Slashdot is powered by your submissions, so send in your scoop


Forgot your password?
DEAL: For $25 - Add A Second Phone Number To Your Smartphone for life! Use promo code SLASHDOT25. Also, Slashdot's Facebook page has a chat bot now. Message it for stories and more. Check out the new SourceForge HTML5 Internet speed test! ×
Networking The Internet Technology

Netflix Compares ISP Streaming Performance 209

boustrophedon writes "The Netflix blog compared streaming performance among 20 top ISPs for the past three months. A Netflix HD stream can provide up to 4800 kbps, but the fastest American ISP, Charter, could sustain only 2667 kbps on average. Most Canadian ISPs beat that, with champ Rogers providing an average of 3020 kbps. Clearwire, Frontier, and CenturyTel were in the doghouse with under 1600 kbps."
This discussion has been archived. No new comments can be posted.

Netflix Compares ISP Streaming Performance

Comments Filter:
  • Reverse the tables (Score:5, Insightful)

    by MrDoh! ( 71235 ) on Friday January 28, 2011 @08:06AM (#35030390) Homepage Journal

    Very nice. Rather impressive to pre-empt the ISP's.
    "well, your competitor is able to provide better speeds to more customers, why are you whining? Oh? AND You charge more for lower service? Interesting. Well, lets let your customers decide for themselves with more facts who they want"

    It'd make sense at this point for an ISP with a bit of sense to make a nice deal with Netflix to improve things here, then everyone wins.

    • Very nice. Rather impressive to pre-empt the ISP's. "well, your competitor is able to provide better speeds to more customers, why are you whining? Oh? AND You charge more for lower service? Interesting. Well, lets let your customers decide for themselves with more facts who they want"

      It'd make sense at this point for an ISP with a bit of sense to make a nice deal with Netflix to improve things here, then everyone wins.

      Not very nice. Remember the two-tier thing in UK []? Perhaps Netflix is trying to reverse that in its favor by hinting for 'arrangements'? Shady deals like that won't really work in favor of the consumers.

      • by MrDoh! ( 71235 )

        If you've got the choice, and the figures to back things up? Perhaps.
        "ok, this company is offering internet for 40 bucks a month, and I get the option for an extra 5 bucks to get Netflix bundled in" (which a smart ISP here, if traffic IS that popular, might be worth getting in on.
        "or I can spend 30 bucks a month, and Netflix works, just not in HD, but I've the choice"

        Ok, ok, it's more likely the ISP's will charge extar for netflix, AND you'd need a seperate netflix account AND if you don't pay, they'll slow

      • Funny thing is, I'm only paying for 3 Mbit/s internet with Rogers in Canda. However, ever since I started using Netflix, my connection suddenly started going at 10 Mbit/s. And not just for Netflix, but for the entire internet. Maybe Rogers got some inside information that Netflix was going to be collecting and releasing this information, and they upped the speed of all customers who they noticed accessed netflix. The change in speed has lasted too long, even through multiple power outages, and was too c
    • by Mousit ( 646085 ) on Friday January 28, 2011 @08:45AM (#35030608)

      ...Well, lets let your customers decide for themselves with more facts who they want"

      Though unfortunately for many customers (the majority I'm sure), "who they want" is a choice between that ISP or nothing, so it doesn't help them too much to simply tell them hey, they're getting screwed.

      However, I would like to see this broken down into smaller areas. By region, or even by city, rather than just the ISP as an overall average. I'd be very, VERY curious to see if the very same ISP performs significantly better in areas where there's some actual competition going on.

      That would be nice to wave around "look here, here's measured evidence of what they're doing in areas they don't have to compete".

      As an aside, I already kind of see this in my area. I have Time Warner broadband. In my personal location, they're the only choice; even DSL is not available to me. The highest service available is 15Mbps and I average 5-8 most of the time. However, in the sections where Verizon FiOS is also available and competing? Why, suddenly Time Warner's got a 50Mbps service available which averages 35-40! Imagine that..

      • by Belial6 ( 794905 )
        Well, this kind of report can do a lot to bring awareness to the masses about what is going. Most people don't know what their speed really is, and thus don't care. They take the marketing terms 'fastest' and 'unlimited' and assume that they are getting the best that is available. People do care about their TV though. If they find out that their ISP is breaking their TV, they are going to be outraged. This is particularly true if it a cable provider that is breaking their TV.
    • by Bengie ( 1121981 )

      ISPs should have to advertise their "dedicated" speed as their speed and the "up to" speeds ad burst

      eg. 16/2 with no cap, but once you add in over subscription, it's more like 2/1 dedicated with up-to 16/2 burst

      If an ISP has a data cap, that should have to calculate into the "dedicated" speed.

      eg. 16/2 with 100GB cap would list as 160Kb/160Kb with up to 16/2 burst. I listed 160Kb for up and down because most caps include up and down, so it would be split evenly.

  • Ah Rogers (Score:5, Informative)

    by Kris Warkentin ( 15136 ) on Friday January 28, 2011 @08:12AM (#35030412) Homepage

    Yeah, my cable modem is stupid fast....only problem is, running full tilt I can go through my monthly bandwidth cap in eleven and a half hours.

    Fortunately, for the moment, the overage cap is $50 so if you download a bunch some month you just say, "Woohoo, unlimited bandwidth." For example, in January I downloaded 750MB which put me 625MB over my cap and would have cost an extra $780. Ridiculous no? And now the CRTC (equivalent of FTC) has ruled that the major ISPs are allowed to pass usage based billing fees onto third party providers which means there will be no more unlimited plans and the billing cap will likely go away.

    Basically, Rogers and Bell want you to watch their channels, not use Netflix, AppleTV, etc. And the wretched hive of scum and villany known as the CRTC is letting them do it.

    Not much point in fast internet if you can't use it.

    • Oops...meant FCC, not FTC.

    • by Malc ( 1751 )

      For example, in January I downloaded 750MB which put me 625MB over my cap and would have cost an extra $780

      Was this on your phone (sounds a bit cheap for Rogers Wireless :P), or did you mean GB?

    • by KiloByte ( 825081 ) on Friday January 28, 2011 @09:56AM (#35031248)

      only problem is, running full tilt I can go through my monthly bandwidth cap in eleven and a half hours.

      We badly need a "truth in advertising" law that would make it illegal to label a "100Mbps connection" with a 5GB monthly cap as anything above the 16331bps it really is (yes, less than 16kbps, this is not an error). Providing a bigger burst is ok but only if that's clearly marked as such.

      Toss in something about the scam that lets ISPs call 100Mbps down/128kbps up by the bigger number. If you want to use just one number, you'd need to print the lower one. Anything else is deceiving the customer.

      • by clodney ( 778910 )

        We badly need a "truth in advertising" law that would make it illegal to label a "100Mbps connection" with a 5GB monthly cap as anything above the 16331bps it really is (yes, less than 16kbps, this is not an error). Providing a bigger burst is ok but only if that's clearly marked as such.

        Toss in something about the scam that lets ISPs call 100Mbps down/128kbps up by the bigger number. If you want to use just one number, you'd need to print the lower one. Anything else is deceiving the customer.

        If you are attempting to compute the speed by dividing the bandwidth cap over the cap period, you end up with a meaningless figure. I don't use my computer 24/7, and the fact that I get 20Mb service for the hours that I want it, and never worry about my bandwidth cap means that for me (and no doubt the vast majority of consumers) the speed and the total volume need to be quoted separately.

        Same with up/down speeds - asymmetric connections don't bother me, because my usage is asymmetric as well.

      • by RulerOf ( 975607 ) on Friday January 28, 2011 @11:35AM (#35032682)

        label a "100Mbps connection" with a 5GB monthly cap as anything above the 16331bps it really is

        I completely agree.

        I'm getting more and more pissed off as greater numbers of people are beginning to understand what monthly transfer caps are, and then proceed to voluntarily or forcedly believe the outright fucking lie that these assholes are perpetuating (and that most folks here also believe!):


        Enforcing a limit on data transfer over a given period of time is a very direct and extremely effective method of completely alleviating the problems that can be caused by a small number of users consuming most or all of the bandwidth on any given, shared network segment.


        The statement that you just read, enclosed in [bullshit] tags, is 100% bullshit.

        It's a problem with bandwidth, not a problem with transfer. Don't ever believe the utter lie that these two concepts are inherently and directly correlated. While they can be correlated, they do not have to be, and, in true Slashdot spirit, they are most certainly not causal.

        Lastly, if you don't understand WHY what I say is true, think of it this way:

        Take a look at the gigabit switch sitting on your desk (or pretend you have one). You've used it very lightly. You just browse the web through it. Maybe some games. No youtube, no torrents, no downloading. You've owned it for a while now, and you've transferred about 10 gigabytes of data through it in that whole time.

        I own the exact same model, and I'm coming over your house later and swapping out switches with you, but the difference between your switch and mine is that I pushed 5 terabyes of data through mine every single day I've owned it.

        Given that neither switch is defective, when I switch hardware with you, will you notice the difference?

        The worst part about this whole thing is that bandwidth is a fundamental commodity and property of multi-segment interconnected networks in general (read: the Internet). It's so fundamental that, rather than paying specifically for the connection speed of a physical link into someone's network, ISPs pay specifically for bandwidth usage based on a well accepted model commonly called 95th percentile billing [] because of how fairly and accurately it reflects a given link's impact on the network. Overall transfer over a given period, while it may be calculated, is irrelevant because the amount of data pushed through a link simply doesn't fucking matter. Data transfer at all levels of a network is a function of bandwidth, not the other way around. Were you to graph it out as a function, as time approaches infinity, transfer does as well.

        On behalf of the ISPs though, this misconception and billing model is absolutely genius. If I literally possessed a LIMITLESS source of product (data transfer) and, irrespective of size, somehow managed to convince you that it was reasonable for me to charge you for a finite, expiring quantity of it, I'd laugh all the way to the fucking bank every time you came back for more.

      • Cogeco's website has now clearly marked the bandwidth limits for each broadband speed here in my part of Canada.

        Sadly, here's the list (from their site []):

        $25 - 3Mbps - 10GB/mo
        $32 - 7Mbps - 30GB/mo
        $42 - 14Mbps - 60GB/mo
        $77 - 16Mbps - 125GB/mo
        $60 - 30Mbps - 125GB/mo (limited availability)
        $100 - 50Mbps - 150GB/mo (limited availability)

        The frustrating package difference for me is from $42/mo to $77/mo for almost no speed increase but an extra 65GB/mo. Interestingly, the over-use charges for the $42/mo service i

      • Well, it's not exactly a burst speed - I can run flat out at 3MB/s all day long. I see your point though - with the cap it amounts to a much slower overall rate if I want to stay off my limit.

    • Either you meant GB instead of MB or your cap is only 125MB. Even when Time Warner Cable was proposing ridiculously low caps, they chose 5GB. If any ISP decided that users should only download 125MB per month, they'd have a huge uprising on their hands.

  • by astern ( 1823792 ) on Friday January 28, 2011 @08:24AM (#35030478)

    ...but how in the hell is anyone supposed to pick the colors out of those graphs, at least three of them are the same shade of sky blue.

    I'd like to see this redone as the graph is certainly compelling, just a little bit more readable.

    • We normally can differentiate 8 colors easily on an RGB Screen

      With a background color we are limited to 7 graph points.
      I would have recommended after they first looked at the data they saw that they were in 3 distinct bands High, Medium, and Low. Then seporated the graphs in those bands. using the more primary colors.

    • The first thing is to blame the chart maker for not having any education in how to visually display quantitative information and for not putting any thought into people trying to read the chart and differentiate between a number of very similar colors.

      There's a number of things the chart could have that would have helped -- ensure no two similar colors are close (black and brown should be in the top band instead of 3 blues), callouts to indicate which line was which instead of relying on a color-coded legen

  • by Anonymous Coward on Friday January 28, 2011 @08:25AM (#35030488)

    Fantastic. The worst ISP in Canada is still faster than the best ISP in the US.

    Also, while interesting, this is basically useless to the average US consumer. It's not like you get a chance to choose between those 16 US ISPs. In the US, you're lucky if you get to choose between 2 of them.

    • Fantastic. The worst ISP in Canada is still faster than the best ISP in the US.

      Yes, but if you try to watch Netflix on a Rogers account you'll blow through the download cap by the second act of the first movie. You'll also be paying more for the privilege, and Ted Rogers will personally come to your house at night to empty the coins out of all your pockets and leave your milk out on the counter.

  • Fiber optical very high speed equipment (used behind the xDSL/Cable copper network and behind the wireless towers) has never been as cheap as its now.
    Long range gigabit ethernet stuff is dirt cheap.
    10 Gigabit ethernet, which allows 2 thousand 4.8Mbps streams is already very affordable for carriers.
    A pair of fiber strands can carry 16 10 Gigabit links easily, that's enough for 32000 top speed streams.
    Long distance fiber optical cables typically have at least 36 strands. Some reach as high as 144 strands. Do

    • by Bengie ( 1121981 )

      "ADSL is the best option for video, as long as you're close enough to your ADSL provider DSLAM that you can get fast enough speed. Cable is only better if you're far from the nearest ADSL DSLAM. DSLAM is the counterpart to the ADSL modem. Your ISP should be able to estimate your max link speed with your address and tell you when you're too far for your selected speed."

      My mom has fiber to the house, she lives about 2 blocks from her ISP's wiring building, she gets a 40ms ping to her first hop which has a DNS

  • by cwtrex ( 912286 ) on Friday January 28, 2011 @08:39AM (#35030566) Journal

    The different connections need to be split.

    For example, Verizon needs to have:

    Verizon DSL 768kbps - 1Mbps
    Verizon DSL 1.5Mbps - 3Mbps
    Verizon DSL 4Mbps - 7Mbps
    Verizon DSL 10Mbps - 15Mbps
    Verizon FIOS 15Mbps
    Verizon FIOS 25Mbps
    Verizon FIOS 50Mbps

    Obviously a low end DSL connection is not going to be the same as those who can order the 10-15Mbps DSL connection. And it is likely that the DSL 10-15Mbps connection is going to be different from the FIOS 15Mbps.

    To group all of those connections into one Verizon line is completely misleading. And if they didn't take measurements from all of those connections, then then that makes the results even more suspect as the graph doesn't specify what type of connection they chose to test with.

    • by papasui ( 567265 )
      All the service providers have multiple tiers of service, not as misleading as you seem to think it is.
      • by cwtrex ( 912286 )

        My point is that those different services need to be split or similar services for each tested and stated with specifics mentioned for each. Verizon was simply an example.

      • yes, but do all service providers offer tiers of service SLOWER than the highest speed netflix streaming offers?

        DSL providers = yes.
        Cable providers may not = yes (my local cableco's lowest offering is 12mbps)
        wireless carries = yes.

        so it is in fact, a POSSIBLE poor metric to use.

    • This is the collected stats from the real world. Picking out what tier of connection they have would be nearly impossible unless it's encoded in the reverse DNS. Associating an IP address with a particular carrier is easy anything past that is near impossible to determine.

    • by dkf ( 304284 )

      The different connections need to be split.

      Not really, especially as each of those ISPs has lots of complexity in their service portfolio so doing the split would be exceptionally tricky (and make the whole graph impossible to read, instead of just plain difficult). What I find more interesting is that the average level of service of the worst performing Canadian ISP would put it in the middle of the top performing group of US ISPs. Maybe it's because the US has a much lower population density than Canada? Or maybe it's because US ISPs prefer giving

    • by Gates82 ( 706573 )

      Mod parent WAY up.

      The first thing I thought when I looked at the graphs, what service plan are these people on. Most I know have the cheapest package they can find with connection speed upper bound at 1.5-5mbs. At those speeds the throughput Netflix is reporting look pretty good. I have a 20mbs connection (from an ISP not listed in the report) and over the summer I routinely streamed (@ 8mbs), the wife would have a Netflix movie on her laptop, and the kids watching some show from Netflix as well.

    • Yes, but penalizing Verizon (or company of choice) for having slow data rates will give them an incentive to upgrade them. I know many people choose slower data plans, but if I were Netflix, I would judge based on what's fastest around the area, within some reasonable price (say, $40/month). I wish they disclosed a bit more about their testing process.

  • The problem here is that you have the difference between the speeds the ISPs can run at and the speeds from the customer to Netflix. I am using the normal Cablevision 15Mbps service, and I DO see speeds up at around 11Mbps. Now, if I have to go through 5 other ISPs to get from Cablevision to the Netflix servers, the problem is the connections between ISPs is where the limits are, not Cablevision itself. The same may apply to the other ISPs out there, where you get the speeds, and you can get to man

    • by RingDev ( 879105 )

      Netflix has content delivery networks all over the country with partnerships with most major ISPs. The stream you are getting from them is likely not even coming over the back bone of the internet, but through a CDN linked directly to your ISP regional center.


  • "A Netflix HD stream can provide up to 4800 kbps"

    To how many people simultaneously? Somewhere must be an evidence (assumption) that Netflix servers work at less than 100% capacity. I am completely unfamiliar of these. Saying "A Netflix HD stream can provide up to 4800 kbps" and missing the total number of users trying to connect is not saying much about that.

  • All that this shows is that there isn't much difference between the ISPs. They had to scale the chart (it doesn't start at 0) just to show the differences. As Netflix commented in the linked post, their HD streams are much higher (4.8kb) than these graphs. Of course the graph is just an average, so it doesn't speak to how HD users are affected.
    • by guruevi ( 827432 )

      Yes it does, RTFA. They filtered out only HD-capable devices on HD-capable networks with HD-capable movies. They can stream 4.8Mbps but on average only seem to hit 2.4Mbps. You can notice the same thing if you use eg. YouTube or another streaming service at 1080p for long periods of time. I have TWC which advertises me a 10Mbps line which I can seem to burst into for the first 5 minutes of a YouTube video (I watch a lot of e-sports and I have a 27" High-Res screen which YouTube automatically selects 1080p f

  • I'm I reading this wrong? That's the limit that the ISP can reliably provide, right? Or are those numbers lower than ISP's max because many clients have low-end broadband connection (2M xDSL or something). My ISP can supply sustainably about 5 times that much. I'm on the other side of the Atlantic, but USA can't be that far behind?

  • This is exactly what we need. They should run this test daily and have a website dedicated to it.

    Better yet, the FCC should be running the test.
  • by lseltzer ( 311306 ) on Friday January 28, 2011 @09:35AM (#35031024)
    The larger the ISP, the more they’re penalized by the more rural regions which are limited to DS3 45 Mbps circuits feeding a whole town.
    • by papasui ( 567265 ) on Friday January 28, 2011 @09:51AM (#35031184) Homepage
      I'm gonna toss this out there. I've been designing isp networks for the last 10 years, including some of the ones in the list. I haven't seen an area that only has a DS3 as it's backbone in about 5 years, and even then it was 3 of them. And yes, I have worked in some extremely rural areas where the entire subscriber base has been less than 100.
    • Your point is? Larger ISPs should not be penalized because they screw over there rural subscribers? If the DS3 is the choke point put something bigger in. US ISP's are claiming all sorts of things to avoid upgrading there networks and often being shortsighted when doing those upgrades by putting the cheapest thing in right now but not the cheapest in the long run. In your own example there is no reason to have a DS3 in a ISP network, a single pair of dark fiber can get you what you need today and with o

    • This is not a population density or rural/urban issue at all. If it was then the Canadian ISPs wouldn't have averaged so much higher. Canada has the lowest population density in the world and has a significant rural population. However, its lowest ISPs would sit in the top few on the American graph and the top Canadian ISPs would actually sit above the American graph.

  • The AT&T numbers will suffer somewhat due to Uverse (VDSL) and regular DSL being sold at varying speeds. While I like the idea of 18-24Mbps, I can't reasonably afford it at this time.


  • Netflix streams at rates that effectively consume the entire subscriber subscription rate for hours on end. It is obvious from the postings which are being made that most who are posting are end users with no network design knowledge. So, here goes.

    Netflix streams at 1.0-6.0 Mbps at a fairly constant clip the entire time a movie is playing. There are exceptions to this behavior. But, for the most part, that is the picture the network engineering folks see. Now, take a rural telco of 5000 access lines

    • by RingDev ( 879105 )

      Actually Netflix is paying for the CDN services, so the ISP isn't paying for upstream. Heck, in the case of Comcast, Netflix is even paying THEM too accept the CDN connection instead of going over their upstream providers.

      The ISPs have over sold their lines. No surprise. It's not possible for an ISP to provite 100% (2000 customer in your example) 3Mbps service consuming 6Gbps of bandwidth for $30,000 in revenue. They can't even provide an order of magnitude LESS than that for $30,000.

      Historically though, th

    • Netflix is paying for the bandwidth on their end, so it's not like they're getting anything for free. The issue is that all of the sudden people want to stream massive amounts of information and it's breaking all the assumptions that went into oversubscription ratios.

      The answer is for ISPs to be honest about what they provide. If there's a monthly cap, say so.

      That said, it would be good for netflix users to be able to pick a speed and have it stay there rather than sucking up all available bandwidth.

  • They don't differentiate between offerings from each ISP. An ISP the majority of whose users are on slow 1.5 Mb/s connections (but with a few on super-fast 20 Mb/s connections) would fare poorly in this exercise compared to a competitor with of its users on mediocre 4.0 Mb/s connections. As a consumer interested in bandwidth, though, I'm going with the first ISP assuming their backbone is capable enough to actually feed that 20 Mb/s pipe.

    Where I live the two highest-performing options are Time Warner (Roa

  • by joeszilagyi ( 635484 ) on Friday January 28, 2011 @12:26PM (#35033510)

    Is the real offense here by Netflix, as evidenced by comments there on the site, is that they've exposed the dirty little secret of many ISPs--that they oversell capacity?

  • The graph doesn't accurately represent the data. Note the Y-Axis. It's values are as follows:
    - - - - - - - - -
    - - - - - - - - -

    Without taking the axis all the way down to ZERO, the graph gives the impression of greater disparity than there actually is. You see this frequently with tech review sites where they start a bar graph at "140fps" so that a difference of 3fps looks epic and the shelling out of $40 more on one video card is suggested.

  • I have frontier DSL with only 3mb down and 1.5 at night... It is horrid sometimes I can only get 1 bar of quality from Netflix and this is their highest plan in my area even though I am right next to fiber lines to Purdue University. Frontier needs to wake up and build a better network IMO. Also Verizon shouldn't have sold out.
  • that's there's actually someone below Centurytel.

"In the face of entropy and nothingness, you kind of have to pretend it's not there if you want to keep writing good code." -- Karl Lehenbauer