonald · · Score: 1

      From a legal point of view there should be no difference between TCP and UDP with regard to dropped packets. Individual TCP packets aren't guaranteed to be delivered, and get dropped all the time and for a variety of reasons. It's only at the application level that the protocol ensures aggregation and retransmission so as to reconstitute the original data stream without missing pieces or duplicates.

      In the absence of an SLA, there really is no guarantee of any specific service on the part of an ISP toward its clients.

      --
      "The state is that great fiction by which everyone tries to live at the expense of everyone else." - Bastiat
    8. Re:Total bullshit by swillden · · Score: 1

      UDP does not guarantee delivery. If ISP's want to, they can simply start dropping UDP packets once the total amount exceeds a certain threshold. This should be almost trivial to implement.

      EXACTLY the same thing is true of TCP.

      In general, an ISP's routers don't see TCP or UDP -- they see IP packets, some of which are TCP and some of which are UDP (and a few of which are other things). IP does not guarantee delivery. TCP adds some retry logic to ensure delivery, because ISPs can and do drop IP packets all the time. One of the basic functions of a router is to decide when it has more IP datagrams to deliver than it can, and which ones to drop. Routers don't try harder to keep IP packets which are carrying TCP segments than those carrying UDP datagrams.

      Routers performing QoS prioritization of packets look at various facets of the IP datagram contents to determine which to move to the head of the line and which ones to discard, but relatively few ISPs actually do QoS, and the "protocol" field of the IP header isn't usually the key decision factor. The port fields in the TCP or UDP headers are typically more important, as well as some of the other IP, TCP and UDP header flags.

      --
      Note to ACs: I usually delete AC replies without reading them. If you want to talk to me, log in.
    9. Re:Total bullshit by carpevita · · Score: 1

      Yes, routers can drop UDP, but the user will still be flooding the incoming links, all the way back to the DSLAM. UDP does not have source-quench based flow control.

    10. Re:Total bullshit by HeronBlademaster · · Score: 1

      I don't think you could successfully sue someone in court for not making an inherently unreliable protocol reliable. UDP does stand for "unreliable", after all, and it's silly to expect an ISP to make it reliable.

      Of course, I wouldn't have thought you could successfully sue someone in court for making hot coffee hot, so I may be way off base here.

    11. Re:Total bullshit by CarpetShark · · Score: 1

      ISPs provide a line over which to send data. That line needs to be reasonably good, or you get high latencies etc. when packets drop. You could easily argue that the service is suffering due to the packet loss, and once that happens, I image you would be able to make a case that their service is much worse than similar services for the same price, or than the service you were getting previously, thus bringing the contractual expectations into play.

      But yeah, it's not the ideal way to have to get a decent service. I don't even know why I'm arguing for this, as essentially, I think court justice processes are pie in the sky for most people with limited funds/time.

  18. In the End by NotNormallyNormal · · Score: 1

    In the end, is this truly going to change how the ISPs work? The article mentions that one of the reason for doing this is because of Bell Canada. I personally don't think Bell Canada is going to care - neither will Comcast and all the other ISPs who throttle and shape the network (can we say all ISPs at this point to at least some extent?).

    Really, all this will do is continue to drive a wedge between the "evil" file sharers and "enlightened" ISPs who will attempt to use the other 95% of the users to make claims to whoever will listen... Personally I don't do much file sharing and I'd get real pissed if my broadband speed dropped to a quarter of what I actually pay for.

    1. Re:In the End by MBGMorden · · Score: 1

      neither will Comcast and all the other ISPs who throttle and shape the network (can we say all ISPs at this point to at least some extent?).

      Spirit Telecom SEEMS to still not be doing anything right now. I only have a 1Mbps downstream so I might be a bad measurement, but I get full bandwidth from that at all times even on Bittorrent. I'm not sure what my monthly bandwidth usage is, but I can say that I have Bitorrent configured to allow 100% utilization while I'm at work and 40% when I'm home, and more often than not I have files queued up for transfer (or at a minimum, I'm seeding files). I still haven't hit any throttling or caps so far. As mentioned though, with the 1Mbps downstream it'd be darned hard to hit the 250GB limit that Comcast set for example.

      --
      "People who think they know everything are very annoying to those of us who do."-Mark Twain
    2. Re:In the End by AndrewNeo · · Score: 1

      I know AT&T's not touching anything (at least yet) when it comes to throttling. I've been using them for about four years now and haven't noticed issues once with running Bittorrent, even when I've left it open for days.

  19. Re:A little extreme there, don't you think? by serviscope_minor · · Score: 3, Insightful

    Using your stupid analogy, this would be more like threatening to raze the entire city to the ground because no one intervened to stopped the wife from being locked in the bedroom.

    So she should sacrifice her entire life for people who clearly don't care? Why not let them all burn? Are you sure you wouldn't do the same if you were in her position? What if it was worse then being locked in the bedroom?

    Ok, moving on from a rather stretched analogy...

    Anyone who is caught using uTorrent with this setting gets their broadband internet access contract torn up.

    Interesting anecdote. A few years ago, my NTL contract specifically mentioned how traffic over TCP/IP had to be legal, etc. For some reason UDP, ICMP, etc was not mentioned. Odd. I'm no longer with them, and they no longer exist anymore, so I can't check to see if its changed.

    Don't even pretend that most bit torrent traffic is legitimate and legal. For every Linux DVD image distributed by bittorrent, there is probably dozens of times that much data in blatantly bootlegged content being distributed.

    I don't care. I have *never* pirated anything over bittorrent, even thought I've used it a number of times.

    --
    SJW n. One who posts facts.
  20. best thing for the Internet? by Ephemeriis · · Score: 1

    Obviously if you're going to try to transfer large files over UDP you're going to need to develop some way to ensure reliable delivery - which is exactly what TCP does. TCP has years of work behind it, so the odds of you coming up with something just as good as TCP are fairly slim. So I can certainly understand why folks out there would be somewhat apprehensive about this decision... There is a distinct possibility that the new protocol will waste tons of bandwidth or do something horrible to existing equipment or summon up a shoggoth. There is certainly the possibility that damage will be done.

    But is that necessarily bad for the Internet? ISPs are regulating the hell out of TCP traffic. They're shaping and compressing virtually every packet that crosses their networks. They're blocking ports and resetting connections. They are intentionally preventing their customers from using the bandwidth they've bought in the way they want. Doesn't that count as damage?

    Maybe this is exactly what the Internet needs to drive home the point of network neutrality. Maybe if ISPs get stuck with a new, horribly inefficient protocol that they can't mangle they'll realize it was a bad idea to abuse TCP.

    --
    "Work is the curse of the drinking classes." -Oscar Wilde
    1. Re:best thing for the Internet? by japhering · · Score: 1

      Problem is most ISPs aren't setup to pay for new equipment at the needed rates. They are setup to only replace equipment as it fails or as it reaches the end of tax deductibility( 3- 5 years in the US ). Around here, we replace everything every third year and figure that 20% of the gear will fail in any given year.

      Thus to change to an every year update plan would probably require a doubling (which the ISPs would see as their chance to triple) the existing rates, with no other benefits than the ability to use your paid for bandwidth. No speed or reliability improvements without adding yet another multiple to the cost.

    2. Re:best thing for the Internet? by kvezach · · Score: 1

      Obviously if you're going to try to transfer large files over UDP you're going to need to develop some way to ensure reliable delivery - which is exactly what TCP does.

      You could also forget about reliability and simply use forward error correction instead, in particular rateless erasure codes. Some UDP packets will be lost, but that's of no concern, since they'll be regained later through combinations of other packets. This could even be used to make a very simple mirroring system: request different codings of the same file from all mirrors, and when you've got enough packets to reassemble the entire thing, tell all the mirrors to stop.

    3. Re:best thing for the Internet? by Enter+the+Shoggoth · · Score: 1
      You Called?

      ... There is a distinct possibility that the new protocol will waste tons of bandwidth or do something horrible to existing equipment or summon up a shoggoth...

      --
      Andy Warhol got it right / Everybody gets the limelight
      Andy Warhol got it wrong / Fifteen minutes is too long.
    4. Re:best thing for the Internet? by RingDev · · Score: 1

      Obviously if you're going to try to transfer large files over UDP you're going to need to develop some way to ensure reliable delivery - which is exactly what TCP does.

      P2P does not transfer large files.

      It transfers small files, very small files. And it is designed in such a way that it expects failures and to be unable to find those files. So if a transfer fails, it just requests that file again. Once it has all those tiny files, they get reassembled into the original large file.

      There is no need for a robust transportation layer, the application is explicitly designed to account for such issues.

      -Rick

      --
      "Most people in the U.S. wouldn't know they live in a tyrannical state if it walked up and grabbed their junk." - MyFirs
    5. Re:best thing for the Internet? by ceoyoyo · · Score: 1

      The bittorrent protocol itself checks packets to see if they were delivered correctly. If not it rerequests them, probably from some other server. In effect, bittorrent implements the reliability of TCP with the additional knowledge that the packet is available from several different places. It will probably work better over UDP.

    6. Re:best thing for the Internet? by Ephemeriis · · Score: 1

      Problem is most ISPs aren't setup to pay for new equipment at the needed rates. They are setup to only replace equipment as it fails or as it reaches the end of tax deductibility( 3- 5 years in the US ). Around here, we replace everything every third year and figure that 20% of the gear will fail in any given year.

      Thus to change to an every year update plan would probably require a doubling (which the ISPs would see as their chance to triple) the existing rates, with no other benefits than the ability to use your paid for bandwidth. No speed or reliability improvements without adding yet another multiple to the cost.

      Personally, I don't really care how the ISP is set up. I don't care what hardware they run, how often they replace it, or how they pay for it. That's not my problem. All I care about is the service that I pay them to provide.

      If I pay them $50/month for "unlimited" bandwidth, I want my unlimited bandwidth. If they tell me that "unlimited" actually means 100 Gb/month, I want my 100 Gb/month. I don't care if it puts an additional burden on them or not - that isn't my problem. If they can't provide 100 Gb/month for $50, they shouldn't sell it to me.

      --
      "Work is the curse of the drinking classes." -Oscar Wilde
    7. Re:best thing for the Internet? by RingDev · · Score: 1

      with no other benefits than the ability to use your paid for bandwidth.

      Which gets back to the root issue. ISPs have over sold their networks. They are unable to guarantee the bandwith the they have sold. The easiest solution is to cut the marketing hype and sell responsible bandwidth allocations that they know that they can guarantee. Yeah, that means everyone takes a hit and that instead of paying $30 a month for 3Mb service (where I will rarely ever see 3Mb), I'll be paying $30 a month for 784Kb service (where I will have 768Kb service 99.9999% of the time).

      Personally, I wouldn't mind seeing a speed vs consumption model. For the first X GB downloaded, you have Speed1 service. For the next Y GB downloaded, you have Speed2 service, for the nezt Z GB downloaded, you have Speed3 service, etc...

      Where the size of X, Y and Z and Speed 1, 2, and 3 are dependant on how much you pay.

      $10 a month? 0GB at 1.5Mb, 5GB at 768, remainder at 512. ...
      $100 a month? 20 GB as 3Mb, 100 GB at 1.5Mb, remainder at 768.

      Fair to everyone, and if you're a P2P junkie, you are either capped at a slower connection speed (and thus not eating other peoples bandwidth) or you are paying significantly so you wind up funding network improvements.

      -Rick

      --
      "Most people in the U.S. wouldn't know they live in a tyrannical state if it walked up and grabbed their junk." - MyFirs
    8. Re:best thing for the Internet? by Ephemeriis · · Score: 1

      The bittorrent protocol itself checks packets to see if they were delivered correctly. If not it rerequests them, probably from some other server. In effect, bittorrent implements the reliability of TCP with the additional knowledge that the packet is available from several different places. It will probably work better over UDP.

      True. I wasn't really thinking in terms of BT, but rather a standard file transfer over HTTP. You're right, you wouldn't need to re-implement TCP.

      As far as I can tell, from my admittedly-limited knowledge, the only downside to making BT use UDP is keeping the ISPs from messing with your traffic.

      --
      "Work is the curse of the drinking classes." -Oscar Wilde
    9. Re:best thing for the Internet? by AndrewNeo · · Score: 1

      I think the problem is that "unlimited" isn't wrapped in quotation marks by the ISPs until it's too late.

    10. Re:best thing for the Internet? by japhering · · Score: 1

      Personally, I don't really care how the ISP is set up. I don't care what hardware they run, how often they replace it, or how they pay for it. That's not my problem. All I care about is the service that I pay them to provide.

      If I pay them $50/month for "unlimited" bandwidth, I want my unlimited bandwidth. If they tell me that "unlimited" actually means 100 Gb/month, I want my 100 Gb/month. I don't care if it puts an additional burden on them or not - that isn't my problem. If they can't provide 100 Gb/month for $50, they shouldn't sell it to me.

      And the question comes down to what is your price point? Are you willing to pay $2, $3, $4 per GB per month for that 95% availability? Or $10-$15 per GB if you want 99.9% ?

      The average smuck, doesn't give a rat's ass, whether it is 50% or 99% available, he only cares that he can read his email, do his banking faster than dialup an that it costs less than $20 per month. However, for the techie that understands and/or works from home, he/she expects 99.9% availability and bandwidth, this is where Net Neutrality argument fails.

      If I'm am willing to pay the premium to get the 99.9% levels of service, why should my traffice be given favorable handling. Priority handling shouldn't be based on where I'm going, it should be based on who is willing to pay for it !

    11. Re:best thing for the Internet? by Anonymous Coward · · Score: 0

      reliable delivery is not needed for BT. if something
      fails to appear it's requested later, and that's that. end of story.

    12. Re:best thing for the Internet? by Anonymous Coward · · Score: 0

      What ISP is advertising unlimited bandwidth to you?

      I'm sure it happens, but most ISP's are smart enough not to advertise something they cannot deliver and end up getting sued over it.

      I doubt you were actually told that you had unlimited bandwidth - you just made it up.

  21. Re:A little extreme there, don't you think? by MBGMorden · · Score: 5, Insightful

    It could be, or it could not be. To me, that's not even an issue that should involve the ISP. I pay them for bandwidth, not to be my nanny. It's akin to a car dealer that keeps checking into to make sure I'm not running drugs in the car I bought from them. Right or wrong, legal or illegal, I paid for the car/bandwidth, so butt the hell out or I'm going to either find another seller who doesn't bother me about what I'm doing, or just ignore your and route around your interference.

    I want an ISP that sells me a pipe. That's it. What I send down it is of no concern, and if I pay for 5Mbps or whatever other arbitrary number, then I can't possibly "steal" bandwidth from other users because by definition I'm already limited to the amount that you sold me. If you can't provide it then don't sell it, because some users will use what you sell them. If you took the current ISP business model to any other industry you'd be laughed out of town, yet they get away with it. Can you imagine signing up for a "3 DVD's at a time" plan from Netflix and then when you actually check out 3 at a time they start bitching up a storm because "You're hoarding the DVD's!!! None of the other customers will be able to rent any of them!!!". Of course not. Because like most industry's they understand that if you sell a capacity you better damn well be able to meet it.

    --
    "People who think they know everything are very annoying to those of us who do."-Mark Twain
  22. Adobe Flash by MouseR · · Score: 3, Insightful

    Is more in cause of the frickin' meltdown of the internet with about half the content of web sites being Flash-based animated and (GAH!) audio adds.

    Flash video is also irreparably defective.

    Disclaimer: did I mention I hate Flash?

    1. Re:Adobe Flash by Andr+T. · · Score: 1

      Maybe if they disable Zombo.com the problem you mentioned will be solved. But... damn, you won't be able to do anything at Zombo.com!

      --

      Any life is made up of a single moment, the moment in which a man finds out, once and for all, who he is.

    2. Re:Adobe Flash by Anonymous Coward · · Score: 0

      Idiot... just because video is playing through Flash does not make Flash the bad guy. In fact Flash is beautifully small for files when used correctly as it uses vector by default. Flash Video isn't irreparably defective either. I don't see why you're allowed to make up such idiotic statements without reference. You're worse than the article itself.

    3. Re:Adobe Flash by Gulthek · · Score: 1

      You would take away homestarrunner.com?

    4. Re:Adobe Flash by jmorris42 · · Score: 1

      > ..about half the content of web sites being Flash-based animated..

      Yes it does suck. Until you get a clue and install flashblock into FF. It speeds up the whole Internet experience and can selectively punch holes for sites where the Flash is useful. I even put in on our public lab machines to save bandwidth. It was worth the time to explain it.

      --
      Democrat delenda est
    5. Re:Adobe Flash by Eil · · Score: 1
  23. Bah, self limiting... by nweaver · · Score: 1

    The problem with UDP rate control is:

    a) Unless you make it TCP fair, you stomp on the user's OWN traffic, which is already a big problem for BitTorrent clients which fill up DSL and cable-modem buffers. And if you DO make it fair, then it doesn't matter.

    b) It doesn't stop ISP traffic management, it just forces their devices to be inline.

    c) The biggest offender, Comcast, is moving away from P2P blocking anyway.

    --
    Test your net with Netalyzr
    1. Re:Bah, self limiting... by Andy+Dodd · · Score: 1

      Not quite. Even if implemented EXACTLY the same as a typical TCP congestion control algorithm, a UDP-based approach will have a significant advantage in the current environment if it has one feature - control flag authentication.

      In TCP, there is no way to authenticate whether an RST packet came from the other endpoint or from a MITM attacker. This vulnerability has been abused by a number of ISPs (notably Comcast).

      With UDP, it is possible to add authentication of headers (including protocol control flags) to determine if they are legitimate or from a MITM attacker.

      If done right it can be a Very Good Thing with few negative side effects, but most likely a lot of clients won't do it right...

      --
      retrorocket.o not found, launch anyway?
    2. Re:Bah, self limiting... by nweaver · · Score: 1

      So? Bell's restrictions are inline, not RST injected, while Comcast is dropping their out-of-band method. (and the Sandvine devices Comcast is using can operate inline as well).

      And with inline traffic managment, using UDP offers no inherent advantage.

      --
      Test your net with Netalyzr
  24. ...youtube? by amclay · · Score: 1

    They use UDP. And it eats bandwidth like none other. Oh noes!

    --
    It's all fun and games till someone divides by 0. Then it's hilarious.
    1. Re:...youtube? by eggnet · · Score: 1

      No they don't.

  25. Re:Greed by Anonymous Coward · · Score: 2, Funny

    The music industry is hardly a golden goose. I'll accept golden turd but not goose.

  26. why by gzipped_tar · · Score: 1

    Correct me if I'm wrong, but I think actually we can reduce the bandwidth by switching to UDP. With UDP you need to implement your own transmission control, and if BitTorrent can make its own lightweight implementation, the transmission control overhead caused by TCP will be reduced.

    Actually I see UDP a better alternative for BT because you don't need to make sure every packet is transmitted successfully, given how BT seeding works.

    I see TFA's point is not that UDP increases traffic, but they are harder to be throttled by ISPs. Well then why don't the ISPs upgrade their own infrastructure to handle the increased traffic and charge their users accordingly to cover the cost? Blame the current economy?

    Again, I don't know much in this area so I may be wrong.

    --
    Colorless green Cthulhu waits dreaming furiously.
    1. Re:why by Fastolfe · · Score: 1

      Well then why don't the ISPs upgrade their own infrastructure to handle the increased traffic and charge their users accordingly to cover the cost?

      Two things:

      There will always be people saturating their data connections. If it's BT transfers of DVDs today, it'll be Bluray transfers tomorrow. The day after? Who knows. If you upgrade your infrastructure, this just raises the speed limits for these people, who will quickly find ways to hit it. It's an arms race that isn't likely to be won by the ISPs in the near future, if ever.

      The costs of upgrading to support a massive increase in utilization of a subset's "unlimited" data connections is, in turn, massive. If you try to pass these costs evenly onto the user, they will flock to other, cheaper ISPs, that haven't "upgraded". Because most people don't care if they have 10Mbit of guaranteed bandwidth, so long as they have ~10Mbit occasionally for surfing the web.

      IMO, unmetered service like this is only sustainable when your outliers can't have this dramatic an effect.

      Put another way, what do you think would happen if someone said "essentially unlimited 10Mbit for $10/month, but no BitTorrent allowed" versus "unlimited 10Mbit, BitTorrent OK, for $500/month". We're stuck in between these two extremes right now, trying to keep the average price the same while reducing the impact of BT users. If you start blocking more than other ISPs, you can get your average price down and outcompete other ISPs, but you get negative press and the attention of regulators. If you block less than other ISPs, BT-heavy users start moving to your ISP, exacerbating the problem, driving your costs up. ISPs are stuck between a rock and a hard place.

      The only way "unlimited" plans can work in a BitTorrent world is through heavy traffic management. But now we have BT clients saying they're going to find ways to disguise the traffic to get around that.

      Here's what I predict will happen:

      • ISPs will start declaring up front their traffic management policies. This is usually the chief complaint when customers hear about filtering after they've signed up. But rather than raise prices, I think it's easier for them to be more up front about what they're going to start blocking.
      • ISPs will ban outright the practice of "hiding" your BT traffic to avoid those policies. You can pretty easily tell the difference between typical DNS lookups, and BT-over-UDP-port-53. These customers should be disconnected for these deceptive practices. This hard hand will earn a bit of negative press, and a few people will come out with sob stories about how application X apparently made them look like a dirty BT user, and got them cut off without the possibility of appeal.
      • As more sophisticated techniques arise for hiding traffic in ways that can't be obviously detected, ISPs will move in two directions:
        1. A new type of "unlimited" plan that comes with heavy restrictions: Only pre-authorized traffic, probably proxied through the ISP, is permitted. SSL might be more tricky, but the ISP can attempt to sniff out bogus SSL servers. The heavy restrictions in this plan will probably make it unattractive even if you could masquerade your file transfers over SSL.
        2. A metered plan with no restrictions whatsoever. Use what you want, when you want.
    2. Re:why by AK+Marc · · Score: 2, Interesting

      I see TFA's point is not that UDP increases traffic, but they are harder to be throttled by ISPs. Well then why don't the ISPs upgrade their own infrastructure to handle the increased traffic and charge their users accordingly to cover the cost? Blame the current economy?

      It's not that it's harder to throttle. It's that if a network is a mix of TCP and UDP traffic filling up the capacity, the TCP will back off, and the UDP won't. In fact, with a crappy back-off protocol in a UDP application, the TCP will continue to back off until almost nothing is left, while the UDP grows and takes it all over. UDP was not intended to be a peer of TCP, but a tool to help. Using UDP to transfer large files in this manner makes as much sense (from a network design logical stance) as using ICMP. Sure, it could be done (embed data in the ping packets), but why? TCP exists to do this, and already does it well. UDP should be left for real-time appliations only where lost packets could never be usefully recovered, and some light-weight low-use applications like TFTP.

      All capacity will be used sometime. If there's a backbone problem and smaller links carry more traffic there could be bottlenecks. Maybe we are just talking about the access to someone's house, and that's easier to clog. Whatever it is, the issue is that the Internet will experience congestion. It has to, that's the way these things work. What matters is what happens when it is full? With more UDP and less TCP, TCP will generally suffer a greater impact. At the heart of it, that's the real issue. Yes, they should have enough capacity to hold the traffic almost all the time, and people won't be filling their tubes all the time either. But this is a design issue that would be true no matter what the capacity is.

    3. Re:why by nog_lorp · · Score: 1

      Agreed. The logic of the doomsayers seems to be "BitTorrent is going to use UDP, and they will OBVIOUSLY be too lazy to implement their protocol in a reasonable way!"

  27. Everyone wants a piece of the pie... by papasui · · Score: 3, Informative

    ...but nobody wants to pay for it. It's been said many, many, many, times before but the average user doesn't have any concept how much bandwidth costs for the circuit to a carrier alone, much less the hardware required to light it. I work with carrier-level Cisco gear, a single linecard alone is in the 50k price range. A single router I work with has 8 of those. It takes at least 2 of those routers to handle a few small to medium size towns, (30k subscribers). That's just the price to give you a connection back to the local building, of course I'm omitting the cost of the wiring to your home, the equipment required to power it, etc, etc. We haven't even discussed how much the transport out to the internet begins to cost. I think a lot of ISP's are beginning to see that it's probably a failing business model, and because of that they are making some-what drastic changes to try and make it sucessful. Things like bittorrent, youtube, etc are what make the web truely great, but at the same time they very well could be the downfall in the current state of the internet. You of course could always get your own internet circuit but even a T1 will be at least $300 per month + construction costs and appropriate gear to utilize it.

    1. Re:Everyone wants a piece of the pie... by RingDev · · Score: 4, Interesting

      16 linecards at 50k each, for 800,000. Lets call it a cool mill in asset costs.

      30k subscribers paying $20 each a month. $600,000 a month. $7.2 mill a year.

      Yeah, I can see how the initial sticker value of a 2 router closet is going to a road to ruin for most ISPs.

      I don't think ISPs are cash cows by any means, once you consider opperating expenses and labor. But a $1 million dollar switch station can be easily amorted out over a 5 year loan when the ROI on that million is quite solid.

      -Rick

      --
      "Most people in the U.S. wouldn't know they live in a tyrannical state if it walked up and grabbed their junk." - MyFirs
    2. Re:Everyone wants a piece of the pie... by Lemmeoutada+Collecti · · Score: 4, Informative

      8 Linecards @ 50,000 ea = $400,000
      2 routers @ $400,000 = $800,000
      $800,000 / 30,000 = $26.67
      12 months * 5 years = 60 months (standard depreciation period for equipment)
      26.67 / 60 months = $0.45 per month per customer for the routers

      I think that when you start throwing large numbers out there to justify cost to the customer, please remember that these costs are amortized over the entire customer base and over time as well.

      Let's say you lease the lines for $50,000 per month for each router:
      50,000 * 2 = 100,000
      100,000 / 30,000 = 3.33 per month per customer

      Let's add in $10,000 per month for power
      10,000 / 30,000 = $0.33 per customer per month

      Add in $100,000 per month for line maintenance, $100,000 per month for repairs
      200,000 / 30,000 = 6.67 per month per customer

      And $100,000 per annum for your salary (being generous for sake of demonstration) and say another $200,000 per annum for overhead expenses and support staff
      $300,000 / 30,000 = $10
      $10 / 12 = $0.83 per customer per month

      So for the equipment (amortized), electric, facilities (as overhead), staff, leased pipes, maintenance, etc. we have a total of $11.61

      Now a low end line goes for ~$24 per month, while a high bandwidth line ~$60...

      --

      You can have it fast, accurate, or pretty. Pick any 2.
    3. Re:Everyone wants a piece of the pie... by DogDude · · Score: 1

      It's been said many, many, many, times before but the average user doesn't have any concept how much bandwidth costs for the circuit to a carrier alone, much less the hardware required to light it.

      You're right. I don't. All I know is that my ISPs charge me $xxx for XX MB/s. How much it actually costs them is irrelevant.

      --
      I don't respond to AC's.
    4. Re:Everyone wants a piece of the pie... by abigor · · Score: 1

      Yes, I think a lot of people in the networking biz understand that metering bandwidth is a probable outcome of all this, kind of like most other utilities (electricity, gas, etc.) Heavy bandwidth users will end up paying enormous amounts, hundreds or even thousands per month.

    5. Re:Everyone wants a piece of the pie... by Forge27 · · Score: 1

      Thats assets, what about recurring costs on the ISP side? If you have 30k subscribers @ 10mb each, you'd need over 300 OC-192 lines to keep up if each sub maxed out his bandwidth. I dont know how much one of those costs, but I'd love to try one out for a day...

    6. Re:Everyone wants a piece of the pie... by papasui · · Score: 1

      They don't sell you XX MB/s. That's what a carrier sells, and which is why they charge tens of thousands of dollars a month for a rated circuit. An ISP (generally speaking) sells you a maximum possible connection with no gurantee that you will ever hit the top rated speed. It's been that way since dial-up internet first came out.

    7. Re:Everyone wants a piece of the pie... by RingDev · · Score: 3, Insightful

      Which is exactly the problem, it is entirely too costly to do. ISPs have been marketing 10Mb service (or 3-5Mb service in my area) with out the ability to actually provide 10Mb as a minimum service level.

      By selling based on the upper limit of service and leaving the lower limit undefined, they can prove that they can provide up to the marketed rate (in ideal conditions) but you can not prove that they fail to meet that lower limit.

      So people assume that by paying for "(up to) 10Mb Service!" that they should be able to get 10Mb service 99.999999% of the time. When in reality they can get 256Kb service or better 99.999999% of the time.

      Once you drop those 30k users down to 256Kb connections, you're only looking at 7,860,000Mbps instead of 300,000,000,000Mbps. Push it up to 10,000,000Mbps and you have the 256Kb minimum with enough head room for people to hit 10Mb upper limit under ideal circumstances. And a single OC-192 will carry it all.

      Sure, if they want to provide a true 10Mb connection with near 100% uptime and bandwidth availability, they're going to need a stack of OC-192. But they don't. It's the old "As little as possible, as much as necessary" line. And the Marketing department hasn't kept in line with the Engineering department, so the issue will inevitably wind up in the Legal department.

      -Rick

      --
      "Most people in the U.S. wouldn't know they live in a tyrannical state if it walked up and grabbed their junk." - MyFirs
    8. Re:Everyone wants a piece of the pie... by HeronBlademaster · · Score: 1

      That's more or less what I see from my ISP. Low end lines for $20, midrange for $50, high end for $80, and "even God wouldn't need this" for $180.

    9. Re:Everyone wants a piece of the pie... by mzs · · Score: 1

      You have power but what about the computer room and office space rent? What about the other utilities and services like shredding and janitorial? Also where are the taxes and fees that you need to pay as a business, that $300,000 per year won't cover it for the number of employees you will need with a 30K customer base. The rule of thumb is to add 50%, you can be stingy at 35% but then you will not have enough benefits to attract good employees. What about capital expenses? You are going to need desktops, pagers, phones, desks chairs, etc. Where is your legal department, you know how much a firm on retainer costs right? And what about marketing, you do what to be able to get those customers at some point to begin with.

      Not so rosey is it...

    10. Re:Everyone wants a piece of the pie... by Lemmeoutada+Collecti · · Score: 1

      Ok, so let's raise the per customer cost to $20 per month. The base price is $24 per month, and that customer probably won't use a as much as the $50 or $80 per month customer. Still making a profit, aren't we. So it's no longer a 100% or greater profit per customer, but it's still nowhere near the level of a dying market.

      --

      You can have it fast, accurate, or pretty. Pick any 2.
  28. Won't create any changes by Thorizdin · · Score: 2, Informative

    ISP's have been managing UDP traffic for years now, this won't change anything. Any of the deep packet inspection boxes (Packeteer, Allot, Sandvine, Ellacoya, etc) can identify the traffic whether it is UDP or TCP as can open source tools like Ntop. Encrypting the traffic can of course disguise what's in the packets, but the overhead hurts transfer speed. In addition, several of the new generation of traffic shapers don't even care what layer 4 protocol you're using, things like Netequalizer just looks at the two IP end points of a given conversation and treats it as a flow regardless.

  29. Re:A little extreme there, don't you think? by encoderer · · Score: 1

    I hate to be the one invoking a Hitler reference--albeit tenuous--but the old parable about "They took the unionists, I was not a unionist, so I didn't protest. They took the _____, I was not a ____, so I didn't protest, ......" seems to fit.

    Personally, I think this is a tough nut to crack. But if transferring files via a well established and well known protocol is going "meltdown" the internet, maybe the internet isn't as resilient as it should be?

    I personally can't remember the last time I downloaded via torrent. I sucked tons of shit off P2P networks, napster, gnutella, fasttrack, even some BT, but I just graduated to an income bracket where I'm more time poor than cash poor.

    But if we don't demand fair practices from ISPs it won't be long until they cross off BT and then move to the next biggest 80/20 rule traffic hog. And THAT might be something i DO care about.

  30. Remember Y2K? by Drakkenmensch · · Score: 1

    This all sounds familiar, this promise that all computers would collapse and the internet become a smoking ruin that could never be used again. As long as I can log on and keep reading these prophecies of doom, I'll know that I still have plenty of time left before I need to go to the hardware store to get the materials for my The End is Nigh sign.

  31. Re:Well Duh by MasterOfMagic · · Score: 5, Interesting

    Sounds like the ISPs should have used the tax incentives we gave them to increase network capacity and reach to, you know, increase network capacity and reach. If they had done that years ago to keep pace with the growth of their network traffic, they wouldn't be in this situation.

    But no, of course, it has to be the person who uses their connection's fault.

    I pay for a pipe. My ISP should take no interest in the source or destination or type of service connections in this pipe. Anything else is just allowing the system to be used abusively.

    It isn't appropriate for legitimate bittorrent users to be driving other TCP off the network.

    The only way the BitTorrent use can drive other users off to the network is if the ISP's network is misconfigured or is being overutilized due to too much overselling (you have to have some overselling, not everyone is on 24/7). ISPs that have their shit together will have their network designed to handle expected and future traffic growth such that all of their customers can use what they paid for.

    you just want to bully other people out of their bandwidth so you get more

    They paid for their bandwidth and I paid for mine. I have a cap on my connection speed; they do as well. The only difference is that their YouTube videos load instantly and my BitTorrent transfer is knee-capped. Who is the bully here?

    This isn't the right way for BitTorrent to move forward

    What is the right way to move forward? Accept that there are two levels of Internet traffic: "clean, good, wholesome non BitTorrent traffic" and "dirty, evil, corrupting BitTorrent traffic"?

  32. Upgrade the core and its routers by suraj.sun · · Score: 2, Insightful

    from http://www.dslreports.com/forum/r21500602- :

    Re: Is this a good thing for the net?

    Yawn, here comes the typical argument... bandwidth is bandwidth, either way you look at it. All p2p does is open several simultaneous connections, splitting the user's bandwidth. Unless you horribly misconfigured your client to open up, say, 1000 ports.

    It's not as if the user is using any more bandwidth than if they were conducting a regular http download. P2P actually is better for a network, as (given enough peers) it completes downloads significantly faster than normal centralized server methods, thus getting heavy users off the network noticeably faster (obviously, unless the user is dumb enough to allocate their entire upstream bandwidth to seeding).

    As to bypassing the "TCP congestion control" you speak of, do you think Bell's solution is ANY better? The throttling of particular packets by itself violates the principles of TCP. Not only that, it also throttles/cripples MANY legitimate applications, such as secure VPN's or other encrypted connections.

    Do you REALLY want that as an alternative to this so-called "problem" of p2p? I've said over an over, the ideal solution is to gracefully scale back speed for ANY upload/download if the said user is using their full bandwidth for more than 20 minutes during peak hours. This actually solves the problem, unlike throttling schemes like bell's, which render many legitimate applications useless. Let's face it, even Comcast here in the states has been forced to take a long hard look at their policy on Sandvine. Soon enough, we can only hope Bell will as well...

    Do I even support the above solution? By itself, absolutely NOT!! IMHO, the ideal solution is to upgrade the core and its routers. However, that takes time and capital that companies like Bell are rather unwilling to spend; they'd rather (ab)use their position in the limited Canadian ISP market to deploy band-aid solutions like throttling p2p.

    1. Re:Upgrade the core and its routers by M-RES · · Score: 1

      No, the '20 minute' model fails most users miserably and made me leave Virgin media as an ISP. They have a policy of throttling anyone downloading at any significant level for 20 minutes solid. This meant that my wife watching on-demand TV shows she'd missed earlier in the evening would be able to see the first 20 minutes of a show, then have to wait 6 hours until the full bandwidth resumed before she could watch the last 10 minutes of the show. Unless of course she was happy to watch 1 second of the show, wait 3 seconds for the file to buffer, watch 1 second, buffer 3 seconds, watch 1 second, buffer 3 seconds.

      Slapping on an arbitrary 'time' cut-off for bandwidth will fail many legitimate users for many different uses. The use I've mentioned is NOT an illegal act, nor is it demanding more of our bandwidth than we should be allowed (given that at the time we were on a 2mb connection) or hogging overall bandwidth. Some users on Virgin Media are paying for 16mb connections or greater - so if we're using 1.5mb of our allocated bandwidth, does that equate to them using 12mb of a 16mb connection, or 15.5mb? How do you set a 'limit' when there is ALREADY a limit placed on the connection speed by the ISP (in our case that was the upper 2mb limit we were paying for).

      People who want greater bandwidth already pay more, so they should receive that bandwidth. If the ISPs can't offer that bandwidth reliably then they shouldn't be allowed to sell it - it'd be like a car manufacturer selling you a car labelled as 'top speed up to 150mph' and then setting the engine management unit to only allow you top speed for a few minutes each day and the rest of the time limiting you to 30mph - they'd get their arses sued off the face of the planet!

    2. Re:Upgrade the core and its routers by mzs · · Score: 1

      The problem is that p2p seems to be insatiable. It devours what ever amount of bandwidth that is thrown at it. So when you spend considerable sums of money to improve the infrastructure and then you have the same exact problem four months later, what do you do next?

  33. About time to meter usage?? by foxalopex · · Score: 3, Interesting

    I find it disappointing that ISPs don't meter usage. It would help cut down on spam and viruses for example if users suddenly realized that something was costing them a lot of money and wasting bandwidth. I mean all our other services are metered. As for myself there are months when I download huge amounts of anime and then there are other months where I download next to nothing yet I still pay the same amount. This fact alone means it's more beneficial for me to download like a nutcase and ruin it for everyone else. Granted the only catch is that ISPs would hopefully charge reasonable rates with a certain flat fee to maintain the line. To folks to believe otherwise, I suspect you're not willing to give up your free lunch to the expense of others. The Internet is a limited resource as some ISPs are learning the hard way. Given the choice between metered usage versus throttled / controlled / broken Internet, I'd pay for metered anyday.

    1. Re:About time to meter usage?? by japhering · · Score: 1

      Except for folks like me that work for a cheap ass fortune 500 company from home. The company caps re-embursement at $50 per month.

      Typical month for me is around 150 GB down and a 100 GB up. Under most of the metered services being either offered or in trial, my cost would easily double just on usage, and up another 20% on taxes .. leaving me to pay $70-80 per month out of my pocket to work for a fortune 500 company (20 years of seniority and 5 weeks of vacation).

      Not many opportunities to move without taking a substantial cut in pay and vaction time.

    2. Re:About time to meter usage?? by IamTheRealMike · · Score: 1

      The reason they don't do that is nobody understands bandwidth units. Back in the dialup days it was easy - everybody knows what a "minute" is.

      These days it's much harder, units like a megabit or gigabyte/month are very hard even for experienced professionals to reason about, as most people don't know how much bandwidth any given application needs. For instance how much bandwidth does XBox Live use? I have no idea.

      The obvious solution is to sell people "unlimited" bandwidth and then buy as much as is necessary to fill demand, which you assume stabilises at some natural level - there's only so much web surfing, game playing etc that can be used.

      P2P completely breaks this fairly simple setup, because P2P users are quite capable of pegging their connection 24/7 at the max downloading stuff that they often never use (it's pretty amazing how much hoarding these people do).

      Given that the alternatives are (a) go out of business, (b) try and teach the world the difference between megabits/sec and gigabytes/month or (c) throttle P2P users specifically is it any wonder most choose C. And by the way contracts almost always state bandwidth limits in them, they are just set high enough that most normal users will never encounter them.

    3. Re:About time to meter usage?? by Cowmonaut · · Score: 1

      What happens if your box becomes a zombie and you aren't aware and it sends out millions of e-mails as part of a botnet? Face it, the majority of users DON'T know how to protect themselves online.

    4. Re:About time to meter usage?? by Anonymous Coward · · Score: 0

      I agree that that may be the only reasonable way out, but it relies on something that's just not going to happen. You said it yourself:

      "Granted the only catch is that ISPs would hopefully charge reasonable rates with a certain flat fee to maintain the line."

      I find it more likely that aliens will come down and solve our infrastructure problems.

    5. Re:About time to meter usage?? by Inda · · Score: 1

      I was offered 110gb for $25 today. Me, Joe Average. I was a little disappointed it was down 15gb from the last time I looked. Recession, huh?

      Bandwidth is so much cheaper than everyone thinks.

      --
      This post contains benzene, nitrosamines, formaldehyde and hydrogen cyanide.
    6. Re:About time to meter usage?? by Anonymous Coward · · Score: 0

      I could make your connection pretty expensive for you if it was metered and I didn't like you for some reason. I could have my botnet send you massive streams of garbage data totally saturating your connection. Or are we now only going to be charged for stuff we choose to receive? How does that work? Or maybe just meter outgoing data? How does that solve anything?

      You see, other utilities are not the same as the internet.

    7. Re:About time to meter usage?? by Detritus · · Score: 1

      Internet bandwidth is not a consumable commodity like electricity or oil. That isn't how the economics work. Network costs are driven by peak capacity, not the total amount of data transferred. Imagine if electricity could be generated at almost no cost at the existing power generation stations. You would still have to pay for the distribution system, which would be designed and sized to handle peak loads. Off-peak usage would have little impact on the cost of the system. An idle or lightly used data link is economically inefficient and wasteful. A rational pricing policy would encourage people to prioritize their traffic, and to make use of system capacity that would otherwise be wasted.

      --
      Mea navis aericumbens anguillis abundat
    8. Re:About time to meter usage?? by Valdrax · · Score: 1

      What happens if your box becomes a zombie and you aren't aware and it sends out millions of e-mails as part of a botnet? Face it, the majority of users DON'T know how to protect themselves online.

      Well, the obvious line of reasoning for why the above poster thought that metering might do something about viruses and spam is that it would provide an incentive for people to learn to protect themselves as well as to fix things when they went wrong (as most of those same users don't even know how to check to see if they are infected).

      Sure, this will hurt some people at first, but it's the same kind of reasoning for why cops pull people over for having brake-lights that are out. Without the stick of a ticket, people have no motive to check something that they wouldn't normally notice was a problem in day-to-day use, or they'll pay professionals to check for them, and the end result is that more people have working brake-lights to keep them safe. It will serve to educate people.

      (That said, I honestly can't imagine viruses and spam botnets generating THAT much traffic compared to normal use. I doubt people would even notice unless their machine was part of a DoS attack.)

      --
      If it's for-profit but free, you're not the customer -- you're the product (e.g., the Slashdot Beta's "audience").
    9. Re:About time to meter usage?? by Eil · · Score: 1

      I find it disappointing that ISPs don't meter usage. It would help cut down on spam and viruses for example if users suddenly realized that something was costing them a lot of money and wasting bandwidth.

      Okay, here's what we'll do. I know the owner of an ISP. I'll convince him to switch over 10% of his customers to metered bandwidth and we'll have you come in and answer all of the billing-related calls for those customers. Since you're such a huge proponent of metered bandwidth, you should have no problem explaining to customers why it's a good thing that their metered bill increased 500% compared to the previous month because their computer caught a virus. Piece of cake, huh?

      Unmetered bandwidth started out as a marketing gimmick and became necessity. Billing someone for metered utilities is easy because water, gas, and electricity are simple concepts to understand, easy to meter, and finite resources. Last-mile bandwidth is none of those. Most people do not understand how their broadband works and are not going to be happy when they see their bill skyrocket because the connection is being utilized by things they don't comprehend. Their default action is going to blame the ISP and the ISP's support costs would triple without a corresponding increase in revenue.

      Also:

      1) An ISP can't offer both metered and unmetered plans because offering unmetered plans in addition to metered plans defeats the entire reason to do metered bandwidth anyway.

      2) They can't just switch everybody to a metered plan either unless they want to see 10% of their customer base walk over to their competition because the competition's unmetered plans became cheaper for them overnight.

      3) Many people like having their bills be a consistent amount from month-to-month and will happily pay somewhat more for a consistent bill in order to avoid surprises which might force them to shuffle things around in their budget every other month.

      To folks to believe otherwise, I suspect you're not willing to give up your free lunch to the expense of others.

      I'm sorry, did you just refer to a $40-$90 per month service as a "free lunch"? Maybe that's close to free for you, but it certainly isn't for me or anyone I know.

      The Internet is a limited resource as some ISPs are learning the hard way.

      No, it isn't a limited resource. And we're talking about the last-mile connection here, not the entire Internet. I'm starting to think you have no idea how a real ISP actually works.

      The cost of any last-mile connection lies entirely within the infrastructure that moves the data, not the data that moves across it. The cost to the ISP of any given customer sending a packet through them is very very VERY close to zero. Packets are extremely cheap and it doesn't make any sense to bill based on their quantity since the other things that an ISP has to pay for (support, administration, overall business costs) greatly outstrip what it costs to send a packet by a huge margin.

      You'd essentially be assigning an arbitrary monetary value to something that holds practically no intrinsic value. This gives rise to a number of problems. One is this: suppose you own an ISP and decide that one gigabyte of traffic is worth two dollars and every customer is automatically upgraded to the highest speed their equipment will support. Two of your customers pull down 15 gigabytes in one month, but one of them maxes out at 768K/sec while the other next door to the CO can get 20M/sec. Two customers, two entirely different levels of service, but they get charged the same. How is that fair? Sure you can prorate the 768K guy, but doing so reveals the fact that charging a set amount for a given quantity of data is an inadequate method of billing for the connection in the first place.

      (Yes, I realize that the ISP has to pay its own metered bandwidth bill to the upstream provider but since that bandwidth is an aggregate of th

  34. Re:A little extreme there, don't you think? by Chas · · Score: 5, Insightful

    Don't even pretend that most bit torrent traffic is legitimate and legal.

    So what? Piracy is a social problem. Blocking BT, which IS being used legitimately, is a wrong-headed attempt to use technology to "solve" a social problem.

    And in this case, they're trying to do it on the most flexible network in the world, one that's SUPPOSED to route around problem areas.

    --


    Chas - The one, the only.
    THANK GOD!!!
  35. Re:Well Duh by maxume · · Score: 1

    People who want to steal content will just go back to running ftp servers, the way they did before teh Napster. Then they will go private and encrypted (this is where most of stealing starts already).

    The end result is that in a few years, content providers will be calling for consumer ISPs to limit the amount of encrypted transfer that they allow on their networks. It will be fantastic.

    --
    Nerd rage is the funniest rage.
  36. Re:Well Duh by Anonymous Coward · · Score: 0

    mod parent up. I couldn't agree more.

  37. Bandwidth throttling... by VinylRecords · · Score: 1
    For years before bandwidth throttling became all the rage for ISPs I had been using torrents to download all sorts of files, discographies, TV show series, radio show .mp3 collections, etc. and not once did my ISP ever say that I was taking too much bandwidth. The entire article is a witch hunt for movie pirates but the author lacks the balls to say it hiding instead behind technical jargon.

    The internet evolved as a gentleman's system in the comfortable confines of the ivory towers of academe, but now that it's an essential part of daily life for more than a billion people, the time has come to get realistic about its management.

    First off the internet originated from ARPANET a military funded library project...it was hardly an evolutionary gentlemen system. Secondly, the things the internet is two most used for are social networking sites, and pornography. Essential part of daily life? I hardly think so for those billion people.

    Some of the people who use this system are spoiled children with no more concern for the greater good than junkies looking for their next fix.

    What the hell is he even talking about? OK children and junkies don't need the internet, gotcha.

    They can't be allowed to spoil it for the rest of us, and the only practical means to prevent their doing so is to unleash effective management upon them.

    When is the last time anyone here heard of someone complaining about lack of bandwidth because their neighbor was using too many torrents? Never?

  38. 50% of internet traffic is P2P? by RingDev · · Score: 1

    Most of the time when I hear crap like "By most estimates..." with out any sign of a source to back it up, I attribute the remainder of the sentence the same amount of credence as the sound of my coworker's ass cheaks flapping together after an especially hanious fart.

    Maybe he's right, but with out anything to back up his opinion, he just looks like some shill who is lobying for some organization with a strong financial incentive for not seeing net nuetrality laws and being allowed to run deep packet inspection.

    The best I can find is Ellacoya's June 2007 report that put P2P at 37% of total bandwidth. http://www.businesswire.com/portal/site/google/index.jsp?ndmViewId=news_view&newsId=20070618005912&newsLang=en

    A wee bit shy of the 50% the author is claiming.

    Another obvious way to see what the impact is would be to look at a tool like http://www.internettrafficreport.com/30day.htm to see if the change to UDP and expected rise in bandwidth actually effects TCP communication. If it is as gloom and doom as the author makes it out to be, we should see a steady rise in lost packets as the P2P users upgrade to the new UDP defaulting version.

    This report from March 2008 http://www.foxnews.com/story/0,2933,342988,00.html sites Arbor Networks (they bought out Ellacoya in early 2008) claims P2P traffic represents about a third of internet traffic.

    I'm all for making a plan to be able to react if a problem is detected. But lets not get all worked up over someone's questionable theories.

    -Rick

    --
    "Most people in the U.S. wouldn't know they live in a tyrannical state if it walked up and grabbed their junk." - MyFirs
  39. Scare Mongering? by Concern · · Score: 5, Insightful

    This sounds like the basest kind of scare mongering, relying on a basic ignorance of the way networks work.

    UDP is not any less filterable than TCP. To even make this argument, the reasoning is so contorted as to be silly. In either case, one uses a router to inspect packets and decide what to do with them. ISPs will simply go as deep through the envelopes as they like; they already do. With that knowledge they will do whatever is allowed by law. At present, almost anything is. If they abuse that power too foolishly, then it will start to be taken away from them.

    And in the meantime, whoever they filter will tweak to retaliate, and it will always be a race. As far as I can see, this is just the ISPs (or their proxies) stopping at one random lap and crying how unfair it all is.

    Why ignore the real issue here? If you sold a teenager in Topeka unlimited use of a large pipe, but now cannot handle her actual unlimited use of her large pipe, then you just need to start cutting better deals.

    It's as simple as that.

    If the teenager cannot actually use her fat pipe, 100% of the time, then stop lying about what it is you have sold to her. Either charge more or advertise less. It's as simple as that.

    When I as a CEO, and millions of others like me, buy #MB upstream and #MB downstream, and utilize it 100%, 24/7, no one quakes over the calamity of the internet backbone melting down.

    All of this discussion over filtering is really a discussion of pricing. And the fact that we are talking about it in the wrong terms is creepy.

    Believe me, you do not want a bunch of unaccountable telecom bureaucrats playing god with the backbone. You want a free market making these decisions.

    --
    Tired of Political Trolls? Opt Out!
    1. Re:Scare Mongering? by dkleinsc · · Score: 1

      Believe me, you do not want a bunch of unaccountable telecom bureaucrats playing god with the backbone. You want a free market making these decisions.

      There ain't no such thing as a free communications market. It's a natural monopoly, so either you end up with an unregulated monopoly or a heavily regulated semi-competitive market. Which leads directly to unaccountable telecom bureaucrats either way, the only difference is who's paying them (Ma Bell vs the FCC).

      --
      I am officially gone from /. Long live http://www.soylentnews.com/
    2. Re:Scare Mongering? by Anonymous Coward · · Score: 0

      It is a free market now. It needs more regulation, to force companies to advertise precise, guaranteed speeds and not the theoretical maximum.

    3. Re:Scare Mongering? by Concern · · Score: 1

      A good point. I used the "free market" buzzword though the term itself is an oxymoron. :)

      All markets are regulated. When it's truly free, there is no market, only the strong ruling the weak, caveman style. :) The buzzword is typically used (badly) to indicate one wants less central control; _fewer_ rules. It usually implies stupid and/or crooked rulemaking.

      I would look at this like the long gone and well missed public electric utilities. When regulated well (as they usually were), the books are open, and the profits are a well-regulated single-digit percentage, after appropriate investments are maintained to serve all customers, plan for the future, etc.

      In a well regulated internet "market," the key issue should not be "how well I can filter your traffic" but "how much are you charging for my traffic?"

      If the telecom bureaucrats are well regulated, they will not be able to advertise falsely, enter into fraudulent contracts, and then arbitrarily filter traffic. It should be very, very difficult for them to filter while staying within the law, and they should expect fines and prison if they do the elementary and thousands year old scam ("HEY UNLIMITED USE 4GB/sec PIPE ONLY $9.99 - fine print only use 1Mb per hour or we silently cap your traffic"). In such an environment, they are forced to honestly negotiate with consumers, speak clearly about what they are selling, and there is a transparent process where they charge enough for it that they make a good profit for themselves and their investors.

      And by "good profit" I mean not using their natural monopoly to price gouge - a nostalgic ideal that I sometimes wonder if anyone even remembers. We certainly know exactly what they do if not regulated properly. This is from the people that brought you the tale of the 5 cent, no 10 cent, no 20 cent text messages...

      --
      Tired of Political Trolls? Opt Out!
    4. Re:Scare Mongering? by Concern · · Score: 1

      Yes. Goes to show how vague and meaningless the term "free market" has become, but you're right, you could put it exactly that way.

      Point being let customers' money decide how much customers' traffic gets carried, and how reliably. Don't charge a fake price in a fraudulent deal and then do filtering based on the whim of some vice president rather than people's dollars.

      For that matter, you also need regulation to force all of these wealthy monopolists to keep their books completely open, so you can be sure they are not lying about what their costs are (2nd or 3rd oldest trick in the book for a regulated, natural monopoly industry), and hurting the economy by price gouging.

      --
      Tired of Political Trolls? Opt Out!
    5. Re:Scare Mongering? by Anonymous Coward · · Score: 0

      Why do people keep bringing up the unlimited advertising? They stopped doing that a decade ago. The argument is no longer relevant and hasn't been for a long time.

    6. Re:Scare Mongering? by CFTM · · Score: 1

      Don't be so logical! Intelligent pricing? Who'd of thunk it!

    7. Re:Scare Mongering? by wye43 · · Score: 1

      I agree with you.

      If anyone didn't read TFA, I can summarize it for you: its half bombastic, half of half fatalistic, half of half random no clue tech words and statistics 95% invented on the spot. Richard does a pure cry for attention and a weak troll at best. The article does not deserve any analysis or argument because there is nothing to hang on to, it's all a big ball of slime.

      I only have one decade notch on my netadmin belt, but if you find me dead drunk in a bar at 5am I couldn't spit out more ludicrous stuff. I wouldn't want to share the kind of attention he got now.

      Now to the core of the issue: I'm not a big fun of BitTorent lately for two reasons:
      1. its architecture causes a very big TCP/IP overhead of control packets, which makes packet shaping a mess. For this, I salute their initiative to take matters in their hands and handle packet flow instead of relying on the one implemented in TCP. For the tech un-aware, UDP does not mean higher speed or priority, it only means you give up on the control and security offered by TCP. Go on, be un-polite and send 1000 packets per second to your ISP and say hello to auto-ban on flood scripts that any ISP on this planet have.

      2. its being abused by kids(of all ages) who have not learned yet that nothing is free. I stopped using BT 2 years ago and I switched to a pay-oriented solution for my download needs and I could never go back to BT. Even a die-hard BT user realizes that the key of a successful/good speed BT transfer is the use of private trackers, that counts your bytes instead relying of the pure heart and kindness of the random user. Public BT was always a big fail - you end up paying more because of the time and lack of reliability.

      Even as a convinced anti-BT, and even at the risk of getting down-modded, I cannot stand aside and look at the article author spitting that BS.

      Rest in pieces, Richard Bennett's reputation.

    8. Re:Scare Mongering? by l00sr · · Score: 1

      This sounds like the basest kind of scare mongering, relying on a basic ignorance of the way networks work.

      FTA:

      Richard Bennett is a network architect and occasional activist in Silicon Valley. He wrote the first standard for Ethernet over twisted-pair wiring and contributed to the standards for Wi-Fi and the Ultra-Wideband wireless networks.

    9. Re:Scare Mongering? by IamTheRealMike · · Score: 1

      If an ISP is actually lying about what they sell, take them to court for contract violation. But I doubt you can actually do that because I doubt any ISP is stupid enough to actually sell unlimited internet. Always, in the contract you sign there will be fine print. In which case it's not lying, is it?

    10. Re:Scare Mongering? by Concern · · Score: 1

      Someone can be a god on paper, and nothing stops them from also being ignorant, mediocre, obnoxious, or a terrible judge of public policy. Unfortunately I've seen this first-hand more times than I can count, with people about 10x as big as Bennett. Sad, but there are many reasons for it.

      On the other hand, if you could tell me where he's right on the facts, and I've gone wrong, that would be more helpful.

      --
      Tired of Political Trolls? Opt Out!
    11. Re:Scare Mongering? by AK+Marc · · Score: 1

      Believe me, you do not want a bunch of unaccountable telecom bureaucrats playing god with the backbone. You want a free market making these decisions.

      The telecom bureaucrats are the free market. The "free market" includes three companies claiming to provide "up to 1 Mpbs" service, where no one can know what will be delivered until it is purchased. And even then, they get to change the rules whenever they want. They could prioritize speedtest sites over others in order to give an impression of faster speeds. One could have caching for lower bandwidth costs, which could improve response with faster page loads, or make it worse with stale pages. The "free market" doesn't have enough granularity in an arena with such high barriers of entry, and so the few companies that compete get to have more control than most other industries. When you have an otherwise free market with barriers to entry, you end up with monopoly rules (it isn't a monopoly, but concepts applying to monopolies better describe the market than those covering free markets when entry is restricted).

    12. Re:Scare Mongering? by Concern · · Score: 1

      I wish they taught some basic law in high school, because it would be easier to have these discussions.

      Deceptive fine print actually is illegal, for instance. I'm always surprised by how many people don't know what; maybe it's the prevalence of those "deal with the devil" movies.

      If the ISP advertises unlimited internet, then it is on the hook re. deceptive trade practices, unless that's actually what they're selling. The more they emphasize it, and/or the finer the fine print is, the more on the hook they are.

      What constitutes common practice and ordinary fair dealing also have a major weight on the court. But with ISPs there is no track record, so many judges would probably find it harder to interpret what's right and wrong here, as opposed to a weight loss or a real estate scam.

      Individuals don't sue their ISPs in civil court because it's a bit unusual for someone to have a few hundred thousand dollars (bare minimum) and a few years of their life to blow on a suit over a $30/mo injustice. That's one reason why these things are regulated to begin with. On the criminal side, the government prosecutors haven't often taken an interest yet either. That's in part because these guys would rather take their cue from the FCC on matters like this - it's novel and it's highly technical and it's supposed to be specifically regulated. Whatever the government does as a matter of policy is what we're actually discussing here.

      --
      Tired of Political Trolls? Opt Out!
    13. Re:Scare Mongering? by Concern · · Score: 1

      You're right; "free market" is just a vague expression. What I mean by it are particular regulations that are focused on people paying the real price for what it costs to move their traffic, whatever it may be, rather than letting ISPs make dishonest deals, oversubscribing their networks, and then and then letting VPs make decisions in back rooms about whose traffic gets where its going.

      I know it's hard to imagine after the last few years of FCC, but it's not that hard - it can be done. Just takes some light shining in those formerly dark corners.

      --
      Tired of Political Trolls? Opt Out!
    14. Re:Scare Mongering? by Raenex · · Score: 1

      On the other hand, if you could tell me where he's right on the facts, and I've gone wrong, that would be more helpful.

      If you're going to slam the guy for being ignorant about networks, and then be told he's quite knowledgeable, the least you can do is read the fucking article. He addresses your "I read the summary" points on page 2:

      "ISPs which throttle users based on raw traffic volume (as the new Comcast system will do) are protected from the effects of the massive use of aggressive UDP inside their networks. And they should be, as these private networks aren't internets in and of themselves. The damage is going to appear inside the core internet links connecting ISPs, which will become much less responsive to load management." [emphasis mine]

      Maybe you can read the rest of the article and post a more nuanced reply than your knee-jerk response.

    15. Re:Scare Mongering? by Concern · · Score: 1

      Ironic - did you read my post?

      This sounds like the basest kind of scare mongering, relying on a basic ignorance of the way networks work.

      I say the argument relies on ignorance. He doesn't need to be ignorant himself to make the argument (though it helps). :)

      You answer that by pointing out he's got a great resume. Without anything said about the facts at hand, it's almost a non-sequitur in my book.

      If I tell you I did read the article, will we argue about it? :)

      Do you have any other specific points to make, other than to reiterate this quote:

      The damage is going to appear inside the core internet links connecting ISPs, which will become much less responsive to load management.

      OK, why? Do you know?

      If you were a carrier, why would you not simply say, "OK, I'm hitting my limit, no more traffic without more money?"

      --
      Tired of Political Trolls? Opt Out!
    16. Re:Scare Mongering? by Anonymous Coward · · Score: 0

      But I don't have a free market, whee I live 1 hour drive from Sacramento, CAlifornia. I have a choice of Satellite at 80/month or AT&T. I have no comcast, I have no other ISP provider, because AT&T has fought and stalled all co-location deals with all the service providers that want to provide decent service at a decent price, with no shaping, or limitations. I have provided documentation to my various state and congressional representatives, and none of them consider this an issue worth doing anything about. So let's get this straight, until I see at the very least 3 viable choices, there is no free market !!!

    17. Re:Scare Mongering? by Anonymous Coward · · Score: 0

      Unless they're "filtering" bittorent traffic by RSTing the tcp streams, in which case UDP would be immune.

    18. Re:Scare Mongering? by jonaskoelker · · Score: 1

      stop lying about what it is you have sold to her. Either charge more or advertise less. It's as simple as that.

      I'm certain the ISP would be happy to sell the teen a 24/7-100%-for-her pipe. I'm also certain she doesn't want to pay.

      I would like to go to www.${ISP}.com and see a bunch of numbers.

      I'd like to know what the oversubscription rations for each of their services are.

      I'd like to know what the measured *actual* rates are, in say four-hour intervals across a typical work week, and in half-hour intervals across the average workday and weekend day.

      Never has so little rrdtool work for so much overview been done so rarely. Err... ;)

    19. Re:Scare Mongering? by cfulmer · · Score: 1

      Who's lying? When you sign up for service, you're handed a piece of paper that tells you exactly what you're getting and exactly what you can do with it. Why didn't you read that paper?

    20. Re:Scare Mongering? by Raenex · · Score: 1

      I say the argument relies on ignorance. He doesn't need to be ignorant himself to make the argument (though it helps).

      Well that's a subtle point. Your statement could have been interpreted either way.

      If you were a carrier, why would you not simply say, "OK, I'm hitting my limit, no more traffic without more money?"

      His argument is that turning on UDP for BitTorrent will kill apps that actually need UDP like voice over IP when the ISPs smack it down. He states that 2% of traffic today is UDP, 50% is P2P, and that by moving to UDP the BitTorrent guys are acting irresponsibly.

    21. Re:Scare Mongering? by Agripa · · Score: 1

      UDP is not any less filterable than TCP. To even make this argument, the reasoning is so contorted as to be silly. In either case, one uses a router to inspect packets and decide what to do with them. ISPs will simply go as deep through the envelopes as they like; they already do. With that knowledge they will do whatever is allowed by law. At present, almost anything is. If they abuse that power too foolishly, then it will start to be taken away from them.

      UDP has the advantage of being immune to the RST man-in-the-middle attack making it more difficult and expensive for the ISP to interfere with it because the attacking system has to be inline with the connection to do the filtering. IPSEC protected TCP also has this advantage but is problematical where an end to end connection is not available.

    22. Re:Scare Mongering? by Drunkenidaho · · Score: 1

      "when the ISPs smack it down" So it is the ISP's that will cause this problem ..? "Richard Bennett is a network architect and occasional activist in Silicon Valley. He wrote the first standard for Ethernet over twisted-pair wiring and contributed to the standards for Wi-Fi and the Ultra-Wideband wireless network" It's a pity that for a man so experienced that he betrays his lack of understanding of basic network concepts (or is he just lying?). FTA "UDP was intended for real-time data transfers such as VoIP that typically move small amounts of data with a low tolerance for delay." VoIP wasn't around when UDP was implemented, and it was designed for applications able to deal with packet loss. Seems perfect for BT. In fact I'm going to go change my settings now, so expect the internet to stop working in the next 5 minutes and the world to end shortly. -- Welcome to the apocalypse my friends

  40. Re:Greed by Anonymous Coward · · Score: 0

    The music industry is hardly a golden goose. I'll accept golden turd but not goose.

    Not golden calf?

  41. Re:A little extreme there, don't you think? by ShieldW0lf · · Score: 0, Flamebait

    Don't even pretend that most bit torrent traffic is legitimate and legal.

    Has it not percolated into your tiny brain that we don't recognize the legitimacy of the bodies that make the laws?

    Have you ever watched Charlie Brown? You know the bit where the adults are talking, but all anyone hears is "Whaa whaa, whaa whaa whaa whaa." That's you.

    Personally, I think the thing to do is to raze the offices of the politicians and corporate executives, with the people inside.

    --
    -1 Uncomfortable Truth
  42. Re:Well Duh by internerdj · · Score: 4, Insightful

    I don't use bittorrent, but frankly those (most of those) people are paying for unlimited internet access. At least that is how it was marketed. What I do uses is streaming video for alot of the shows I had been watching on TV. If my ISP is selling me unlimited internet and they decide not to deliver, I want a rate cut. If they don't have the capacity to reasonably provide what they sold me, they shouldn't be allowed to legally weasel out of providing it without penalty.

  43. Time and Money by howman · · Score: 1

    Perhaps if the big telco's spent a bit more on upgrading, widening and developing their networks rather than just pounding penny profits to shareholders this wouldn't be an issue. When are they going to realize that the people paying $35 ~ $200 a month for services which today cost about 10% of the charge are the real shareholders, and are the only real reason they are in business.

    --
    flinging poop since 1969
    1. Re:Time and Money by japhering · · Score: 1

      Perhaps if the big telco's spent a bit more on upgrading, widening and developing their networks rather than just pounding penny profits to shareholders this wouldn't be an issue. When are they going to realize that the people paying $35 ~ $200 a month for services which today cost about 10% of the charge are the real shareholders, and are the only real reason they are in business.

      Never! As stated by the CEO of AT&T, his goal is that every household in America be paying AT&T $120 before taxes for landline, television and cellular service (this being base line services not the level of service most people actually use)

    2. Re:Time and Money by Conor+Turton · · Score: 0

      When are they going to realize that the people paying $35 ~ $200 a month for services which today cost about 10% of the charge are the real shareholders, and are the only real reason they are in business.

      When are you going to realise what the actual real cost of bandwidth is? Clue: It's a fucking lot more than what you're paying now which is why contention ratios exist.

      I assume you're one of those people who thinks that if you pay for 10Mbit, you should be able to get that 24/7? Here's a simple task for you. Find out the monthly supply cost to an ISP of a typical 640MBit pipe. Divide that by the package you're paying for (so if you're on 10Mbit and it's a 640Mbit pipe, the answe is 64). Divide the monthly cost to the ISP of that pipe by your answer and you get the actual bandwidth cost to the ISP, excluding any costs for their infrastructure, to provide your bandwidth 24/7. I can guarantee that the cost is many many times what you're paying a month. If you want your bandwidth fully available 24/7 with no slow down, no problem but it'll be at least 10% higher than the end answer you came up with.

      --
      Conor "You're not married,you haven't got a girlfriend and you've never seen Star Trek? Good Lord!" - Patrick Stewart
  44. Re:Well Duh by Yoo+Chung · · Score: 1

    The proper way for ISPs to handle this kind of problem is to meter bandwidth, not completely block off an entire service.

    --
    I'm not sure if I'm real.
  45. Re:A little extreme there, don't you think? by Atticka · · Score: 2, Insightful

    "Better that ten guilty persons escape than that one innocent suffer"

    That should sum it up.

    --
    No sig here...
  46. What intense spin! by KonoWatakushi · · Score: 1

    Richard Bennett could not more obviously present himself as a shill for comcast and the like. The article is complete nonsense, attempting to portray bittorrent as the enemy of the Internet.

    This idiot drones on about the "ungentlemanly" conduct of using UDP for such purposes, but conveniently avoids the fact that comcast/sandvine caused this mess by injecting face TCP resets, to break bittorrent's TCP connections. Well, what does he expect would happen?

    Obviously, UDP is not a good choice for bulk transfers as it lacks congestion control, but lets be fair about where the fault lies. This is not something that can be worked around at the application level, and after being pushed into this corner, there is little else that can be done to work around their abuses of the TCP protocol.

    1. Re:What intense spin! by IamTheRealMike · · Score: 1

      Eh? It's BitTorrent that abuses the internet and Sandvine that tries to stop that abuse! Really BitTorrent is the most inefficient way of distributing files you could possibly design. It has one, and only one, reason for existance - it lets its users externalize bandwidth costs that they should be paying onto everybody else. There are no legitimate uses of this technology, anybody who legitimately needs to distribute huge files to lots of people can use CDNs like the mirror network or Akamai, and then set their cache headers correctly. Otherwise every time somebody distributes a big file with BitTorrent, they effectively make everyone on the internet pay for that bandwidth instead of themselves.

      Your argument is sort of like a factory saying, hey, we're only dumping our toxic waste onto the roads because when we dumped it into the rivers the rivers authority got on our backs.

  47. Re:A little extreme there, don't you think? by Conor+Turton · · Score: 0

    Has it not percolated into your tiny brain that we don't recognize the legitimacy of the bodies that make the laws?

    ...whilst hypocritically expecting the Police to enforce laws designed to protect you made by the bodies you don't recognise. You'd be really pissed off if no laws were enforced, someone decided they wanted your computer and either beat the living shit out of you or shot you in the process of relieving you of its ownership.

    You voted them in. Stupid fuck.

    --
    Conor "You're not married,you haven't got a girlfriend and you've never seen Star Trek? Good Lord!" - Patrick Stewart
  48. Re:Well Duh by frieko · · Score: 2, Insightful

    That makes sense if you're used to being screwed by your ISP. But the CORRECT response would be to actually supply the amount of bandwidth that they advertise.

    Ten years ago people only maxed out their connections 5% of the time. Nobody promised it would be like that forever.

  49. Re:A little extreme there, don't you think? by blackfrancis75 · · Score: 5, Interesting

    that Car Dealer thing is a terrible analogy. With the ISP model, everything you do with the 'bandwidth' you paid for goes through *their* systems first - they're understandably concerned that the drugs you're running across their borders are going to reflect badly on them in the long run.

  50. Re:Well Duh by RingDev · · Score: 1

    I'd bet at least 2/3 of all torrent traffic is for pirated movies, music or software and a large portion of the remaining 1/3 is probably porn.

    As long as we're empowering gamblers with legal and commercial ramifications, I bet that you are a child molester that steals from your employer.

    Now how about instead of making blind accusations we investigate and have a meaningful conversation.

    -Rick

    --
    "Most people in the U.S. wouldn't know they live in a tyrannical state if it walked up and grabbed their junk." - MyFirs
  51. Re:A little extreme there, don't you think? by themightythor · · Score: 1

    Has it not percolated into your tiny brain that we don't recognize the legitimacy of the bodies that make the laws?

    That is a slippery slope, friend. You have chosen to live in a society and by extension have chosen to live by society's rules. If everyone gets to pick and choose which ones they want to abide by and not, then that becomes anarchy. Under your argument, if I don't agree with the rule that people have a right to private property, I can break down your door, take your stuff, and it's cool because I don't agree with the rule.

  52. I have it on good authority, that... by firefarter · · Score: 1

    when you enter "google" into google, you can break the internet!

  53. Funny. by Opportunist · · Score: 1

    One would have guessed Spam is more of a problem. Or YouTube. Or the internet TV some networks are pushing now. Or maybe even WoW. Why? Because EVERYONE does it! Everyone gets spam, everyone is on YouTube, 11 Millions playing WoW... ok, nobody cares about IPTV, but still.

    No. It ain't the spam that clogs my mailbox (and no, spam is no longer text. It's effing HUGE pics!), it's not megabytes of videos being streamed to every other computer connected to the net, it's not WoWheads spending 20 hours a day in front of their machine. It's Bittorrent. Something that less than one in thousand internetusers uses with some dedication that could be called "heavy use".

    How about doing something against spam and botnets? I'd wager my salary that would instantly take care of any congestation, too. At least if that's the real problem we're trying to deal with...

    --
    We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    1. Re:Funny. by Valdrax · · Score: 1

      It ain't the spam that clogs my mailbox (and no, spam is no longer text. It's effing HUGE pics!)

      Are you sure those pics are being emailed to you or are they hosted on a web server somewhere? While I used to get spam with attached images, I haven't seen those in a while. In my spam folder, I have 691 messages, only 2 of which have attachments, which are both ZIP files probably containing some sort of awful trojan.

      I don't know if my ISP is now filtering image-based spam, but if so, the method is now ineffective, and I suspect spammers have moved on. The last news stories I can find on the subject via Google are from 2006. An audit of my mailboxes reveals that I only got a few MBs of email last month, whereas I easily did several GB of P2P traffic.

      While I am certainly not a good statistical representative of the internet as a whole, I would not be surprised if people transferring movies, music, software, etc. via P2P took up significantly more traffic than people transferring text, HTML, and rich text via email -- even spam. It takes a whole lot heck of a lot of spam to equal one episode of a TV show via BT or YouTube.

      (P.S. If you're seeing images in your spam email, FOR THE LOVE OF MIKE TURN OFF IMAGES IN YOUR CLIENT! Have you never head of web bugs? You may be verifying the existence of your address to spammers.)

      --
      If it's for-profit but free, you're not the customer -- you're the product (e.g., the Slashdot Beta's "audience").
    2. Re:Funny. by Opportunist · · Score: 1

      You may take into the calculation that by far not everyone is using P2P software to transfer gigabytes of data, but almost every single person (or rather, almost every single email address) gets spam. Additionally, some countries have laws prohibiting ISPs from denying you deliver of mail, no matter where it comes from. They may flag it, but you and only you may filter. As it should be, btw.

      And no, I don't see images. The client of my choice does not support them. I just see a lot of .gif or .jpg attachments.

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
  54. More on this story... by JCSoRocks · · Score: 4, Funny

    BitTorrent is believed to be harboring weapons of mass destruction. These weapons are believed to be capable of destroying all of the internet tubes. The government has no choice but to authorize the ISPs to use lethal force to prevent these terrorists from succeeding.

    --
    You are using English. Please learn the difference between loose and lose; they're, there, and their; your and you're.
    1. Re:More on this story... by supernova_hq · · Score: 1

      Holy crap, don't even say that!

      It only takes 1 ISP exec to hear about this and then BOOM, no bittorrent...

    2. Re:More on this story... by Atrox666 · · Score: 1

      I heard that several terrorist have already used bit torrent to transfer files.

      They also use Word so we should ban that too.

    3. Re:More on this story... by qmaqdk · · Score: 1

      Operation Fix The Tubes.

      --
      My UID is prime. Hah!
  55. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 5, Interesting

    "that Car Dealer thing is a terrible analogy. With the ISP model, everything you do with the 'bandwidth' you paid for goes through *their* systems first - "

    Which is bullshit, consider the post office, I order something online from a retailer, does this give the shipping company or government the right to open my mail and packages because it passes through their facilities? It's bullshit plain and simple. They don't have a right to watch and monitor what you send. It's just another cash grab disguised as "helping the consumer"

  56. Re:A little extreme there, don't you think? by jgeiger · · Score: 1, Informative

    Can you imagine signing up for a "3 DVD's at a time" plan from Netflix and then when you actually check out 3 at a time they start bitching up a storm because "You're hoarding the DVD's!!! None of the other customers will be able to rent any of them!!!".

    Umm, I believe Netflix was throttling your movie delivery times based on your usage.
    http://slashdot.org/article.pl?sid=06/02/11/0754230

  57. Is there congestion control? by Andy+Dodd · · Score: 1

    While UDP itself fundamentally has no congestion control, this doesn't mean that the transport protocol layered over it by the application (Almost all uses of UDP have an additional application-based transport protocol layered over them, such as RTP or Sun RPC) doesn't also have congestion control.

    Was this meant to bypass congestion control (probably not, TCP congestion control is fine and traffic shaping is usually fine if done right), or was it done in response to Sandvining which has NOTHING to do with congestion control and everything to do with the ability of an attacker to shut down a TCP connection with a Man-In-The-Middle attack (fake RSTs)?

    I'm assuming it's a defense against MITM attacks, in which case it doesn't mean the end of the Internet as long as the new congestion control approach is sensible. Unfortunately we can likely expect lots of bugs and misbehaving applications so this could be bad.

    --
    retrorocket.o not found, launch anyway?
  58. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    If everyone gets to pick and choose which ones they want to abide by and not, then that becomes anarchy.

    Pssst... You're clearly arguing with a junior high "anarchist". Anarchy (at least, the cool kind where everything works right and he gets cool guns and maybe a hot girlfriend in a leather thong) is his goal. You need a new tactic, quick!

  59. You are not listening... by Anonymous Coward · · Score: 2, Insightful

    His example is that multiple users behind ONE of these DSLAM ports have congestion. Per your example, the congestion is as soon as they reach their 64 kb/s policy.

    However, everyone in these bittorrent debates pretends that the DSLAM port is the bottleneck. In a highly interconnected environment like a world full of bittorrent and other users, there are many other places for congestion far from the simple consumer-to-ISP policy enforcement point. TCP congestion control helps with congestion anywhere that multiple flow paths intersect. The Internet does not magically prevent intersections and congestion except at consumer head-ends.

    1. Re:You are not listening... by MasterOfMagic · · Score: 4, Insightful

      I am saying that, in the case where multiple users have congestion, it is not a problem of user behavior. It is a problem of the ISP not having a wide enough uplink. If the users that are causing the congestion stop using their connection then they are not getting the service that they paid for. The ISP has three options at this point:

      1. Do nothing and let stupid shit like this happen
      2. Use the revenue from their business to increase network capacity
      3. Lower every user's line speed so they can fit more people on the same link

      Almost every ISP in the country is selecting the first option and wondering why everybody is pissed at them. Number 2 would probably take away from their stock price (not that it has much further to slide at this point) despite it being the right thing to do, and Number 3, while honest and straightforward, would never fly.

      However, everyone in these bittorrent debates pretends that the DSLAM port is the bottleneck. In a highly interconnected environment like a world full of bittorrent and other users, there are many other places for congestion far from the simple consumer-to-ISP policy enforcement point.

      I'm not pretending that it doesn't exist. As a matter of fact, as I've said in other posts, this is due to oversold uplink connections and upstream networks not ready for this increase in bandwidth. Bandwidth is being charged for. Somebody is making money. Spend the money on increased network bandwidth at interconnects that are traditional and measurably congested and stop doing stupid shit like cutting off peering because someone looked at you funny.

      However, BitTorrent here is a scapegoat - you'd have the same problem with large FTP sites, video archives, or masses and masses of streaming porn. A bottleneck isn't caused by the protocol. The bottleneck is caused by the demand, and demand for a service is independent the protocol it's wrapped in.

    2. Re:You are not listening... by Anonymous Coward · · Score: 0

      Reducing the line speed wouldn't *work*. I currently have a 10 Mbps connection. If it was reduced to 5, I wouldn't reduce the total amount I download, but each one would take twice as long. The line speed would have to be reduced a lot (probably to 1 Mbps or less) to actually reduce overall congestion.

      There is an option you omitted - monthly caps, or charging per Gb. A reasonable charge would both act as an incentive not to download huge amounts and to provide funds to improve capacity, both of which would act to reduce congestion. If the amount charged was a fair representation of the cost of the capacity required, who can complain?

    3. Re:You are not listening... by MasterOfMagic · · Score: 1

      Reducing the line speed wouldn't *work*. I currently have a 10 Mbps connection. If it was reduced to 5, I wouldn't reduce the total amount I download, but each one would take twice as long.

      You're missing the point. If the uplink is 100Mbps and your connection speed is 10Mbps, that means 100Mbps/10Mbps = 10 customers can be online and fully utilizing that link. If we reduce your connection speed to 5 Mbps, that means 100Mbps/5Mbps = 20 customers can be online and fully utilizing that link. It doesn't matter that your download takes longer or that you use it twice as long - twice as many people will be able to use the link as before, and presumably some of them won't be maxing our their allotment simultaneously.

      It's not about how much you download - it's about how much instantaneous utilization you have. So long as your link is not completely utilized, people can use it without problem. By halving the line speed of all users, you double the number of people that can use the uplink simultaneously, thus providing relief for the local congestion problem.

      There is an option you omitted - monthly caps, or charging per Gb.

      Because it's a pain in the ass that most consumers would reject flat out. It also stifles innovation by making it too expensive to participate in the network. It also makes it trivial to violate the principles of Net Neutrality. Your ISP starts a video on demand site. They make this video on demand site not count towards your quota, and makes the third party sites competing with them count towards your quota. This promotes unfair competition and is against the spirit of how it's supposed to work on the Internet.

  60. Re:Well Duh by chrysrobyn · · Score: 1

    BitTorrent is going to find out, very soon, that it shouldn't try to be a bully; it's making other customers vote with their wallets, and if you force the point, there are actually a ton of ways to stop this cold (which unfortunately hurt the rest of us too, like caps).

    BitTorrent is responding to the bully. ISPs have a choice here, acknowledge customer behavior and find a way to work with it, or fight it. They almost managed to work with it with the P4P initiatives, but they involved media companies who will undoubtedly find the centralized and friendly owned tracker logs easier to get. If ISPs went with common carrier arguments and found a way to publish their network topologies and got trackers to behave similarly to P4P, then everyone would benefit. P4P isn't about denying people access to off-ISP data, it's about preferentially treating free pipes. If you need to upload and the free pipe isn't available, you still get access -- and those off big company owned ISPs still get their data.

    BitTorrent is designed to maximize use of everyone's available bandwidth. Azureus can give me better transfer speeds than any single HTTP or FTP server I've found. If the ISPs want to continue to ratchet up this game, then maybe the 'net truly is in for a meltdown. If the ISPs backed off just a hair, there wouldn't be a reason to investigate these harder to block methods and we could all find solutions that work for everyone (except maybe copyright holders) because siding with the copyright holders will only harm consumers and ISPs.

  61. What we need is a working QOS by haapi · · Score: 1

    I think part of the answer is for Quality of Service (QOS) to be implemented properly and universally. Would even the most rabid BT user/provider care hugely if his traffic throughput took a back seat to video for the space of several fragments? It still wouldn't be shut down completely. The win is that when no higher-QOS traffic is on a network segment, BT gets the whole "tube."

    There is much more of a workable QOS in IPv6 than in IPv4, where it was more or less grafted on after the original design.

    Let's get moving to IPv6.

    --
    Well, apparently, you only have to fool the majority of people for a little while.
    1. Re:What we need is a working QOS by daveime · · Score: 1

      Yes, in principle, real time video streaming NEEDs higher priority because of the nature of "real time" as opposed to "deferred" file transfer.

      But in practice, this implys that "User A's video is MORE important than User B's file".

      I'm sorry, but some asshole who simply MUST view a movie in "HD 1080" realtime, when there's plenty of compressed alternatives that take up a fraction of the bandwidth AND still deliver a reasonable quality video does not get any more sympathy than an asshole sharing a torrent on max ul/dl 24/7.

  62. The main issue with bittorrent by m.dillon · · Score: 1

    Right now the biggest problem ISPs have with bittorrent is not the bandwidth it uses, but the massive packet load it puts on their border routers, DSLAMs, etc. This is 99% due to allowing hundreds of simultaneous incoming connections. bittorrent clients have never been able to throttle incoming bandwidth aggregated across hundreds of connections very well, and the result is thousands of packets worth of backlog on the ISP's border routers, DSLAMs, etc, which blows them up.

    Changing to UDP does not solve this problem, it just makes things even worse. The bittorrent people need to get their act together. The ISPs are just going to respond by changing their bandwidth filtering to be whole-IP-based instead of connection-based, and the result will be that people trying to use bittorrent will wind up with crappy, unreliable links for EVERYTHING they are trying to do over the internet.

    I don't know why people using bittorrent should expect the ISPs to 'play nice' when they clearly don't give a damn about the mess bittorrent makes of the ISPs own infrastructure.

    -Matt

    1. Re:The main issue with bittorrent by JoelKatz · · Score: 1

      Actually, changing to UDP makes things better. With TCP, you have very little control over the transmit pacing and congestion control. With UDP, you have much finer control and immediately change how you are handling one connection based on what's going on with another one.

      It remains to be seen if the BitTorrent developers can pull this off though. Many people thing that with pacing and windowing under their control they can do a better job than TCP does. Few actually succeed, since TCP already embodies most of the good idea in this area.

  63. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    They're already safe from liability. They don't need anything more.

  64. Re:Well Duh by palmhack · · Score: 1

    Perhaps it really isn't about bullying, but getting every bit of what you pay for. Just because you have found a way to utilize all of your bandwidth doesn't make you liable for melting down the internet. It just means that the ISPs need to evolve along with the technology. They have been quoting bogus bandwidth amounts and corresponding prices for years. And now that their outdated model has proven to be a disaster, they should evolve or die like the rest of us.

  65. Can't stand The Register any more by bencollier · · Score: 1

    These sorts of heavily biased, misleading articles are why I can't stand reading The Register any more. It's all GNU-bashing and items on defence spending. I don't remember it being this bad a few years ago. In any case, I don't want to read it any more.

  66. The electricity sold to your home by VShael · · Score: 1

    Look, I'm a huge BitTorrent guy, I run uTorrent every day and pretty much max out my connection for about 8 hours a night.

    That said, I don't understand this attitude of "If you sold me 10Mbps, then you'd better be able to give it to me 24/7"

    The electricity in your home is also sold to you on the assumption that you can run any and all household appliances from it.

    But guess what? If you switch everything on, because you're allowed to and can afford to, and so do your neighbours, and everyone else on the grid... the grid collapses.

    There were certain statistical assumptions built into the grid and the pricing model. One of those assumptions was that their customers wouldn't take up 100% of their allowable usage ALL THE TIME.

    This is hardly a new thing.

    1. Re:The electricity sold to your home by despisethesun · · Score: 1

      The difference is that the power company charges me for usage, so I will self-regulate to lower my electricity bill. My ISP sold me "unlimited" at a flat rate and is now getting pissy that I'm going above and beyond what they consider reasonable. If they can't sell something, then they shouldn't sell something and bitch because they can't deliver it. They should also not be allowed to market it as "unlimited" and, in the fine print, have "for varying values of unlimited."

      --
      This poo is cold.
    2. Re:The electricity sold to your home by nog_lorp · · Score: 1

      You make a good point. But the power grid functions just fine despite the numerous people who use their power to capacity constantly. Even in the face of Marijuana grows that utilize thousands of times that of the normal household 24/7 and bypass the meter, the grid keeps chugging. The real issue is that electricity isn't sold at a flat 'full usage' rate, whereas bandwidth is. It is starting to look like that is a mistake.

  67. Re:A little extreme there, don't you think? by Oqnet · · Score: 2, Interesting

    I agree but I wouldn't say it's as much like buying a car from a car dealership, it's more like leasing the car for a term. They can set the cap on the milage you can take it and they can put in a governer and charge you more if you damage the car removing the governer or go over your alloted. But your point is that they shouldn't be able to limit how you use it, and I don't think there is anything in the contract saying that they can. They don't have any right to decided what is a proper use of your bandwidth that you are allocated. They can't all of the sudden decide to limit how much to use.

    At the end of the month if your over your limit that is set(cap) charge them more. If they are only allowed 50gigs of data and they have more charge them per gig or meg or however you want to spell it out. It's not like they are uncapping their connection and stealing bandwidth from the stream. They are using their bandwidth that was given to them to the fullest potential. It's not their problem that the ISP decided to oversell their bandwidth. Thats like saying four people can have 100 dollars having 200 and when Billy spends his 100 dollars accuse him of stealing from the other 3 because theres only 100 dollars between the last 3.

  68. Just another data flow to filter/black hole by ekimminau · · Score: 1

    Anyone who doesn't think that numerous products, Narus (http://en.wikipedia.org/wiki/Narus) being one example that comes to mind, won't rapidly generate IPDR to track and immediatly filter/blackhole such excessive UDP dataflows is sadly mistaken. I remember when ping floods were the death nail. It rapidly became a non-issue. If TOrrent wants to make a brillany decision that immediately shines the megawatt spotlight on them being the nasties in the network neighborhood they will, in very short order, see the million monkey army come up with that quick fix brillant solution to quickly put them out of business.

    In today's world of high speed networking, I'm honestly surprised that UDP is even allowed to traverse the backbone. Short of the million monkey solution, rather than allowing a runaway child to melt down the big boy back bone providers, I would see them black holing UDP and forcing all protocols to use TCP. Sure it will kill some audo and video streaming. It will also decrease utilization at the backbone by 75% and improve all the "real" traffic (HTTP/HTTPS/SMTP) performance by an order of magnitude. Sucks to be a media content provider. They beter start looking at TCP alternatives if they want a sustainable business model. Its not like people haven't been considering the possibility (http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=01295064, http://en.wikipedia.org/wiki/Streaming_media). RTSP will just become the defacto standard rather than an alternative.
    My .02.

    --
    Armaments, 2-9-21 And Saint Attila raised the hand grenade up on high, saying, 'O Lord, bless this Thy hand grenade' N
    1. Re:Just another data flow to filter/black hole by Luthe_Faydwire · · Score: 1

      Both have a place in the network.

      TCP is used for connection based traffic that needs to be retransmitted at the protocol layer when dropped. As such the TCP protocol does not require the application to maintain state as the protocol handles retransmits and flow control.

      UDP is used for traffic that is connectionless where it is not necessarily desirable to have retransmits. The application handles both the flow control and retransmits.

      VOIP is "real time" UDP because it makes no sense to resend a lost packet. A retransmitted packet would require more delay "jitter" in voice calls. Just skipping the missed packet is really the only option here.

  69. Re:Greed by Opportunist · · Score: 1

    Oh, please make it a goose! You know how the story ends, right?

    I vote goose!

    (And I really don't care if it's golden inside, I'll live happily ever after!)

    --
    We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
  70. Re:A little extreme there, don't you think? by adonoman · · Score: 5, Interesting

    The problem with bittorrent, is that it's MORE convenient than watching TV the old fashioned way. All the benefits of TIVO, except that I can use my computer (and keyboard) to specify which shows I want. I don't care which channels are broadcasting them, they just appear in the downloaded folder. I can watch from any computer in the house (or outside with a laptop). There are no DRM restrictions.

  71. Re:A little extreme there, don't you think? by Shakrai · · Score: 4, Insightful

    That is a slippery slope, friend. You have chosen to live in a society and by extension have chosen to live by society's rules.

    Didn't that society also make a few promises to the people that decided to live in it? Like freedom of speech, freedom to keep and bear arms, freedom against self-incrimination, etc, etc, etc?

    If everyone gets to pick and choose which ones they want to abide by and not, then that becomes anarchy

    So pot-smokers and people who exceed the speed limit lead us down the road to anarchy?

    --
    I want peace on earth and goodwill toward man.
    We are the United States Government! We don't do that sort of thing.
  72. Good point, but I disagree with your conclusion by CFD339 · · Score: 2, Insightful

    Its true for now that most links are sold purely by bandwidth, so your statement about getting what you've paid for is valid -- unless what you're paying for includes by contract a cap on total use or continuous use, or something else. Most home network access contracts contain those use case caps.

    What really caught my attention as I read your note is that comment about the number of open tcp connections. As I read it, I'm surprised that hasn't been used as a valid limit on use by contract.

    If you think of things that add cost and hurt performance from an ISP perspective, total number of sessions is one of them. It increases the load on routers and adds overhead and latency to network (or it can, unless more money is spent on bigger and faster routers).

    Limiting concurrent sessions is probably just around the corner.

    I currently pay for the highest bandwidth version of consumer net access offered in my area. Its more that sufficient for downloads, but because I work from home it is slower than I'd like for uploads. I use a hosted server at a co-lo site so that my business system isn't carried over a consumer line, but I still pull down a pretty huge amount of data sometimes.

    I'm completely convinced that if my ISP wanted, they could slow my links by about the third week of most months. I believe they don't only because they don't offer a higher level of service than I'm paying for. At least for me, they've always been fair and responsive.

    If anyone is limited by an ISP when they've got an agreement to pay for services that doesn't support those limits being applied, they should take legal action. If not, they should pay more attention to what they purchased and either refuse to buy what's offered or live inside it.

    If you can't live with what's in the agreement, lease a line and pay for your own service to somewhere. What you'll find is that without the aggregation that's done by the big ISP's, you'll never be able to afford the on-demand use you want to buy.

    I want massive bandwidth on demand too -- I want to download 4gb movies in under 30 minutes whenever I want. I do not, however, want to pay for a leased line capable of doing that. When I buy into a shared provisioning system (a consumer isp arrangement) I'm agreeing to live within that ecosystem and share the cost of that high bandwidth as well as sharing that bandwidth.

    The contracts are obscure and don't come right out and say so. Maybe it would be better if they did.

    --
    The problem with quotes on the internet, is that nobody bothers to check their veracity. -- Abraham Lincoln
    1. Re:Good point, but I disagree with your conclusion by Ed+Avis · · Score: 1

      If you think of things that add cost and hurt performance from an ISP perspective, total number of sessions is one of them. It increases the load on routers

      Why is that? Surely the router doesn't care what is inside the IP datagrams it is sending from one place to another. Whether they are made of one TCP session between two hosts, or a hundred separate TCP sessions between those same two hosts, or they aren't TCP at all, should make no difference. Communicating with a large number of different hosts would need more space in the routing table, but it's unlikely to be a significant effect.

      --
      -- Ed Avis ed@membled.com
    2. Re:Good point, but I disagree with your conclusion by yabos · · Score: 1

      High # of connections is a problem on crappy home NAT routers because they have to maintain a translation table of ports to internal IP addresses in memory. This shouldn't be a problem in any real router because all it does is forward packets to the correct network. It does not maintain any state for a TCP connection. That's the job of the clients on either end to do that.

    3. Re:Good point, but I disagree with your conclusion by Cramer · · Score: 1

      Wrong. Routers maintain state information for "flows". Otherwise, there's a route table lookup for every single packet. If you want to see this for yourself, login to your million dollar Cisco 12000, turn off route cache and watch it route packets only slightly faster than your 50$ linksys wireless "router". Many systems don't maintain a cache for UDP streams since they have no setup or teardown.

      The major flaw in the logic from the idiots at uTorrent... UDP packets can be dropped pretty much at will (and often are.) Furthermore, even decade old network gear throttles UDP traffic. If they think using UDP will magically evade blocking and shaping technology, they are 100% flat out WRONG. They just made it 50 orders of magnitude easier to spot... ask yourself, what uses udp across the tubes today? DNS, IPSec tunnels, audio and video streaming... all of it known, recognizable traffic.

  73. The ISPs are not "entirely" to blame... by Lord+Jester · · Score: 1

    I will admit to the occasional download using BT. I justify my downloads as they are available for free from the web site of the show, but the plugins are not available for me to view the streams.

    Anyway, I get letters from my ISP that are copies of the complaint sent to them by the studio. The studio is threatening the ISP to try to force them to do the bullying of the "violator".

    I am not in any way condoning what the ISPs are doing and am in no way condoning uTorret's use of UDP to try to circumvent the issue under discussion in the original post.

    Just my $0.02 worth.

  74. All applications should be what now? by Digital_Quartz · · Score: 2, Insightful

    It enforces bad design -- most client/server applications should be either stateless or session-based, rather than connection-oriented.

    What? Why? Why is a connection based application "bad design"?

    A "session" is just a hack to give you connection-like qualities over a connectionless protocol, such as HTTP. If you want connection-like behavior, and you're free to design your own protocol, why not just use connections? Why make your life more complicated?

    There are plenty of advantages to connection-based applications; no need to re-authenticate on every message, for one. Clear indications of when a client is done talking to you for another (the connection is dropped, whereas in a connectionless world you never really know if the client has died or is just about to send you another message).

    Even most "connectionless" applications, such as your web browser, try to cheat and get connection based behavior. Renegotiating an SSL connection for every request would be remarkably expensive for the server, so the server and browser try to reuse the same connection as much as possible. Fire up wireshark, and you'll see your browser will only open two connections when you read Slashdot, and all the images and text all come across those two connections.

    1. Re:All applications should be what now? by Man+On+Pink+Corner · · Score: 2, Insightful

      What? Why? Why is a connection based application "bad design"?

      Because connection maintenance is a very high-level task that should not be delegated to the very bowels of the application, much less to someone else's opaque API.

      A "session" is just a hack to give you connection-like qualities over a connectionless protocol, such as HTTP. If you want connection-like behavior, and you're free to design your own protocol, why not just use connections? Why make your life more complicated?

      The complication comes in when you have to code "connected versus unconnected" states into your app all the way up to the user-interface level, and you realize that you're doing a lot of redundant work to try to keep track of what TCP/IP thinks the connection state is. Admittedly, it's hard to explain unless you've been there.

      There are plenty of advantages to connection-based applications; no need to re-authenticate on every message, for one.

      TCP is doing this behind your back. Maybe you can do it better.

      Clear indications of when a client is done talking to you for another (the connection is dropped, whereas in a connectionless world you never really know if the client has died or is just about to send you another message).

      That's one of the worst examples you could pick. When, and whether, TCP will drop a connection is up to factors far beyond the application's control. You have to handle the "TCP dropped connection" state anyway; it's not really any easier to do that at the lowest networking level than it is to do it at a higher level.

      Most applications I've worked on have ended up with their own keepalive-based housekeeping mechanisms anyway; the obvious tactic is to use those mechanisms for connection maintenance instead of a low-level TCP connection whose persistence your own code has to mirror.

      Even most "connectionless" applications, such as your web browser, try to cheat and get connection based behavior.

      Again you're making my point for me. Because TCP-level connections are not appropriate for Web browsing, various Procrustean hacks get brought into play.

      Renegotiating an SSL connection for every request would be remarkably expensive for the server, so the server and browser try to reuse the same connection as much as possible. Fire up wireshark, and you'll see your browser will only open two connections when you read Slashdot, and all the images and text all come across those two connections.

      Sure, but that has nothing to do with any inherent advantages of TCP-level connections, except insofar as SSL is tied to them. If you were driven by absolute maximization of server performance and weren't saddled with the baggage of existing protocols like HTTP, you certainly wouldn't use TCP; it'd be like doing unnecessary work in the inner loop of a graphics routine. That's the decision the BitTorrent people are faced with.

    2. Re:All applications should be what now? by windex82 · · Score: 1

      Again you're making my point for me. Because TCP-level connections are not appropriate for Web browsing, various Procrustean hacks get brought into play.

      Just asking a question but I don't think UDP is appropriate. How is the web browser to know if it received the right data? Isn't part of TCP making sure it received it correctly? With bit torrent you have a file on both ends that say whats expected, you don't have such a luxury when requesting web pages or many of the other examples you have given for mis-uses of TCP.

      It almost sounds to me as if you feel programmers should just build off UDP to achieve what they want from TCP. Looking through your arguments it looks as if your reasoning is because most applications use TCP then have to recreate various functions of TCP to work correctly anyway. So they should just use UDP to begin with?

    3. Re:All applications should be what now? by Man+On+Pink+Corner · · Score: 1

      I wouldn't argue in favor of serving static, linearly dependent and linearly organized web pages with a UDP-based custom layer. I wouldn't argue against it, but it's not one of those cases where you just slap your forehead at the stuff TCP does to get in your way.

      There's a good chance that if you set out to design a transport layer for HTTP you'd end up reimplementing TCP badly, as others in the thread have pointed out. But it's not 1988 anymore, and modern networked applications do a lot of stuff that they didn't do back then. There's no need to reinvent the wheel, but there's also no need to put wheels on a jetpack.

    4. Re:All applications should be what now? by windex82 · · Score: 1

      Damn, you replied to the wrong questions! =P

      This is the part I was hoping for clarification on.

      It almost sounds to me as if you feel programmers should just build off UDP to achieve what they want from TCP. Looking through your arguments it looks as if your reasoning is because most applications use TCP then have to recreate various functions of TCP to work correctly anyway. So they should just use UDP to begin with [and build the other bits in thier application]?

      Sorry for reasserting this question but I'm not a real programmer (tiny personal projects and report parsers at work) or in a position where I need to know the very nitty gritty workings of all the networking layers but still find this topic very interesting, in particular these thoughts on UDP v TCP you have brought up. Mostly because they seem to be backward from what I've learned but still seem to make good sense.

    5. Re:All applications should be what now? by Man+On+Pink+Corner · · Score: 2

      It almost sounds to me as if you feel programmers should just build off UDP to achieve what they want from TCP. Looking through your arguments it looks as if your reasoning is because most applications use TCP then have to recreate various functions of TCP to work correctly anyway. So they should just use UDP to begin with [and build the other bits in thier application]?

      Opinions will vary, just read the thread. It wasn't too long ago that anyone challenging the supremacy of TCP/IP for any and all networking applications would have been modded down to -1, Heretic.

      From the application developer's perspective, TCP maintains connections on your behalf. What's a connection, you ask? Simply a remembered state ("I'm talking to host X on port Y") with a bunch of buffers associated with it to guarantee reliable delivery of the data you send to host X. Outgoing data is kept around until the remote host sends an ack back saying it got it OK. If the ack doesn't arrive within a certain amount of time, typically measured in thousands of milliseconds, TCP helpfully retransmits your data. The reverse happens on the receive side; because outgoing packets are sequence-numbered by the transmitter, duplicated or out-of-order packets can be thrown away (if duplicated) or buffered up until the missing packets arrive to fill in the gap (if out-of-order delivery is detected).

      What's wrong with that? Not a thing, if your application is synchronously sending and receiving chunks of text or linear pieces of binary data between two hosts.

      The thing is, that's not a good description of what most of the Internet's publicly-visible applications do anymore. If you're streaming VoIP, music, or video, you don't want to stall the stream for thousands of milliseconds if a single packet gets lost. The application already has to maintain its own media buffers to hide latency from the user, and it may be able to synthesize missing VoIP frames from context, drop video frames when necessary (and compensate by adjusting timing), or whatever. If you're running a game server, the client physics is already doing prediction and interpolation to hide latency and packet loss, so when a packet gets lost, it's a case of "It's gone, dude, let it go."

      Similarly, if you're running BitTorrent or something else that amounts to a peer-to-peer file system, you're already using your own high-level protocol to assemble file images from disparate, potentially out-of-order fragments. You probably want to be able to determine your own strategies for acknowledging packet delivery, abandoning or punishing uncooperative peers, and managing peer traffic volume.

      TCP brings essentially no value to the table in any of these situations. It's going to fanatically deliver that data to you, even if it has to retry 10 times and choke back a megabyte of traffic to maintain packet order. It'll get that data to you, even if you don't need it anymore.

      So yeah, conceptually, you'll end up using UDP to emulate a lot of the semantics of TCP, but in practice what you do as the application developer is probably quite different than what TCP would do on your behalf. Applications nowadays are more distributed, less synchronous, and more latency-sensitive than they were back in the 1980s when Unix-heads used the terms "file" and "stream" more or less interchangeably.

      There is nothing wrong with TCP/IP -- it's a hell of a nice piece of engineering, in fact. So was the Apple II. The world moves on.

    6. Re:All applications should be what now? by Digital_Quartz · · Score: 1

      The complication comes in when you have to code "connected versus unconnected" states into your app all the way up to the user-interface level, and you realize that you're doing a lot of redundant work to try to keep track of what TCP/IP thinks the connection state is. Admittedly, it's hard to explain unless you've been there.

      Oh, I've been there. I'm not saying there aren't applications where using stateless/connectionless abstractions aren't a good idea. There are lots of them where this is a great idea. Web browsers, for example.

      But, are you really trying to infer that, say, SSH would be better if it were connectionless? Or telnet?

      Or take, for example, POP3. POP3 is a connection oriented protocol. In what way does POP3 enforce bad design? I've never seen a POP3 mailer which has connected/disconnected states propagated all the way to the GUI (beyond, of course, the "I can't connect" icon, but that would be true in a connectionless application as well).

      TCP is doing this behind your back. Maybe you can do it better.

      I'm not sure what you mean here. TCP has nothing to do with authentication. Unless you mean; if you have a connection oriented protocol, then you authenticate once and TCP takes care of knowing which packets are part of the connection and which ones aren't? If you're trying to run a connectionless protocol over TCP, then you need to reauthenticate on every message. If we take SOAP, for example, you'll see a WSSE header in every message, unless you're using something like WS-Secure Conversation, which effectively tries to emulate an encrypted TCP connection over SOAP (probably over TCP).

      That's one of the worst examples you could pick. When, and whether, TCP will drop a connection is up to factors far beyond the application's control.

      Umm... close()?

  75. Re:A little extreme there, don't you think? by SecretSquirrel321 · · Score: 4, Insightful

    Yes, I do have 10,000 sheep. But this land is common, I have a right to let them all graze there if I want to.

  76. Secure TCP protocol - anti ISP packet injection by OdinOdin_ · · Score: 1

    Isn't the main issue against ISPs not the throttling of flows but the injection of fake TCP RST (Reset) packets and other such illegalities. Illegal from the PoV that the protocol specification and IETF have not ratified this behavior. http://www.eff.org/wp/detecting-packet-injection

    What is needed is a "secure TCP" where all control information within the packets at TCP level are cryptographically signed like with a MAC checksum. (No SSL does not fix this problem! SSL sits on top of TCP and ISPs a messing with flows at TCP level)

    This will however require kernel support at both endpoints. Maybe it could even be implemented as a series of TCP options.

    I would not support actions that lead to an internet meltdown that the article suggests, /. is presuming that no flow or congestion control will be implemented via this UDP alternative to TCP (which remains to be confirmed and certainly the forum in the article indicates THERE WILL BE flow/congestion control implemented with the UDP alternative).

    Why don't they just use a form of TCP protocol but apply techniques from "VJ Compression" and add a MAC code it should be possible to get the overhead of sequencing .

    TCP header (no options) is 20 bytes. UDP header is 8 bytes. UDP provides you port info already for connection tuples. So you have a 12 byte budget to implement:

    * reliable sequencing
    * flow-control/retransmission (window control/timestamps/selective-ack)
    * MAC/protocol security (the real reason IMHO why they need to resort to UDP in the first place)

    That should be ample budget. We specifically don't need hi-performance delivery just a protocol that scales well enough in the domain of 30mbit at the users access point communicating to between 1 and 30 others.

  77. You can only do that a the very edge by Nicolas+MONNET · · Score: 2

    Routers deeper inside the network cannot keep tabs on millions of IPs and who uses how much, they already have much to do.

    1. Re:You can only do that a the very edge by mbone · · Score: 1

      For about the last decade, the core of the network has been in good shape, and the problems occur at the edges, so at the edge is where filtering (e.g., Sandvine) occurs.

      From what I hear, that is not likely to change anytime soon.

    2. Re:You can only do that a the very edge by dhldelivers · · Score: 1

      Big ISPs already have a method to apply bandwidth caps on individual users. Comcast comes to mind. So their routers ARE in fact keeping tabs on millions of IPs. So substitute caps with UDP throttling and there ya go... the gaming/voip armageddon is averted. Just like myxiplx said. Its not a controversy.

  78. Half-truths by neokushan · · Score: 1

    This article (And the summary, of course) is spinning this way out of control.

    This is taken DIRECTLY from the guys behind uTorrent:

    This UDP-based reliable transport is designed to minimize latency, but still maximize bandwidth when the latency is not excessive. We use this for communication between peers instead of TCP, if both sides support it. In addition, we use information from this transport, if active, to control the transfer rate of TCP connections. This means uTorrent, when using uTP, should not kill your net connection - even if you do not set any rate limits.

    Source: http://forum.utorrent.com/viewtopic.php?id=49813

    Hey look at that, this actually stops uTorrent using more Bandwidth than you have. If your ISP sells you an 8Mbit connection and you use all 8Mbit of it, surely that's all well and good? If the ISP can't handle you using all 8Mbit, then they shouldn't sell you it. Simple-as.

    If (And it's a big if) this actually does cause any kind of "Internet meltdown", it'll be because the ISPs oversold on what they can actually deliver - it's not your fault, my fault or uTorrent's fault.

    Hopefully ISP's will either stop overselling their bandwidth or update their infrastructure to cope.

    Progress++;

    --
    +1 IDisagreeSoHeMustBeATrollOrAnAstroturferOrAShill
    1. Re:Half-truths by cdrguru · · Score: 1

      Neither is likely to happen. The problem is 80-90% of the users are not using anywhere near the bandwidth they have available or what they have been "sold". The big (imaginary) numbers being tossed around are a marketing tool. It is like having a car with a speedometer calibrated to 180 when the car might get up to 120 going downhill with a tailwind.

      To update the infrastructure is a non-starter. Why can't they just get more bandwidth? In most cases it is partly because there isn't any more at the head end. Period. Getting two OC48s going to the same router connected to an OC48 does not get you "more bandwidth". That is clearly going to be the situation in a lot of cable head ends. I suspect DSL is likely worse.

      Stop overselling? Sure, that has worked well with car speedometers. Until overall usage starts to justify building fatter backbones for the Internet in the US, we are unlikely to see any real improvements. And the cost of doing this will be significant. So, are we going to get reality from the sales and marketing departments? No, because it is all about market share and people want their car with a 180MPH speedometer or a 50Mb/sec Internet connection that can really only deliver 2Mb/sec.

    2. Re:Half-truths by IamTheRealMike · · Score: 1

      The big numbers aren't imaginary, they're what you can use at burst speeds. Unless you consider any use of overcommit to result in "imaginary numbers" in which case water, gas, electricity, also sell you imaginary things.

  79. Re:Well Duh by Shakrai · · Score: 1

    Who gets to decide how traffic is metered? If it had been metered back in the late 90s/early 2000s with typical usage levels of the time I doubt we'd have all these wonderful video on demand services.

    Metered bandwidth is a death blow to innovation.....

    --
    I want peace on earth and goodwill toward man.
    We are the United States Government! We don't do that sort of thing.
  80. Re:A little extreme there, don't you think? by 3p1ph4ny · · Score: 1

    > You voted them in. Stupid fuck.

    No. Suppose I vote against someone, but they still get elected. Have I voted them in? No. If I don't vote (because there's nobody I like), then you people say it's my fault because I didn't vote. Basically, voting is tyranny of the majority. I suppose, though, that when you're in the majority it makes sense and is a great thing ;-).

    I'm not for or against piracy, but this is a common misconception that I feel compelled to dispel.

  81. Re:A little extreme there, don't you think? by AceJohnny · · Score: 4, Insightful

    Can you imagine signing up for a "3 DVD's at a time" plan from Netflix and then when you actually check out 3 at a time they start bitching up a storm because "You're hoarding the DVD's!!! None of the other customers will be able to rent any of them!!!". Of course not. Because like most industry's they understand that if you sell a capacity you better damn well be able to meet it.

    Actually yes, I can very well imagine that. Overselling capacity is a common practice in lots of industries, based on the customers' statistical use. For example, where I live, I have signed for an electrical plan that entitles me to use a certain amount of electrical power at a given time (=bandwidth). If everyone in my neighborhood used the power they're entitled to, the power lines would melt.

    See also: banks and loans, but that's not a good example nowadays ;)

    The ISP's problem is they oversold based on a given statistical model. That model is becoming obsolete as people increasingly use P2P. So they're trying to stem the tide by crying wolf (as in this example), or by claiming that the users are doing illegal stuff (copyright infringement) and should stop.

    --
    Misleading titles? Inflammatory blurbs? Keep in mind that Slashdot is a tabloid.
  82. Ignorant much? by burris · · Score: 5, Interesting

    The author of this article could have called or emailed Bram Cohen before writing this article, but then he wouldn't have had such sensational tripe to garner page views. If he had, he would have known that he has got it completely wrong. The switch to uTP is actually to make BitTorrent traffic more friendly to Internet traffic. You see, BitTorrent is trying to sell a content delivery service based on their client and the #1 complaint from their customers (businesses with content to deliver) and their customer's customers (end users) is that the BitTorrent DNA client seeding/downloading in the background hurts the performance of other applications. That's unacceptable if you're trying to sell an unobtrusive alternative/complement to traditional CDN.

    Yup, good ol TCP is what is causing the problem. That's because BitTorrent breaks the assumption in TCP that one application needs only one TCP stream to do its work. To solve the problem BitTorrent acquired advanced congestion control techonology and it's inventors from "Plicto." The congestion control technology lets BitTorrent work without causing crazy latency for other applications on the box. BitTorrent is the responsible party here, recognizing the need for congestion control and implementing it in their protocol. Compare that to the author of this article who saw that BT was using UDP and assumed it was a naive attempt to get around ISP blocks.

    The people who work at BitTorrent are smart enough to know that you can't beat your ISP by making a new protocol. The ISP sees all and can control all, even if it may lag behind the changes. That's why BitTorrent has been working to make changes where it can make a lasting difference, in the political layer of the network.

    1. Re:Ignorant much? by thermian · · Score: 0, Redundant

      Note how your interesting explanation hasn't been modded up? You should added some 'foam at the mouth' reactionary stuff about the ISPs turning of the interwebs, and possibly a little 'conspiracy theory', in the first paragraph,then you'd have been modded up.

      --
      A learning experience is one of those things that say, 'You know that thing you just did? Don't do that.' - D. Adams
    2. Re:Ignorant much? by H0p313ss · · Score: 1

      Note how your interesting explanation hasn't been modded up? You should added some 'foam at the mouth' reactionary stuff about the ISPs turning of the interwebs, and possibly a little 'conspiracy theory', in the first paragraph,then you'd have been modded up.

      :-)

      Doesn't this sort of go without saying? Surely this comment could be applied to 95% of the comments in 95% of the stories?

      --
      XML is a known as a key material required to create SMD: Software of Mass Destruction
    3. Re:Ignorant much? by Anonymous Coward · · Score: 0

      in the political layer of the network.

      Where in the OSI model is that layer?

    4. Re:Ignorant much? by burris · · Score: 1

      That would be OSI Layer 8.

    5. Re:Ignorant much? by mzs · · Score: 1

      That is a very nice explanation, but the problem is that until outside people get a chance to look over their ideas about congestion control the door is open to this sort of FUD be it valid or not. The concern is that some other BT client could abuse this new uTP to use unfair amounts of bandwidth and that concern cannot be addressed until people know more about the details.

  83. Re:A little extreme there, don't you think? by multisync · · Score: 2, Interesting

    You know what I'd like to see happen? Anyone who is caught using uTorrent with this setting gets their broadband internet access contract torn up.

    You know what I'd like to see happen? Deliver the throughput that I pay for. If I exceed that throughput, charge me for whatever I use in excess of my allotment, or cut off my service. Whatever the terms of my contract state.

    My ISP charges me a fixed rate for a fixed amount of throughput (100 GB per month). If I and everyone one else try to download large files during peak times, our transfer rates will suck. Just like everyone getting on the freeway at the same time to drive to work causes traffic congestion, or those same people all firing up the air conditioner at the same time when they get home from work may cause brown outs.

    Do you want the utility company to decide how you can use the electricity that comes in to your house?

    Don't even pretend that most bit torrent traffic is legitimate and legal.

    My traffic is just as "legitimate" as yours. We're both just moving bits of data. Why should your bits take priority over mine?

    --
    I don't care why you're posting AC
  84. bingo by Anonymous Coward · · Score: 0

    mod up

  85. IETF ALTO by mbone · · Score: 2, Interesting

    Both BitTorrent and Comcast are working in the IETF ALTO working group, which is intended to improve the use of bandwidth and other resources by P2P.

    Having been in these sessions, it is clear to me that BitTorrent has no interest in melting down the Internet and is well aware of the implications of what they are doing. Note that if worse comes to worse, UDP can be blocked too.

  86. "I paid for the bandwidth" by wytcld · · Score: 1

    Is the IP selling constant bandwidth, or peak bandwidth? I'd argue that if you have a business account, it's constant bandwidth. But when they sell residential accounts, what you buy is peak bandwidth.

    Buying a car that easily goes 100 m.p.h. doesn't mean you've bought the right to constantly go 100 m.p.h. - even though you've paid taxes and registration on the car and taxes on the fuel that helped build the roads.

    Most residential bandwidth users don't care about constant bandwidth. All they want is peak to be there when they require it. And all most drivers require from their 100 m.p.h.-capable engine is quick acceleration on the on-ramp, or to avoid a hazard. In selling you that, there's no ethical requirement that you also be provided the option of running what you've bought constantly at the peak capacity.

    If you want that, you need an arrangement with a race track ... or a business-class Internet account.

    --
    "with their freedom lost all virtue lose" - Milton
    1. Re:"I paid for the bandwidth" by atraintocry · · Score: 1

      Buying a car that easily goes 100 m.p.h. doesn't mean you've bought the right to constantly go 100 m.p.h. - even though you've paid taxes and registration on the car and taxes on the fuel that helped build the roads.

      I've never considered someone a danger to society because my packets were going too fast.

    2. Re:"I paid for the bandwidth" by Endo13 · · Score: 1

      That's a terrible analogy. Really. In so many ways. There's not really a car analogy that fits at all. But if you want a transportation analogy, it's like buying an unlimited one-month ticket for the metro, and then having them complain because you use it 10 times a day and during peak hours. So then they say the real problem is too many people are using it to smuggle an illegal copy of a DVD or audio disc to their friend.

      --
      There is no -1 Disagree mod. Slashdot.org/faq defines mod options. USE IT.
    3. Re:"I paid for the bandwidth" by scotsghost · · Score: 1

      Is the IP selling constant bandwidth, or peak bandwidth? [...] when they sell residential accounts, what you buy is peak bandwidth.

      True, but the problem is that the difference is unadvertised, and only clearly stated (if ever) in the Terms of Use. It's the same problem people complain about when talking about usage caps on "unlimited" service plans. They've sold the consumer unlimited, always-on service, not some limited number of minutes or bytes -- at least, according to the advertising.

      The simple fact is that these ISPs need to fix the difference between what they're marketing and what they're actually providing. Frankly, I don't care if they fix it by moving to usage charges, or by upgrading their networks to handle real unlimited services. But it's time for these ISPs to update the model a little bit so they can figure out how to do it properly and reasonably: without resorting to crying wolf or scapegoating bittorrent.

    4. Re:"I paid for the bandwidth" by Mister+Whirly · · Score: 1

      This IS Slashdot. If you can't find a car analogy to fit ANY situation, you aren't looking hard enough.

      --
      "But this one goes to 11!"
    5. Re:"I paid for the bandwidth" by WhatAmIDoingHere · · Score: 1

      If when I bought the car, I was told "you get unlimited access to 100mph driving" I'd be pissed when I was told I had to go 25mph through town, yeah.

      --
      Not a Twitter sockpuppet... but I wish I was.
    6. Re:"I paid for the bandwidth" by Walpurgiss · · Score: 1

      I think this is the best and most rational response to the "but I bought X bandwidth, I should be able to max it out constantly" argument I have ever read. Good job.

  87. Re:A little extreme there, don't you think? by Austerity+Empowers · · Score: 1

    Yet it does not matter. There is a lot of legitimate use of bittorrent. From linux images to world of warcraft updates. The ISP should not be throttling any of it. If they are going to be unable to support the traffic from everyone using the bandwidth they pay for at the same time, I think they're going to need to use some of the money we pay them to update their network infrastructure.

  88. Re:Well Duh by Anonymous Coward · · Score: 0

    And the only effect of people insisting on this will be that there will be a more prominent (*) next to the word "unlimited", with a paragraph of 2 point legalese type at the bottom of the ad from henceforth, clarifying that unlimited doesn't really mean unlimited, which most people won't notice or care about, because it will always be the case that there are more users who just want to surf the web and check email than run bittorrent (and even people streaming video aren't, for the most part, watching streaming video 24 hours a day).

    Network capacity will always be oversold because it makes sense from a business perspective to do so. People who complain loudly about this will only find a new emphasis on legal distinctions being made, and you'll have to pay a lot more to find an ISP that will give you "true" unlimited bandwidth. And that is the way it should be.

  89. Re:A little extreme there, don't you think? by cbiltcliffe · · Score: 1, Insightful

    You're a liar.
    Why?
    Because I think you might be, and I don't agree with your opinion.

    See how that works?

    Whatever happened to innocent until proven guilty? Do you have any proof (or even evidence) that the GP has pirated over bittorrent?
    Then the legal assumption is that they haven't. End of story.

    --
    "City hall" in German is "Rathaus" Kinda explains a few things......
  90. Re:A little extreme there, don't you think? by jbezorg · · Score: 5, Insightful

    A car lease would be a more accurate analogy since you are only leasing the equipment.

    Still, would you lease a car if it came with some guy who sat in the back seat and bitched about the miles you put on the vehicle? Maybe disable the car or limit how far you can travel during periods of high usage? Or said "No, you can't drive to X because X is the bad part of town and you can't possibly have a legitimate reason to go there"?

    --
    I've lost all my marbles except one & It's fun to test angular & centripetal acceleration in my skull
  91. Multicast? by mybecq · · Score: 1

    If the ISPs are so interested in saving bandwidth, why don't they turn on multicast on their routers.

    Oh wait, that would cost money.

    1. Re:Multicast? by mzs · · Score: 1

      There are very reasonable technical issues to resolve regarding using multicast on a wide scale. First who would decide how to divide-up the multicast address space? For some thing like BT you would need them to be ephemeral in a sense. The planned solution to get multicast adopted in a general case was to use IPv6, but that has not been widely adopted.

      The other problem is with IGMP which is used by routers to communicate between each other what multicast streams to pass between each other. For something like BT where the addresses to subscribe to would be changing frequently that in itself would be a tremendous amount of traffic. Also in the case of IPv6 that would be some gigantic tables that routers would need to maintain. If that was not enough there are serious DOS issues to contend with as well.

  92. Bandwidth lending by shredswithpiks · · Score: 1

    Seems to me the problem isn't bittorrent. I happen to pay for a 7.5mbit down, 1.5mbit up connection. So does everyone else with my provider. But, I guess the internet providers pass out bandwidth the way banks pass out money - that is, all the customers have a certain bandwidth to share and the provider simply hopes no more than 10% of their customers (or whatever the number is) will make a run on the bandwidth all at the same time. How about you give and guarantee me the bandwidth I pay for? You know, the bandwidth in all your advertising and contracts? I never use more than my 7.5/1.5mbit connection, so there should be no reason that me maxing out my connection should interfere with anybody else - if it does that's because it's really shared bandwidth (not the bandwidth that I bought which should belong to me, used however I see appropriate), and perhaps we should look at fixing your infrastructure problems and business model instead of pointing at my usage habits?

  93. Re:Well Duh by Anonymous Coward · · Score: 0

    I understand that a lot of the users fall into your catagory, that is why I think that a cell phone esk model should be created, you know get so many peak GB, and so many off peak GB, if you are over you pay a reasonable fee per GB.

    I test OS's so every month that there is a new release of Fedora, SUSE, etc. I download at least a couple of the available releases. This means that some months I can easily get 20 to 30 GB above my normal use. (Plus uploading, I seed to a minimum ratio of 2.5) The cost of the overage GB's for those months would still be less than getting 4 or 5 different disks shipped from who knows where every 3 months.

    Looking at the comments UDP could be beneficial on the basis of lower overehead. If ISP's spent less time trying to control us and more time exploring a fair payment and delivery this debate would not be so heated.

    The last comment I will make, my contract promises me up to 5 Mbps, I have yet to measure over 3 Mbps, if I tried I bet I could show I have never (not for one second) experienced 5Mbps throughput on my connection and that is a provable fraud.

  94. Re:Well Duh by The+Cisco+Kid · · Score: 1

    Who, exactly, is this 'BitTorrent' entity you are lecturing to? bittorrent is just a protocol. This isn't some company, or even loosely affiliated organization, that can be spoken to, or can 'find out' anything.

    Its like saying FTP is doing something wrong, and its going to find out it isnt allowed to anymore.

    And, like another post mentioned, you pay an ISP for a particular amount of bandwidth, and any sane ISP rate-limits you to exactly that bandwidth. What you are sending or receiving, or via what protocol, or to (or from) who (so long as that entity desires/agrees to send/receive/exchange whatever it is, with you), is none of their damn business.

    As ISP's, monopolistic media cartels, and governments try more and more to control what information can be sent, I think theres going to be one good way forward for new protocols - fully encrypted tunnels between endpoints - rather than having various specific ports open, there will be one specific port (perhaps ssh) that will be opened, and then all further negotiation of protocols will occur over an already encrypted wrapper channel. To be effective, it must be something they can't block without causing major upheaval to the aveage end-user - so here's an idea that Mozilla and Apache could collaborate on - have a *new* http-type protocol that would operate this way, that both Firefox and Apache would support, and would try by default. In transition, administrators would/should configure Apache to listen for both legacy http, as well as the new transport. Firefox would try the new transport first, falling back to legacy http. When to cut off legacy http would be a judgement call for each server admin

  95. Hrm, why is it bittorrent's fault? by Anonymous Coward · · Score: 0

    I'm not sure why BitTorrent is getting the bad rap here... The real problem is companies like Comcast selling connection speeds that their network can't actually support if most people were to use them. Instead of investing in there network or perhaps selling what they could actually support they start filtering content.

    Comcast *shut off* two of my friends connections for downloading the new Fedora ISOs via BitTorrent. This is just getting out of hand.

  96. Re:Well Duh by Anonymous Coward · · Score: 1, Insightful

    In three words: Do as Sweden.

    We got tons of high-speed fiber layed out and over one fourth of the country got fiber. Most ISPs sell 100/100 without throttling or caps for as little as $29 USD a month. ($20 with student discounts).

    I haven't heard about any problems regarding bittorrent clogging the intertubes here, and most ISPs seem to deliver what the people wants.

  97. Re:A little extreme there, don't you think? by Real1tyCzech · · Score: 3, Insightful

    ...and those 10 guilty persons, what about them?

    They'll never cause another innocent to suffer?

    Your logic (I know it's a stretch to even call it that) falls flat when those 10 guilty persons set free cause suffering to countless other innocents; such that could have been prevented but for the suffering of that one innocent.

    We all suffer for the individual and the individual suffers for all. That's called society. Deal with it.

  98. Is this really a problem How fubar are the USA ISA by TheSunborn · · Score: 1

    If a user have bought a 2Mbit connection then it does not matter to the ISP what kind of trafic that goes on that link, so it should not impact any other users if I use udp instead of tcp. It is not as if I am allowed to send more then 2Mbit just because I use udp. (It is all just ip packets for the router anyway).

    There are 2 situations where using udp might be a problem.

    1: If the isp sell you a 2Mbit connection but can't handle that on their internal network. In that case the tcp connections might(We don't know which slowdown solution that uTorrent uses) back down faster then the udp, and thus give more bandwidth to upd.

    But does this really happen? I live in Denmark and the 5 different danish isps I have had so far, have always been able to deliver the full speed i bought on their internal network. So if this is a problem for isps in USA, then its time for the Isp to upgrade their hardware. An temporary solution might be to lower the speed of all customers duing peek time.

    2: If you share a single internet connection, and don't have any internal rate limit software this might be a real problem, but the solution is simply to limit the speed in the uTorrent client.

  99. Re:Well Duh by Anonymous Coward · · Score: 0
    Block P2P and I bet piracy goes way down

    Ya, since there was never any software or media piracy before the late 90s... You must be new to this trolling business.

  100. Re:Well Duh by BrianRoach · · Score: 1, Redundant

    you just want to bully other people out of their bandwidth so you get more.

    Um, what?

    How can I "bully" anyone? My modem is capped at the speeds Comcast sold me, no more, no less. In addition, I have a monthly transfer limit.

    If Comcrap can't provide what they are selling ... they shouldn't be selling it. Oh, but wait! That's not their fault, it's those users! They're actually trying to use what was sold to them.

    I'm not a big bit torrent guy, except for WoW and other legitimate torrents. But the thought that people are being told that they can't use bit torrent for any technical reason is silly - it's the ISPs over-selling and under-delivering, plain and simple.

  101. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 3, Insightful
    I order something online from a retailer, does this give the shipping company or government the right to open my mail and packages because it passes through their facilities? It's bullshit plain and simple. They don't have a right to watch and monitor what you send.

    FedEx/UPS/DHL have every right to open your packages, yes. You grant them that right when you agree to their shipping terms. Perhaps you should read the airbill before you sign it. The government operates under a different set of rules than private companies. If you'd like the government to run you ISP service then you can have the right to not have your traffic monitored.

  102. BT Devs Sleep With Illegal Content Providers by man_ls · · Score: 1

    I forget the statistics, but let's admit it -- it's highly likely that BitTorrent developers, on all platforms all know, understand and encourage the fact that some enormous fraction (far above half) of total BitTorrent traffic is used to illegally distribute copyrighted content.

    I'm not going to make a value judgment on that for the purposes of this post, although I have an opinion on its moral correctness -- but many of the features introduced by BitTorrent clients (protocol encryption being the biggest example) seem to exist solely because BitTorrent is being blocked by ISPs.

    BitTorrent is being blocked by ISPs because it is hugely taxing on network infrastructure, and is almost always being used to do something illegal. I can count on one hand the number of times anyone I know has downloaded Linux ISOs over BitTorrent, but a colleague's recent purchase of as many 1TB hard drives as his SATA controller will support for the express purpose of "downloading every Bluray rip he can find" is, I believe, reflective of the general use of the protocol. Maybe not its intended use, but certainly its defacto use.

    BitTorrent developers have to realize that their protocol is almost exclusively for illegal purposes. By constantly adding features to "get around" restrictions placed by ISPs on the protocol, they're actively supporting such activity.

    It is insane to think that broadband shouldn't be oversold by a contention ratio. Why shouldn't it? Almost every ISP advertises speeds "up to X megabits per second", key word being "up to". Most people even in normal use will never see those speeds -- because their usage habits never require it of the system. Or if they do, it's for a fraction of the time that a BitTorrent session will max out a connection. The most taxing thing I've done that I can think of is load a page of several hundred ~1MB photographs in Firefox. It took a long time to download, but that's only a 200MB transfer that happened once -- not someone downloading multiple HD movie rips at all hours of the day, all the time.

    If the majority of BT usage was for legal purposes, the traffic using the protocol would drop down to near-zero and it wouldn't be an issue. It's only come up because of the connections to illegal activity.

    What we need is a legal solution to the problem. Let people use their connections for whatever they want -- we just need a more reliable way to punish those who break the law, and to do so more reliably. The exact mechanics of this solution can be debated from now until the end of the Universe -- but a technical solution to a social problem will never be successful. Whether it's a change in business models, more policing, aggressive prosecution of large-scale Internet distributors, or something else, there needs to be a change on the human side of things.

    Otherwise, they're likely right -- the Internet, in its current state, will not survive. And it will be BitTorrent's fault.

    1. Re:BT Devs Sleep With Illegal Content Providers by baronvonchickenpants · · Score: 1

      I'm curious what your opinion is on the "moral correctness" of companies who manufacturer hard disks, since "it's highly likely" that some illegally obtained data will be stored on said disks?
      How about the "moral correctness" of data encryption?

      --
      "The bad machine doesn't know he's a bad machine."
    2. Re:BT Devs Sleep With Illegal Content Providers by Anonymous Coward · · Score: 0

      cool story bro

  103. BitTorrent? Internet? Hunh? by Bob9113 · · Score: 1

    Wait - let me see if I get this straight...

    ISPs, the gateways to the Internet, are doing bandwidth management at the TCP layer and above. Since bandwidth on an IP network is properly measured at the IP layer (duh), obviously the ISPs are not actually doing bandwidth management. They are doing something, but it is not bandwidth management.

    Some software operates on not-TCP. If that software is high bandwidth, the ISP's "bandwidth management" (which is not really bandwidth management at all) fails. And that is the fault of the software?!?

    "We built a toll road, and in order to eliminate traffic jams, we strictly regulate the number of blue cars entering the road. But people are driving cars that are not blue, and causing traffic jams. Those people driving not-blue cars are flooding our road!"

    1. Re:BitTorrent? Internet? Hunh? by JoelKatz · · Score: 1

      Mod this up. This is dead on.

  104. Comment removed by account_deleted · · Score: 1

    Comment removed based on user account deletion

  105. Re:A little extreme there, don't you think? by blackfrancis75 · · Score: 1

    err, this is exactly what the Customs department does to mail coming into the country.

  106. Re:Well Duh by MasterOfMagic · · Score: 4, Insightful

    Don't meter then. Sell them a realistic line speed.

    My ISP is selling me a line speed. In an ideal world (leaving out the marketing droids), they will be selling me a speed that I can reasonably expect on their already oversold network. They will cap my network connection at this speed such that I can never exceed it, and that's it. That's all that they will need to do.

    In the real world, however, the line speed they sell seems to have nothing to do with what their network capacity is. Their line speed seems to do with "having a bigger one than the next guy" to bring in more subscribers even if their network can't handle it. As a result, they oversell a network that already can't realistically cope with their utilization numbers. Instead of looking at utilization and capacity numbers and figuring out what they can realistically support, they make shit up.

    This making shit up is biting them in the ass. Hard. The need to do one of two things:

    1. Increase network capacity - we gave them tax breaks to do it, so where are the results and why shouldn't the ISPs have to pay those back taxes with interest if they refuse to do it?
    2. Decrease the line speed of all of their users so that they can cope with the utilization of their network

    They've been dragging their feet on the first item because they want to erect tollbooths and speedbumps (destroying network neutrality along the way) so that they become the gatekeepers of the Internet - using public funds to fuel a private agenda, penalizing popular sites because they didn't think of the idea first or because it threatens their business model. They won't do the second because honesty is apparently taboo even if their realistic line speeds are pretty much an open secret (see dslreports.com).

  107. the nice thing about capitalism ... by DerWulf · · Score: 1

    the nice thing about capitalism is that it's not my job to worry about the health of the internet. I have a contract that clearly states what I can expect for the monthly service fees I'm paying and this means I get to download at 16Mbits ALL DAMN DAY. Should I have priority over VoIP and gaming? I don't know and that's really not my job either. Let the ISPs figure it out, they are the (sorry to use the word) stakeholders in this.

    --

    ___
    No power in the 'verse can stop me
  108. Overselling peak bandwidth is fine by roystgnr · · Score: 4, Interesting

    Mislabeling it is not. If you sell 1MBps with a 25GB/month cap, then you need to be advertising your "1MBps peak bandwidth, 0.01MBps constant bandwidth" service, not misleading your prospective customers.

    Practically every ISP should be overselling peak bandwidth; because people don't all use it at the same time, your only choices are to let them use as much as they can (overselling) or to throttle them. But both peak and aggregate bandwidth are important; if you're not providing much of the latter you shouldn't get to imply otherwise.

    1. Re:Overselling peak bandwidth is fine by MBGMorden · · Score: 1

      A very valid point. Despite me wanting what I pay for, I also do not use 100% of my connection all the time. A little overselling would be fine. However as you noted we have situations where the available constant bandwidth is less than (and in some cases MUCH less than) 10% of the burst. It's just ridiculous.

      --
      "People who think they know everything are very annoying to those of us who do."-Mark Twain
    2. Re:Overselling peak bandwidth is fine by phoenix321 · · Score: 1

      Which would call for a paradigm shift in billing Internet access.

      What about the same paradigm every other household commodity is billed?

      Volume AND max peak?

      How about it?

      "20 Dollar for 5 MB/fortnight peak and three microdollar per Mebibyte volume"

      Natural gas, electricity and telephony are billed like this, if not on a household level then at least on an industrial scale.

      Which is a pretty much accurate model on how the real costs are generated: the pipe in itself costs something and whatever is transferred through costs another part.

      Capacity and volume - the basis of all pipeline-based trading.

      And the damn ISPs just won't get it, crying wolf all the time.

    3. Re:Overselling peak bandwidth is fine by IamTheRealMike · · Score: 1

      The problem is the phrasing. I can easily pull down 1Mbps for several hours at a time every so often and not run anywhere close to my cap, but I know if I did that 24/7 I would hit it. So what does "constant" mean? And why is it clearer to explain it that way than just state peak bandwidth and total cap?

    4. Re:Overselling peak bandwidth is fine by rocketman768 · · Score: 1

      I often wonder where people see "peak" or any other quantifying word on these advertisements. These companies slap a number on their website "10 Mbps*" and then when you look at the "*" it says "this is no guarantee". However, they nowhere tell you what exactly the 10 Mbps* DOES mean...

      This is what I mean.

    5. Re:Overselling peak bandwidth is fine by roystgnr · · Score: 1

      And why is it clearer to explain it that way than just state peak bandwidth and total cap?

      Either way is fine. I think expressing the total cap as ["constant", "average", whatever] bandwidth makes the overselling ratio clearer. But I'd be just as happy if every advertisement for "unlimited internet" had to say "100GB/month" or whatever the cap was instead.

      Actually, I'd be happier if it was "100GB/30 days", which instead of cutting you off cold turkey just throttled you back to dialup speeds until your rolling usage total dropped again. And I'd be happiest if they managed to do so in a way that didn't count "unsolicited" packets toward the total. But my own ISP has been fine so far, and even the problem ISPs can fix things one problem at a time.

    6. Re:Overselling peak bandwidth is fine by Mista2 · · Score: 1

      In NZ, the ISPs have started sellings plans with 20GB caps and ASL rates advertised as "As Fast As Your Line Will Allow" Damn cheeky as I am paying the same as everyone else on my plan but can only get 2.5Mbs out of my DSL line, while my sister who happens to live closer to the DSLAM gets 7Mbs. We are both on the same plan with the same ISP.

      The ISP could throttle the traffic wherever they want and just say, " its as fast as you can get where you live."

    7. Re:Overselling peak bandwidth is fine by endymion.nz · · Score: 1

      You can check on this by seeing what speed your DSL modem is connecting at and comparing that to your peak download speed. Traffic shaping happens on a higher level than the physical link.

      --
      mediocrity rules, man
    8. Re:Overselling peak bandwidth is fine by Anonymous Coward · · Score: 0

      the problem is ISPs do not tell you what constant bandwidth (those 0.01MBps you mentioned) they can garantee. All they saying is peak (max you can get if noone else is using) bandwidth.

      In other words ISPs sell you undefined/badly defined service

  109. Re:A little extreme there, don't you think? by jbezorg · · Score: 1

    "I don't care. I have *never* pirated anything over bittorrent, even thought I've used it a number of times."

    The unverifiable claims are the easiest to fabricate.

    There are legitimate usages. Very large game patches for instance. Especially on the day of release. Given the demographics of the slashdot crowd, I'd be willing to bet money that the statement applies to someone here.

    --
    I've lost all my marbles except one & It's fun to test angular & centripetal acceleration in my skull
  110. Re:A little extreme there, don't you think? by Rasvar · · Score: 1

    Maybe its time to end the all you can eat buffet. You either get speed or you get data. If you want the speed, you pay more once you exceed a center data threshold. You can get both if you want to pay for both or you can just get data and suffer lower speeds.

    One or the other, the all you can eat data buffet is no longer a sane business model.

  111. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    Then pay for a T1 or OC3 connection.

    You're the person who whines about ISPs overcharging for bandwidth, I'm sure, when they charge the full cost for the pipe. 7MBps for $40/mo with no caps and full utlization.

    You want business class services at economy prices, and you already use way more of your connection than anyone else - you take up 80% of all traffic (sorry, not you personally, but I wouldn't doubt 4x what others use). Face it, you are *already* benefitting from massive infrastructure investment that is being subsidized by your no-nothing aunt and parents who barely use their connections.

    But of course you are whining about the legroom and not getting your 'fair' share. Which you can have, just pay for it. Ah, but that's against the principle of NOT paying for anything - BitTorrent's prime audience. It's not unfairness or unclear advertising, you know what is going on and are just trying to get the most bang for your buck. That's fine, but you don't really have a high horse here to climb on.

    Not 'you' personally, of course this is characterization.

  112. Re:Well Duh by moose_hp · · Score: 1

    And thats when you start embeding encripted info on alternative files like images, or so. BTW how do you plan to distinguish between normal raw binary data and encripted data? how do you tell between a legal data of a PNG file and a RAR file containing encripted files? You plan to use the evil bit?

    --
    DON'T PANIC.
  113. Re:A little extreme there, don't you think? by badfish99 · · Score: 1

    You have chosen to live in a society

    Are you sure? Supposing he didn't choose to live in society. Where would he go?

  114. Re:A little extreme there, don't you think? by srussia · · Score: 4, Interesting

    If you took the current ISP business model to any other industry you'd be laughed out of town, yet they get away with it.

    Cough...fractional reserve banking...cough

    --
    Set your phasers on "funky"!
  115. Re:A little extreme there, don't you think? by jhol13 · · Score: 1

    Why should your bits take priority over mine?

    Emergency call. Actually any call, if your data is ftp, http, torrent, or similar bulk data.

    Or if I pay more - this is capitalism.

    And, perhaps, because I use less (average) bandwidth (i.e. am a better customer).

    And yes, I want the utility company to limit it, as it is obvious you will not (use QoS).

  116. Joe the Plumber? by cbraescu1 · · Score: 1

    Someone get a plumber, quick!

    Let's call Joe the Plumber ;-)

    --
    Catalin Braescu
    Ofaly.com
    1. Re:Joe the Plumber? by thebheffect · · Score: 1, Troll

      A real plumber, not an unlicensed faux plumber.

    2. Re:Joe the Plumber? by sexconker · · Score: 1

      You mean the guy who was a licensed plumber, but then bought into a business where he takes on a managerial role and sends out other fully licensed plumbers? He doesn't need a license because he's no longer doing the work.

    3. Re:Joe the Plumber? by BlueStrat · · Score: 1

      A real plumber, not an unlicensed faux plumber.

      [break]

      You mean the guy who was a licensed plumber, but then bought into a business where he takes on a managerial role and sends out other fully licensed plumbers? He doesn't need a license because he's no longer doing the work.

      How *dare* you attempt to impugn the liberal practice of "shoot the messenger"!? He *allowed* the Messiah an opportunity to say something that revealed his true thoughts and beliefs!! Burning at the stake is too good for such a heretic!!

      Good day sir, I say good DAY! :P

      --
      Progressivism (aka US 'Liberalism'): Ideas so good they need a police/surveillance-state to enforce.
    4. Re:Joe the Plumber? by BronsCon · · Score: 1

      I wish Biden had worked to get his license; think about it...

      McCain mentions Joe the plumber in a debate, Biden stands up, Obama says "I'd like to introduce joe the licensed plumber."

      --
      APK quotes people (including myself) without context and should not be trusted. Just thought you should know.
    5. Re:Joe the Plumber? by thebheffect · · Score: 1

      If he isn't doing the work, and he isn't licensed, then maybe we shouldn't call him up. Maybe we even shouldn't call him Joe 'The Plumber' and instead call him Joe 'The Managerial Role Player Who Sends Out Other Fully Licensed Plumbers'.

    6. Re:Joe the Plumber? by Toonol · · Score: 1

      You're ridiculously and irrationally partisan.

      The guy made a living from plumbing. What do we call people that do that?

    7. Re:Joe the Plumber? by thebheffect · · Score: 1

      Sarcasm and joke-playing on the internet tubes is impossible. I threw my vote away on Barr, did you see that one coming?

    8. Re:Joe the Plumber? by Mr.+Slippery · · Score: 1

      You mean the guy who was a licensed plumber, but then bought into a business where he takes on a managerial role and sends out other fully licensed plumbers?

      That guy would neither be Samuel Joseph "Joe" Wurzelbacher, nor a plumber. He was never a licensed plumber, nor even a trained one. And did not buy into the business, he was only considering it - a pipe dream, his personal finances were nowhere near in order.

      where he takes on a managerial role and sends out other fully licensed plumbers

      Well, such a guy would be "Joe the Manager". Again, he would not be Samuel Joseph "Joe" Wurzelbacher.

      --
      Tom Swiss | the infamous tms | my blog
      You cannot wash away blood with blood
    9. Re:Joe the Plumber? by sexconker · · Score: 1

      Semantics.
      It's a common practice for a tradesman to let their license lapse while starting their own business / referral service in the trade.
      The license is just a certification. The lack of a license is probably due to a lack of time or a lack of need to keep it up to date. Unless his license was revoked because he was caught sabotaging pipes or something, it doesn't matter.

      (If he was caught installing non-low-flow toilets, I WILL be calling him up and paying him on the sly.)

    10. Re:Joe the Plumber? by sexconker · · Score: 1

      People actually paid attention to him enough to find out any of that?
      You Obama people are crazy.

      (My official party affiliation is "Teh LOL Cats".
      I am no longer registered (screw jury duty).)

    11. Re:Joe the Plumber? by pugugly · · Score: 1

      More interestingly, people that decided to use him as a bulwark of their campaign didn't pay enough attention to him to find any of that out.

      But wanted people to believe they were up to the task of running a government. Using their 'gut' to distinguish the 'truthy' answers to our problems no doubt.

      Pug

      --
      An Invisible Entity of Vast Power whose existence must be taken on faith alone: Liberal Media
    12. Re:Joe the Plumber? by pugugly · · Score: 1

      I don't know, is it similar to the term for a person that installs electrical wiring incorrectly because he never actually studied for an electricians license?

      Pug

      --
      An Invisible Entity of Vast Power whose existence must be taken on faith alone: Liberal Media
    13. Re:Joe the Plumber? by sexconker · · Score: 1

      As a (no longer) registered LOL Cat, all I can do is respond with captioned animal pictures whenever someone starts talking politics.

      Slashdot is text only, and I'm too lazy for ASCII art that would render properly.

      LOL?

    14. Re:Joe the Plumber? by socsoc · · Score: 1

      I am no longer registered (screw jury duty).) I don't know what state you are in, but that is usually just one a few databases they pull your info from. Did you get rid of your driver's license too?

    15. Re:Joe the Plumber? by BlueStrat · · Score: 1

      I don't know, is it similar to the term for a person that installs electrical wiring incorrectly because he never actually studied for an electricians license?

      Pug

      Hate to break it to you, but in the three states where I worked as an electrician and a plumber, all you had to do to be licensed was know someone in the business who knew someone on the licensing board, and have the cash for the fee. Only about a quarter, maybe less, of the licensed plumbers and electricians I worked with/for ever actually studied for or took an exam, and of those that did, nearly all just crammed for a couple weeks to simply pass the test by rote.

      And union electricians and plumbers? Ha! I wouldn't let a union electrician set up an electric train set of mine, or a union plumber use a plunger on my toilet. They'd screw it up while charging me triple what I could have it done for elsewhere by someone that actually took pride in their work because they'd lose their job if they did shoddy work, unlike the union bozos who'd have to cause mass deaths to have any chance of being fired.

      Cheers!

      Strat

      --
      Progressivism (aka US 'Liberalism'): Ideas so good they need a police/surveillance-state to enforce.
    16. Re:Joe the Plumber? by sexconker · · Score: 1

      I have been removed from the jury pool for the county covering the address on my driver's license.

      (By submitting a utility bill showing my current address, and saying I don't live there anymore. All true.)

      So, hah.

    17. Re:Joe the Plumber? by neomunk · · Score: 1

      So you're saying that This post is based off of no personal knowledge (since you obviously are above looking into the matter) and is just something you pulled out of your ass wholecloth? Brilliant.

    18. Re:Joe the Plumber? by sexconker · · Score: 1

      I saw him on the teevee for about 20 seconds, where he said he was a plumber, and was buying into a business, and omg obama ur gunna raise mah taxes.

    19. Re:Joe the Plumber? by pugugly · · Score: 1

      And I should believe an electrician from a state replete with lousy and incompetent electricians why exactly - {G}

      Pug

      --
      An Invisible Entity of Vast Power whose existence must be taken on faith alone: Liberal Media
  117. Mod parent 'Informative' by Anonymous Coward · · Score: 0

    It says what is really happening - assuming it is true, of course.

  118. Re:Well Duh by akozakie · · Score: 1

    Sure, there must be some overselling, but how much?

    The sensible way to do this is to watch what's in the pipes and use this information. For a long time over 90% of traffic was TCP. Now suddenly one class of high-volume traffic will switch to UDP. Ooops. Should ISPs have seen this coming? I don't think so. This is not expected traffic growth, this is different.

    UDP is a very bad protocol to use for mass transmission. There is no built-in feedback loop. Unless the protocol running over UDP is very well designed (basically mimicking TCP), UDP will always saturate the bottleneck on any path. If the upper level protocol accepts losses, it gets worse.

    Of course, this can be done well - just put rate caps on each transfer, inside the client. But hey, everybody wants their new movie asap! With open source this will not fly. With TCP the transfers were at least competing fairly with other flows. With UDP bittorrent will soon start competing only with itself. More bandwidth won't cut it, TCP will suffocate.

    So far ISPs tried to fight bittorrent for all the wrong reasons - it's a useful technology with many positive uses, just a bit heavy on the backbone and with the stigma of piracy. Limiting it was the wrong choice, but an easy one. Fighting the caps was the right thing to do, whether you actually use bittorrent or not. Switching to UDP changes the game.

    Switching to UDP will make it public enemy number one. Watch for new contracts specifically disallowing it, heavy caps on all UDP traffic, and so on. Even worse than before, but now ISPs will have my full support.

  119. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    Interesting anecdote. A few years ago, my NTL contract specifically mentioned how traffic over TCP/IP had to be legal, etc. For some reason UDP, ICMP, etc was not mentioned. Odd. I'm no longer with them, and they no longer exist anymore, so I can't check to see if its changed.

    Well, UDP & ICMP do run over the IP protocol, so they are probably covered. I guess it depends on the legal meaning of "TCP/IP" instead of "TCP".

    Contracts often have a generic "no illegal activity" clause.

  120. Re:Well Duh by FictionPimp · · Score: 1

    My car analogy.

    I'll sell you a unlimited gasoline plan for 29.99 a month. All the gas you can use in a single car!!

    * Please note you are only drive said car for 15 miles a month and are limited to 10 gallons gasoline a month.

  121. Re:A little extreme there, don't you think? by Jimmy+King · · Score: 4, Insightful

    While not correct if someone wants to be pedantic about it, it's very common to refer to the entire IP stack as TCP/IP or the TCP/IP stack. I can't think of a book that touches on networking either in part or is the entire subject of the book that I've read that does not use TCP/IP as the generic term for the entire stack. Possibly not a good idea for a legal document, but that's how it is.

    Just like even though kleenex is a type of tissue, but tissue is not a type of kleenex, if someone asked you for a kleenex you wouldn't respond "I don't have any. All I've got here are these Great Value Facial Tissues", you'd just point them to whatever you have and know exactly what they meant. The same goes for when someone says "TCP/IP", while TCP/IP is a more specific thing than just IP, you know (or should know) what someone means and know that they very well may be referring to the entire stack, not just TCP and its sub-protocols specifically.

  122. No more than what one has paid for? by Anonymous Coward · · Score: 0

    Why do they say that this will happen? One has paid for a certain width on ones internet, so one should be able to use it. If they don't let us use what we have paid for, then they have sold us something that dont exist...?

  123. Yeah, with all that lack of TCP overhead.... by Mutiny32 · · Score: 1

    Dr. Peter Venkman: This city is headed for a disaster of biblical proportions. Mayor: What do you mean, "biblical"? Dr Ray Stantz: What he means is Old Testament, Mr. Mayor, real wrath of God type stuff. Dr. Peter Venkman: Exactly. Dr Ray Stantz: Fire and brimstone coming down from the skies! Rivers and seas boiling! Dr. Egon Spengler: Forty years of darkness! Earthquakes, volcanoes... Winston Zeddemore: The dead rising from the grave! Dr. Peter Venkman: Human sacrifice, dogs and cats living together... mass hysteria! But really. The Internet isn't a damn packet radio network. Transmission errors are largely a thing that has been taken care of via providers putting infrastructure in place to make retransmits unnecessary. In fact, BitTorrent over UDP shuld sould like a good thing to Service Providers....unless they are over-subscribed kinda like this whole subprime thing. Wait. Comcast...node...saturation....no wonder they're spreading fire-and-brimstone FUD. They HATE spending money. On the other-hand, we have hashing. So if the connection is adequate, then ISPs shuld praise this sort of thing for lowering their network overhead.

  124. Re:A little extreme there, don't you think? by ogdenk · · Score: 1

    I don't remember being given a choice. Just try "leaving society behind" and let me know how that straitjacket or that cold slab in the morgue feels. I'll give you a hint, it doesn't work very well.

    And yes, you could *try* to take my stuff. You wouldn't get far. No government intervention or laws would be required for me to solve that problem.

    And no, I'm not an anarchist. I am a libertarian but not to the point of being a weird luddite.

    Picking a choosing laws can be a slippery slope but I like to refer to it as "civil disobedience".

  125. Chicken Little by kaizendojo · · Score: 1

    Every week there's another post about how "X" is going to cause the Internet to come to a grinding halt and cause a meltdown. Yet each day more and more videos are posted on YouTube of kittens riding roombas, and somehow the Internet survives.

    Call me when the sky is MEASURABLY and DEMONSTRATIVELY falling.

  126. Car analogy fail by tylerni7 · · Score: 1

    What? That makes no sense.

    Unless I missed something and nowadays downloading at high speeds suddenly endangers the lives of those sharing your connection, you may want to rethink that comparison.

  127. Comment removed by account_deleted · · Score: 1

    Comment removed based on user account deletion

  128. Citation needed by Anonymous Coward · · Score: 0

    and get off your lawn? Care to back up any of your claims with actual information? "OMG, Flash sucks!!!!!!" doesn't mean shit.

    How is Flash video defective exactly?

    Too bad you don't like newfangled audio/video on your websites. A lot of us find it very useful, especially for tutorials and such.

    1. Re:Citation needed by AlpineR · · Score: 1

      To support the grandparent a little, let me say that Flash advertisements suck.

      When I'm trying to find the little bit of original writing on a page full of links and diversions, the least helpful thing in the world is to have three blinking, beeping, moving advertisements screaming for my attention. I had to block Flash in my web browsers just to keep my sanity.

      I try to whitelist sites with useful Flash like New York Times or YouTube, but that often doesn't work because the Flash host site is different than the core site. Or some sites have both good and bad use of Flash and the good gets blocked with the bad.

      So good things can be done with Flash, but the torrent of intrusive uses is going get it classified with spam and telemarketing.

  129. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    Err... you HAVE ISPs that will "sell you a pipe and that's it" pretty much in every big city of the developed world. What I bet is that you are NOT willing to pay for what that service costs.

    Ask your ISP how much for a corporate unmettered, unfiltered, 5Mbps full-duplex link with a barely-acceptable SLA (say, 4h MTTR, 95% bandwidth available @ 98% of the time to their peering points). Chances are it won't be below US$ 1k/month even if network backbone connectivity is easy and cheap where you live.

  130. Metered QoS by cam312 · · Score: 2, Interesting

    I've been thinking about this topic for a while. It almost always degenerates into a "I paid for X mbps, I should get to use it 100% of the time" vs. "You're killing my connection, and my XYZ traffic is getting hit even though I'm a good consumer, we should pay for each bit we use, and let the market sort it out." What if we implement a QoS service level based largely on the existing pricing model. When you subscribe, you get a certain bandwidth of traffic that you are (almost) GUARANTEED (as if you were (almost) leasing a T1 to yourself) The ISP doesn't mess with it. The rest of your traffic is "best efforts" at between X and Y mbps. Let the ISP shape the "best efforts" bandwidth in whatever way they feel brings the best average consumer experience. Let the customer choose if they want to use their guaranteed traffic to surf the web, run VOIP, Games, BT etc. That way I'm not limiting your BT, and your BT isn't killing the voice quality of my phone. Everyone talks like QoS, shaping, and throttling is a bad thing. I've used all 3 tools on my own LAN to IMPROVE the connection of my network for ALL it's users. Sure some HTTP traffic gets delayed while Voip jumps the queue, and when there's heavy surfing, BT slows down. Network bandwidth is a finite resource. Burning it up like fossil fuels in the 60s is a bad long term idea. I can't afford a guaranteed bandwidth connection at home. I'd much rather participate in a MUCH bigger shared and shaped pipe than be stuck with what I can afford to buy all for myself.

    1. Re:Metered QoS by Anonymous Coward · · Score: 0

      committed information rate vs burst information rate is what you're attempting to get to.

  131. I didn't invent them or design them, just use them by CFD339 · · Score: 1

    Something about more sessions to track uses more cpu and memory. I'd imagine it has to do with the tables required to track the sessions.

    The same is true in your workstation. There are performance limits and real serious points of diminishing return as you increase the number of concurrent sessions. Some operating systems are better than others at dealing with this, but there are limits in all cases.

    --
    The problem with quotes on the internet, is that nobody bothers to check their veracity. -- Abraham Lincoln
  132. Re:A little extreme there, don't you think? by Sheik+Yerbouti · · Score: 1

    Actually if the DEA drug dogs or the X-ray machine turns up something suspicious you can bet your ass the USPS will open that package to protect their system from misuse.

    The car analogy is really bad using torrent to pirate shit and use up all the local bandwidth is more akin to doing donuts in the dealers lot which I am pretty sure they would take a dim view of and probably call the cops.

    It's called a society and there are acceptable and unacceptable behaviors. Being a filthy pirate and hogging all the bandwidth is not nor should be acceptable behavior even though you really like all the free stuff you get from it.

  133. Re:A little extreme there, don't you think? by multisync · · Score: 1

    And yes, I want the utility company to limit it, as it is obvious you will not (use QoS).

    I didn't say "limit it," I said "decide how you use it."

    --
    I don't care why you're posting AC
  134. The only solution... by Anonymous Coward · · Score: 0

    If you want true net neutrality get rid of broadband and make everyone connect, including businesses, using a 14.4 modem. Current infrastructure can handle that kind of bandwidth for every citizen. In ten years upgrade everyone to 28.8, future infrastructure will be able to support it I think...

    Might as well, because in a net neutral world that's what happens. Not because of technical mumbo jumbo some techie tells his CEO about, but because of the bottom line cost. Equality reduces throughput for everyone, and increases it for no one. That's the way business works and thinks.

    Analogy time: In 1990 the average professional woman's salary was 60% of what a man's was with similar experience. In 2000 it was 80%, but the average salary of women only increased 4%. Guess what happened, to make things more equal men were payed less. Money is a limited resource, bandwidth is a limited resource. Business isn't going to pay anyone more to make things equal, they are going to pay someone less.

    Even if they upgraded infrastructure, people would just download more movies and audio. People who download from BT don't just get 1 movie or one song. They get whatever they can, which IS limitless, unlike the bandwidth they are using to get it.

    Simple supply and demand economics really.

    That said, I'm all for net neutrality. In fact I don't even support overall bandwidth cap limits. If your network can do 1000Mbps down, let me try to pull it off on my machine, along with everyone else on your network...it would be fun watching this thing seize like a 90y/o epileptic at a laser light show. After all, I miss Prodigy.

    1. Re:The only solution... by utopia27 · · Score: 1

      actually... before cable and DSL, the local telcos were _very_ unhappy about modem usage. It destroyed their statistical multiplexing business model, because people kept the line open continuously. The (Plain Old Telephone Services) infrastructure could not accomodate the data traffic demands put on it.

  135. Re:Well Duh by Nimey · · Score: 1

    I pay for a pipe. My ISP should take no interest in the source or destination or type of service connections in this pipe. Anything else is just allowing the system to be used abusively.

    Counter-example: botnetted computers spewing spam. Your ISP should damn well care about that.

    --
    Hail Eris, full of mischief...

    E pluribus sanguinem
  136. Re:Well Duh by Anonymous Coward · · Score: 0

    How is it being a bully? Really. Explain this to me in terms my little brain can understand.. So walk me thru this.. We have these huge ISPs overselling their networks--knowingly and wantonly--and refusing to invest in a practical solution (i.e. upgrade at least enough to deliver what they promise in ads, contracts, etc.)

    In the other corner is the small fraction of users who use the "unlimited" 'net connection (it doesn't make a bit of difference WHAT the traffic is from) and pay good money for the privilege, but find out that "unlimited" really means "if you only browse amazon, a few news sites and check your email a few times a day, you'll never know the difference."

    Bittorrent is not the issue. There is no file transfer protocol that will ever be an issue. The only issue here is that ISPs have oversold network capacity by a huge amount, are unwilling to upgrade the infrastructure and are (apparently) uninterested in re-evaluating the way pricing is calculated.

    So yea, I must be stupid because I just can't see the guy in the suit with the money coming out of his pockets as the victim here. In fact my ignorance goes so deep as to feel SORRY for the evil bully users who don't give a shit about anything but getting full use out of their paid-for bandwidth.

    maybe I'm extra jaded today because I've already reached my allotted bandwidth for December on my "unlimited" plan..

  137. Re:A little extreme there, don't you think? by mweather · · Score: 2, Insightful

    A car used to run drugs can be confiscated, costing the dealership money if you are still making payments.

  138. uTP has congestion control ? by mbone · · Score: 2, Informative

    See http://forum.utorrent.com/viewtopic.php?id=49813

    "What is in 1.9:
    uTP, the micro transport protocol. This UDP-based reliable transport is designed to minimize latency, but still maximize bandwidth when the latency is not excessive. We use this for communication between peers instead of TCP, if both sides support it. In addition, we use information from this transport, if active, to control the transfer rate of TCP connections. This means uTorrent, when using uTP, should not kill your net connection - even if you do not set any rate limits.

    What was in 1.8.1:
    uTP, but connection attempts were not initiated by default, and there was no control over TCP as described above. You can enable it, but likely you will see the uTP connections not transfering much data, because they are pushed out of the way by TCP."

    This sounds like congestion control of some sort to me.

  139. Re:A little extreme there, don't you think? by Atheose · · Score: 1

    And, perhaps, because I use less (average) bandwidth (i.e. am a better customer).

    I'm paying for a certain amount of bandwidth a month. Using a lower percentage of that than I do does not make you a "better customer".

  140. Re:Imagine: by StikyPad · · Score: 2, Funny

    LOL! Well.. good luck, I hope she's worth it, and with any luck the wife will never find out about her. Don't forget to burn the receipts!

  141. Re: Small business by Lonewolf666 · · Score: 1

    Imagine a small business where 50 people are sharing a T1 line. For web browsing, this many users could all get decent performance, even if a handful of people are doing big downloads, provided they are all using TCP. But all it takes is one guy hammering the link at full throttle to ruin it for everyone else.

    That is an internal problem of the small business. They rent one T1 line for 50 people, which is obviously not enough for 50 people watching stuff on YouTube. So they need some policy to prevent excessive use. On a former job of mine we actually had such an event:
    One guy was running eMule from his laptop and collecting Gina Wild videos ;-)
    We found him through the router management software and told him to switch his P2P application off, problem solved.

    The problem with most end-user ISPs is their excessive overselling:
    They have a bandwidth per user that may not be much better than in your example, but they market the connection to every single user as if he had the line for himself. Then the ISP complains or starts throttling the bandwidth, if it is actually used heavily. Users feel cheated.
    My point is that it is very much the fault of the ISP if they make empty promises. It is not the duty of the customer to figure out how much capacity the ISP actually has and restrict his usage accordingly. Actually, I think the behavior of some ISPs borders on fraud and I'd like to see them lose a lawsuit over it. AFAIK there is actually one brewing, some users have sued Comcast.

    --
    C - the footgun of programming languages
  142. I thought the problem was the opposite? by Fujisawa+Sensei · · Score: 1

    I seem to remember the pundits saying that there weren't enough applications that could make use of the broadband connections and all that bandwidth was going to waste.

    --
    If someone is passing you on the right, you are an asshole for driving in the wrong lane.
  143. Re:A little extreme there, don't you think? by dumb_jedi · · Score: 2, Informative

    For example, where I live, I have signed for an electrical plan that entitles me to use a certain amount of electrical power at a given time (=bandwidth). If everyone in my neighborhood used the power they're entitled to, the power lines would melt.

    That's half-true. The power company MUST meet peak demand, as well the rest of the electrical system. You can't say to people "sorry, you won electricity tonight because your neighbor is consuming too much power". That's absurd and ridiculous. What ISPs did was to HEAVILY oversell capacity. Too much greed is the problem, not heavy usage.

  144. SCTP by sgt+scrub · · Score: 2, Interesting

    p2p applications should switch to SCTP.

    http://www.ietf.org/rfc/rfc2960.txt

    --
    Having to work for a living is the root of all evil.
    1. Re:SCTP by Agripa · · Score: 1

      Unfortunately, Windows lacks native SCTP support unlike Linux or BSD.

    2. Re:SCTP by mzs · · Score: 1

      The problem is that they would need to do it with raw sockets as or install strange kernel extensions for the most common OSs.

  145. Re:Well Duh by maxume · · Score: 1

    So to transfer your 1 gigabyte movie file you will 'surreptitiously' transfer 50 gigabytes of images? Right.

    From the point of view I'm arguing, there isn't any normal raw binary data to worry about, you are supposed to be using the internets for commerce and legitimate licensed content.

    Note that I'm not advocating this, I'm just pointing out that technical wack-a-mole doesn't really lead to an internet that anybody would like, whereas the post I replied to was all like "just turn it off, don't affect me none."

    --
    Nerd rage is the funniest rage.
  146. Re:A little extreme there, don't you think? by lysergic.acid · · Score: 5, Insightful

    exactly. the argument espoused in this article is fundamentally flawed. in fact, it reads like it was written by an industry mouthpiece for the sole purpose of demonizing P2P users without absolutely no regard to logic or reality.

    first off, as you said, it's impossible for the "download fiends" to actually use more than their share of bandwidth. if i have a 56K dial-up connection, there's no way for me to just decide, "hrmmm, this isn't fast enough for me. i think i'll be a dick and download at 9 Mbps by stealing bandwidth from my neighbors."

    secondly, the author seems to be suggesting that everyone should use, or have access to, the exact same amount of bandwidth regardless of what they paid for, and that this level of bandwidth is decided by how much he personally uses/needs. well, that's very convenient for him and the ISPs. most of us are paying for 3+ Mbps connections, some people are paying for much more than that, but i guess we should all only be allowed to use 1~3% of the bandwidth we paid for because that's how much the author needs for his daily web surfing, e-mail, and posting of shitty articles on the web.

    but why stop there? why not divide up internet bandwidth evenly between all 6.6 billion people around the globe. total global broadband internet bandwidth was estimated by Cisco to be 5,372 petabytes per month in 2008. divided up between 6.6 billion people means we all get a 0.00265869476 Mbps connection--that's each person's 'fair share' of internet bandwidth. of course, we would all have faster internet connections if it weren't for those darn greedy business/enterprise internet subscribers.

    internet bandwidth isn't a fixed commodity, or a limited natural resource. technology has always been driven by consumer demand, and broadband internet is no different. it's bandwidth-intensive applications like P2P, streaming-video/audio, enterprise applications, etc. that create the push for infrastructure upgrades and ever-increasing connection speeds/network capacities. it's idiotic to accuse "power users" or "downloaders" of destroying the internet or stealing other people's bandwidth. it's even more idiotic to think that everyone should use as little bandwidth as you do, as there's always going to be a someone who uses even less bandwidth. artificially manipulating internet usage while overselling more and more is what's going to cause broadband connection quality to continue to decrease. meanwhile, there are ISPs in Japan and Korea who are doing the exact opposite by increasing network capacity and connection speeds to meet the growing demand. perhaps if ISPs in the U.S. and Canada focused on making technological progress rather than opposing it, we'd be rolling out 1 Gbps symmetric broadband connections too, rather than fussing over people actually using their 3-4 Mbps connections.

  147. Service Industry! by Lord_Alex · · Score: 1
    Many comments here are focusing on the point that the providers can't provide what they are selling and comparing it to a product. If you pay for a product, then yes it is your property (unless it's the MAFIAA you're buying from) to do as you please. However, the internet isn't a product.

    There are roads and plumbing and electricity and the Internet. These are services.

    You pay for road access (tolls and taxes) but if the road is too busy, that sucks and deal with it. There is not enough room on any roadway to handle all potential customers.

    You pay for water but if everybody flushes their toilet and waters the grass and takes a shower at the same time, water becomes scarce and that sucks but you deal with it. There is not enough water throughput to deal with all potential customers claiming their purchased usage.

    You pay for electricity. Too many users = brownout. That sucks, deal with it.

    The internet isn't a product, but a service. Like all services, it is oversubscribed. If there is a sudden surge of demand it becomes unavailable and that sucks but just deal with it. Go outside; it's hi-def too.

    If there is a continuous over-demand for the service, the providers will build more infrastructure. And that will probably mean temporary limitations.

    Just like road construction, or plumbing and electrical upgrades.

    Don't get me wrong, I like to "download Linux" over bittorrent like everybody else. But I don't have a Service Level Agreement with my ISP, or my city road crew, or my utilities providers. I just deal with downtime.

    -Alex

    --
    How much work could a network work if a network could net work?
  148. Well you get what you pay for by hesaigo999ca · · Score: 1

    If my ISP starts blocking traffic I consider valid coming to me, because it happens to be torrent traffic, they deserve what they get. Regardless of what type of traffic I am getting, if I use the bandwidth for A, B , or C it does not matter how I use the traffic, I still have 1gb per month download. Don't penalize me for using one form over another, or getting all my download at once instead of over the course of the month.

    I hope enough people complain that this does not become an accepted practice amongst the ISPs to block torrent. Many technologies use the torrent download system, and do so because of better performance for people using the same technologies in conjunction with torrent

  149. This ought to weed out the crappy ISPs by Anonymous Coward · · Score: 0

    Only ISPs that have oversold their bandwidth should suffer. What a shame... Now they will actually have to invest to deliver what they actually sold to their customers.

  150. Did anyone READ the article? by utopia27 · · Score: 1

    Having actually read the article, the author has his facts wrong. His characterization of the technologies (UDP v. TCP) is incorrect and... prejudicial. The use of UDP in this application will avoid large amounts of TCP overhead and largely unnecessary TCP resends - for a net reduction of traffic.

    Although the article characterizes this as an attempt to dodge throttling this actually looks like a good engineering decision. I'm not part of the design team - I don't know the rationale, but it certainly seems to have a good basis in technology.

  151. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    Then pay for a T1 or OC3 connection.

    I looked into that. Where I am would be $24,375 per year for a 2Mb line or over $275,000 for a 45Mb.

  152. Can't resist... by nog_lorp · · Score: 0, Offtopic

    If she can't use her fat pipe, she can use mine...

  153. Anonymous Coward by Anonymous Coward · · Score: 0

    Would Jesus uTorrent?

  154. Re:A little extreme there, don't you think? by Orion+Blastar · · Score: 1

    BitTorrent is used to distribute open source software and materials. You cannot just block BT because a few also use it for piracy it will hurt open source and you cannot throw the baby out with the bathwater.

    --
    Remember, Slashdot does not have a -1 disagree moderation, and no, troll, flamebait, and overrated are not substitutes.
  155. UDP? by winphreak · · Score: 1

    I am not a networking master, but wouldn't UDP be a better choice to avoid the TCP syn/ack packets? As many connections as a P2P program makes, changing from TCP to UDP would help alleviate some stress on routers worldwide. Although in this case, more unreliable, hash checks and pieces would help prevent corruption amongst files.

    --
    "I'm a well-wisher, in that I don't wish you any specific harm."
  156. Conspiracy Much? by Theoboley · · Score: 1

    Sounds like another RIAA/MPAA conspiracy to get people to stop downloading via torrent...I'll believe this when i see it.

    --
    Stupidity only gets you so far, then you've gotta try
  157. Re:A little extreme there, don't you think? by Dallas+Caley · · Score: 1

    Exactly!

    I've been waiting for someone to say this. Sure, I've used torrents for other activities, but my primary one is watching TV shows because it's simply easier, and as far as i know this should be legal. I think the ISPs (in my case Time Warner) need to realize this and adjust their strategy accordingly. I've often wondered why it is that i really pay for cable TV when i can pretty much get the same stuff over the net. I think eventually all we will have is a network connection and all TV/Phone/Internet will flow over it.

  158. Re:Hello! by danieltdp · · Score: 2, Funny

    you missed the "World" part

    --
    -- dnl
  159. Re:A little extreme there, don't you think? by i_ate_god · · Score: 5, Insightful

    It's called a society and there are acceptable and unacceptable behaviors. Being a filthy pirate and hogging all the bandwidth is not nor should be acceptable behavior even though you really like all the free stuff you get from it.

    You can't hog all the bandwidth, you can only hog the bandwidth allocated to you.

    What you're saying is this:

    The ISP gave my neighbourhood 500mbps, and some asshole is using all of it so I can get on the internet, but still paying for it!

    The realty is this however:

    The ISP gave me personally 10mbps, and the asshole ISP is telling me now I can't use all of it but still expecting me to pay.

    See the difference here?

    --
    I'm god, but it's a bit of a drag really...
  160. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    I do both... yeah, I've hit a few things.

  161. Re:A little extreme there, don't you think? by SanityInAnarchy · · Score: 2, Insightful

    See also: Airlines.

    The difference is, of course, that if your flight is overbooked, the airline will actually spend more money -- on hotel space, a taxi to take you to the hotel, dinner, etc -- and then put you on another flight.

    If your ISP has determined that they've got too much load, they can just cut you off -- this would be like the airline telling you to go home.

    --
    Don't thank God, thank a doctor!
  162. Re:A little extreme there, don't you think? by BlueStrat · · Score: 2, Insightful

    ...and those 10 guilty persons, what about them?

    They'll never cause another innocent to suffer?

    Your logic (I know it's a stretch to even call it that) falls flat when those 10 guilty persons set free cause suffering to countless other innocents; such that could have been prevented but for the suffering of that one innocent.

    We all suffer for the individual and the individual suffers for all. That's called society. Deal with it.

    The difference you're missing here is that 10 *individuals*, even if guilty and sure to cause harm, have a limited ability to cause society harm as they have only the power to compel others on a limited basis as individuals, whereas government has, for all practical purposes, unlimited ability to compel through force of arms & law, and hence the power to cause nearly unlimited harm to society and the individuals within it.

    Cheers!

    Strat

    --
    Progressivism (aka US 'Liberalism'): Ideas so good they need a police/surveillance-state to enforce.
  163. Re:A little extreme there, don't you think? by clare-ents · · Score: 1

    UK ADSL offers this, picking one provider, here's some pricing options for you,

    8Mbit contended, 10GB/month cap : £27.00
    8Mbit contended, 50GB/month cap : £50.00
    0.5Mbit uncontended unlimited : £157.00
    2Mbit uncontended unlimited : £412.00

    scaling up, you could get 8Mbit uncontended unlimited for around : £1600/month

    Consequently, you can get the performance of a £1600/month connection most of the time at a price of £27/month providing you're willing to share it with sixty other people. If you use more than 1/60th of the connection you'll either get a bill (bandwidth capped connection) or throttled ('unlimited' connection). Either way you aren't going to get to use much more than you pay for unless the ISP is trying to go bust.

    If you want an ISP with low latency you want a bandwidth cap because they have spare capacity, if you want to try and squeeze more bandwidth than you pay for out of the line, the a throttled connection will let you do that but your internet access will be high latency because the ISPs lines will always be full - that's how they bandwidth limit.

    --
    Only two things are infinite, the universe and human stupidity, and I'm not sure about the former. (Einstein)
  164. I'm no computer scientist... by Anonymous Coward · · Score: 0

    but why would you trust the programmer/user to report the time-sensitivity of a piece of data? Do we trust injured people at the hospital to triage themselves?

  165. Re:A little extreme there, don't you think? by krull · · Score: 1

    Netflix is a bad example too. They will throttle you if you start sending back your 3 DVDs too quickly... Of course they don't advertise that.

  166. Re:A little extreme there, don't you think? by multisync · · Score: 1

    Emergency call

    What's an "emergency call?" Are 911 calls routed through the Internet in your area?

    Actually any call, if your data is ftp, http, torrent, or similar bulk data.

    Sorry, why? Your voice call takes priority over my file transfer or http traffic because ... you say so? What's so special about your voice call that it should take priority over the updates I need to run on a machine I am deploying? Why is your kids telling Grandma what they did at school today more important than me getting useful work done?

    Or if I pay more - this is capitalism

    Excellent point. If you require guaranteed levels of service, it is you who should pay extra for it. My bandwidth should not be throttled to reduce the amount of time Youtube needs to buffer your streaming videos because someone at the ISP makes an arbitrary decision that your traffic should take priority over mine.

    And, perhaps, because I use less (average) bandwidth (i.e. am a better customer).

    So you and I go to an "All You Can Eat" buffet and you eat less than I do so that makes you a "better customer."

    And yes, I want the utility company to limit it, as it is obvious you will not (use QoS).

    I've already responded to this little straw man of yours, but I will add that limiting all customers equally would be acceptable. That's what those of us who are not in favour of "traffic shaping" are saying: sell us bandwidth, not services, and if the level of service degrades because everyone is trying to use it at the same time, we all suffer equally.

    It's not up to IPS - or you - to decide my traffic is less important than yours.

    --
    I don't care why you're posting AC
  167. Re:A little extreme there, don't you think? by SanityInAnarchy · · Score: 1

    I just graduated to an income bracket where I'm more time poor than cash poor.

    That is, incidentally, why I still use BitTorrent. There is not yet a DRM-free or even Linux-supporting service which will allow me to download high-def, reasonably uncompressed movies over the Internet.

    I don't have the time to deal with Windows more than I have to. Nor do I have the time to take an extra trip to the video store. I suppose I could use Netflix, but that's going to be even more hassle for even less quality (DVD vs 1080p).

    Now, if such a service existed, it would probably use BitTorrent anyway, so that solves nothing for the ISPs. But if such a service existed, and would provide a decent selection, I might pay for it. As it is, no one has even reached feature-parity with piracy, let alone surpassed it.

    --
    Don't thank God, thank a doctor!
  168. Re:A little extreme there, don't you think? by Real1tyCzech · · Score: 1

    That's why we have a judicial system and a system of checks and balances.

    My response was solely concerning the post above mine, and the implied assumption that no-one should be criminalized, just in case we might be wrong...

    It's ridiculous to the extreme.

  169. Re:A little extreme there, don't you think? by Sapphon · · Score: 3, Insightful

    You do, if you've paid for the right to graze 10,000 sheep there. If the land can handle 20,000 sheep, and the land owner has sold these grazing rights thrice, who is at fault?

    --
    Antiquis temporibus, nati tibi similes in rupibus ventosissimis exponebantur ad necem.
  170. Re:A little extreme there, don't you think? by SanityInAnarchy · · Score: 1

    For every Linux DVD image distributed by bittorrent, there is probably dozens of times that much data in blatantly bootlegged content being distributed.

    And if BitTorrent went away, Linux DVDs would be much slower to download, and much more costly to host.

    Why should Linux distributions have to suffer because of a completely unrelated activity? I suppose, if they moved to an HTTP-based protocol, we should just ban HTTP, or web hosting on residential connections? What's next -- NAT every connection, and start banning Skype, because it punches wholes through NAT?

    I don't want to live in a country where whole protocols are condemned because they might be used for something of questionable legality. I kind of like actually having the Internet.

    --
    Don't thank God, thank a doctor!
  171. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    If everyone gets to pick and choose which ones they want to abide by and not, then that becomes anarchy

    So pot-smokers and people who exceed the speed limit lead us down the road to anarchy?

    Oh god, someone invoked the pot-smoking and speeding argument. Well guess what, you speed and you get a fine. Feel free to speed often, and have your drivers license revoked. Feel free to smoke some pot and spend the next couple of months protecting your precious rear entry from a guy who calls you Susan.

    If the law is not correct, civil disobedience is not the way to make people see that it's incorrect. Civil disobedience in modern society just gets you in a lot of trouble.

  172. BT isn't the problem by Supergibbs · · Score: 1

    BT isn't the problem, it's the internet providers offering more than they can handle. If I am capped at 5Mb/s then I should be able to use that regardless of my protocol and so should everyone else. Internet providers, upgrade your infrastructure and stop over selling!

    --
    First post! (just in case I am...)
    1. Re:BT isn't the problem by Anonymous Coward · · Score: 0

      Oversubscription is a perfectly reasonable model. If you expect your ISP to provide you with a dedicated share of bandwidth that you can use at any time, you will pay out the ass for it.

      It is simply not economical.

  173. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    You could lay your own fiber for much much cheaper, even accounting for buying up all the property on the way.

  174. Re:Well Duh by kaizokuace · · Score: 1

    why would you side with the ISP after a switch to UDP with BT? The ISP's actions caused this arms race. The power is all in their hands. They could spend the money they were supposed to on building up the infrastructure and this problem could be solved. How much energy is being wasted just fighting the desires of their customers?

    --
    Balderdash!
  175. Re:A little extreme there, don't you think? by Spez · · Score: 2, Insightful

    You're absolutely right.

    And while we're at it, most thiefs enter houses using doors don't they? We probably should ban doors.

    And people who do highway speeding or drug smugling use cars? Probably should ban cars also.

    Do you want me to follow that line of thoughts? Because some people use some things illegaly doesn't make it right to ban the thing outright! That's not the same problem!

    --
    I wouldn't mind you in my head, if you weren't so clearly mad -Lews Therin Telamon
  176. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    Emergency call. Actually any call, if your data is ftp, http, torrent, or similar bulk data.

    And who gets to make that decision?

    Certainly, if the ISPs actually provided enough throughput, you could simply do QoS on your own router and be done with it.

    Or if I pay more - this is capitalism.

    So long as it applies equally to all the bits on that connection, I've got no problem with it.

    And, perhaps, because I use less (average) bandwidth (i.e. am a better customer).

    Not using what you paid for doesn't make you a "better" customer, any more than buying a donut and eating half of it would.

    And yes, I want the utility company to limit it, as it is obvious you will not (use QoS).

    Let's think about this -- we're comparing the Internet to a utility company.

    What happens to those 911 calls when everyone's air conditioner kicks on at once, causing a particularly old piece of equipment to fail, killing the power?

    That's right -- they have backup generators. Just as they would have a backup phone network, and very likely pay more for their service, and ensure that all calls make it through.

    That's fine -- but the ISP does not get to pre-emptively throttle me because they think I might cause problems for 911 calls, someday, maybe, which is likely bullshit when the 911 center in my area probably isn't using VoIP anyway.

  177. The client application can't know about congestion by George_Ou · · Score: 1

    The client application can't know about congestion in the core of the network, so it breaks control at the core of the Internet where there's less management. If you read the article fully, this would have been apparent.

    Real-time applications use UDP because they have built-in bandwidth caps and they don't burst to the full capacity of the network like file transfer applications. It's dangerous to put P2P on UDP on a very large scale and it will require a massive change in the core of the Internet to deal with this new behavior.

  178. Re:A little extreme there, don't you think? by cromar · · Score: 1

    Civil disobedience in modern society just gets you in a lot of trouble.

    What a cowardly point of view (no pun intended).

  179. Re:I didn't invent them or design them, just use t by nabsltd · · Score: 1

    Something about more sessions to track uses more cpu and memory. I'd imagine it has to do with the tables required to track the sessions.

    A "router" doesn't have session state. The only information it keeps are routing tables, and those are not dependant on the traffic being sent, but rather on the network topology.

    Most home users have routers that also contain address-translating, stateful firewalls, and this is probably what you are thinking of. Too many active connections can cause such a device to stop working, but in practice even the cheapest sold today can handle somewhere between 1000 and 2000 connections.

  180. Re:A little extreme there, don't you think? by phoenix321 · · Score: 4, Interesting

    Excellent analogy.

    Selling a clearly marked service "
    - "5mb/sec, 50gb/month"
    - "1 air transfer to new york, you and 20kg of stuff, this friday at 0800"

    then they oversell their capacity based on statistical analysis and when their statistical model fails, which it will always do, statistically speaking, they tell you

    - "you bandwidth hog, we bill you on a backdated, horribly expensive business plan AND cut you off from now on AND never deal with you again. And if you sue, we tell everyone about your midget porn"

    respective

    - "We are totally sorry you cannot take this plane, take a later plane with an upgrade to business class OR take a hotel on us OR take some hundred dollar compensation"

    And I was always furious about airlines doing this. Now it turns out they're actually pretty sensible about this matter and pure angels when compared to other businesses.

  181. Some equipment doesn't handle UDP well by Anonymous Coward · · Score: 0

    Actually, no, it's not a good thing.

    I once brought a very large and very expensive intranet to its knees by accident. Basically I was using UDP packets to transfer a few gigs of data back and forth between a master node and a bunch of slave nodes. Neither the ATM interfaces on the Solaris boxes nor the switches themselves handled this well; the former wedged completely requiring cold reboot, and the latter just froze for long periods of time. You'd think it wouldn't matter, but evidently the designers had anticipated TCP would be the bulk of the bandwidth, and optimized for it.

    Using UDP to move large amounts of data around on a network you have complete control of is risky. Doing so on the public internet is a very, very bad idea.

  182. Re:A little extreme there, don't you think? by Kijori · · Score: 1

    The land owner is at fault - but it would be both short-sighted and selfish to keep on grazing your sheep if you knew it was destroying the land.

  183. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    Not to mention that nobody actually "chooses" to live on the land they were born into. That notion is just absurd. What happens to 99% of the world's population is that they are born into a society and CANNOT choose a different society without paying an overwhelming penalty. Therefore they make due with the cards they were dealt.

    Very few people actually enjoy the ability to sit down and "choose" a better place to live. Out of the few people who do change societies, 99% of those are forced in one way or another (work, family, health, etc).

  184. Re:A little extreme there, don't you think? by HiThere · · Score: 1

    Well ALL of my bittorrent traffic is legitimate. And I don't know anyone else to compare it to. I've got to presume that you're commenting about either your own use, or that of your friends. ... Either that or that you've been illegally snooping.

    I'll grant that there *are* people in a position to legitimately have information justifying the position that you have taken. It's just that the ones I know have never expressed one even similar to yours. (OTOH, I haven't asked them. It would seem a violation of professional confidence.)

    --

    I think we've pushed this "anyone can grow up to be president" thing too far.
  185. Global Warming by Wraithlyn · · Score: 1

    You're just another global warming apologist. Oh SUUUURE... it's BITTORRENT causing all this melting...

    --
    "Mind, as manifested by the capacity to make choices, is to some extent present in every electron." -Freeman Dyson
  186. Re:A little extreme there, don't you think? by I(rispee_I(reme · · Score: 1

    "You'd be really pissed off if no laws were enforced, someone decided they wanted your computer and either beat the living shit out of you or shot you in the process of relieving you of its ownership."

    Who is this "someone" that seems to be held back from killing and looting only by the continued integrity of our legal system?*

    If murder and theft were suddenly decriminalized, my desire to commit them would remain unchanged. I suspect the great majority of people feel the same way.

    Perhaps laws against murder and theft exist not to prevent people from killing and stealing, but to punish those who do?

    If that's the case, the people might be able to do away with their legislative body without becoming murderous, avaricious berserkers.

    (Aside to moderators: I know this discussion is off-topic, but he started it.)

    *Sounds like a pirate, ironically. Arr! (Cue 57 responses debating the definition of irony. Tinny and Bronzy, now we only need 56.)

  187. Re:A little extreme there, don't you think? by Fnord666 · · Score: 1

    Can you imagine signing up for a "3 DVD's at a time" plan from Netflix and then when you actually check out 3 at a time they start bitching up a storm because "You're hoarding the DVD's!!! None of the other customers will be able to rent any of them!!!". Of course not.

    Funny you should mention that as an analogy. In fact, there has been a lot of discussion in the past about DVD shipping delays and how they seem to happen to people who turn their rentals around overnight. Turn your rentals around too quickly, and suddenly they won't be "received" for four or five days. In effect, your DVD bandwidth gets throttled. To the best of my knowledge, no one has been able to prove that this is happening deliberately though. Maybe it's just coincidence, if you believe in that sort of thing.

    --
    'The tyrant will always find pretext for his tyranny.' - Aesop's Fables
  188. Re:Is this really a problem How fubar are the USA by IamTheRealMike · · Score: 1

    Consider doing such a transfer trans-Atlantic when there's a temporary loss of capacity due to (say) a ships anchor cutting a fibre route. Suddenly your connection is congested although your ISP has not been overselling you - there's just been a loss of capacity on the network and now the backoff features no longer work. So instead of stuff just getting slower the whole system starts to break. That's what the author of TFA is afraid of - whether the actual implementation in uTorrent will do this, I can't say, but it sounds plausible.

  189. Re:A little extreme there, don't you think? by Shakrai · · Score: 2, Interesting

    Civil disobedience in modern society just gets you in a lot of trouble.

    Stupid Rosa Parks and her civil disobedience. Could have avoided all that hassle if she had just given up her seat......

    --
    I want peace on earth and goodwill toward man.
    We are the United States Government! We don't do that sort of thing.
  190. Re:A little extreme there, don't you think? by phoenix321 · · Score: 4, Interesting

    The real world of us grown-ups outside the Soviet Union is not about real actual costs and real actual usage, it is about contracts and contractual compensation.

    Which is the reason why a bottle of Coke costs 1 dollar at the store and 20 dollar at a fancy restaurant.

    Which is the reason that all the people flying with you in an airplane all paid a different price for their seat.

    If you abolish that, you help people in the short run, but instantly abolish freedom of contract as the basis of any and all successful economies.

    But that's too far out to mention here, because in this country, we have laws of commerce which basically just say "a contract is a contract is a contract" albeit in a hundred different clauses.

    Which brings us back to your post: company A offers a contract to the general public explictly stating "x mbit/sec and no other limits for the low low price of 10 dollars per month". When General Joe Public accepts this contract, Company A and Joe are in a binding contractual obligation with each other, out of which neither can escape for non-serious reasons without serious lawful consequences.

    Company A didn't sell "a reasonable and sane share of x mbit/sec, while we define what 'sane' actually means" just as Joe Public didn't pay with only a part of his 10 dollars.

    If that wouldn't be the case, we would have an economy where every partner in a contract could give as much or as little as he wanted. This may work for money donations on Christmas and candy on Halloween, but is no basis for an economy. That's why we write down contracts since the Middle Ages and have contract lawyers a dime a dozen.

    If you object to that, I will gladly sell you my new car for which YOU pay full retail while I deliver only a glossy brochure, three wheels, a tiny spare wheel and a bag of seat stuffing. And then terminate my contract with you telling all the world how greedy YOU are.

  191. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 2, Insightful

    Actually the whole "better 10 guilty people go free than 1 innocent person be punished" is the basis of the legal system's "innocent until proven guilty" and "beyond reasonable doubt" standards.

    We, as a society, have made the choice. We would rather risk a guilty person walking free, and possibly harming more people, than risk punishing an innocent person. *That* is society, deal with it.

  192. Re:A little extreme there, don't you think? by IamTheRealMike · · Score: 3, Interesting

    I think you lost a lot of credibility when you called a contributor to the WiFi and Ethernet specs an "industry mouthpiece".

  193. Re:Well Duh by Shakrai · · Score: 1

    I agree. They shouldn't be selling 10/15/20+ mbit connections if they can't provide that speed to the end users. I wouldn't hold them accountable if their network can't handle the provisioned speeds during unforeseen events (like the cell networks not keeping up during the VA Tech shootings) but if they can't meet the provisioned speed a majority of the time then they need to upgrade their damn network or stop selling those speed tiers.

    I guess it's easier to market if you use great big BOLD letters that say "10 megabits" and little tiny ones in 4 point font preceding them that say "Up to"

    --
    I want peace on earth and goodwill toward man.
    We are the United States Government! We don't do that sort of thing.
  194. But if the internets go down by revjtanton · · Score: 1

    then my torrents will download slow!

  195. SCTP? by Anonymous Coward · · Score: 0

    If you're going to transfer files over UDP then you need to build some TCP-like protocol on top of it. The article doesn't say exactly how BT works in this respect, but he's probably right. There's no way that BT's protocol could be as sophisticated as TCP, given its 30+ years of development.

    Isn't this partly why SCTP was created? (Of course not all OSes and routers / NATs know about it, so it would only be of limited practicality in this instance.)

  196. Awful article. Why even link to it? by squiggleslash · · Score: 1

    Gamers, VoIP and video conference users beware. The leading BitTorrent software authors have declared war on you - and any users wanting to wring high performance out of their networks

    No, they haven't. What starts as a claim that BitTorrent has declared war on VoIP turns out to be a claim that BitTorrent has made a change to their protocols that might impact VoIP users as collateral damage - but ONLY if ISPs decide to engage in a foolish and moronic packet blocking scheme that would also impact DNS and therefore is unlikely to ever be implemented.

    The article is choc-full of half truths and downright lies. The reality is that ISPs have many choices in how they "shape" user traffic, and the most obvious solutions (outside of upgrading their networks) that are fair rather than discriminatory are also the solutions that will have zero effect on VoIP users.

    You can identify heavy bandwidth users and throttle their traffic. It's easy. Each packet has this thing called an IP address on it, that records where the packet is from, and another one recording where it goes to. If someone's identified as making heavy use of bandwidth at a time of peak congestion, you can use this hitherto completely unknown attribute of every IP packet to throttle traffic to and from that customer.

    Easy. But it's not a knee jerk "It's BITTORRENT that's destroying out Internets!" response. So you get the Richard Bennetts of this world - who clearly have an agenda that's anti-BT rather than anti-bandwidth hogging - pretending it doesn't exist.

    Idiots.

    --
    You are not alone. This is not normal. None of this is normal.
  197. Re:A little extreme there, don't you think? by HiThere · · Score: 2, Interesting

    Actually, one could block BitTorrent. It's possible. Of course, it would be re-written into a different form, that one would also need to block. And again. And again.

    The general term for such a game is "arms race". It frequently continues until both participants are eliminated. You don't find either saber-toothed tigers or mastodons around anymore. And BOTH Athens and Sparta ended up conquered by Macedonians.

    Personally, to me it seems fair to offer a fixed amount of service/month + a cost for extra service. AND TO MAKE IT CLEAR!!! Hiding things in blocks of text is not making it clear. And if they advertise unlimited service, then they are *emphatically* required to deliver on their promises, even though they can't possibly do so. There should be (are?) severe legal penalties for lying in your advertisements. They should be enforced.

    I see the entire mess as companies trying to get out of living up to their advertising claims. I see no justification in allowing them to do so.

    --

    I think we've pushed this "anyone can grow up to be president" thing too far.
  198. Re:A little extreme there, don't you think? by The+Living+Fractal · · Score: 1

    So pot-smokers and people who exceed the speed limit lead us down the road to anarchy?

    No, pot smokers who speed lead us off the road right into a tree ;p

    --
    I do not respond to cowards. Especially anonymous ones.
  199. Re:A little extreme there, don't you think? by phoenix321 · · Score: 1

    Post whatever price you see fit - all are fine with me.

    But if you can't keep your contract BUT keep my money, you're going to jail.

    Note to self: never make any explicit measures except the asking price in a contract of mine and then only sell vague assumptions that I never have to fulfill while collecting serious hard cash from gullible consumers.

    Note to the general public: I have a reasonably new car that can drive reasonably fast, looks reasonably shiny and has a reasonable fuel consumption assuming you drive responsibly. It also has a low probability of failure*1, is not too loud on idle and will start without serious problems in a reasonably warm winter*2. The price is 10000 dollars and is not negotiable*3.

    *1 this term does not apply for sales in Mexico
    *2 this term does not apply for sales in Canada, Montana and Wisconsin.
    *3 if you make any real offers, I will apply a 3000 dollar surcharge for a reason I will only tell you after the sale

    And if you apply NOW within three minutes, I will NOT charge you a broker's fee.

    Sounds to good to be true, eh?

    Just look through your ISP contract and come back whining.

  200. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    And no ads.

  201. It's all about "the PVC" by recharged95 · · Score: 1
    Ted Stevens says:

    "As long as the UDP doesn't reach 176 degrees, the PVC tubes should hold up."

  202. Blame the ISPs, Not BT by Mouldy · · Score: 1

    Surely the issue isn't using UDP to get around ISP's 'traffic management', the problem lies with the ISPs who have forced BitTorrent to use UDP with said 'traffic management' policies.

    If the ISPs didn't throttle bandwidth, BitTorrent would have no need to use UDP and the world would be a better place. If the ISPs didn't complain to their customers for using the bandwidth they supply but had networks that could support their advertised bandwidth, everyone would be happy.

    Unfortunately as well we all know, using 10Mbps of the 10Mbps connection you paid for is bad, you're not allowed to do that - heaven forbid you use the bandwidth you're buying from them :o

  203. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    Informative? Try more like "troll" or "flamebait."

    Using your stupid analogy, this would be more like threatening to raze the entire city to the ground because no one intervened to stopped the wife from being locked in the bedroom.

    You know what I'd like to see happen? Anyone who is caught using uTorrent with this setting gets their broadband internet access contract torn up. Don't even pretend that most bit torrent traffic is legitimate and legal. For every Linux DVD image distributed by bittorrent, there is probably dozens of times that much data in blatantly bootlegged content being distributed.

    Please, go back to facebook.

  204. Re:A little extreme there, don't you think? by adonoman · · Score: 1

    I'd be happy to watch ads if it meant I could get the same speed/selection/quality as bittorrent. A big issue with current online offerings from networks is that either you can't play them outside of the US.
    Often they use some proprietary client, or a terrible quality flash version, or they won't let you view in full-screen mode. Or you have to individually queue up 1/4, 2/4, 3/4 and 4/4 to actually watch a full episode. That's all assuming they have enough bandwidth to actually stream it to you in the first place.

  205. Re:Is this really a problem How fubar are the USA by TheSunborn · · Score: 1

    Would this not only be a problem with transfers that are running while the cut happens? I mean if I start a udp transfer after the bandwidth is cut, then uTorrent should detect the lower transfer bandwidth and set the transfer speed lower. They do not have any way to know how the bandwidth between me and an random other peer, so when a new 'connection' is opened between me and an other peer, they need to determine the bandwidth. And in case of a cut, they should detect lower bandwidth.

    And I think they really do need code to do dynamic available bandwidth detection(Similary in effect to tcp), because If I open a connection in my browser that uses half my available bandwidth, things would really fuck up(Both for uTorront and my browser) if uTorrent did not lower the speed.

     

  206. Re:A little extreme there, don't you think? by toriver · · Score: 1

    There is also the "80 Hole". Basically since firewalls are often set up to block other ports than the regular HTTP port of 80 (plus SSL ports), anything else ends up being rewritten to tunnel through HTTP. With the overhead and security risks that incurs...

    Are they willing to block the "80 hole"?

  207. Overreacting a bit here... by SleepingWaterBear · · Score: 1

    The best way to ensure that uTP doesn't kill the internet is to throttle it at the source, and any law that stands in the way of ISPs exercising that level of management is deadly to the internet.

    The problem here is that he starts with a valid premise: completely unmanged uTP is a threat to the continued smooth operation of the internet, and comes to the completely unsupported conclusion that any law restricting the ISPs is bad.

    ISPs need to be allowed to control bandwidth flow in a fair fashion to provide the best service possible to their clients, but this doesn't mean we should let them do whatever they want either. ISPs should, for instance, not be allowed to treat packets differently based on who they're coming from/going to, or what their content is, but some ISPs have been talking about doing exactly that.

    Over regulation is bad. This doesn't make no regulation good.

  208. Anonymous Coward by Anonymous Coward · · Score: 0

    Drugs are illegal, yet it's a multi-billion dollar international trade, despite many more times that amount spent on eliminating it. Why? Because there're drug users.

    Vast majority of P2P traffic is probably also prohibited by various IP laws, but if enough people want something badly enough, no power in the world can prevent them for long.

  209. Re:A little extreme there, don't you think? by jmilne · · Score: 2, Insightful

    The Post Office is a good example for the Internet. Right around the holidays, everyone starts to send catalogs, Christmas cards, and other packages. Far more than the Post Office deals with on a normal basis. Which causes delays in delivery. They even warn people: send everything by such-and-such date or it won't arrive in time for Christmas.

    That's pretty much the Internet. Everyone expects a certain amount of bandwidth to be used. Occasionally, someone will exceed that, but usually at the same time, someone else isn't using theirs, so it's okay. But with Torrent, it's basically everyone using their bandwidth all at the same time. It's always Christmas. Now, the Post Office could staff for that situation, but obviously, prices will have to go up to accommodate their extra load. Likewise, your ISP can provide all the bandwidth necessary to let everyone use their limit of bandwidth all the time, but they're going to have to raise the prices a lot in order to provide that.

  210. Re:A little extreme there, don't you think? by blahplusplus · · Score: 2, Informative

    Note that they don't actually open the packages themselves unless there is an extenuating circumstance (bomb, etc), they might quickly look inside the box with a scanner to detect explosive devices/etc, but this is far and away from what ISP's can do, you can't send bombs that can blow people up in packets. Your counter example is not with the intent of my original message - being able to open private mail.

  211. Re:A little extreme there, don't you think? by WhatAmIDoingHere · · Score: 1

    The problem is that running ANY bittorrent program is considered "running a server" by just about EVERY ISP, and if you read your terms of use agreement, "running a server" is terms for cancellation for most home connections.

    --
    Not a Twitter sockpuppet... but I wish I was.
  212. Re:A little extreme there, don't you think? by WhatAmIDoingHere · · Score: 1

    "does this give the shipping company or government the right to open my mail and packages because it passes through their facilities?"

    Yes? Have you met the ICE? How about Homeland Security? Hell, even before that your packages were sniffed for drugs.

    --
    Not a Twitter sockpuppet... but I wish I was.
  213. Re:A little extreme there, don't you think? by WhatAmIDoingHere · · Score: 1, Informative

    You can use it but what you can't do is use it for things you agreed not to use it for in your Terms of Service agreement.

    That tends to include such things as "running servers." Because of the amount of data uploaded by things like BitTorrent, the ISPs tend to consider that "running a server."

    --
    Not a Twitter sockpuppet... but I wish I was.
  214. Re:A little extreme there, don't you think? by WhatAmIDoingHere · · Score: 1

    Yup, I had a 5-at-a-time plan and would go through all five movies in two nights. After sending all 5 back on the same day, I'd get the next 5 spread out over 3-4 days.

    --
    Not a Twitter sockpuppet... but I wish I was.
  215. Bah. You think whining to CS does something? by Valdrax · · Score: 1

    Guess who has a lower tolerance for BS? ..."Lynette" whose children are screaming at her because their Wbox 3 is 'broken'?

    The developers of the next generation of consoles and game software will do so in the environment created by the ISPs.

    Give me one good reason why a console game *needs* the ability to send out multiple streams of UDP data at the same time. 'Cause that's what ISPs will look for -- not individual protocols. You just look for an app that *looks like* a badly behaving P2P app and throttle the entire user's stream. Well-behaved P2P apps, like Steam, will be whitelisted.

    And I don't see very many mothers continuing to scream when the service rep looks at why the connection is throttled and asks if their family is using any file-sharing apps and strongly hints that the ISP doesn't support piracy of movies and music and that they should either shut off their filesharing or upgrade to a package that supports it or be faced with possible termination if they're caught violating their ToS. Little "Lynette" here isn't likely to even be AWARE of most legitimate uses for P2P, and frankly most big ISPs (the ones making the filtering decisions for the little ones that sublease their lines too) don't have to give a damn about customer service because they're one of the only two providers in town. ...And the other guys are doing the same thing.

    Game, set, match for the ISPs. It's cheaper to hire low-skilled workers in India to listen to screaming moms than it is to upgrade backbone bandwidth. You don't honestly think whining to the outsourced customer support rep of the local duopoly actually *means* anything, do you?

    --
    If it's for-profit but free, you're not the customer -- you're the product (e.g., the Slashdot Beta's "audience").
  216. Re:A little extreme there, don't you think? by WhatAmIDoingHere · · Score: 2, Interesting

    Haven't you heard of "rolling blackouts?" They're saying "sorry, you won't get electricity tonight because your neighbor is consuming too much power."

    Recently the hospital I work at got a call from the local power company asking us to run on genny for a few hours and sell them some of our excess juice.

    --
    Not a Twitter sockpuppet... but I wish I was.
  217. Re:A little extreme there, don't you think? by Shakrai · · Score: 1

    No, pot smokers who speed lead us off the road right into a tree ;p

    Hahaha, true enough. Reminds me of a joke: What's the difference between a stoned driver and a drunk driver? The drunk driver blows right past the stop sign without even slowing down. The stoned driver stops at the stop sign and waits for it to turn green.

    --
    I want peace on earth and goodwill toward man.
    We are the United States Government! We don't do that sort of thing.
  218. Re:A little extreme there, don't you think? by meson2439 · · Score: 1

    You have chosen to live in a society and by extension have chosen to live by society's rules.

    Oh.. really. But the internet has a different society (world) and in here BT is OK. Protecting ourselves from the people, laws and morality of the physical world is justifiable.

    A meltdown is good, at least those ISP will start to upgrade their services. Those ISPs have been living on a free income for too long.

  219. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    The government do have that right. There's an entire department devoted to it - Customs.
    Whether they should or not is a different matter, but they do have that right.
    Did I just miss some sarcasm..?

  220. Re:A little extreme there, don't you think? by bluefoxlucid · · Score: 1

    The post office is a private industry, not the Government.

  221. Heavy users benefit from anti-heavy user pricing? by Valdrax · · Score: 1

    Everyone here seems to work under the assumption that heavy bittorrent users would be worse off in a world with download caps or metered bandwidth. I don't think so. It would force companies to compete to give good service with clear contracts where they actually tell you what they are really selling. This is bound to increase, not decrease, the availability of real bandwidth per dollar for most users, included us computer geeks.

    How?

    Is this some sort of strange free market fundamentalist idea that the market will provide solutions that make everyone happy, or do you have a good clear model by which free riders on the system stand to benefit under a system that holds them accountable and is explicitly designed to discourage their behavior?

    I mean, I have to accept that what I am, from the view of lying "We sell unlimited bandwidth and are happy to serve customers of all stripes!" ISPs -- a "free rider" of sorts. I pay for the absolute cheapest DSL package available in my area, and I use about a third of its maximum capacity (upstream) every month. I probably transfer 10-100x the data of the average user of their *most expensive* package, and my ISP probably sees me as someone using "more than their fair share."

    What ISPs want to do by metering connection is to create a world that provides a financial disincentive to heavy users. This gives them more breathing room to slow down upgrades, lets them attract more customers (who can't afford current rates), and lets them gouge the living heck out of the those who have high demands (restoring the usual "supply v. demand" pricing curve you get elsewhere) and turn high bandwidth into a premium luxury good that you can charge increasing rates for (like they do for business customers).

    In a world priced to suit low bandwidth users and to dig more money out of high bandwidth users, how do high bandwidth users benefit more? Right now I pay less than average for my connection and use far more than average. I can see policy reasons for the public as a whole maybe benefiting from such a move, but how on earth does flipping the cost equation benefit me at all?

    --
    If it's for-profit but free, you're not the customer -- you're the product (e.g., the Slashdot Beta's "audience").
  222. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    first off, as you said, it's impossible for the "download fiends" to actually use more than their share of bandwidth. if i have a 56K dial-up connection, there's no way for me to just decide, "hrmmm, this isn't fast enough for me. i think i'll be a dick and download at 9 Mbps by stealing bandwidth from my neighbors."

    I think you misunderstand.

    The point isn't that you or I will use more than our share of bandwidth on our local network, it's that we'll use more of our share on intermediate servers between us and our destination.

    With TCP, when I run into a congested intermediate server, my connection backs its speed down.
    UDP doesn't and everyone else suffers for it.

  223. Re:Imagine: by bluefoxlucid · · Score: 1

    I knew a girl who would be ecstatic if her man bought her some sexy underwear. She likes to flirt sometimes, ya know? Girls like to feel pretty and wanted...

  224. Re:A little extreme there, don't you think? by mcarp · · Score: 1

    Except that you forgot the only reason they let you watch those shows on TV is because the commercials are included. It seems trivial, but the commercial advertising model is the one they depend on for revenue. Otherwise there would be no TV, no radio and now no internet. If you are willing to just press mute and or skip via TIVO they're willing to let you keep watching at the same price whatever that is. Its a gamble on both ends. Not that you shouldn't complain about it if you feel its a problem, but keep in mind that the result is probably going to be higher prices. Everyone complains that ISPs are advertising x and you're paying for it. Sure they're counting on you not noticing the overselling and not reading the fine print. But the bottom line is you would not be able to buy it at all if you really want it that way. Advertising is a broken business model that only works because SOME people actually watch commercials and are influenced by them. Overselling bandwidth is a similar broken business model but it works for a similar reason in that only a few people fully utilize and only a few people are interested in complaining about it.

    I would love to see a statistical analysis of taxes paid vs bandwidth between those ISPs in countries people keep raving about doing so well providing internet vs US. People keep saying how the internet in the US sucks compared to so in so country. Well if you consider how many people are actually using a particular network you might see where the problem is. In the US we're lazy and consumption spoiled. You can get almost anything at any time. The quality of that which you get is mostly based on what you pay. Pay less, get less, pay more get more. This "rule" doesn't always work out but if you are a careful shopper it may work out for you. That's all anyone can count on unless one gets off one's ass and produces their own product. In some other country that may have much more taxpayer subsidy or a smaller number of users to support or a smaller percentage of users to support or a smaller land mass to cover maybe they are getting better service. It's a lot easier to support 10 users than 10,000. Its a lot easier to support 10sq miles than 10,000sq miles. If you want to keep griping, I challenge you to produce a service that is superior to that which is available. Talk to me in a decade.

  225. Re:A little extreme there, don't you think? by bluefoxlucid · · Score: 4, Insightful

    You can't destroy the Internet; it's an instantly renewable resource. Once it's exhausted, it's done. It's a pure flow resource and if you overuse it the way to fix it is to back off; if you overuse a stock-flow resource like land, you have to back off AND wait, or you may find that it just doesn't grow back anymore.

  226. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    While your analogy about Netflix is good for the example, Netflix actually wants you to hoard the DVDs as long as you can because they make/retain more money that way.

  227. Re:A little extreme there, don't you think? by Incadenza · · Score: 1
    A good example indeed. The problem of overgrazing on communal grounds is quite old. In the north east of the Netherlands a lot of communal grazing grounds turned into drifting sand because of overgrazing centuries ago.

    Local families even were named after the drifting sands, or in Dutch 'stuifzand': Peter Stuyvesant.

  228. Re:A little extreme there, don't you think? by bluefoxlucid · · Score: 1

    So, incur maintenance costs, and fuel costs, on a small scale, which costs about 3 times as much as power plant retail power, and sell back some of it? Sure, but you're paying us the difference between your cost and our cost for what WE use, and full price for what we sell you.

  229. Difference being... by EgoWumpus · · Score: 1

    You pay for electricity by the pound, not on a monthly rate. If you want to run an ISP like a power company, then you have to accept a rate plan based on how much you use, rather than based on how much you want access to.

    The disconnect with ISPs is that they are overselling because they're selling access - except they can't deliver on it certain peak situations. For the vast though shrinking majority of their customers, the maximum access potential will never be reached. It's those few times, people and places that actually hit that max that are causing them problems - because in those cases they've sold a product they can't deliver.

    Unfortunately, without changing to a pay-as-you-go scheme, they don't have many tools for reducing the problem users; forcing them to quit, suing them, or trying to ignore them being the obvious ones. If they raised their rates to match the power user use, they'd lose market out of the bottom bunch of people. Who is going to pay $100 a month to check their email at home? No one, especially with cell phones covering that these days.

    Telecoms don't WANT to move to a pay as you go plan, though, because they're making a lot of money right now off of those customers who don't use the service much. Ideally, all their customers would be like that - paying more for less - and they will want to manipulate the market in that direction.

    And that is why regulation is needed.

    --

    [Ego]out

    1. Re:Difference being... by Kalriath · · Score: 1

      And those that DO want to move to a pay as you go plan (i.e. all of them) get bitched at because "it's just another cash grab! They should be offering me unlimited!"

      Face it, these people (not the ISPs, the SLASHDOT READERS) are just trying to justify their own greed.

      --
      For a site about things like basic rights, Slashdot users sure do like to censor "dissent".
  230. Re:Bah. You think whining to CS does something? by Chyeld · · Score: 1

    The basis of your argument for why complaints won't mean diddly ("the company doesn't care") is the exact reason why this would blow up in their face.

    Because the company isn't going to care enough too selectively whitelist services or even differentiate between 'well behaved' and 'ill mannered'. You know they aren't going to, because they aren't right now.

    And because they aren't differentiating, they will catch enough people in their dragnets that they will manage to piss off the wrong people and pay for it.

    Have you noticed lately how badly cable companies are getting their lunches eaten by the satellite companies or the phone companies having their lunches eaten by VOIP and cable providers? These are groups that used to have a monopoly in their area and are now fighting off fairly strong competition because they got complacent and arrogant enough to not care what the customer thought of them.

    No, I'm not saying that they are quaking in their boots right now, but the one thing I am certain of is that the genie is already out of the bottle. People are ramping up their internet usage and they aren't going to be willing to settle for less rather than more. If the current providers can't provide service, someone else will. Maybe that'll be a direct competitor or maybe it'll be something completely different. But it will be something, because as powerful as the telco and cable companies are, they aren't powerful enough to shut out everyone.

  231. Maybe that's why they're deploying 20,000 troops. by Ungrounded+Lightning · · Score: 1

    BitTorrent is believed to be harboring weapons of mass destruction. These weapons are believed to be capable of destroying all of the internet tubes.

    Maybe that's why the government has has deployed 4,700 troops domestically, ramping to 20,000 over three years, trained to respond to "weapons of mass destruction attacks".

    Think that will be enough?

    --
    Bantam Dominique roosters crow a four-note song. Once you've heard it as "Happy BIRTHday" you can't NOT hear it that way
  232. Re:A little extreme there, don't you think? by Matheus · · Score: 1

    You know.. this one time..

    The sign DID turn green.

    My life's never been the same since!

  233. Oh, the high road or the low road... Can't decide. by Valdrax · · Score: 1

    How *dare* you attempt to impugn the liberal practice of "shoot the messenger"!? He *allowed* the Messiah an opportunity to say something that revealed his true thoughts and beliefs!! Burning at the stake is too good for such a heretic!!

    I'm so torn! I could go one of two ways...

    The High Road Reply:
    "You know, you'd be a bit more credible if you simply noted that partisans of all stripes play the 'shoot the messenger' game, and portraying it as a 'liberal practice' only reveals your own short-sighted, partisan bias. You could have pointed out that the whole 'is he or is he not a plumber because of a union-backed licensing program' was a silly argument to begin with by people desperately grasping at straws to discredit and already non-credible messenger that the McCain camp looked silly embracing in the first place when they could have just let the guy flame out on his own."

    The Low Road Reply:
    "At least his wife's cover wasn't blown, severely damaging her career, (arguably treasonously) endangering undercover agents, and destroying our line of info on Iran's nuclear program over an article calling BS on an obvious lie. 'Cause that's the kind of stupid thing you'd never expect security-conscious conservatives to do!"

    --
    If it's for-profit but free, you're not the customer -- you're the product (e.g., the Slashdot Beta's "audience").
  234. Re:I didn't invent them or design them, just use t by swillden · · Score: 1

    Something about more sessions to track uses more cpu and memory. I'd imagine it has to do with the tables required to track the sessions.

    Routers don't track sessions, so more sessions has no effect on CPU and memory.

    Network Address Translators have to track sessions, but those are at the edges of the network. Network hosts (i.e. your PC and the one you're pulling bittorrent data from) have to track sessions, but again those are at the edges of the network.

    Your ISP's routers only have to track sessions if they're doing some sort of session-based QoS. Few ISPs do that, and none should.

    --
    Note to ACs: I usually delete AC replies without reading them. If you want to talk to me, log in.
  235. Re:A little extreme there, don't you think? by ArhcAngel · · Score: 1

    By comparing it to Netflix wouldn't I have to fill out a form of what web sites I want to browse to and if the site that's highest on my list isn't "available" I'll be redirected to a site lower on my list?

    --
    "A person is smart. People are dumb, panicky dangerous animals and you know it." - K
  236. True but awful. by Valdrax · · Score: 1

    So, in other words, people complaining about BitTorrent users overutilizing the network should read their contract, see there's no minimum guarantee of service or line speed, and get stuffed instead of trying to bully other people into using the network in ways that would make life more convenient for them?

    Despite being a heavy BT user, I can't feel anything but horror at that line of thought because that line of thinking is behind every single tragedy of the commons situation EVER.

    "There's no law saying that I can't."
    "It's my land, so I'll do what I want with it! Don't you tell me what to do with it."
    "I don't care about people downstream; I'll do what I see fit to do with MY water."

    Et cetera. I mean, that's the situation as stands, but actually encouraging that line of thinking only encourages those on the short end of the stick to consume as much as possible to "get theirs." Pretty soon, it sucks for everybody.

    --
    If it's for-profit but free, you're not the customer -- you're the product (e.g., the Slashdot Beta's "audience").
  237. Re:A little extreme there, don't you think? by reddburn · · Score: 1

    Can you imagine signing up for a "3 DVD's at a time" plan from Netflix and then when you actually check out 3 at a time they start bitching up a storm because "You're hoarding the DVD's!!! None of the other customers will be able to rent any of them!!!". Of course not. Because like most industry's they understand that if you sell a capacity you better damn well be able to meet it.

    BUT... Netflix is notorious for "choking" customers who return DVD's too quickly. Basically, if you return a movie per day, you cost them more in postage than you pay for your monthly fee, and eventually, they start delaying your movies by a day or two, slowing down your "bandwidth" so that they don't meet the "capacity" they sold you.

    --
    "Those who believe in telekinetics, raise my hand" - Kurt Vonnegut, Jr.
  238. ISPs brought on the Users' nuclear option? by Ungrounded+Lightning · · Score: 1

    UDP senders don't know when they're flooding the connection, so they just keep doing it. A TCP stream would back off to try to be fair, but your UDP stream is just going to keep on blasting at full speed.

    If that's the way that it's implemented.

    But UDP is just a pass-through of the underlying IP transport. You can build anything you want on top of it - including recreating as much of TCP (or an equivalent tuned better to your own usage patterns) as you want.

    However: Suppose they DO just ignore flow control and hammer away: This is being done as a workaround for ISPs who throttle Bittorrent traffic. So it looks to me like the ISPs just brought it on themselves.

    uTorrent looks to me like the users' nuclear option - a threat that creates the incentive to abandon war and come to some peaceful arrangement.

    --
    Bantam Dominique roosters crow a four-note song. Once you've heard it as "Happy BIRTHday" you can't NOT hear it that way
  239. Re:A little extreme there, don't you think? by drsmithy · · Score: 1

    That's half-true. The power company MUST meet peak demand, as well the rest of the electrical system. You can't say to people "sorry, you won electricity tonight because your neighbor is consuming too much power". That's absurd and ridiculous.

    Say what ? That's EXACTLY what happens - when power companies can't meet demand you get brownouts and blackouts (which may or may not be planned and scheduled).

  240. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    Don't even pretend that most bit torrent traffic is legitimate and legal. For every Linux DVD image distributed by bittorrent, there is probably dozens of times that much data in blatantly bootlegged content being distributed.

    Assuming you're right: So what? You're claiming that legit activity is the minority; I noticed that you didn't claim legit activity doesn't exist at all.

    So.. what to do about the legit BT users? Your solution appears to be: kick them off the 'net.

  241. Re:A little extreme there, don't you think? by Ex-MislTech · · Score: 1

    They do not have this problem in the top tier countries for
    internet access, we have fallen almost out of the top 20
    here in the USA.

    To me it is pathetic, but the reason is greed.

    We can run DWDM lines between all the major cities,
    and have more bandwith that we can possibly use.

    http://en.wikipedia.org/wiki/DWDM#WDM_systems

    1.6 Tera bit over a single fiber pair and it has been
    kicking around for several years, with proof of concept
    in the 1970's.

    Most of the fiber in the ground is Dark Fiber:

    http://en.wikipedia.org/wiki/Dark_fiber#Dark_fiber_overcapacity

    We don't have a resource problem, just like the corrupt and
    crooked high bonus financial thieves, we have a greed problem.

    The bent over shaved sheeple also were sold a load of manure
    being told we would give 200 Billion in Tax dollars for
    an upgrade to the system and we got the shaft.

    http://www.tispa.org/node/14

    That is right, we paid the evil slimy bells 200 Billion in
    US tax payer money and they ran off laughing and gave us nothing.

    They decided to cheap it and run DSL over existing lines
    and give us a sub par product that did not even meet half
    of what was spec'd and they slow rolled it out to us.

    They also committed sabotage against other companies trying to
    use their lines to get DSL in faster than they wanted it put in.

    Greed is job #1 in the USA.

    And that is why we are about to fall out of the top 20 on
    net access world wide when we should EASILY be #1.

    --
    google "32 trillion offshore needs IRS attention"
  242. Re:A little extreme there, don't you think? by JackassJedi · · Score: 1

    At least where I live, there are special laws in existence guarding the transfer of mail, and they are *special* and as far I can tell *exclusive* to postal mail, and I'd think that the U.S. has similar laws. So no big surprise that there is nothing going on with your mail, but an ISP is obviously not bound to these laws.

    --
    Power corrupts the few, while weakness corrupts the many.
  243. Re:A little extreme there, don't you think? by i_ate_god · · Score: 5, Insightful

    That's equivalent to saying "here is some electricity, but you can only use it to power your stove. If you use it for your air conditioner, you're violating our ToS and we'll cut you off"

    It makes absolutely no sense.

    --
    I'm god, but it's a bit of a drag really...
  244. Re:A little extreme there, don't you think? by merreborn · · Score: 1

    If you took the current ISP business model to any other industry you'd be laughed out of town, yet they get away with it.

    Cough...fractional reserve banking...cough

    Similarly, overselling is also common in shared web hosting (e.g. dreamhost and all the other $5/month hosting services) and telephone service. While nearly all cell plans allow for "unlimited night and weekend" calling (and some now even offer "unlimited everything"), and many POTS services allow for "unlimited local calling", were people to try to use these services for 100% of the time they theoretically could, we'd find that existing infrastructure wouldn't even remotely be able to handle it.

    Hell, airlines and hotels overbook all the time.

    Sorry, grandparent post, but overselling is in no way unique to ISPs.

  245. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    So pot-smokers and people who exceed the speed limit lead us down the road to anarchy?

    if so, I must take up weed and speed immediately.

  246. It's not criminal by jonaskoelker · · Score: 1

    After you sold it to me, it's simply criminal to then say

    No, that would be a civil lawsuit.

    (ianal, tinla, sorry to nitpick)

  247. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    Absolutely - The Gvt instpects every package that traverses their facility.

    Ultimately, consumers are expecting to get everything for nothing. The ISP's caused this in the early days of marketing, but the bottom line is that a 6 or 10 mbit connection that is rated for continuous usage is well beyond what most individuals are willing to pay.

    The job of the ISP is and always will be to smooth the peaks and valleys of demand so that it will fit onto the smallest amount of upstream bandwidth. Routers and pipes are very expensive. The goal is to minimize the expense and spread this across many customers. Due to technology, you are getting much greater individual peak capacities, but the aggregate capacity has not grown nearly as much.

    If you really want a constant 6Mb pipe that will run at full capacity 24x7 and you live in suburban america - you should be prepared to pay $1500 to $2000 per month. Consumers are responsible for this state of affairs just as much as they are for Detroit. Everyone is complaining that Detroit hasn't invested in high-mileage technology, but 24 months ago, how many people voted for an SUV instead of a Corolla? The big 3 followed the money. The same has happened with bandwidth.

    So, nearly 100% of .torrent traffic is piracy and oddly enough - an ISP can get sued for NOT stopping it, or it you hold up medical data, or if you interupt someone's 911 VOIP call. ISP's must have the ability to shape traffic. Finally, any legitimate use of .torrent (Like Blizzard.net) is a terrific use of the technology and operates on bursts like any other legitimate stream.

  248. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    The USPS reserves the right to inspect mail... sorry.

    http://www.usps.com/websites/depart/inspect/usc18/

  249. Re:Well Duh by akozakie · · Score: 1

    Because I'm a bit egoistic, like most people, except fanatics? I don't use BT, although I do see the value in it - I just don't really need it. As long as it uses TCP it doesn't cause me much harm. I think arbitrary caps on a protocol are not ethical and a breach of contract, so I side with BT, even if some of the uses are disputable (IP law is blown way out of proportion, harming fair use, but there is something wrong in getting everything for free on the day of release). Maybe I could get a slightly better connection if TCP BT was capped, but I'm not willing to support this solution for ethical reasons. But in an arms race you have to look out for collateral damage. UDP in BT will affect my daily, TCP-centric use of the net. Why should I support that?

    This is actually important. If Joe Sixpack starts seeing its connection slow down to a crawl, hears that BT is the cause and sees a dramatic change after strict UDP caps are introduced, then instead of not caring, he will be against Beat-Tow-End, or whatever that thing is. What then?

    It's hard to side with protesting masses, when they burn tires right under your window. BT just rolled out the tires in all corners of the Internet and is looking for matches. Yes, it will be noticed by those who don't use it yet. No, they will not be supportive.

  250. Re:Well Duh by Anonymous Coward · · Score: 0

    "Don't meter then. Sell them a realistic line speed."

    Great...Now we are going to have to pay more to steal things for free!

  251. Re:A little extreme there, don't you think? by FredFredrickson · · Score: 1

    I'd pay extra for the guaranteed allotted bandwidth.

    --
    Belief? Hope? Preference?The Existential Vortex
  252. Re:A little extreme there, don't you think? by SerpentMage · · Score: 1

    Interestingly enough you are actually defeating your own argument....

    You see you can connect an air conditioner so long as it has been verified to only consume so much amperage.

    If you want to use an air conditioner that uses 200 Amps, you can bet your ass that the electricity company will come and visit you quite quickly. They will ask, "ok so why are you using 200 Amps?" What gives. And if you say, "none of your business", they will reply, "ooops sorry no electricity for you..."

    --

    "You can't make a race horse of a pig"
    "No," said Samuel, "but you can make very fast pig"
  253. yeah yeah by Allnighterking · · Score: 1

    I'm sorry but the "Bittorrent (or video, or pr0n) is going to kill the internet" BS is touted in the US about as often as Wall Street Hit's up Washington for their allowance. I don't mean to troll here but honestly I'm growing weary of the FUD.
    To the ISP's of the world. If your tubes fill up, Build/Buy/Design bigger ones. (Oh and I don't want to hear about how large the US is, Canada is larger has more space between cities and does a better job of getting true broadband to people than we do.)
    Perhaps we would be better served by trying to find ways to accommodate the uses of the net, instead of spreading fear, and sticking our heads in the sand, while the rest of the world passes us by.

    --

    I'm sorry, I'm to tired to be witty at the moment so this message will have to do.

  254. Re:Well Duh by kaizokuace · · Score: 1

    If using UDP on BT will slow the rest of the nets to a crawl I don't want that either. There is a simple answer. BT doesn't have to resort to such tactics if the ISP's stop their dirty practices. All they have to do is stop. They are the oppressors in this situation. Users are just fighting back in whatever way they can. It's either fight or give up. Backing people into a corner is never a good idea. It makes them do things out of desperation.

    --
    Balderdash!
  255. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    If everyone gets to pick and choose which ones they want to abide by and not, then that becomes anarchy

    Actually, during the earlier years of the internet, this was exactly what we had. And it worked great.

  256. Pay nothing! ;) by jonaskoelker · · Score: 1

    If my ISP is selling me unlimited internet and they decide not to deliver, I want a rate cut.

    I think you should argue that you should pay for the share you're getting. If you get bandwidth limited by a constant k, but paid for unlimited bandwidth, it would only be fair to pay a limited part of an unbound whole:

    lim_{n \rightarrow \infty} \frac{k}{n}

    (i.e. 0)

  257. Re:Imagine: by FredFredrickson · · Score: 1

    Lies! You know a girl!?

    --
    Belief? Hope? Preference?The Existential Vortex
  258. Re:A little extreme there, don't you think? by Dallas+Caley · · Score: 2, Interesting

    I didn't realize i was griping, but i'll address your points one at a time here:

    Commercials yes i realize they make money from the commercials, why don't they just make their own torrents which include commercials? Personally i wouldn't mind a bit, it's not the commercial-freeness of the shows i see online that i like, it's that i can get an entire series all at once and not have to worry about missing an episode.

    No TV/Radio/Internet without advertizing? I agree on the TV and the Radio, but i pay for my internet with cold hard cash, without advertising, there may be less content, but advertising has nothing to do with my internet connection, or are you saying that they subsidize the internet with advertising dollars that they make from cable?

    Higher Prices yes, perhaps for some the prices will be higher, however if they were to offer many tiers of bandwidth then the prices might actually be lower (assuming that all programing and internet were through one connection) Here's an example. i use an average amount of bandwidth, and watch relatively few shows on cable, so adding the cable shows to my internet bandwidth would not really affect it much, for others however, they might not use the internet much and instead chose to spend countless hours watching some inane completely mindless utterly ridiculus cable programming (such as ESPN) for them, adding the cable would drastically increase their bandwidth and therefore they would have to pay more for it.

    Other countries? first, i mentioned absolutely nothing about other countries, but what you say is probably true, and the reason for it is likely that the technology originated in this country therefore since it's been around awhile we now have an antiquated system whereas newly connected countries can put the highest quality systems in right from the begining. its the same reason why there are more cell phones vs landlines in Iraq than there are here. it costs money to change the systems, but at some point you have to do it if you are going to remain competitive.

  259. Re:A little extreme there, don't you think? by i_ate_god · · Score: 2, Interesting

    I don't know where you live, but I can use electricity any way I want, how ever much I want.

    The limitations are not from the electric company, but the buildings own infrastructure. Glass fuses are pretty old school. Probably not a good idea to have 3 computers plugged into the same outlet. But if I decide to run my own mini datacentre with AC and humidity control, in my own apartment, the electric company can not say anything.

    A sudden spike in electricity usage is also not grounds for termination, but it can be grounds for a search warrant due to marijuana hydroponics, but that mostly applies to homes. And even then, if police discover you growing tomatoes instead, there is nothing the electric company can do.

    Of course, if you're running a hydroponics growing operation, regardless of what you're growing, your electric bill will be pretty high. But hey, if I transfer 500gb of data in a month, my internet bill should be kinda high too.

    I think the trick here is to find the right balance between dollars and bits and turn the internet into a utility. $1 / gigabyte is NOT a good balance. $0.10 / gigabyte might be. That's $50 on that month if I downloaded 500gb.

    These are numbers pulled out of my ass here, but in my non-expert opinion, $0.10 to $0.20 / gigabyte of data transferred seems like a good rate, maybe ontop of a small set monthly rate for speeds. $5/month for 3mbps, $10/month for 8mbps, + $0.10/gigabyte transferred.

    That seems fair to me.

    --
    I'm god, but it's a bit of a drag really...
  260. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    Have you heard about banks? You are entitled to the amount of money written under your name in the bank. The bank will have no problem if some people will try to take a large portion of their money, but if many will do it it will collapse.
    I've never heard of banks being laughed out of town...

  261. MOD PARENT UP by Anonymous Coward · · Score: 0

    Good utility analogy. It's time to stop pretending bandwidth is not a utility.

  262. Re:A little extreme there, don't you think? by lgw · · Score: 1

    On the upside, I just fininshed my month of "one extra DVD-at-a-time" thanks to the settlement.

    Netflix just needed to update thier customer agreement. If they had a clear rule like "if you send a DVD back the same day you get it, we'll pretend we didn't receive it until the next day" then they would have avoided the complaints and lasuits.

    This is the problem wit the ISPs too, of course: for the most part, they won't tell you what the rules are.

    --
    Socialism: a lie told by totalitarians and believed by fools.
  263. Re:A little extreme there, don't you think? by riceboy50 · · Score: 2, Insightful

    Does that give the Post Office the right to screen my mail and packages for things it considers not worthy of delivery? The real problem is the way the ISPs are selling their service. It needs to become utility pricing $10/Gb or something similar. All the other utilities manage to price their service based on usage, it's time for the ISPs to step up.

    --
    ~ I am logged on, therefore I am.
  264. hmm by masshuu · · Score: 0

    I thought that UDP had less overhead than TCP, so how is it worse, exactly, the article is very vague. If the ISPs Can't supply the bandwidth they have on the label, then its there fault, not the application developers fault, that the rest of the users cannot access the internet? Sure they will need to use more money, but it wouldn't hurt anyone except the CEO if they invested more into bandwidth.

    --
    O.o
  265. Re:A little extreme there, don't you think? by lgw · · Score: 1

    That is right, we paid the evil slimy bells 200 Billion in
    US tax payer money and they ran off laughing and gave us nothing.

    C'mon now, that was just a proof-of-concept excercise for the bailout.

    --
    Socialism: a lie told by totalitarians and believed by fools.
  266. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    Of course, your post office argument is invalid as well...

    OP suggested that anyone caught using uTorrent with the UDP setting turned on should have their internet disconnected. While that's probably a little bit extreme, it doesn't correspond to your argument about the post office opening packages. OP isn't suggesting that the ISPs run DPI on the packets. More accurately, it would be checking the "shipping label" - who's sending it, who is it being sent to, and how is it being sent. That is significantly different from looking at the contents of the package itself.

  267. BitTorrent calls Register report "utter nonsense" by Ian+Lamont · · Score: 2, Informative

    BitTorrent claims it is actually trying to reduce congestion.

  268. Re:Well Duh by stonecypher · · Score: 1

    Ask your friends in Phoenix or Las Vegas about their water situation. Yes, they pay for what they get, but there's also a sort of required community baseline behavior to not overload the resource itself.

    --
    StoneCypher is Full of BS
  269. Re:A little extreme there, don't you think? by BeardsmoreA · · Score: 1

    And that doesn't happen in civilised countries, basically, ever (short of storms bringing down lines). What kind of government would survive if it allowed 'brownouts'?

  270. Re:A little extreme there, don't you think? by Sancho · · Score: 1

    Commercials yes i realize they make money from the commercials, why don't they just make their own torrents which include commercials? Personally i wouldn't mind a bit, it's not the commercial-freeness of the shows i see online that i like, it's that i can get an entire series all at once and not have to worry about missing an episode.

    Because they'd get nowhere near the exposure. Advertisers want specific people to view their ads. It's not generally the people who would download the ads for entertainment.

    No TV/Radio/Internet without advertizing? I agree on the TV and the Radio, but i pay for my internet with cold hard cash, without advertising, there may be less content, but advertising has nothing to do with my internet connection, or are you saying that they subsidize the internet with advertising dollars that they make from cable?

    Most websites make revenue from advertising. No advertising, no revenue, no website.

    Higher Prices

    They're effectively doing that with bandwidth caps and penalties. And people are complaining to high heaven.

  271. Re:A little extreme there, don't you think? by nrlightfoot · · Score: 1

    Well, normally not, but if you start shipping thousands of boxes full of lead bricks to Alaska in priority mail flat rate boxes, they would put an end to it eventually.

    --
    what sig?
  272. Uninformed Question by Arancaytar · · Score: 1

    By "reducing the value of bandwidth", do they mean "cutting into our profit margins by actually using the bandwidth that we only promise because we are sure you won't use it"?

    Because screw that.

  273. Re:A little extreme there, don't you think? by Al+Dimond · · Score: 1

    Did the ISP really give you 10mbps? Can the ISP even guarantee you that?

    They can't, and so they're limiting users so they can guarantee a reasonable level of service to everyone without raising prices.

    Before you cry about what they advertise and sell to you, try reading the terms and the fine print, not just the big stupid number. They're almost certainly not selling you a constant 10mbps pipe.

    Before you say you're being victimized by your low-usage neighbors, imagine a truly fair Internet billing scheme: in addition to a low general periodic charge people are charged per bit, probably with some bits more expensive based on time of day. Maybe we come up with a pie-in-the-sky way to request low-latency packets and charge more for them, too. This way you as a heavy P2P user would probably pay less per-bit by using the cheapest times possible, but your overall bill would still be a lot higher because you use the network more. Currently Grandma down the block (assuming her computer isn't in a botnet) is subsidizing your torrents.

    Now, I think a "fair" scheme like this would have some negative effects: the clamp-down on people and companies doing innovative things and contributing a lot to the Internet community is the biggest one. Another is that people that get viruses or otherwise wind up downloading a lot could wind up with enormous bills, and the effort spent disputing and explaining them would be unjustifiable, considering that the subsidizers aren't the ones threatening to leave. So I don't exactly recommend anyone implement this idea.

    I might suggest to heavy P2P users that if they want to leave their computers on all day generating Internet traffic that they ditch their crummy consumer-level ISP. They're basically using commercial levels of traffic, so if they want commercial-grade service guarantees they should choose their ISP accordingly. More expensive? Absolutely. You get what you pay for.

  274. The big problem: DNS by Brett+Glass · · Score: 1

    uTP was explicitly stated -- by its developers -- to be an end run around providers' reasonable network management practices, and Richard is absolutely correct when he notes that it could cause severe network problems. In fact, Ricard understates the case, because he neglects to mention one extremely important point. By switching to UDP, BitTorrent will not only compete with VoIP and some video and audio applications but also with DNS. This could well be catastrophic, because DNS (domain name service), as ISPs know all too well, is a "critical path" protocol in virtually every application. If DNS is slow, EVERYTHING ELSE that users do will also be slow. Remember, most network applications, including Web browsers, have to stop and wait -- unable to do anything else -- until they resolve one or more domain names. So, they'll hang frustratingly if DNS packets are dropped due to congestion. And what underlying transport protocol does DNS use by default? UDP. (It can use TCP as well; however, it does so if, and only if, it has a lot of data to transfer. And TCP, due to its complex handshaking and "slow start" flow control, is much less efficient and much slower.) So, what we're talking about is not just congestion but sand in the gears of the entire Internet. Also, because uTP does not conform to any explicit congestion management protocol that could detect congestion BEFORE packets are dropped, the only way it would be able to detect congestion in the network would be after packets were dropped. Which means that by the time it did anything -- IF it did anything -- to mitigate the congestion it caused, it already would have damaged the network. Finally, do you actually trust P2Pers -- who already, in the vast majority of cases, are brazenly engaging in illegal activity -- to be courteous to anyone? There's no honor among thieves, folks. YMMV, but personally I wouldn't want to be on the same cable segment with someone using this new version of BitTorrent.

  275. Re:A little extreme there, don't you think? by Mista2 · · Score: 1

    The other advantage is I don't have to wait for the local broadcaster to pich up a show and decide to screen it when I am not home.
    The downloads I get are better quality than the terrestrial coverage I can get, and I download over night and watch when I want to in the week, or on my phone when catching the train to work, etc.

    This way I never have to worry about accidentally catching an episode of Suvivor when what I was really looking for was Mythbusters. 8)

  276. Re:A little extreme there, don't you think? by Renraku · · Score: 1

    It makes plenty of sense.

    You're subject to be cut off by your power company if you use too much power. For example, running large motor devices for a long time will cause them to cut you off, because your circuit and your neighborhood's circuit probably wasn't set up for you to be running large and very high power demand devices. There have been people cut off for running machine shops, plant growing operations (not necessarily for illegal substances..), etc.

    The reason it isn't protested about is that it happens to so few people.

    If everyone used the maximum amount of power that their houses could support, the power infrastructure would melt down. There's simply not enough electrons or metal.

    Moving to a pay-per-demand system wouldn't be a bad idea, however, it would be abused. You'd end up paying Aussie bandwidth prices for a helluva lot smaller amount of bandwidth than you'll get today.

    --
    Job? I don't have time to get a job! Who will sit around and bitch about being broke and unemployed then?
  277. Re:A little extreme there, don't you think? by dacut · · Score: 2, Interesting

    Last I checked, the USPS still asked if you were shipping anything dangerous, flammable, or perishable. They also employed a team of postal inspectors to handle cases of fraud, abuse, and other illegal activities taking place in the postal system.

    So, yes; they do have the right to screen your mail.

  278. Re:A little extreme there, don't you think? by riceboy50 · · Score: 1

    Well, this would be akin to opening all my mail and deciding that certain things should not be delivered because they didn't feel like it. Just give up; it's a stupid practice.

    --
    ~ I am logged on, therefore I am.
  279. Re:A little extreme there, don't you think? by BeeRockxs · · Score: 1

    Not in my country. We don't have the regular blackouts you seem to have in the USA.

  280. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    You have chosen to live in a society and by extension have chosen to live by society's rules.

    Says who? nobody picks the life they're born into.
    With the world in the state it's in, it may take as long as 29 years to be able to afford to move out of the country you're forced to live in.

    If when I was born I had a chance to read and understand all the laws in every country, and then got the choice to go and live where I wanted, I wouldn't have stayed here.

    But you don't. In this day and age, there's countless people that can't stand how things have "always been".

  281. Re:A little extreme there, don't you think? by rdnetto · · Score: 1

    There also aren't any stupid copyright restrictions. I live in Australia, and most of the services I've tried (paid or free) give some notice about being unable to access the video because I don't live in the USA. Australia has several copyright treaties with the US which basically makes their law valid here, but they still aren't accessible.
    OTOH, BT is accessible anywhere, and can be easily viewed on any computer, MP4 player or streamed to a TV by an Xbox, etc.

    --
    Most human behaviour can be explained in terms of identity.
  282. Re:A little extreme there, don't you think? by HornWumpus · · Score: 1

    You've got physical limits in the wiring almost certainly less the 200A.

    Try to hack on those limits too hard and you bet your ass you will get cutoff.

    Data isn't the same as power, the analogy only goes so far.

    As I understand it most 'Hogs' are given the chance to upgrade to 'business class' service and refuse.

    TOS agreements should be clear about hogging and how much discretion the ISP has. Just like power rate tiers should be clear in the power companies TOS.

    --
    John McAfee 'It was like that time I hired that Bangkok prostitute; to do my taxes, while I fucked my accountant'
  283. Re:A little extreme there, don't you think? by truesaer · · Score: 1

    Terrible analogy. Electricity is metered. There's a reason most utilities are metered. It seems like no one on slashdot understands that it fucking costs money to provide a utility. You can't have a reserved 10Mbps connection for fifty bucks. You just can't, if everyone was guaranteed their full bandwidth simultaneously internet access would rise by an order of magnitude.

    So overselling capacity is essential to the model, assuming you don't want to pay hundreds of dollars a month for your internet connection. Another option would be to meter usage, this would put an appropriate market force in place. But when Comcast tried this in a test area they were roundly condemned.

    Bottom line, there is a choice...oversold capacity, metered usage, or you pay a fuckton more for a reserved slice of bandwidth.

  284. ISPs asked for this by Dan541 · · Score: 1

    The ISPs started this war, I say bring it on.

    --
    An SQL query goes to a bar, walks up to a table and asks, "Mind if I join you?"
    1. Re:ISPs asked for this by vux984 · · Score: 1

      The ISPs started this war, I say bring it on.

      Its not a "war" you can win.

      The end game is simply getting your internet bandwidth metered. X$ for access to speed Y + Z$ per GB on a sliding scale. If you push the ISPs that's what they'll strike back with.

      Then they don't care if you blast your connection full bore 24x7; you'll be paying $4500/mo for the privilege though. Hell, they'll even upsell you to a partial T3 and offer you an up-time SLA.

      The ONLY reason they haven't gone that route already is that its too 'confusing'; customers don't understand bandwidth, so trying to explain how much they are using, or how much they need is difficult. And for the time being they aren't using what their metered caps would be anyway, so its simpler to just offer them 'unlimited'.

      But if push really comes to shove they'll simply meter it.

    2. Re:ISPs asked for this by Dan541 · · Score: 1

      My ISP throttles the connection once I reach my quota, so how am I going to get a $4500?

      --
      An SQL query goes to a bar, walks up to a table and asks, "Mind if I join you?"
    3. Re:ISPs asked for this by vux984 · · Score: 1

      My ISP throttles the connection once I reach my quota, so how am I going to get a $4500?

      1) Then your ISP has already 'won' the war.

      2) The bill will go up if/when you decide you don't want to be throttled at your quota.

    4. Re:ISPs asked for this by Dan541 · · Score: 1

      1) Then your ISP has already 'won' the war.

      How? I get what I pay for.

      --
      An SQL query goes to a bar, walks up to a table and asks, "Mind if I join you?"
    5. Re:ISPs asked for this by vux984 · · Score: 1

      How?

      By not being affected by anything, say, a torrent client might do, in order to acquire a greater share of bandwidth for itself than the ISP wishes to provide you.

      I'm not really suggesting that you in particular, by getting what you pay for, have somehow "lost" the war... but simultaneously, you have nothing to gain from the 'arms-race' you invited when you said:

      "The ISPs started this war, I say bring it on."

      And anyone one who does have something to gain, will ultimately lose. And if your ISP decides tomorrow to start giving you 'less than think you paid for', changing torrent clients etc isn't going to help your cause. Your only option will be to either pay for increased access or switch to another ISP...(of which in most places there are very few).

  285. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    Clearly you've never rented with utilities included.

  286. Re:A little extreme there, don't you think? by dacut · · Score: 1

    Ah, you won't get any disagreement from me about the ISP aspect -- they have no business inspecting the packets and should be taking a hands-off approach. They should be clearly setting the terms of the service (peak and average bandwidth) and throttle or reject usage above this limit.

    I was just saying that the post office isn't necessarily a good comparison. They certainly should be opening/rejecting anything which will cause physical harm to the carriers or recipients (letter bombs and the like). I'm less pleased with the law enforcement allowances (that's a loophole which can be too easily exploited), but it's there nonetheless. (And, I have to admit, the postal inspectors are rather successful at their mission. They keep a low profile and use discretion, which is a lot more than one could say about many other law enforcement agencies.)

  287. Re:A little extreme there, don't you think? by CaptainCarrot · · Score: 1

    The post office is a private industry, not the Government.

    It's an agency wholly owned by the United States Government, and the top management are all Presidential appointees. In what sense is that "private industry"?

    --
    And the brethren went away edified.
  288. Re:A little extreme there, don't you think? by fru1tcake · · Score: 1

    That's equivalent to saying "here is some electricity, but you can only use it to power your stove. If you use it for your air conditioner, you're violating our ToS and we'll cut you off"

    No, it's more like saying, "Here's some electricity and some water, use it for what you like, as long as it's not illegal. If you use excessive amounts of water, we might investigate you for breaching water restrictions*. If you use excessive amounts of water and electricity, we might get suspicious that you've got a hydroponics setup and tip off the police."

    If the terms of service say you can't use the service to do certain things (whether for legal reasons or otherwise), and you DO those things, you're violating the contract you signed. If you want to run a server, pay for a business plan that allows you to.

    You do not have the right to do whatever you like. Read the fine print.

    *There are currently water restrictions active in most states of Australia - and rightly so, considering the severity of the drought we're in.

    --
    It's not a bug, it's a lepidopter!
  289. Back to the student bench by Anonymous Coward · · Score: 0

    Using UDP in BitTorrent can't make that much of a difference.

    It's only natural to move BitTorrent to UDP, considering that the bulk file transfers don't have the "session" nature, and also that Bittorrent already has to deal with transmission errors. Let's cut the fat...

    The main problem with TCP is managing the memory of the non-ACKed transmitted packets, and the flow control is intended more to share the machine's connection with other TCP connections, than anything else. TCP doesn't know about the Internet, about "congestions"... The "Congestion control" of TCP Reno, Vegas, etc, is more of a kludge than can and should be enhanced. Using UDP we can even create more conservative policies to prevent congestions.

    The bandwidth available to each machine is controlled by the gateways and routers, by the ISPs between the bitTorrent and Skype users, deciding when to drop the packets. The way routers can decide that, and consequently implement a certain QoS to its clients, does not depend on TCP or UDP use, the packets will be allowed and dropped just the same.

    Now think about this: if UDP had this problem, of taking up band irrestrictedly, it would not just cause havoc on the Internet, it would first cause problems to the other UDP connections in the machine itself!! If UDP really had no flow control at all, it would consume your own machine's bandwidth before causing a "congestion" problem way up in the network. Last time I checked, it's the OS who tells the programs when it is ready to receive a new package, and never the other way around. There is sure SOME kind of limitation to UDP in any OS, even if it's nothing as sophisticated as the Renos around.

    Flow control is not "congestion" control. What TCP has is congestion fear, and not control. It doesn't control it's fear yet... We need extra protocols to handle QoS properly, for the routers to tell the clients when are congestions going on the network... IPv6, MPLS and RSVP now!!! The ISPs need to put their money on these new technologies, and not blame the users to use the network exactly the way they are supposed to: just using as much as they can. The routers can drop the packets whenever they like, and that's they way TCP/IP works... Enforcing QoS up in the middle of the network, and not asking the users please to hold on.

  290. Re:A little extreme there, don't you think? by jhol13 · · Score: 1

    You are right, it is not up to me. But it certainly is up to the ISP.

    I cannot see why ISP should (or would) not limit high users more than low users. Therefore those who use it for VoIP should not even notice if there is congestion, after all VoIP takes very little bandwidth.

    Your buffet analogy is good - I am certain the owner does think those who eat little and fast are better customers than those who eat several hours and a lot. As I am certain ISP thinks about those who turn on their ADSL routers only rarely and use it very little.

    It is interesting to notice the "capitalism" point, because I personally do not fully believe in it. That could (therefore would) lead to the situation where one VoD company would get good bandwidth (on some ISP) and the others would get shitty.

  291. Re:A little extreme there, don't you think? by zgornz · · Score: 1

    I agree that it makes no sense, however the electric company used to do exactly that:

    "When electricity was first introduced into the household, it was primarily used for lighting. At that time, many electricity companies operated a split-tariff system where the cost of electricity for lighting was lower than that for other purposes. This led to portable appliances (such as vacuum cleaners, electric fans, and hair driers) being connected to the light fitting."

    http://en.wikipedia.org/wiki/Domestic_AC_power_plugs_and_sockets

  292. just a thought ... by Anonymous Coward · · Score: 0

    UDP and IP multicasting go well together for transmitting the same data to many hosts ... couldn't it help reduce the torrent traffic after all?

  293. Re:A little extreme there, don't you think? by multisync · · Score: 1

    I cannot see why ISP should (or would) not limit high users more than low users.

    Well, see, that's a different thing than traffic shaping. If you are arguing in favour of caps, I am in agreement with you. I have no problem with an ISP - or a restaurant owner - saying you get this much for that amount. I just don't want my ISP saying you can't use a certain protocol or you're getting throttled.

    They can even say only so much during certain hours if they like. As long as they spell it out clearly in their contract exactly what you are paying for that's fine, and fair.

    You talk about VOIP, and how that should be looked upon favourably because it uses little bandwidth. Well, suppose your ISP (who may also be a Telco in a lot of cases) offers a VOIP service as a value add? And they decide to "shape" your Skype traffic, so the QOS is lousy compared to their competing service, to make it more attractive. Is that also "up to the ISP?"

    If we allow them to throttle our traffic based on content or protocol, we've traded our free and open Internet for AOL.

    --
    I don't care why you're posting AC
  294. Re:Well Duh by socsoc · · Score: 1

    This would be mitigated if ISPs blocked port 25. Although I am not in favor for a stringent no exceptions policy...

    Imagine if you had to ask for port 25 to be unblocked for you... Most of the people making the request would know how to handle their machines, but then again, but it's a slippery slope (on the other hand, Grandma certainly does need some help securing her Windows box).

  295. Re:A little extreme there, don't you think? by volkris · · Score: 1

    It may make absolutely no sense... but it's their ToS, and their right to be as eccentric as they wish, just as it's your right to use the electricity for senseless things if they don't ban it.

    They get to propose conditions on the agreement, and we get to refuse the agreement if the conditions are too dumb. Such is the nature of free exchange.

  296. Re:A little extreme there, don't you think? by volkris · · Score: 1

    The post office moves your property around.

    The ISP shuttles around signals which cannot be owned.

    Not to mention that a private postal system would have every right to require the ability to inspect the contents of every package as part of the agreement. Don't like that arrangement? Find yourself a different postal system.

    Same with ISPs.

    It's their business and their property. Who are you to tell them what they can and cannot do with it while expecting preservation of your own property rights?

  297. Re:A little extreme there, don't you think? by billster0808 · · Score: 1

    You cannot just block BT because a few also use it for piracy

    What about if the vast majority of people use it for piracy?

  298. Re:Well Duh by billster0808 · · Score: 1

    Wow, that's like taking hostages, and saying it's the cop's fault when you shoot them.

  299. TCP sessions don't matter by Cato · · Score: 1

    The number of TCP sessions *makes no difference at all* to an ISP - assuming they are not doing deep packet inspection of course. Apart from that case, all IP packets are routed, with no inspection of the TCP header, so there's no way the number of sessions could make a difference.

    If you want to use no. of TCP sessions as a weak indicator of P2P activity, go ahead, but BitTorrent developers will develop workarounds (maybe this is one of them) - ultimately everything may end up as encrypted UDP traffic that's really hard to traffic shape even using DPI.

    I generally agree that you get what you pay for - there are shared pipes all over the place, so if people use BT 24/7 and fill their DSL/cable access link, they should expect to pay more than people who simply do email, surfing and occasional video clips. Traffic shaping and usage caps are just different approaches to making behaviour fit the costs of running the network.

  300. Great analogy, chief by svunt · · Score: 1

    Yes, I do have 10,000 sheep. But this land is common, I have a right to let them all graze there if I want to.

    Sorry, your internet connection is part of the commons? Mine is paid for privately, and I can graze all the fuck I want on the paddock that I rented FOR GRAZING.

  301. Re:Well Duh by kaizokuace · · Score: 1

    not quite. ISP's arent the police and shouldn't have the powers that come with policing citizens.

    --
    Balderdash!
  302. Re:Well Duh by RMH101 · · Score: 1

    Just out of vicarious interest, how long would you expect downloading an 800MB, heavily-seeded DVD rip to take at those speeds?

  303. Re:Imagine: by Hucko · · Score: 1

    shame the ones I know dont dress like they do. Lowest common denominator -- what ever gets them by.

    --
    Semi-automatic amateur armchair Australian philosopher; conjecture ready at any moment...
  304. Re:A little extreme there, don't you think? by drsmithy · · Score: 1

    And that doesn't happen in civilised countries, basically, ever (short of storms bringing down lines).

    You might want to expand on "civilised countries" here, so we can tell how much of an ass you're being.

    What kind of government would survive if it allowed 'brownouts'?

    Electricity supply is privatised (typically with negative results) in many countries. Hardly something the Government has a huge amount of control over.

  305. Disclaimer: I am an ISP Network Engineer by kieran · · Score: 1

    Bandwidth is and always has been priced according to average usage. No ISP in the world has ever had enough transit to cover the full bandwidth of even 25% of it's customer's total combined link bandwidth, and that doesn't mean they're ripping off the customer; it's simply indicative of the fact that customers do not need to be filling their link all the time in order to find it valuable.

    That said, the sky is not falling. If bandwidth demand goes up, ISPs will (and do) deal with by providing two options:

    1. Maximum total monthly downloads with per-Mb charging or a hard cut-off thereafter.
    2. Higher prices for unrestricted connections.

    Bandwidth gets cheaper every year and does so more quickly in the face of high demand, so whichever you choose it shouldn't be too painful.

  306. Re:A little extreme there, don't you think? by stars_are_number_1 · · Score: 1

    I understand your frustration and agree with you. However, have you ever had a commercial electric account? My experience with commercial electric has been that if you use the electricity in a certain manner...say, turning on three air conditioners at once, you will be pushed into a higher rate bracket because you are deemed a heavy demand on the system. I wonder if a system like this would work for ISPs and consumers alike?

  307. Their comments are moderated by upside · · Score: 1

    ... not real time. So at least 37 people posted before you and that's as far as the moderators had got since publication. Sometimes I have to wait overnight to see how others have responded.

    --
    I'm sorry if I haven't offended anyone
  308. Re:A little extreme there, don't you think? by pipatron · · Score: 1

    You have chosen to live in a society

    No, you're born into it, and randomly moving away isn't always an option.

    --
    c++; /* this makes c bigger but returns the old value */
  309. Re:A little extreme there, don't you think? by pipatron · · Score: 1

    when those 10 guilty persons set free cause suffering to countless other innocents

    When that happens we'll lock them up. What's so difficult with that?

    --
    c++; /* this makes c bigger but returns the old value */
  310. the free market by Anonymous Coward · · Score: 0

    will happily disconnect bittorrent using customers, as thats the most profitable path to take. For people like me, I'll simply lose internet due to lack of competition (that is the result of the free market in my location).

    All the isps need to do is to periodically disconnect the top one percent of customers based on bandwidth use.

  311. Re:A little extreme there, don't you think? by Real1tyCzech · · Score: 1

    *laughing*

    No, the Presumption of Innocence has nothing to do with the discussion above.

    Read for context next time. Here's a hint in case your scroll-wheel is broken:

    "You can't blame your wife for stabbing you in the face when you keep locking her in the bedroom."

    "Using your stupid analogy, this would be more like threatening to raze the entire city to the ground because no one intervened to stopped the wife"

  312. Re:A little extreme there, don't you think? by Real1tyCzech · · Score: 1

    So letting those "innocents" get hurt to protect *one* other is just the price those "innocents" pay?

    They'll just gonna shrug it off and pretend everything's OK?

    When we could have locked them up before hand, and had only one innocent suffer?

    Cute.

  313. Meltdown? How? by Anonymous Coward · · Score: 0

    There's no way ISPs are selling more (how is it called? Link width? Connection speed?) than they have, is there?

  314. The solution has been there for 10 years by Anonymous Coward · · Score: 0

    The technological solution has been there for 10 years already, the ISPs/vendors are just too lazy to utilize it. It's called DiffServ.

    All you need is to classify your traffic into 3 classes and use separate queues for them, with strict priorities:

    - High Prio - <= 1% of the end user's theoretical maxed out traffic
    - Medium - <= 10% of the theoretical traffic
    - Low Prio - the rest

    Games & VoIP would go into High Prio (Low Delay).
    Anything unqualified (Web browsing, e-mail, etc.) would be Medium (good enough for Interactive traffic)
    BitTorrent and big downloads would be Low Prio (Bulk).

    The traffic itself can be classified by the applications on the socket interface.
    You would be surprised to hear that some of it already happened even before DiffServ - eg. Telnet/SSH on Linux labeled it's traffic as Low Delay before ages.

    Anyway, the max. percentages can be easily enforced by re-labeling any user's traffic to a lower class if it exceeds the percentage on a daily/monthly average basis. So the end-users and application software vendors clearly have the incentive to comply and not to abuse the system.

    That's it, and you have the fastest possible delay for gaming, reasonable performance for browsing, and you can utilize the surplus resources for bulk transfers at virtually no effect to the other traffic.

    It's all old, available and proven technology, just start using it please...

    All it needs is ISPs wanting to cooperate instead of negligence.

    If we used Explicit Congestion Notification on top of it (also a technology that has been available for 7 years), there would be almost no congestion at all. All the pipes would be fully utilized, yes, but without congestion.

    Actually, instead of a technological solution a rather easy and fair business solution is also available - instead of capping the already existing unlimited users, offer a discount to the users who volunteer to be capped.

  315. Re:A little extreme there, don't you think? by Creepy · · Score: 1

    The only blackouts I've seen in ~20 years on the intertubes (since before it was a public network) was due to cable cuts, router or power failures, or routine maintenance (oh, and the two weeks I had no service after Northpoint disappeared overnight - incidentally, my part of the lawsuit was finally settled - 7 years later).

    This is all a bunch of fear mongering. The protocol isn't the issue, it's throttling it, and there's no reason you can't throttle UDP. In fact, UDP doesn't guarantee delivery, so if there's too much UDP on the fat pipes, just start tossing packets at random - who's gonna know (ok, if you do too many the WoW players might complain, but lag happens, right)? ISPs can start tossing packets for anyone abusing their network and if asked could claim the packets never arrived. It's not like there are records of UDP packets moving through a network.

    People have predicted the backbones would collapse for years and guess what? It's never happened (completely, at least - I recall one backbone had a failure for a couple of days, but I wasn't on that one, however some major sites were).

  316. Re:A little extreme there, don't you think? by Endlisnis · · Score: 1

    Your airline analogy breaks down when you think about constant traffic. For it to work, the airline would have to [only] sell monthly, "all-you-can-fly" tickets. You pay a reasonably low fee, say $100/month, and you can fly anywhere you want, anytime you want. It works fine if each of us fly once a year, but when some guy decides to fly back-and-forth to Australia each day, then they would have to say, "During peak travel times, you can only fly once per day/week/month" or something.

  317. Re:A little extreme there, don't you think? by neomunk · · Score: 1

    See, what you're not getting is that the choice to make a victim suffer (though that may not be the primary motivation) is the whole reason the act is criminal. By your standard, society as a unit should act criminally in order to prevent crime. Great folly lies along such paths, with the folly being completely obvious to anyone who remembers that authority figures are people with unpure motivations, just like the 'criminals' you're so worried about. And tell me, would you be willing to see your son locked up for life because of society's erring on the side of incrimination? Would you still feel safer?

  318. Re:A little extreme there, don't you think? by JoelKatz · · Score: 1

    Umm, no, that's not true. So long as you have 200 amp service, you can use 200 amps 24x7, any way you want.

  319. Re:A little extreme there, don't you think? by Real1tyCzech · · Score: 1

    The quote I replied to had no such reasoning behind it.

    "Better ten guilty persons escape"

    Keyword: Escape. They've been found guilty. In the context of the posts prior to that, the only logical assumption was that the poster intended nothing more or less than the release of all who have been found guilty, as an innocent may be among them.

    Such a suggestion is ludicrous, no mater how you spin it.

  320. Re:The client application can't know about congest by JoelKatz · · Score: 1

    You're just making that up, and it makes no sense. The "core of the Internet" can regulate TCP traffic and UDP traffic precisely the same way, by dropping packets. And that's exactly what it can and will do with no changes.

    The "core of the network" treats each packet as its own universe. It looks at the source, destination, and perhaps packet size and type of service, and that's it. It doesn't care if it's TCP or UDP.

  321. Re:Well Duh by neomunk · · Score: 1

    I know, right! The ISP hijacked the connection I was paying for, and got all upset when a way was found to get what was mine back.

    That IS what you meant, right?

  322. Re:The client application can't know about congest by George_Ou · · Score: 1

    I can assure you I am not making it up. Routers and other network devices typically don't drop UDP packets because UDP end points don't respond like TCP end points which halve their bandwidth whenever a packet isn't delivered. It's also hasn't been necessary to drop UDP packets because traditional UDP applications are typically small bursts of data or low/fixed bandwidth applications like VoIP and online gaming. Now this is all about to change when you get a huge bulk transfer application like BitTorrent which accounts for a significant portion of the Internet's traffic.

  323. Re:A little extreme there, don't you think? by Orion+Blastar · · Score: 1

    Hard to prove that, but even so it cuts out legit use of BitTorrent.

    --
    Remember, Slashdot does not have a -1 disagree moderation, and no, troll, flamebait, and overrated are not substitutes.
  324. Re:A little extreme there, don't you think? by Anonymous Coward · · Score: 0

    I'd rather have them use technology to solve a social problem, than use laws to classify it as something else completely.

  325. Re:A little extreme there, don't you think? by phoenix321 · · Score: 1

    If they say so clear in the contract, then so be it. I just have a huge problem with companies or people weaseling out of contracts they advertised and received good money for.

    If they can quantify their "reasonable use" clause to something both parties can agree on beforehand AND objectively measure afterwards in case of a dispute, fine.

    But spare us the ISPs that bet everything but the farm on their use patterns and then cry foul when they don't match the customer's.

  326. Re:The client application can't know about congest by JoelKatz · · Score: 1

    "Routers and other network devices typically don't drop UDP packets because UDP end points don't respond like TCP end points which halve their bandwidth whenever a packet isn't delivered."

    That's simply not true. Routers and other network devices typically treat UDP and TCP precisely the same.

    "It's also hasn't been necessary to drop UDP packets because traditional UDP applications are typically small bursts of data or low/fixed bandwidth applications like VoIP and online gaming."

    Nevertheless, they've dropped them the same way they've dropped TCP packets. They do this simply because there has not been (and still is not) any good reason to treat TCP packets differently from UDP packets.

    "Now this is all about to change when you get a huge bulk transfer application like BitTorrent which accounts for a significant portion of the Internet's traffic."

    Nothing will change. The traffic will be UDP instead of TCP, and routers won't care one way or the other, just as they never have.

    The only devices that will be affected are unusual "invasive" devices, such as those specifically used to throttle P2P.

  327. Re:A little extreme there, don't you think? by Alsee · · Score: 1

    The problem with bittorrent, is that it's MORE convenient than watching TV the old fashioned way.

    Chuckle. Yeah, I know what you mean.

    The problem with electricity, is that it's MORE convenient than eating dinner in the dark after cooking it over a firepit.

    -

    --
    - - You can't take something off the Internet! That's like trying to take pee out of a swimming pool.
  328. Re:A little extreme there, don't you think? by mzs · · Score: 1

    Two points:

    The ISP sees that you are accepting connections on port 80, assumes that is a web server, points to the 'no servers' clause in the T&Cs, and after a month they are no longer your ISP.

    When you look at the pattern of connections to port 80 for a web server vs a BT there are at least two glaring ways to quickly see that this is not normal web traffic so the "80 Hole" is not much of an effective disguise.

  329. Re:The client application can't know about congest by George_Ou · · Score: 1

    No, routers do not treat UDP and TCP the same. Richard Bennett is a network architect and I trust his assessment of the situation more than I trust your's.

  330. Re:Well Duh by mzs · · Score: 1

    And they have in very rural and metro areas but not as much as they should have in the rest of the country. So let's say in my opinion they are half to blame on this front.

    The problem is that p2p rapidly consumes all of the available bandwidth. Even if the capacity had been increased a thousand fold, in six months to a year we would be right back at the same problem where we were before.

    But I have seen people argue that they the average users would still use the same amount of bandwidth, but I do not think so. There would be more flash and streaming video on the internet. There would be more people using VOIP, NetFlix, downloading movies and TV shows from iTunes, the Xbox video market place, the PS3, and there would be more people downloading video games.

    Soon we would be right where we started where the average users would again be complaining that they not getting a fair share do to the massive increase of p2p bandwidth. The average users would no longer be content with simply email and web browsing when they had 'new improved faster internet' and would expect all those other things I outlined to work flawlessly.

  331. Re:Well Duh by mzs · · Score: 1

    UDP is a very bad protocol to use for mass transmission. There is no built-in feedback loop.

    Not having built-in congestion control does not necessarily make it a bad protocol for bulk transfer.

    I could see timestamps being used to figure-out latency and bandwidth instead of TCP window sizes changed based on packet loss. This could be much nicer for routers.

    Also with a simple approach one socket and UDP port could be used per client. This would make it a whole lot easier for the OS and NAT.

  332. Re:The client application can't know about congest by JoelKatz · · Score: 1

    Richard Bennett never said that Internet core routers do not treat UDP and TCP the same. You are misunderstanding what he is saying.

    I am not asking you to trust me over Richard Bennett. I am asking you to not misrepresent Richard Bennett's argument.

    *Your* statement -- "The client application can't know about congestion in the core of the network, so it breaks control at the core of the Internet where there's less management. If you read the article fully, this would have been apparent." -- is a misrepresentation of Bennett's argument. In fact, the client can know about congestion in the core of the network with UDP the same way it does with TCP, by inferring congestion when there is packet loss. TCP's congestion control is implemented by the endpoints, not the network core. (With the exception of ECN, but that's so rarely used that it doesn't really matter.)

  333. Re:The client application can't know about congest by George_Ou · · Score: 1

    Yes, he has said that UDP is treated differently than TCP, and it makes sense to treat them differently. I know the man we have spoken by phone and in person. It makes no sense to drop UDP packets since it doesn't produce a response from the end-points.

  334. Re:The client application can't know about congest by JoelKatz · · Score: 1

    The reason you drop TCP or UDP packets is not to produce a response from the end-points. It's because the link is congested and you simply can't carry all the traffic. Well-behaved applications, both TCP and UDP, respond to packet loss by reducing their bandwidth consumption.

    "I know the man we have spoken by phone and in person."

    Well, you've now set the bar impossibly high. In order to satisfy you, I have to refute a claim to which I have no access based on evidence and argument to which I have no access.

    The truth is, so long as a protocol layered on top of UDP detects congestion and responds with appropriate backoff, it will be just as Internet core friendly as TCP.

  335. Re:The client application can't know about congest by George_Ou · · Score: 1

    "The reason you drop TCP or UDP packets is not to produce a response from the end-points. It's because the link is congested and you simply can't carry all the traffic"

    You do it for both reasons, but the FIRST reason you do it is to get the end-points to voluntarily backoff first before you reach a point of crisis. That's the whole point of Random Early Detection which is to get the clients to backoff before the network gets completely saturated in which case really nasty things happen. Routers drop packets before they reach 100% congestion not to trim the bandwidth; but to get end-points to back down.

    There's another good reason to do this because it balances out the load between single-flow TCP applications. When a TCP end-point backs off to 50%, it's giving a new TCP flow a chance to take up the slack and speed up until the two TCP flows reach a state of equilibrium. UDP end points lack this behavior.

    As for Richard Bennett's claim that UDP isn't generally dropped by routers, this is the reason he is concerned about this change in BitTorrent. This will force routers to start dropping UDP packets just like TCP packets and it will have a bad affect on other UDP applications that have a good reason to use UDP e.g., they're low/fixed bandwidth or they only send short/small bursts of data which means they benefit by bypassing the overhead of TCP. Bulk file transfer applications shouldn't be bypassing TCP for UDP and even if BitTorrent is well intentioned, such a large change could be risky for the Internet. That's the whole point Bennett is trying to make.

  336. Re:A little extreme there, don't you think? by BlueStrat · · Score: 1

    The quote I replied to had no such reasoning behind it.

    "Better ten guilty persons escape"

    Keyword: Escape. They've been found guilty. In the context of the posts prior to that, the only logical assumption was that the poster intended nothing more or less than the release of all who have been found guilty, as an innocent may be among them.

    Such a suggestion is ludicrous, no mater how you spin it.

    Here's a wiki entry on the quote in question.

    http://en.wikipedia.org/wiki/Blackstone's_formulation

    You can agree or disagree with it, but it's a principle closely tied to the presumption of innocence in the US judiciary system. Benjamin Franklin was reported to have stated it as "it is better [one hundred] guilty Persons should escape than that one innocent Person should suffer". Bismarck and Pol Pot are said to have believed the opposite. I'll take good ol' Bens' version, thanks all the same.

    Cheers!

    Strat

    --
    Progressivism (aka US 'Liberalism'): Ideas so good they need a police/surveillance-state to enforce.
  337. Re:Well Duh by Anonymous Coward · · Score: 0

    There is nothing wrong with metering, having a plan capped at 5/15/20/50GB etc a month and having the speed reduced after that (to 64KB per second and with an option to pay extra for more GB of downloads at the plans usual speed) is what is generally done here in Australia.

    It works out better for both the ISP AND the customer as you pay only for what you require and don't subsidize those users who download vast amounts and the ISP can more easily determine how much bandwidth they need to add depending on how many new clients they have signed up under which type of plans (eg light or heavy users).

    This way the ISP can also not complain about the amount you have used as you have specifically paid to use that amount and so you don't end up with this ridiculous notion of trying to reduce the amount your customers are using.

    Advertising as Unlimited and then complaining about people taking you up on that offer is the ISP's fault and they need to stop doing this and set pricing levels at reasonable limits which obviously will increase as requirements go up.

  338. Re:The client application can't know about congest by JoelKatz · · Score: 1

    "There's another good reason to do this because it balances out the load between single-flow TCP applications. When a TCP end-point backs off to 50%, it's giving a new TCP flow a chance to take up the slack and speed up until the two TCP flows reach a state of equilibrium. UDP end points lack this behavior."

    You have this completely backwards. TCP endpoints can only detect congestion through packet loss on the connection. UDP endpoints are free to back off for *any* reason, including but not limited to packet loss.

    Because every TCP connection is basically independent, you cannot use information gained from one connection to backoff on another. With UDP you can.

    A UDP application can backoff as aggressively as TCP, less aggressively, or more aggressively. Nobody yet knows how BT will rig its backoff algorithm.

    They've hinted that it will backoff even more aggressively than TCP does, using congestion information from one connection to increase how severely they treat congestion information from other connections.

    They've also hinted that they'll rig BitTorrent to act *in* *total* much like as single TCP connection, rather than like hundreds. This is good for the user, as using BT won't make his web pages and games get 1/100th of his bandwidth but 1/2, like they should. But it's also good for Internet's core, as one BT client looks more like one connection than hundreds there too.

    "As for Richard Bennett's claim that UDP isn't generally dropped by routers, ..."

    I don't even see where Bennett claimed that. And I've counter-claimed that routers generally treat UDP and TCP precisely the same. I believe this is a mis-statement of Bennett's claim. Can you cite any public claim of his to this effect?

    I think Bennett was simply assuming that their motive was evil -- to get around congestion control -- rather than benign -- to fix a defect in TCP that it treats each connection as the distribution unit rather than each application. (Which is bad when an application with 100 connections tries to live on the same connection as one with two.)

  339. Re:The client application can't know about congest by George_Ou · · Score: 1

    "'There's another good reason to do this because it balances out the load between single-flow TCP applications. When a TCP end-point backs off to 50%, it's giving a new TCP flow a chance to take up the slack and speed up until the two TCP flows reach a state of equilibrium. UDP end points lack this behavior.'

    You have this completely backwards. TCP endpoints can only detect congestion through packet loss on the connection. UDP endpoints are free to back off for *any* reason, including but not limited to packet loss."

    Looks like you misread. I said routers drop packets (before total congestion), TCP endpoints detect and react by cutting speed in half which gives slower TCP streams a chance to rise to equilibrium.

    "Because every TCP connection is basically independent, you cannot use information gained from one connection to backoff on another. With UDP you can. A UDP application can backoff as aggressively as TCP, less aggressively, or more aggressively. Nobody yet knows how BT will rig its backoff algorithm."

    Yes it can backoff; if the routers dropped UDP packets the same way they dropped TCP packets. But they don't, so there's your problem.

  340. Re:The client application can't know about congest by JoelKatz · · Score: 1

    "Looks like you misread. I said routers drop packets (before total congestion), TCP endpoints detect and react by cutting speed in half which gives slower TCP streams a chance to rise to equilibrium."

    I understand that, and I agree with this. However, this says nothing whatsoever about UDP. In this case, the exact same thing will happen with UDP. The routers will drop the packets early (because they do not treat UDP differently from TCP) and the UDP endpoints will backoff (because they will be programmed to do so).

    "Yes it can backoff; if the routers dropped UDP packets the same way they dropped TCP packets. But they don't, so there's your problem."

    Yes, they do. At least, they should. RED is not as effective for UDP as it is for TCP (as many UDP flows are not responsive) but that is not a good reason to exempt UDP from RED just because it might not be responsive.

    If there are people out there who exempt UDP from RED, independent of any QoS indication that the packets are precious and not in limited internal networks where it is known that UDP traffic is precious, they should fix their networks.

  341. Re:Well Duh by akozakie · · Score: 1

    I agree, it is possible. Not even very difficult - the lack of need for retrasmissions, packet ordering etc. makes it much easier to implement than full TCP. That is not the problem I was thinking about.

    The problem is the combo of lack of built-in, system level congestion control, open source and egoistic users. With TCP, whatever you do, the protocol limits you. The most you can do is use multiple connections - a bit complicated and still only giving relative advantage. You can get more than your fair share of bandwidth on a path, but you can't dominate it.

    With UDP "playing nice" depends on application-level limits. Before deploying something like that (we're not talking about a niche application here, this is a huge share of todays traffic), rigorous tests should be run to verify how this protocol interacts with TCP. However, even supposing that everything works fine and the new BT works as intended, how long will it take until we see a fork, with the limits turned off? Of course, a single client built like that will not be a problem - other nodes won't let it reach full speed, unless the authors make a mistake, but if it catches on... It makes sense for the user - you can get a lot more speed. Then the web will become slow, mail will trickle and every user will bitch on every possible forum about ISPs not increasing bandwidth enough, while downloading the newest game/movie/whatever at 10x the speed he should. More bandwidth will just mean faster BT transfers, with no change to WWW etc.

    So, in fact, this is VERY difficult to implement properly. BT must not only make sure that they get the congestion avoidance right and leave enough room for TCP, it must also make sure that any client with a modified protocol will be unable to connect to normal peers at all, to block the adoption of any BT-on-steroids. Even that is easy to circumvent by using a "dual-protocol" client.

    I expect this change to backfire. You don't - fine. We won't know until after the fact. Still, I think that BT should stay on TCP - the solution to the problems is forcing ISPs to act fairly. How to do that, or if it's even possible in less than a decade is a different question, but I don't think switching to UDP will do the trick.

  342. Re:A little extreme there, don't you think? by Real1tyCzech · · Score: 1

    You're entitled, of course, I just believe it is insanely shortsighted.

    Your examples however, are absurd.

    1st: Bismark and Pol Pot also did not believe in a peer jury or a modern criminal justice system. Thankfully, we do.

    The odds that we will cause an innocent to suffer are thus greatly reduced from the likes of Bismark and Pol Pot.

    2nd: Let *any* guilty (found as such by a jury of their peers) persons go free, on the grounds that there might be some small chance they *may* be innocent puts at risk other innocents. Countless innocents if you go with Good ol' Benjy's "100's".

    We have a criminal justice system for a reason. It is not perfect, but it is a *far* cry from Benjy's quote, Bismark, or Pol Pot.

    I'll take our current system over any of the above, thankyouverymuch. :)

  343. Re:A little extreme there, don't you think? by BlueStrat · · Score: 1

    You're entitled, of course, I just believe it is insanely shortsighted.

    Your examples however, are absurd.

    1st: Bismark and Pol Pot also did not believe in a peer jury or a modern criminal justice system. Thankfully, we do.

    The odds that we will cause an innocent to suffer are thus greatly reduced from the likes of Bismark and Pol Pot.

    2nd: Let *any* guilty (found as such by a jury of their peers) persons go free, on the grounds that there might be some small chance they *may* be innocent puts at risk other innocents. Countless innocents if you go with Good ol' Benjy's "100's".

    We have a criminal justice system for a reason. It is not perfect, but it is a *far* cry from Benjy's quote, Bismark, or Pol Pot.

    I'll take our current system over any of the above, thankyouverymuch. :)

    Ok. I'll try to get you to understand this one last time because I hate to see someone so misinformed, and since you haven't devolved to ad hominem attacks, maybe you'll actually listen.

    What you're not getting here is that we *have* and *are living under* a judicial system (when things work as they should) that takes Bens' quote as a cornerstone of jurisprudence. That's a major reason *why* there's a presumption of innocence, trial by a jury of peers, and our modern justice system with its' other protections that you laud so highly. Without the principles and ideas embodied in that quote, none of that would exist.

    "Guilty", in the context of the quote, refers to those that have committed a crime for which they go unpunished, or those who, though guilty of committing a crime, are found guilty by lapse of due process to which they are entitled or other miscarriage of the enforcement and prosecution of the laws under which we live in accordance with the rights affirmed in the COTUS and the BOR.

    Essentially, it boils down to the fact that it is better that guilty persons go free who would otherwise be imprisoned, if to convict and imprison them would require violating the rights so affirmed to all in the COTUS and BOR. Otherwise, if it's OK to violate *this* persons' rights because, well, he's really really bad, then it's simply a matter of defining-down to reach the stage where the government may violate anyones' rights for most any reason or no reason at all.

    If that's the kind of system you desire, there are plenty of places in the world still where individuals have no rights. You're welcome to live there. Don't attempt to remove *our* rights in some misguided attempt to "get ALL the bad-guys".

    Cheers!

    Strat

    --
    Progressivism (aka US 'Liberalism'): Ideas so good they need a police/surveillance-state to enforce.
  344. Re:A little extreme there, don't you think? by Real1tyCzech · · Score: 1

    So, in order to argue with me you are taking the quote completely out of the context it was used in the original post I replied to?

    Well...that explains why we are completely unable to come to terms. ...but then you had to go and accuse me of trying to take away the rights of others and imply I should go live somewhere else.

    How quaint.

    So.. A persons rights are only valid if they agree with you, and because I took the quote as posted, in context (and not the context you apply to it), I no longer deserve to live in this country?

    *laughing*

    Ahhhh... One does have to admire the hypocrisy.

    Believe me. I have a bit of knowledge regarding our judicial system, its many flaws, and its many strengths. I've tried to impress upon you and others in this thread that I was replying to the poster, and _his_ use of the quote, in the context of the thread, and more specifically, the original post in which it was quoted, *not* in the context in which it was originally used. This has apparently been repeatedly ignored.

    So please, do me the honor of sparing us your ego-stroking "informing the mis-informed" condescension. This is not a schoolroom, you are not a school-marm, and I am no longer a student.

  345. Re:A little extreme there, don't you think? by BlueStrat · · Score: 1

    So, in order to argue with me you are taking the quote completely out of the context it was used in the original post I replied to?

    The context it was used n was quite clear. That you've chosen to deliberately take it out of the context in which it was said (in response to another post) indicates you are either back pedaling or were simply looking for an argument. That you have no other reply than "but I meant something else because he meant something else!" when the original meaning was clear is specious.

    So.. A persons rights are only valid if they agree with you, and because I took the quote as posted, in context (and not the context you apply to it), I no longer deserve to live in this country?

    *laughing*

    Ahhhh... One does have to admire the hypocrisy.

    The claim you make that I said anything about where you "deserved" to live is a strawman. I made no such statement. I simply offered the possibility that you might find another system more to your liking. Likewise, I also made no claims or statements pertaining to your rights or their validity. Another strawman.

    *shakes head & sighs*

    My points stand and I'm done here.

    Good day, sir.

    --
    Progressivism (aka US 'Liberalism'): Ideas so good they need a police/surveillance-state to enforce.
  346. Re:A little extreme there, don't you think? by Real1tyCzech · · Score: 1

    ...and I quote:

    "If that's the kind of system you desire, there are plenty of places in the world still where individuals have no rights. You're welcome to live there."

    I repeat:

    "You're welcome to live there"

    The implication being that such a person is *not* welcome to live _here_.

    If that's not the implication you intended to make, you should have chosen your words more carefully.

    You points would stand if we were discussing even remotely the same thing. As you've once again chosen to ignore the context completely, I concur.

    We're done here.

  347. Mostly a noisy distraction by steve_bryan · · Score: 1

    This article and many like it are just attempts to distract attention from a more fundamental issue. Why is Moore's law essentially almost null and void when it comes to provisioning of internet bandwidth? How do things need to be organized so we get the same sort of benefits in this area as we get in such diverse areas as printer performance, large flat screen monitors, processor speed and capability, memory cost, hard drive capacity, etc?

    The only area of this part of the economy that seems to be mystified by the idea of Moore's law are the monopoly and duopoly ISP's. Qwest proudly proclaimed they would guarantee a certain level of bandwidth without price increases for some number of years. Are they kidding? Their costs keep dropping toward zero per bit and they think they are being generous because they will restrain themselves by not increasing prices! What a load of crap.

    Nobody thinks bandwidth is cost free (see below for some details). What is clear to anyone involved in digital electronics for the past fifty years is that except for monopolies and government interference the price for a given level of service will always be dropping precipitously. The fact that it isn't for internet access is evidence that there is something rotten going on.

    About that cost free issue it is worth noting that even for things that are not free, like roads, it does not make sense to make every road a toll road. The same sort of idea may make sense for a modest and increasing level of bandwidth. The FCC will be considering exactly this topic in the near future. The free lunch for fat cat monopolists may be in some danger.