Beta
×

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

Thank you!

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

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

Hunting the Mythical "Bandwidth Hog"

kdawson posted more than 4 years ago | from the careful-they-got-tusks dept.

The Internet 497

eldavojohn writes "Benoit Felten, an analyst in Paris, has heard enough of the elusive creature known as the bandwidth hog. Like its cousin the Boogie Man, the 'bandwidth hog' is a tale that ISPs tell their frightened users to keep them in check or to cut off whoever they want to cut off from service. And Felten's calling them out because he's certain that bandwidth hogs don't exist. What's actually happening is the ISPs are selecting the top 5% of users, by volume of bits that move on their wire, and revoking their service, even if they aren't negatively impacting other users. Which means that they are targeting 'heavy users' simply for being 'heavy users.' Felten has thrown down the gauntlet asking for a standardized data set from any telco that he can do statistical analysis on that will allow him to find any evidence of a single outlier ruining the experience for everyone else. Unlikely any telco will take him up on that offer but his point still stands." Felten's challenge is paired with a more technical look at how networks operate, which claims that TCP/IP by its design eliminates the possibility of hogging bandwidth. But Wes Felter corrects that mis-impression in a post to a network neutrality mailing list.

cancel ×

497 comments

Sorry! There are no comments related to the filter you selected.

Interesting headline. (-1, Offtopic)

Anonymous Coward | more than 4 years ago | (#30324352)

Re:Interesting headline. (0)

Anonymous Coward | more than 4 years ago | (#30324388)

Or maybe it's even a variation of the article that HE FUCKING LINKED TO! ("Is the 'Bandwidth Hog' a Myth?") Some Slashdotters see a conspiracy everywhere they look......

Re:Interesting headline. (0)

Anonymous Coward | more than 4 years ago | (#30324522)

Or maybe it's even a variation of the article that HE FUCKING LINKED TO! ("Is the 'Bandwidth Hog' a Myth?")

Huh? Who clicks on the links in the summary?

Re:Interesting headline. (0)

Anonymous Coward | more than 4 years ago | (#30324478)

lol, you give us AC's a bad name.

Re:Interesting headline. (-1, Flamebait)

ProblemWithAmerica (1693012) | more than 4 years ago | (#30324620)

This is the problem with America these days, people can't even RTFA before trying to be a show off.

The "bandwidth hogs" aren't using TCP (4, Interesting)

afidel (530433) | more than 4 years ago | (#30324356)

They are generally using UDP so the original assertion that degrading the other users experience should be true as UDP should break down long before TCP does. Though I do agree that if Comcast's system works as described it's probably the best solution for a network that can't implement QoS.

Re:The "bandwidth hogs" aren't using TCP (2, Interesting)

ShadowRangerRIT (1301549) | more than 4 years ago | (#30324482)

Why do you think they are using UDP? Most of the bandwidth being used at this point, to my knowledge, is for streaming video (read: porn) and BitTorrent (read: porn). Both of them use TCP for the majority of their bandwidth usage (Some BitTorrent clients support UDP communication with the tracker, but the file is still transferred by TCP). Getting built-in error-checking, congestion control and streaming functionality in TCP makes much more sense than a UDP based protocol where you have to reimplement that yourself. I'm sure a few multiplayer games use UDP for latency reasons, but the data transferred for a multiplayer game is negligible and frequently loss-tolerant (if you missed where a player was one second ago, it doesn't matter once you get the new update).

Re:The "bandwidth hogs" aren't using TCP (3, Informative)

Bill_the_Engineer (772575) | more than 4 years ago | (#30324674)

Why do you think they are using UDP? Most of the bandwidth being used at this point, to my knowledge, is for streaming video (read: porn) and BitTorrent (read: porn). Both of them use TCP for the majority of their bandwidth usage (Some BitTorrent clients support UDP communication with the tracker, but the file is still transferred by TCP).

Most of the streaming protocols that I dealt with used UDP as their basis. The need to deliver the next frame or sound byte as soon as possible outweighs the need to guarantee that every single frame or byte arrives. We accept the occasional drop out in return for expedited delivery of data.

Unfortunately when trying to achieve the necessary data rate to satisfy the occasional drop outs, some protocols neglect being a good stewart of network bandwidth and have no throttle (ie congestion relief).

Re:The "bandwidth hogs" aren't using TCP (1)

ShadowRangerRIT (1301549) | more than 4 years ago | (#30324844)

Yeah, on looking around, it looks like the streaming protocols are UDP based. That still doesn't give it a flat majority of traffic; BitTorrent, along with the dedicated file sharing programs, are huge bandwidth consumers (the customers that are maxing out their connections aren't actively streaming video 24 hours a day), so if overusers of congestion unfriendly UDP are the problem, dropping the users of the highest bandwidth won't solve the problem (because they're using the relatively network friendly TCP most of the time).

Re:The "bandwidth hogs" aren't using TCP (0)

Anonymous Coward | more than 4 years ago | (#30324974)

The need to deliver the next frame or sound byte as soon as possible

BZZZT. Wrong.

Streaming protocols need to deliver the next frame on time. So the ones that use UDP deliver at a fixed rate, which makes your assertion that UDP is the bandwidth hog *WRONG*.

Re:The "bandwidth hogs" aren't using TCP (2, Insightful)

afidel (530433) | more than 4 years ago | (#30324762)

Modern Torrent clients that support DHT (most of them) generally default to UDP. Since the Torrent protocol already includes block checksumming there's no reason to also use TCP for that, congestion control generally isn't an issue with Torrent traffic either, you just push the pipe till it's full. For video unless you have significant buffering there's little reason to have error checking or congestion control because if you can't get the bits in fast enough without retransmits then the video's not going to be watchable. I'm not sure how much video is done using UDP vs TCP, Flash is TCP and Netflix appears to use a design where they adaptively send different encoding levels of the same content across a HTTP 1.1 stream as they see bandwidth starvation.

Re:The "bandwidth hogs" aren't using TCP (1)

ShadowRangerRIT (1301549) | more than 4 years ago | (#30324948)

I acknowledged my error on streaming video, but BitTorrent (and other file sharing programs) are still big TCP users.

While DHT is UDP based, the file transfer is still TCP based, and no client I know of allocates more than 10% of its bandwidth to DHT use (usually much less). Beyond the protocol compatibility issues, why waste a download of an up to 4 MB block when you could have TCP fix the error much earlier? TCP has a rough error interval of one bit in every trillion bits (that's from memory, but it's within an order of magnitude, might be every trillion bytes). UDP has whatever you code for it, and most of the time that means a hell of a lot less reliability (or more overhead than TCP requires; it was designed quite well for some things).

"Pushing the pipe until it's full" actually is a problem for UDP, when congestion gets out of hand performance degrades drastically as packets go missing more and more often. You need some level of congestion control or you will sabotage yourself.

Re:The "bandwidth hogs" aren't using TCP (2, Informative)

FrankDerKte (1472221) | more than 4 years ago | (#30324554)

No, bandwidth hogs normally use file sharing which is implemented with tcp (i. e. bit torrent).

The problem is tcp distributes bandwidth per connection. Someone using more connection gets a bigger part of the available bandwidth.

Same tired argument (0, Troll)

BadAnalogyGuy (945258) | more than 4 years ago | (#30324366)

We aren't getting the advertised bandwidth! Waaah!

Richard Bennett's response is worth the read, and it puts Benoit's theory of "fair bandwidth" in its place.

No one is going to take Benoit up on his offer because there is nothing to be gained either way for the telcos, and there is no point in giving this attention whore any credibility by responding to him.

Re:Same tired argument (0)

Anonymous Coward | more than 4 years ago | (#30324746)

What you're really upset about is that there's always someone out there getting more for their money than you are. But envy is more pathetic than entitlement, isn't it?

Re:Same tired argument (3, Interesting)

betterunixthanunix (980855) | more than 4 years ago | (#30324994)

"We aren't getting the advertised bandwidth! Waaah!"

Yes, actually, false advertising is a problem. If an ISP tells me I can make unlimited use of my 10Mbps connection, I expect to be able to make unlimited use of it -- including sustaining 10Mbps or something reasonably close all day and all night. If such a level of service is impossible for an ISP to provide and remain profitable, why the hell are they advertising these plans?

If they are lying to consumers about the level of service they can provide, they should cover themselves by increasing the network capacity, or they should admit they lied, reduce the bandwidth they provide to users, and hope that nobody sues them over it. Kicking people off the network for trying to use what they paid for is not an appropriate response to overselling, and if the FCC had any spine they would kill the practice before it gets out of hand.

No site has ever been slashdotted (0)

Anonymous Coward | more than 4 years ago | (#30324380)

Because TCP doesn't allow it.

I hear all the websites are switching from token ring because of this.

Re:No site has ever been slashdotted (3, Informative)

Anonymous Coward | more than 4 years ago | (#30324656)

During a Slashdotting, the problem is rarely network-related (aside from people who use a cheap host and have very low artificial bandwidth limitations, or are hosting their site on a low-end cable connection).

More often than not, the database goes down. MySQL is especially prone to just dying when put under any significant workload. That's why you'll often see error messages saying that the web front end can't connect to the database. You can still get to the site because the network can handle the volume of traffic just fine, and you can get the error message because the web server can also handle the volume of traffic just fine.

The next most common problem is the server-side web apps being unable to handle the load. I don't mean the web servers, as most of those can handle huge amounts of traffic, even on ancient hardware. I mean web apps implemented using PHP, Ruby on Rails, ASP.NET, JSP and so on. Many sites don't use PHP bytecode caching, for instance, nor do they do much data caching. So it just ends up taking too long to generate pages, and your browser times out.

Re:No site has ever been slashdotted (2, Interesting)

Qzukk (229616) | more than 4 years ago | (#30324658)

You think you're being sarcastic, but has anyone ever seen a network go down in flames due to slashdotting, or has it always been the server?

Re:No site has ever been slashdotted (1)

ender- (42944) | more than 4 years ago | (#30325056)

You think you're being sarcastic, but has anyone ever seen a network go down in flames due to slashdotting, or has it always been the server?

I'm inclined to think the network can certainly play a part. I had a K6-350Mhz/256MB server slashdotted on 9/11 with ftp/http links to pictures and video. The server ran with no issues, and was able to push out 100Mbit/s worth of data all day. I had a fairly weak server but an incredibly fast and robust network [100Mbit port to dual OC-12s with only a few customers on it].

A less robust network would have surely caused problems. Though also if I had configured the server poorly it would also have caused problems.

Anyway, my point is I have to think it's just as likely that a good number of sites that are not able to handle being slashdotted are due to the network getting saturated/failing long before the hardware is heavily taxed. At least with simple static sites. Obviously a highly dynamic site will put more load on the server.

Why? (2, Interesting)

Maximum Prophet (716608) | more than 4 years ago | (#30324392)

Why would any business cancel paying customers that don't negatively impact operations?

Re:Why? (2, Interesting)

BESTouff (531293) | more than 4 years ago | (#30324458)

Because they're probably heavy music/movies "illegal" downloaders, so they inconvenience their friends the media moguls ?

Re:Why? (3, Insightful)

godrik (1287354) | more than 4 years ago | (#30324468)

Because the operators pay for the bandwidth. The high bandwidth users are less profitable than the other ones.

Re:Why? (4, Insightful)

olsmeister (1488789) | more than 4 years ago | (#30324664)

I guess it's cheaper to sacrifice 5% of revenue than to have to undertake a network upgrade.

This mentality is part of why the U.S. lags so much in broadband.

Re:Why? (1)

Bob9113 (14996) | more than 4 years ago | (#30324978)

Because the operators pay for the bandwidth. The high bandwidth users are less profitable than the other ones.

That is why tiered services would solve the problem. High bandwidth users should be more profitable than other ones. Then the ISPs would be profit motivated to encourage heavy bandwidth usage, and the users would be cost motivated to be efficient with their usage.

No single thing is more at the root of this problem than the word "unlimited."

Re:Why? (3, Insightful)

Trepidity (597) | more than 4 years ago | (#30324480)

They don't negatively impact operations in the sense of taking up a scarce resource that degrades other customers' performance. However, they do still use above-average amounts of bandwidth, which costs ISPs money. When offering a flat-rate, unlimited-use service, your economics come out ahead if you can find some way to skew your customers towards those who don't actually take advantage of your claimed "unlimited use".

Re:Why? (1)

ShadowRangerRIT (1301549) | more than 4 years ago | (#30324546)

Because they're worried that if they don't, they'll have to pay for equipment upgrades to handle the extra load, and I doubt they don't have the monitoring in place to figure out whether a "hog" is actually impairing the experience of other customers (after all, you'd need to analyze a whole lot of factors at each link in the chain where connections join, and that costs money too). Their paranoid belief is that half the customers will up and leave because there connection is one step shy of perfect, so they decide to sacrifice a few users to "save" the remaining base.

Interesting (0)

Drasham (1626825) | more than 4 years ago | (#30324398)

I'd love to see the result of such a data analysis.

Who? (1)

thelonious (233200) | more than 4 years ago | (#30324406)

So the telcos are like, "Felten who? Yeah, we'll get right on that"

East ireland (1)

jaggeh (1485669) | more than 4 years ago | (#30324432)

i was kicked off ESAT's 'no limits' service back in 2001 because i used it too much/was a heavy user. shortly after they instituted a time cap on the 'no limits' service.

in hindsight im sure i could have brought them to court over the trade discription.

Re:East ireland (5, Funny)

cupantae (1304123) | more than 4 years ago | (#30324540)

Marge: We drove around until three in the morning looking for another open all-you-can-eat seafood restaurant.
Lionel Hutz: And when you couldn't find one?
Marge: [crying] We... went... fishing.

Bandwidth can be hogged - I've seen it (3, Interesting)

BobMcD (601576) | more than 4 years ago | (#30324488)

I have personally witnessed hogging of bandwidth and, I'd wager, so have you. This term describes when an individual user uses more bandwidth resources than they were assumed to need.

Example: My brother moves in with two of his friends. His latency is horrible. When his roommate is not home, the internet is fine. When he's away at work it becomes unusable. He calls me to look at the situation, and we determine that one of his roomies is a heavy torrent user. Turns out the roommate was ramping up torrents of anime shows he wanted to watch while he was gone. He was aware of the impact to his own internet experience, and so ramped it back down when he wanted to use it himself.

If that's not hogging bandwidth, I'm not too sure what is.

If this doesn't scale, logically, up to the network at a whole, I'm not sure why.

Now, to be completely clear - I feel overselling bandwidth is wrong. I feel the proper response to issues like this on the larger network is guaranteed access to the full amount of bandwidth sold at all times. On the local scale, these men should have brought in another source of internet. On the larger scale, the telco should do the same.

Denying that the issue can happen, however, is stupid to the point of sabotage.

An end-user can download all his access line will sustain when the network is comparatively empty, but as soon as it fills up from other users' traffic, his own download (or upload) rate will diminish until it's no bigger than what anyone else gets.

So, if I understand this statement, if a user is hogging all the bandwidth until no one gets any connectivity - since it is all the same it is totally fair. One user can bottleneck the pipes, but since their stuff isn't fast any more either, we're all good?

How does an argument of this kind help anyone but a bandwidth hog?

Re:Bandwidth can be hogged - I've seen it (2, Informative)

Anonymous Coward | more than 4 years ago | (#30324616)

I used QoS with iproute2 and iptables (see http://lartc.org/howto [lartc.org] ) when I faced that issue.
I do not mean to say I had room mates, but when I used bittorrent and noticed how it abused the network, I used that howto to limit it's bandwidth.

It worked very nice.

Re:Bandwidth can be hogged - I've seen it (3, Insightful)

randallman (605329) | more than 4 years ago | (#30324642)

This could just be a problem with your router. Maybe it struggles to handle all of the torrent connections.

Re:Bandwidth can be hogged - I've seen it (1)

lastchance_000 (847415) | more than 4 years ago | (#30325012)

I've seen a similar thing with a neighbor of mine in our apartment building. We're on Comcast--and the congestion stopped when he switched to DSL (He had been sharing the connection of another neighbor, who moved out.)

Re:Bandwidth can be hogged - I've seen it (1)

enigmatiX (858831) | more than 4 years ago | (#30324646)

Simple Fix: Limit his download (and more importantly *upload*) bandwidth--tell him to get a torrent client that allows it. Problem solved.

Re:Bandwidth can be hogged - I've seen it (1)

BobMcD (601576) | more than 4 years ago | (#30324794)

Which is dissimilar to what the ISP's are doing, how?

Re:Bandwidth can be hogged - I've seen it (1)

FictionPimp (712802) | more than 4 years ago | (#30325050)

The ISP already limits my bandwidth. Say you purchase 'unlimited' 5mbps/768kbps service. You have a 5mbps download limit and a 768kbps upload limit. If they can't support you using that at full blast, then they should lower the limit. Instead they punish you for using the allocation they gave you. It would be like imposing a limit on your roommate, then kicking him out for using the limit every day.

Re:Bandwidth can be hogged - I've seen it (0)

Anonymous Coward | more than 4 years ago | (#30324650)

Nice anecdote.

Re:Bandwidth can be hogged - I've seen it (1)

Interoperable (1651953) | more than 4 years ago | (#30324652)

You pay for a 70Mbps connection. The ISP is saying that if you buy that service and then have the audacity to use the service you buy you're doing something wrong. Taking up 60Mbps and leaving 10Mbps for your roommate is one thing, but if the two of you are paying for 70Mbps you should get to use it.

The ISP should be required to provide the service paid for. If they throttle, they should be required to specify say 70Mbps instantaneous rate 10Mbps sustained, for example. That would provide a clear description of the product they offer. Anything less is false advertising.

Re:Bandwidth can be hogged - I've seen it (1)

BobMcD (601576) | more than 4 years ago | (#30324734)

We agree on this. Do we also agree that denying that hogging bandwidth is possible is not helpful to the discussion?

Re:Bandwidth can be hogged - I've seen it (3, Interesting)

Zen-Mind (699854) | more than 4 years ago | (#30324926)

I think you pointed-out the real problem. The telcos want you to pay for the 70Mbps line, but don't want you to use it. If you cannot support a users doing 70Mbps, don't sell 70Mbps. I know that building an infrastructure based on the assumption that all users will use maximum bandwidth would be costly, but then adapt your marketting practices; sell lower sustained speed and put a "speed on demand" service that is easy to use so when you want/need to download the new 8GB PS3 game you can play before the next week. Otherwise you can always have a maximum sustained bandwidth based on high/low period of the day, but this needs to be clear.

Re:Bandwidth can be hogged - I've seen it (2, Insightful)

bws111 (1216812) | more than 4 years ago | (#30324982)

You pay for an 'up to' 70Mbps connection. 'Up to' means exactly what is sounds like - you are never going to go above that rate. It says absolutely nothing about the minimum or average rate. Since they make no claims at all about minimum or average rate, there is no false advertising. Every consumer is well familiar with what 'up to' means. How many times do you see an ad that says 'Sale! Save up to 50%'. Does that imply that you are in fact going to save 50% on everything you buy? No, it implies that somewhere in the store is at least one item that is 50% off - every other item may be full price, or more likely, discounted at a rate less than 50%.

Re:Bandwidth can be hogged - I've seen it (1)

jeffmeden (135043) | more than 4 years ago | (#30324668)

The basic counter argument is that TCP "fairness" assumes everyone wants the same experience. As you pointed out, a true bandwidth hog doesn't care about the latency during their hogging sessions since they plan around them, and therefore arguing that TCP is fair because it treats all packets the same is pure rubbish. If everyone (including the hog) is trying to make a VOIP call or play WOW then sure, the system is fair because the hog has degraded service just like everyone else. The enterprising hog simply waits for periods when they don't care about latency and cranks up the download speed, ruining the experience for everyone else.

Re:Bandwidth can be hogged - I've seen it (4, Informative)

ShadowRangerRIT (1301549) | more than 4 years ago | (#30324682)

I should point out that this sort of thing, while true, is often overstated because of poor local network configuration. When I first set up my new Vista machine a couple years back, I noticed that torrents on it would frequently interfere with internet connectivity on other networked devices in the house. I hadn't had this problem before and was curious as to the cause. I initially tried setting the bandwidth priorities by machine IP and by port, setting the desktop and specifically uTorrent's port to the lowest priority for traffic (similar to what ISPs do when they try to limit by protocol, but more accurate and without an explicit cap), but that actually made the situation worse; the torrents ran slower, and the other machines behaved even worse.

Turned out the problem was caused by the OS. Vista's TCP settings had QoS disabled, so when the router sent messages saying to slow down on the traffic, or just dropped the packets, the machine just ignored it and resent immediately, swamping the router's CPU resources used to filter and prioritize packets. The moment I turned on QoS the problem disappeared. The only network using device in my house that still has a problem is the VOIP modem, largely because QoS doesn't work quickly enough for the latency requirements of the phone, but it's not dropping calls or dropping voice anymore, it's just laggy (and capping the upload on uTorrent fixes it completely; the download doesn't need capping).

Re:Bandwidth can be hogged - I've seen it (2, Interesting)

BobMcD (601576) | more than 4 years ago | (#30324776)

Are you advocating a system where the ISP has mandate power over the OS configuration?

Re:Bandwidth can be hogged - I've seen it (1)

beefnog (718146) | more than 4 years ago | (#30325024)

I'm fairly certain that ShadowRangerRIT was talking about local networks only. He's referring to internal QoS, which will in no way affect the total bandwidth he's using relative to the ISP. The connection is saturated in both scenarios. Using QoS internally, he's just prioritizing his traffic.

Re:Bandwidth can be hogged - I've seen it (0)

Anonymous Coward | more than 4 years ago | (#30324688)

So, if I understand this statement, if a user is hogging all the bandwidth until no one gets any connectivity - since it is all the same it is totally fair. One user can bottleneck the pipes, but since their stuff isn't fast any more either, we're all good?

I agree totally. It sounds like some journalist found out how TCP/IP works _on paper_ and decided to write a story. Though I like his intentions, he misrepresents the way things actually work for users.

Re:Bandwidth can be hogged - I've seen it (0)

Anonymous Coward | more than 4 years ago | (#30324706)

I have personally witnessed hogging of bandwidth

You missed the point slightly.

If a roommate is hogging your apartment's bandwidth, you can't extend that to say that he must be hogging the entire network. He is just filling up the pipline to your single apartment.

The correct metaphor would be if each roommate paid for a separate internet connection, and when one roommate ramped up bittorrent, the other two's connections dropped. THAT would prove the existence of a "Bandwidth Hog"

But point of the article is that all apartments in your area (for example) get equal distribution of bandwidth.

Re:Bandwidth can be hogged - I've seen it (1)

tepples (727027) | more than 4 years ago | (#30324802)

The correct metaphor would be if each roommate paid for a separate internet connection, and when one roommate ramped up bittorrent, the other two's connections dropped. THAT would prove the existence of a "Bandwidth Hog"

Which is close to what happens on cable Internet.

Re:Bandwidth can be hogged - I've seen it (4, Insightful)

betterunixthanunix (980855) | more than 4 years ago | (#30324728)

"If this doesn't scale, logically, up to the network at a whole, I'm not sure why."

Plenty of reasons why that won't scale up to the network as a whole. First and foremost, your ISP's network topology is a lot more effective for many users than the simple "star" topology most home router/switch combos give you. Beyond just the topology, the ISP uses better equipment that can cap bandwidth usage and dynamically shift priorities to maintain a minimum level of service for all users even in the presence of a very heavy user. The ISP also has much higher capacity links than what you have at home, and certainly more than the link they give you, and so even if there were a very poor topology and no switch level bandwidth management, it would be very difficult for a single user to severely diminish service for others.

I do not have any sympathy for ISPs when it comes to this issue. If they sell me broadband service and expect me to not use it, then they are supremely stupid, and retaliating against those users who actually make use of the bandwidth they are sold is just insulting. They oversold the bandwidth and they should suffer for it; blaming the users is just misguided.

Re:Bandwidth can be hogged - I've seen it (1)

BobMcD (601576) | more than 4 years ago | (#30324854)

They oversold the bandwidth and they should suffer for it

I agree.

blaming the users is just misguided.

I disagree. The system wasn't designed, nor sold, with torrents in mind. End points are supposed to be content consumers, not content providers. It isn't exactly the ISP's fault that those end users want the system to function in a way against which it is designed.

The ISP should redesign the system. Absolutely, without a doubt. Meanwhile those users that aren't getting what they want shouldn't necessarily be ruining it for everyone else, should they?

Re:Bandwidth can be hogged - I've seen it (1)

betterunixthanunix (980855) | more than 4 years ago | (#30325078)

"It isn't exactly the ISP's fault that those end users want the system to function in a way against which it is designed."

I would agree if the ISPs were honest about what how they built their network, but they continue to lie and then complain about people believing their lies. If an ISP designed its network with downloading in mind, and provides only the minimum upload capacity needed to facilitate such service, they should be very clear about that. It is not "unlimited Internet access," it is "Internet download service."

If they cannot market what they designed without lying to people, it is their fault, and as you said, they should redesign their product and sell what people actually want. The ISP lied, and that is where the blame stops. Nobody should be blamed for believing that their ISP is selling them the service that was advertised.

Re:Bandwidth can be hogged - I've seen it (0)

Anonymous Coward | more than 4 years ago | (#30324730)

Turns out the roommate was ramping up torrents of anime shows he wanted to watch while he was gone. He was aware of the impact to his own internet experience, and so ramped it back down when he wanted to use it himself.

If that's not hogging bandwidth, I'm not too sure what is.

This is not the same thing - your brother's roommate is hogging the single bandwidth-limited connection from the residence to the net. It would matter if the roomie's torrent affected the folks in the next house over by clogging the connection from the curbside unit to the backbone.

This argument is not about the rate limit to your house.

Re:Bandwidth can be hogged - I've seen it (1)

Drethon (1445051) | more than 4 years ago | (#30324774)

I think the difference may be that a bandwidth hog of a single connection is a user that can use near 100% of the bandwidth. With ISPs on the other hand, the average use by a single user is probably only around 10-25% of daily bandwidth or less (uneducated guess). That means if 5% of the users are using 100% of the bandwidth continually, than everything is fine as long as the ISP can supply at least ~30% of the user bandwidth x the number of users. I could be completely off base however...

Re:Bandwidth can be hogged - I've seen it (0, Offtopic)

Drethon (1445051) | more than 4 years ago | (#30324816)

Ok how do I get new line characters into my post? I did a (very) brief search on this and don't see anything. Is it just because I'm using IE6?

Re:Bandwidth can be hogged - I've seen it (-1, Offtopic)

Anonymous Coward | more than 4 years ago | (#30325060)

Bound your paragraphs with the p tag.

Re:Bandwidth can be hogged - I've seen it (1)

noname101 (1481803) | more than 4 years ago | (#30325074)

Well first stop advertsing you are using IE6 it does not help any.

For a new line you need to put in <br>

newlines (0)

Anonymous Coward | more than 4 years ago | (#30325116)

Try posting in plane old text.
if you want to use HTML, use
.

Re:Bandwidth can be hogged - I've seen it (1)

noname101 (1481803) | more than 4 years ago | (#30324966)

You are comparing the results of a sub set of the network and not as a whole. Person B that was running the torrents was using all of the bandwidth of the given connection. So person A could not connect. That is fine that is what you have accepted as use with your telco, So much down and so much up. The issues that you missed is that it did not effect your neighbor next door or down the street or next town over because they have their own internet connection.

If the ISP sold me a 5 Mb line that it is mine to do with as a please. If they could not support it then they should not be advertising a 5 Mb line. Which on a side note I have a 5 Mb line and I have never seen over 3Mb even on their "optimized" internal network. So what the telco's are really afraid is going to happen is that people are going to find out that there is no way for them to support the line speed they are promising.

Can Ford tell me where I can drive my car? Does Dish tell me I have to watch a certain channel? Does Sony stop me from buying a Toshiba DVD player? Does the pone company tell me who I can and cannot call? So where are we allowed to be pushed around by the ISP?


---------------
Signature would go here if I was clever.

Re:Bandwidth can be hogged - I've seen it (0)

Anonymous Coward | more than 4 years ago | (#30324998)

In my experience, the main problem with bittorrent on a shared connection is that it opens up many connections that the router is keeping track of and when you increase the number of connections that are allowed to be open or decrease the amount of time the connection is stored, the performance generally increases.

This isn't configurable in many routers' default firmware. I know it is an option in DD-WRT and Tomato firmwares for the Linksys WRT54G (which is a great router)

Re:Bandwidth can be hogged - I've seen it (2, Insightful)

Hatta (162192) | more than 4 years ago | (#30325106)

That's just bad configuration, not bandwidth hogging. Prioritize ACK packets and you can run torrents all day without affecting other uses of the network.

One user can bottleneck the pipes, but since their stuff isn't fast any more either, we're all good?

If the "bandwidth hog" isn't fast anymore, he's no longer a hog.

Bandwidth != Volume (0)

Anonymous Coward | more than 4 years ago | (#30324490)

The problem with the argument that the ISPs use is that they always talk about volume, but they call it bandwidth. Network capacity isn't cumulative. Bandwidth that you don't use now isn't saved and therefore cannot be used later. An important consequence of that observation is that total amount of bits transfered is not a useful metric for the impact that a particular user has on the network, but somehow all residential ISPs have chosen precisely that misleading metric to determine who is a "bandwidth hog" and who isn't.

You can't eliminate heavy users. (0)

cupantae (1304123) | more than 4 years ago | (#30324492)

The thing is, because of the distribution of people using broadband (bandwidth usage plotted as an ogive comes out as a sharp exponential), there will always be a situation of 5% of the population downloading 95% of the material, no matter who you disconnect.

Re:You can't eliminate heavy users. (0)

Anonymous Coward | more than 4 years ago | (#30324898)

The thing is, because of the distribution of people using broadband (bandwidth usage plotted as an ogive comes out as a sharp exponential), there will always be a situation of 5% of the population downloading 95% of the material, no matter who you disconnect.

Ummm, no.

There will ALWAYS be a top 5% of users (and a bottom 5%), no matter what you do.

But to state that the top 5% are always downloading 95% of the material is flat-out ridiculous.

Re:You can't eliminate heavy users. (1)

jschen (1249578) | more than 4 years ago | (#30324912)

If those numbers are correct (5% taking up 95% of bandwidth), then kicking out the top few percent of users (of the entire population, not necessarily of the current customer base) seems exceptionally good for one's bottom line. After that, there's no point removing the new "heavy users" since you've already removed most of your traffic, and your existing infrastructure can more than handle the remaining traffic, so you're better off getting the revenue.

If there's no such thing as a bandwidth hog... (1)

teneighty (671401) | more than 4 years ago | (#30324514)

If there's no such thing as a bandwidth hog, then why are is anyone worried about "hunting" them?

Something tells me PETA is behind this...

PS: Yes we'd all like to be able to download 20 TB of movies a month for free. We'd all also like free gasoline so we can drive Humveees with 30 inch chrome wheels.

Re:If there's no such thing as a bandwidth hog... (1)

betterunixthanunix (980855) | more than 4 years ago | (#30324822)

"We'd all also like free gasoline so we can drive Humveees with 30 inch chrome wheels."

Speak for yourself.

Nice theory... (2, Interesting)

thePowerOfGrayskull (905905) | more than 4 years ago | (#30324526)

Where are the facts again? Oh, right, he tells us!

The fact is that what most telcos call hogs are simply people who overall and on average download more than others. Blaming them for network congestion is actually an admission that telcos are uncomfortable with the 'all you can eat' broadband schemes that they themselves introduced on the market to get people to subscribe. In other words, the marketing push to get people to subscribe to broadband worked, but now the telcos see a missed opportunity at price discrimination...

It's nice of him to declare that without evidence. Now I know it to be true.

I'm not saying he's wrong... quite possibly he's right, but seriously - how does someone's blog entry that doesn't provide one single data point to back up the claim make it to the front page?

Re:Nice theory... (0)

Anonymous Coward | more than 4 years ago | (#30324768)

There is no evidence that santa clause do not exist either. Everyone grown-up person will agree it a myth tho.

Re:Nice theory... (3, Insightful)

eldavojohn (898314) | more than 4 years ago | (#30324838)

I'm not saying he's wrong... quite possibly he's right, but seriously - how does someone's blog entry that doesn't provide one single data point to back up the claim make it to the front page?

The important thing that he's doing is trying to shift the burden of proof back onto the ISPs and telcos. They just declared that some people are bandwidth hogs and terminated their connection. They didn't give the public any proof that they were ruining the internet experience for anyone else ... nor did anyone come forward after the purge and say, "Gee, my internet sure is fast now that the bandwidth hogs are disconnected!"

So he calls for proof since he hasn't seen any. He has to say that there are no bandwidth hogs in order to get a response from the telcos. Saying someone might be wrong is not the same impact as calling someone a liar. Yes, he's basing this on an assumption but it's just the same that everyone assumed there were individuals out there ruining the experience. All of us just let the telcos terminate the service of whoever they wanted to and then we moved on with our lives.

I welcome his opposing viewpoint and challenge to "because we said so." They can release anonymous usage data without harming anyone so why not open it up to a request?

Re:Nice theory... (0)

Anonymous Coward | more than 4 years ago | (#30324986)

how does someone's blog entry that doesn't provide one single data point to back up the claim make it to the front page?

See this story from earlier today [slashdot.org]

Sessions (0)

Anonymous Coward | more than 4 years ago | (#30324532)

Sure, TCP will do this. But that's per stream. What if I have 100 streams open? Then I get 100x the bandwidth of someone with one stream.

Small ISP (5, Interesting)

Bios_Hakr (68586) | more than 4 years ago | (#30324566)

Lately I've had to deal with this problem. Our solution was rather simple. We use NTOP on an Ubuntu box at the internal switch. We replicate all the traffic coming into that switch to a port that the NTOP box listens on.

It may not be a perfect solution, but it can easily let us know who the top talkers are and give us a historical look at what they are doing.

From that report, we look for anyone uploading more than they download. We also look for people who upload/download a consistent amount every hour. If you see someone doing 80gb in traffic each day with 60gb uploaded, you probably have a file sharer. When you see the 24-hour reports for the user and see 2~3gb every hour on upload, you *know* you have a file sharer.

After that, it's as simple as going to the DNS server and locking their MAC address to an IP. Then, we drop all that traffic (access list extended is wonderful) to another Ubuntu box. That box has a web page explaining what we saw, why the user is banned, and the steps they need to take to get back online.

Most users are very apologetic. We help them to set up upload/download limits on their bittorrent client and then we put them back online.

Re:Small ISP (1, Insightful)

Anonymous Coward | more than 4 years ago | (#30324764)

Or stop overselling your bandwidth and then you wouldn't have to worry about how much bandwidth your users use.

Re:Small ISP (1)

betterunixthanunix (980855) | more than 4 years ago | (#30324864)

Why not just throttle them? Or limit the maximum bandwidth provided to a level that is less likely to allow one user to disrupt service for everyone else?

Re:Small ISP (4, Interesting)

imunfair (877689) | more than 4 years ago | (#30325020)

Is there really a problem with allowing your users to actually use their connection? By my rough calculations 2-3gb/hr is only 60-90kb/s upload. I really don't understand why you can't handle that unless you're massively overselling. I would be a lot more sympathetic if we were talking about users maxing out fiber connections or something higher speed.

Re:Small ISP (1, Informative)

Anonymous Coward | more than 4 years ago | (#30325040)

If you advertise your service as "unlimited", then doing this means you need to be cockslapped to death. Not only are you treating your users like shit, but you're encouraging them to be leecher scum.

Re:Small ISP (1)

lobosrul (1001813) | more than 4 years ago | (#30325100)

How does your TOS read I wonder. Until recently I shared a 12mb/768kb DSL line with 3 room-mates from QWEST. I'm sure we nearly maxed the thing out most days during peak hours. *Most* of that traffic was actually legit. I pay thru the nose for it (~$70/month), but *gasp* somehow QWEST can afford to have a few customers actually use all of the service they pay for. I never received any sort of warning in over a year. How about ISP's actually giving their customers what they advertise. If you want to limit your customers, offer a plan for limited monthly bandwidth.

Bandwidth hogging is relatively easy to solve (1)

drinkypoo (153816) | more than 4 years ago | (#30324580)

You need a TCP/IP stack with queueing. You give each IP address a fair chance to transfer and/or receive some data, and as always you drop any traffic for which you have no time.... but you drop them from the bottoms of queues first, and the queues are per-IP (or per-subscriber, which is harder to manage unless you are properly subnetted... in which case, they can be per-network, for which computation is cheap.) This should be the only kind of QoS necessary to preserve network capacity for all users and prevent "bandwidth hogging". Let the users implement their own QoS for VoIP traffic within their available bandwidth.

Re:Bandwidth hogging is relatively easy to solve (1)

godrik (1287354) | more than 4 years ago | (#30324884)

Ensuring fairness at one point of the network won't ensure fairness over the whole network which is what you really want.

TCP is only fair if no one cheats. (0)

Anonymous Coward | more than 4 years ago | (#30324590)

TCP enforces fairness for well behaved apps. If each app only opens one stream to do its job, the streams will adjust their windows to give each stream an even share of the bandwidth.

But then a download accelerator simply has to open n streams for one job, grabbing n times its fair share. TCP is a perfectly reasonable system in that it works as long as you don't deliberately break it.

The best way to ensure fairness is by pricing for heavy usage (> 250GB seems reasonable nowadays), along with adequate information. People know how many minutes they use because they get a report each month. ISPs need to give out similar reports, probably broken down by protocol or top sites like youtube, so users have some clue how much bandwidth they're actually using.

I don't know. (0)

Anonymous Coward | more than 4 years ago | (#30324612)

Bandwidth is a finite resource; it stands to reason that if User A uses more than his fair share it would negatively impact User B. I think everybody would agree on that. So the only question left is how much does it take to start affecting other users? Unfortunately, this is probably a question that only the providers can answer.

What about spammers? (1)

LuxMaker (996734) | more than 4 years ago | (#30324640)

I can hear them now saying "I'm in your networkz hogging your bandwidth."

ISP says: (1)

L3370 (1421413) | more than 4 years ago | (#30324654)

"... I'll advertise that you'll have up to 10mbps connection speed and unlimited bandwidth, and you'll get it. But if you ever come close to using the maximum potential of the service you actually paid for I'm gonna cripple or stop you completely."

If these companies are going to be doing this they just need to stop calling their service packages "unlimited."

Too bad there isn't any real competition in this sector. We all just eat it.

YES! (1)

GNUPublicLicense (1242094) | more than 4 years ago | (#30324690)

Finally, it's coming through! In the context of replacing totally the services provided by classic telephony, we must set up neutral IP traffic classes (VoIP over mobile radio link do *NOT* work reliably, and won't be after broad adoption of the FTTH). Indeed, the idea is to give priority to voice traffic on client initiative. The *only* allowed exception to this rule would be emergency calls, because that has to be done at the ISP initiative. We can even think of a video stream for emergency calls! With enough good video quality... imagine the amount of people we could additionnally save thanks to the video!!! We already have the terminals able to do so! We need to set up that next gen Internet ASAP!

Friends and family coming soon to your ISP! (2, Interesting)

140Mandak262Jamuna (970587) | more than 4 years ago | (#30324760)

These ISPs sold what they ain't got. Sold more bandwidth than they can sustain, and when someone actually takes delivery of what was promised, these telcos bellyache, "we never thought you will ask for all we sold you! whachamagontodoo?". Eventually they will introduce billing by the Gigabytes, and pipesize. Like the electric utilities charge you by the kWh and limit the ampearage of your connection.

Then they will introduce the "friends and family" of ISP, some downloads and some sites will be "unmetered", and the sources will be the friends and family of the ISP. You know? the "partners" who provide "new and exciting" products and content to their "valued customers". Net neutrality will go down the tubes. ha ha.

Google needs the net to be open and neutral for it to freely access and index content. When the dot com bubble burst Google bought tons and tons of bandwidth, the dark fibers, the unlit strands of fiber optic lines. If the net fragments, I expect Google to step in, light up these strands and go head to head with the ISPs providing metro level WiFi. Since it is not a government project, it could not be sabotaged like Verizon and AT&T torpedoed municipal high peed networks.

Re:Friends and family coming soon to your ISP! (1)

teg (97890) | more than 4 years ago | (#30325076)

These ISPs sold what they ain't got. Sold more bandwidth than they can sustain, and when someone actually takes delivery of what was promised, these telcos bellyache, "we never thought you will ask for all we sold you! whachamagontodoo?

Basically, they want to sell a product with high speed - but not continual use. A product where more of the bandwidth is used - or dedicated, not oversubscribed - is vastly more expensive, and is what they sell to businesses. To fix this problem, they should start with metered costs per gigabyte, or specify the products better so that normal users get their current experience at their current price, and those who really want a different product at the current price, are shifted to that product.

Freedom of information act (1)

TimeElf1 (781120) | more than 4 years ago | (#30324780)

Felton has thrown down the gauntlet asking for a standardized data set from any telco that he can do statistical analysis on that will allow him to find any evidence of a single outlier ruining the experience for everyone else. Unlikely any telco will take him up on that offer but his point still stands."

It's too bad there isn't a freedom of information act for business, that could come in handy for this sort of thing. Although if there was I suppose that would make industrial espionage really easy.

An Impasse? (0, Offtopic)

lymond01 (314120) | more than 4 years ago | (#30324788)

Felten's challenge is paired with a more technical look at how networks operate, which claims that TCP/IP by its design eliminates the possibliity of hogging bandwidth. But Wes Felter corrects that misimpression in a post to a network neutrality mailing list.

Wait till I get going! The blogosphere, initially made famous by one Cory Doctorow, has impressed upon us for years that the internet highway is headed for a 100 car pileup. The Distinguished and Honored Senator from Alaska, Ted Stevens, tells us that the tubes are filling up every day. But only a fool would liken the internet to a series of tubes when clearly the highway analogy is what's best! And clearly you can't think that any single user confined to the HOV lane is going to encroach upon the bandwidth of the other 10 lanes of traffic! It's obvious that I know where the problem with the Internet is. I've known from the beginning! Wait! What in the world could THAT be! Oh. Never mind. It was nothing. Now. I'll drink from FiOS in front of me and you drink from your DSL in front of you. Hah! You fell victim to one of the greatest internet blunders of all time! The first being that you never believe what you read on the Internet followed closely by the fact that you never take Slashdot seriously when money is on the line! Ha ha ha! Ha ha....

My point being: if they're going to cut you off for maxing out your line regardless of how it affects other people, THAT'S the real problem. Imaginary or not, you can still die from fright over the boogeyman in the closet.

I do it too (3, Interesting)

holophrastic (221104) | more than 4 years ago | (#30324810)

I also go through my client list and drop those that consume more of my time and resources in favour of the easier clients who ultimately improve my business at a lesser cost. What's wrong with that? My company, my rules. "We reserve the right to refuse service to anyone" -- it's in every restaurant. Why would you expect a business to serve you? Why would you consider it a right?

Re:I do it too (0)

Anonymous Coward | more than 4 years ago | (#30325042)

a minimal level of internet access should be a right though. It's fairer to just throttle the hogs rather than cut them off from possibly crucial services like email.

Re:I do it too (5, Informative)

Colonel Korn (1258968) | more than 4 years ago | (#30325098)

I also go through my client list and drop those that consume more of my time and resources in favour of the easier clients who ultimately improve my business at a lesser cost. What's wrong with that? My company, my rules. "We reserve the right to refuse service to anyone" -- it's in every restaurant. Why would you expect a business to serve you? Why would you consider it a right?

Your company's service isn't based on federal subsidies meant to provide internet access to all citizens.

Charge us per GB (0)

T Murphy (1054674) | more than 4 years ago | (#30324880)

Charge for internet like electricity. You get charged for the power used, not the power available, and you get charged less during off-peak hours. If bandwidth hogs insist on running torrents during peak hours, they are just helping to pay for system upgrades. I don't trust the ISPs, so the government would have to enforce the rate of a basic connection (such as 256k with 20GB/month), and the government would have to enforce some amount of expenditure on system upgrades. In theory, the upgrades would allow the basic package to improve without much change in price.

The other option is to be annexed by Finland.

Anonymous Coward (0)

Anonymous Coward | more than 4 years ago | (#30324910)

He's obviously never met any of my previous roommates. The bandwidth hog(s) is/are alive and well.

-Dras

bandwidth limiting per process (0)

Anonymous Coward | more than 4 years ago | (#30324984)

perhaps slightly off-topic, but does anybody here know about a way to limit bandwidth consumption on a per-process basis under linux?
for example, if i wish to limit bandwidth usage of my torrent client, how do i do that?

i've seen some horribly complicated methods using iptables, so i was wondering, is there anything simpler?

Ut Oh (1)

bittles (1619071) | more than 4 years ago | (#30324990)

Shit! they're on to me! 200+ torrents in transmission, nooooo I'm not a bandwidth hog.

Elusive? (1)

2names (531755) | more than 4 years ago | (#30324996)

Ted Nugent has 10 of these hanging on his walls.

Using what you bought (1, Redundant)

gmuslera (3436) | more than 4 years ago | (#30325048)

If you bought a month of internet use at up certain speed, you can't be blamed if you use it, even if you use all of it. If doing that causes problems to other customers or the ISP, is isp fault for selling more than what they have, not yours.
Load More Comments
Slashdot Login

Need an Account?

Forgot your password?

Submission Text Formatting Tips

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

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

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

<ecode>    while(1) { do_something(); } </ecode>