Hunting the Mythical "Bandwidth Hog"
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.
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.
There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
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.
Because TCP doesn't allow it.
I hear all the websites are switching from token ring because of this.
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......
Why would any business cancel paying customers that don't negatively impact operations?
All ideas^H^H^H^H^Hprocesses in this post are Patent Pending. (as well as the process of patenting all postings)
I'd love to see the result of such a data analysis.
So the telcos are like, "Felten who? Yeah, we'll get right on that"
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.
I would give everything i own for a little bit more.
lol, you give us AC's a bad name.
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?
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.
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.
--
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.
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?
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?
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.
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.
I'd rather you do it wrong, than for me to have to do it at all.
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.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
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.
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.
I can hear them now saying "I'm in your networkz hogging your bandwidth."
I regret that I only have one mod point to give per post.
"... 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.
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!
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.
sed -e 's/Chuck Norris/Rajnikant/g' joke > fact
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.
Cannot find REALITY.SYS. Universe halted.
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 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?
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.
My webcomic
He's obviously never met any of my previous roommates. The bandwidth hog(s) is/are alive and well.
-Dras
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?
Shit! they're on to me! 200+ torrents in transmission, nooooo I'm not a bandwidth hog.
Ted Nugent has 10 of these hanging on his walls.
"I'm just here to regulate funkiness."
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.
Try posting in plane old text.
if you want to use HTML, use
.
First of all, I am, and always will be, a bandwidth hog. Why? Because I'm better at using the internet than everyone around me. That means I find more things, and bigger things, to download. If they someone banned P2P, I'd still have more streamed video than anyone I know. If they banned that, too, I'd still download more images. If they banned that, i'd still have more web traffic, email, IM, etc etc etc. I will always be a 'hog' in any environment. I was even told that I was "#1 abuser" of the "Unlimited" service when I was on dial-up in a small town and they tried to charge me an extra $300 that month. As someone else had just come into town, I switched, obviously.
I don't pay for the top tier of residential service to just let it sit idle. I'm going to -use- it.
I have absolutely no sympathy for people that sell me something and then get upset when I actually use it within the original limitations. I have only a small amount of sympathy for people that sell me something and I use it beyond their arbitrary limitations, even if I agreed to them.
Why?
America has -crap- for internet compared to other developed countries. We are quickly falling behind the rest of the world in terms of internet bandwidth. This is purely from greed and laziness on the part of the ISP. They refuse to upgrade and try to prevent competition at the same time. Sprint even has the nerve to advertise Pure and claim that it's faster than Cable internet, despite being 1/10th of the speed.
"If you make people think they're thinking, they'll love you; But if you really make them think, they'll hate you." - DM
That having said, a more complex implementation of TCP might do it differently and reduce the bitrate for all session coming from one IP-adress.
It is all a design choice.
No. There is no way to change TCP to do this. Congestion control is handled at the end hosts. Intermediate switches and routers just fling the packets. You can't solve a layer 2 problem at layer 3.
I work at an ISP for corporate clients and I can tell you we have customers that are "bandwidth hogs". For instance, we have one well-known customer that uses something like 60% of our capacity in one of our locations, a site which has hundreds of customers. The thing is, we charge by 95p bandwidth. This means they pay us much more than the other customers, which allows us to invest in the hardware and other infrastructure needed to handle their traffic.
a.k.a ManBearPig!!!!!!!!
If you pay for up to 10MB per second bandwidth service then the ISP is selling you a Maximum 10MB/s x 31536000 seconds in an average year. I believe this is a maximun of 315.4TB a year they are being paid money to provide.
The "average" person will never use that much but this is what is advertised, paid for, and agreed upon. The ISP should be held responsible to provide the agreed upon and paid for service. If they cannot provide then they shouldn't be selling the service, not punishing the people that are paying for the agreed upon service. IANAL, just my opinion.
I thought bandwidth hogs had a name already. They were called spammers.
Unlike streaming technology that is consistent and less likely to impact other users on the same network (unless they're attempting to stream the same thing from the same sites), spam tends to be bursty and disruptive for other network users.
Just asking.
Warning: this article may contain humor, sarcasm, parody, and perhaps even irony. Read at your own risk.
There have been times when telephone networks, wireless networks, and utilities have been knocked offline due to too much demand. Most utilities have "turn off" agreements with heavy industrial users who can tolerate a shutdown in exchange for a concession, such as a lower rate, to ensure consumers still have service.
Even that doesn't work. Witness the jammed cell-phone lines after a major event or in days of yore jammed long-distance phone lines on holidays.
Cutting off or throttling heavy users during times when the network is saturated is sensible. A more sensible route is to charge by the GB or TB, as long as the charge is fair and reasonable.
A fair and reasonable charge would be "X" for your initial allowance plus Y for every block of bytes after that point. X would cover fixed costs such as the cost of billing. On a per-byte basis, X would be higher than Y. A fair and reasonable charge could include time-of-week-sensitive, bitrate-sensitive, and quality-of-service-sensitive billing. For example, there could be a 20% surcharge during afternoon and evening hours, a discount when you voluntarily throttle to a very low bitrate, or a discount when you accept a lower quality of service, such as for bulk file transfers.
Involuntary speed reductions or QOS reductions could be imposed on either heavy users or those users who volunteered for them in exchange for a discount when the network is saturated. These should not last more than the duration of the saturation, and the effect should be spread around in a fair way. Of course, since customers are paying by the bit and paying higher for higher-rate/higher-quality transmission, every time a service provider did this they would be hurting their revenue stream, at least a little.
Knowledge is how to play a game, intelligence is how to win, wisdom is knowing what game to play.
That's why i choose the cheapest internet money can buy 250kbps/128kbps ~9€/month :D
I keep DC++ up around the clock on a silent 256 RAM 350MHz. I get on average
a movie per day, that's more then plenty for me.
Even Youtube often works _while_ p2p does two full uploads!
[HKEY_LOCAL_MACHINE\System\CurrentControlSet\Services\Tcpip\parameters] ;unlock larger TcpWindowSize And no Timestamp save 12 Byte every packet ;smoother traffic. 'd' also works, but perhaps high latency ;connections suffer if there's too long wait between ACKs... ;1-6 = 100-600ms Def=200 ;no extra packet overhead ;=4095 Def=1000(ms) between keepalives when no response is received ;Linux def=75000 (may have changed nowadays?) ;XPDef=5 requests for data. LinuxDef=9
"Tcp1323Opts"=dword:1
"TcpAckFrequency"=dword:9
"TcpDelAckTicks"=dword:6
"SackOpts"=dword:0
"KeepAliveInterval"=dword:fff
"TcpMaxDataRetransmissions"=dword:4
Carefully add one at a time and measure overall performance over time. Check if it
makes things better or worse or has no effect. I've been using these with no noticable
problems over several years.
Oh, and the 350MHz PC is also a DNS server, helps cut more traffic.
(i tweaked W2003 until it ran fine on 256 RAM)
Why would any business cancel paying customers that don't negatively impact operations?
They do it so they can tell the paying customers that they have to purchase "premium" access to maintain their use level. They know that there are plenty of people out there who are willing to do so.
Damn_registrars has no butt-hole. Damn_registrars has no use for a butt-hole.
I wonder if this just gets worse. Or traffic shaping to legit sites like Hulu, but degraded if I want the same content from iTunes or Amazon.
If I'm paying for a 15 mb connection, I should be able to use 15 mb of bandwidth 24/7 if I want to. If the ISP is going to limit bandwidth usage to a certain amount or throttle the connection during peak hours, the customer should be made aware of this before the purchase.
The Pareto Principle is well known in both IT and Businesss circles. It states that for many events roughly 80% of the effects come from 20% of the causes. (This is sometimes called the 80/20 rule) So it should not have suprised anyone that a fairly small group of so-called "bandwidth hogs" use most of the bandwidth. Since this is well known (Even MBA-holding PHBs should have heard of it) I have always called BS when ISPs bring up the bandwidth hog boogeyman.
Any insufficiently advanced magic is indistinguishable from technology.
Qwest wanted me to pay extra for their broken (won't work with my PVR) TV service. I declined. But their hand is tipped: they're happy with the idea of people using the wire for high-bandwidth multimedia. So yeah, by the ISPs' own standards, there is no such thing as a bandwidth "hog." You can stream all day at full blast, and as long as you pay extra to get it from their own (subcontracted) server, it's business as usual.
One problem is by default many network devices/OSes do bandwidth distribution on a per _connection_ basis not on a per IP basis. So if there are only two users and one user has 1000 active connections and the other has just one active connection the first user will get about 1000 times more bandwidth than the second user.
;).
;) ), BUT even when they "log out" they _still_ get always-on internet access except it's just on a lower priority (but NO byte quota!). A customer might be restricted to say 10GBs at "priority" a month.
P2P clients typically have very very many connections open. Wheres other clients might not.
A much fairer way would be to share bandwidth amongst users on a per IP basis. That means if two users are active they get about 50% each, even if one user has 100 P2P connections and the other user has only one measly http connection.
Then within each customer's "per IP" queue, to improve the customer's experience you could prioritize latency or loss sensitive stuff like like dns, tcp acks, typical game connections, ssh, telnet and so on, over all the other less sensitive/important stuff.
Of course if you have oversubscribed too much, you will have way too many active users for your available bandwidth. A fair distribution of "not enough" will still be not enough.
If you have two people and you give each a fair slice of one banana, they each get half a banana. Maybe both are satisfied.
If you have 1000 people and you give each a fair slice of one banana, they each get 1/1000th of a banana. Not many are going to be satisfied
And that's where we come to the other problem.
The problem with P2P is many customers will often leave their P2P clients on 24/7, EVEN when some of them don't really care very much about how fast it goes (some do, but some don't). To revisit the banana analogy, what you have here is 1000 people, and 1000 of them ask for a slice of the banana, EVEN though some of them don't really care - they'll only really feel like having a slice next week, when they're back from their holiday!
So how do you figure out who cares and who doesn't care?
Right now what many ISPs do is have quota limits - they limit how much data can be transferred in total. When the quota runs out "stuff happens" (connections go slow, users get charged more etc). So the users have to manage it.
BUT this is PRIMITIVE, because if you can figure out when a user doesn't care about the speed etc, technology allows you to easily prioritize other traffic over that user's "who cares" traffic.
So what's a better way of figuring it out?
My proposal is to give the customers a "dialer" which allows users to "log on" to "priority Internet" (and then only something starts counting the bytes
The advantage of this method is:
1) There is no WASTED capacity - almost all the available bandwidth can be used all the time, without affecting the people who NEED "priority" internet access (and still have unused quota).
2) It allows a ISP to better figure out how much capacity to actually buy.
3) If there is insufficient capacity for "priority Internet" the ISP can actually inform the user and not put the user on "priority" (where the quota is counted). While the user might not be that happy, this is much fairer, than getting crappy access while having your quota still being deducted.
Perhaps this system is not needed and will never be needed in countries that don't seem to have big problems offering 100Mbps internet access to lots of people.
But it might still be useful in countries where the internet access and telcos are poorly regulated/managed. For example - you run a small ISP in one of those crappy countries and so you pay more for bandwidth from your providers- this system could allow you to make better use of your bandwidth and to be a more efficient competitor. And maybe even give your customers better internet service at the same time.
Yes the ISP could always buy enough bandwidth so that _everyone_ can get the offered amount even though not everyone really cares all the time (believe me this is true). But that could mean the ISP's internet access packages being much more expensive than they could be.
SELECT user_id FROM usage ORDER BY bytes_out DESC
or is that assuming too much?
It won't work because for 90% of internet users their monthly bill will go DOWN, a LOT.
I use an old Samsung pre-pay mobile, my average monthly cost is less than 2 dollars.
Which is why telco's LOVE stuff like line rental, monthly plans, etc etc etc.
The whole cost of bandwidth thing is just arbitrary bullshit, the actual physical cost of running a given pipe at 0% capacity, and the same pipe at 100% capacity, is measured in cents worth of electricity per hour.
It is artificial scarcity, no more.
http://slashdot.org/~GuyFawkes/journal
X would cover fixed costs such as the cost of billing.
Billing is a very large cost. In the telco world, the cost of billing passed the cost of transmission about two decades ago. That's even more true for Internet transmission at the retail level. With proposed "economic" solutions, you have to factor in the costs of billing. Those costs apply both to the provider and the customer. If customers have to meter to control their expenses, that's a cost to the customer in attention, and drives business to competitors that require less attention.
Handling one phone call about a billing complaint eats up months of profits from selling the service. Complex billing means big call centers.
It's actually much less than wrong; overselling is precisely what a communications network like the Internet was designed to achieve. Bandwidth on long-haul communications cables is a limited resource. The Internet is a scheme to share that bandwidth efficiently by overselling it.
Do you think that the existing transatlantic cables, taken together, have enough bandwidth to allow everybody in the USA with an Internet connection to simultaneously get their local maximum bandwidth to Europe? The whole point of the way the network is designed is that since the majority of the users aren't sending packets to Europe at any given time, they get a better deal (bandwidth/price) on connectivity by sharing a transoceanic cable that might not be able to accommodate them all at once, instead of each of them setting up their own dedicated transatlantic cable or channel.
This isn't the case only for Internet, but also for the old phone network ("all circuits are currently busy"), the power grid (blackouts during times of heavy use), or pretty much any public utility.
Are you adequate?
There is no evidence that santa clause do not exist either. Everyone grown-up person will agree it a myth tho.
I believe you meant Sanity Claus. ;)
[UID-HeinzIntel]
I know, do not feed the trolls ;)
I'll bite: I FULLY AGREE WITH YOU!!!
The only bandwidth hogs I know of are the ad servers.
Except this is no longer true in a full-duplex world, you can approach 99% utilization on Ethernet at full-duplex. At the time token-ring was competitive, full-duplex Ethernet was just emerging. While IBM's marketing and some of the complexity of token-ring hurt it, what really killed it was the widespread emergence of full-duplex ethernet switches which basically eliminated the under-utilization problem while not having the complexity of dealing with a token-ring network.
Agreed, lots of people seem to think that ethernet implies CSMA/CD and make claims about modern ethernet networks based on CSMA/CD ethernet networks.
note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
Some of us have plenty use for 100mbit connections. 720p video streaming, voip telephony, video or audio conference, remote desktop, desktop view sharing all require higher through put. Most of them as well as gaming also require lower ping time. You also have multi processing network such as distributed network video encoding and application over terracotta cluster that you can actually set up at home over the net with your friends. Some people lack both experience and imagination in using the bandwidth given, that does not mean those of us who can dream and produce should be held back by lower standards.
Where is the "Ignorant" mod tag?
Problem is, they oversold bandwith to the point, where upstream is saturated. So, you cancel heavy user, or preferably heavy users with a high percentage of unique traffic. Because that's all you can do as an ISP once your backbone is gone.
What are the options here? Upgrade their network to pretend like everyone will use the max speed like 75% of the time and charge me $300/month for internet to make up the expense OR disconnect someone that's taking up the same amount of bandwidth as 100 other average users. That's 100 customers worth and they're paying 1/100th as much for what that service would cost. I say kick em out. I'm a web designer and a very busy geek in general who uses youtube and Hulu and online games and I still don't even come close to the assholes that run downloads basically 24/7 just because they can and they're greedy.
Google's Super Secret Search Algorithm: SELECT @search_results FROM internet WHERE @search_results = 'good'
This must be some new definition of the word "corrects" that I am not familiar with.
'The tyrant will always find pretext for his tyranny.' - Aesop's Fables
In most cases, this is the fault of the companies who advertise "high speed" and leave open the implication that you can do anything you want with it. Put that in front of a geek and we will push those limits and come up with a dozen new ways to use that bandwidth up.
In a past incarnation I worked for a CLEC who had a large number of bank customers who used 64 Kbps DDS circuits for each automated teller machine. Everything went through a frame relay connection and those customers would constantly tinker with their Bc Be and CIR values for each frame circuit. We spent an inordinate amount of time each month tweaking each circuit to the new values that the customer wanted.
The big secret was that we did not penalize them for sustained bursts of traffic. Of course we told them that we would and that we would drop packets if they went beyond the duration of a burst. As long as the connections did not overwhelm our backhaul off of the data switches we never really cared too much. A few customers figured that out and if I had a moment of morbid curiosity I would peek in at their usage and see a high sustained data rate (usually a branch office and not an ATM and their IT folks would try to do backups across the frame relay network at night).
Tisha Hayes
Though I honestly think that mesh networks can work, I am kind of against broad use of municipal wifi because it really doesn't scale well as it is now. Better, broader, lower frequency signal ranges are needed for even mesh networks to scale well in congested areas, and as it stands it's the cellular/wireless carriers that are snagging most of the bandwidth that gets opened up.
THEY do! They're everywhere, clicking the links in the summaries on tech sites.
I just got my bill from Cogeco Cable the other day up here in Ontario, Canada.
I has rather pissed to see that I got charged an additional 30$ on top of the 70$ I already pay monthly for my CableTV/Internets. My cap is 60GB and I exceeded that. I don't contest that. I also concede that Cogeco has a right to charge for extra bandwidth over cap.
What does piss me off, is that they charge 1.50$ a GB, where it should be more inline with 0.25$ a GB. They and Bell are using their duopoly to artificially inflate their numbers as usual.
However even that I could maybe live with, what really pisses me off is that we are more less blind. You see, as part of your online account services you can monitor your "Internet Usage" which I did use to make sure I didn't exceed my cap. In most cases I can schedule my downloading appropriately to my cap, and if I REALLY want to download, then I have full disclosure and know how much it will cost me if I so choose. However, what they DON'T tell you (if you search around it is in small print someplace) is that the stupid POS "Internet Usage" tool, only updates every day or two. So what happened to me is I starting downloading, hit some great speeds, and basically killed my cap and exceeded it in TWO days without notice. Then on the third day I see I am at 150% of my cap, up from 0%. That sure is a useful tool!
Sure one could argue, that its your responsibility to keep track of this sort of thing, however I would argue they your wrong. For one you are paying for this service they should be required to provide this better, and secondly they are the ones stipulating a limit on you, they should be responsible for monitoring not me. At any time (and I never have) I could march outside and look at my electric meter, and see exactly how much I have used and are currently using.
God I hate them so much.
Top 5% of users probably consume around 30% of the total bandwidth. That means they need to pay for 30% more out-of-network core bandwidth. Is that cost footed by the heavy users? No. It's distributed across every paying customer.
The technical analysis of how TCP works is a bit flawed. Dropped packets from the server to the client show up as unacked bits in the stream being sent. The server will have a limit of how many bits it will send from the previous acked bit. Thus, if it stops receiving acks, it will continue to resend data that was sent previously but un-acked. Thus, the server does not reduce the number of packets it is sending, it just keeps re-sending data that has not been acked. The only rate limiting in TCP is the rate of 'new' data sent.
There are also other conditions that occur that break this assumption that TCP will slow everyone down equally. Any effects of TCP self-limiting its rate of transfer will only impact long connections, not connections that are established for a short period... such as an http get/response on a small file, DNS requests, etc.
ISPs disconnecting "bandwidth hogs" is about as proper as The Phone Company disconnecting customers with teenaged daughters (for those of you who remember the days before ubiquitous cell phones, anyway)
Some sites sort statistics by who used the most and, if that amount is much more than anyone else, they cut off that user, even if there was no problem with that amount of usage. Find the outliers for a month, penalize or cut them up, repeat until your user base is sufficiently cowed.
My city's government website silently cut off my employer's access by IP range because I was accessing too many traffic cameras at once for too long of a period of time (building a time-lapse video of snowfall and melt across the city, from at most 3 IP addresses not simultaneously). The government website simply pretended to be off-line to our subnet (stopped at their router). Human Resources was unable to do criminal background checks on potential employees (head of HR is retired law enforcement). They expected anyone they cut off to contact them to regain access.
Thing is, if I had used a service like TOR to anonymize my IP address for this, they wouldn't have been able to identify any particular IP user or IP range as an outlying bandwidth user and they probably wouldn't have noticed it at all, though it would frustrate the timing for the timelapse video.
It's like they're trying to organize the data in ways that let them find witches to burn.
Oh, say does that Star-Spangled Banner entwine / The myrtle of Venus with Bacchus's vine?
I can't tell the difference between the Netflix HD movies and my DVDs (i.e. they come in at DVD quality), and I get that at 3mbit, and voip, RDP, and desktop sharing don't require all that much bandwidth for what they do - the big issue with all of those is latency, not bandwidth (after a certain point, very low bandwidth would be an issue). Video conferencing will use a bit more than those, especially if you have a very high quality video conferencing setup, but I would be extremely surprised if you saturated a 10mbit line with that, and certainly you aren't using more than 20mbit.
Also note that a 100mbit connection can have a latency of 4,000ms just as easily as a 56k line. Latency has absolutely nothing to do with bandwidth, and those applications you mention all require very low latency to achieve high quality results, but except for video they don't require much bandwidth at all. And the video requires a lot less than you think it does. Hell, if your latency is really bad even web pages will load slowly. It would look kind of odd, you'd click a link and wait, and wait, and wait, and wait, and all of a sudden the page would be there, regardless of what it was. You wouldn't get slow page loads, you'd get delayed page loads, which can be even more annoying. You'd be able to send 12 megs per batch of packets, but if it takes 5 seconds to get to the destination it's still going to take 10 seconds to load (5 there 5 back).
You're not dreaming and producing as much as you think you are if you think all of that stuff is saturating your 100mbit connection, either that your you aren't paying attention to what your true throughput is and you're only really getting less than an average 5mbit connection would.
Where a 100mbit connection would be useful is in massive downloads. If you download 30-40 gigs a day, you might find a 100mbit line usefull, as downloads don't care about latency (it just queues up the next packet, any latency just means it starts a few seconds later) and your downloads would be extremely fast. Any packets that drop are simply re-sent later.
Security is mostly a superstition... Avoiding danger is no safer in the long run than outright exposure. - Helen Keller
I saw first hand a print out done by a ISP. Has customer ID, bandwidth, bytes transferred, log on time, and time in session. In a neat roll it showed several customers. They can have more information I suppose if they wanted. I do realize that the ISPs think they are in a pickle about whom is hogging what. But I do also hope they keep in mind many more people are logging on to do more than download from a file sharer website. Many more work at home just to be able to keep their jobs. If you start limiting bandwidth per month eventually it will harm those that need it most. I have never seen a controlled limit not get out of hand. I also never seen such a limit put on customers that did not hurt a few regardless of the size of the limit. Those that will hurt the most are those that do work at home two or three days per week, or work full time at home.
Respectfully I don't want to see any type of Limits period done by any ISP. You are just opening Pandora's box. Everything a ISP does from that day forward will have a excuse as to why it's needed. Give them a inch, and they will take a mile.