Hi, I'm Dave Temkin, and I work for Netflix. I'd like to dispel a few incorrect assumptions portrayed in this thread. I'm going to avoid going point by point, but will try to cover the concerns raised broadly. First and foremost, we built our CDN, Open Connect, with the intention to deploy it as widely as possible in order to save ISPs who are delivering our traffic money and improve our mutual customer experience. This goes for ISPs large and small, domestic and international, big endian and little endian. We've never demanded payment from an ISP nor have we ever charged for an Open Connect Appliance. When we first launched almost three years ago, we set a lower boundary for receiving a Netflix Open Connect Appliance (which are always free) at 5Gbps. Since then we've softened that limit to 3.5Gbps due to efficiencies of how we pre-load our appliances (more on that below). We explicitly call our "cache" an Appliance because it's not a demand driven transparent or flow-through cache like the Akamai or Google caches. We do this because we know what's going to be popular the next day or even week and push a manifest to the Appliance to tell it what to download (usually in the middle of the night, but this is configurable by the ISP). The benefit of this architecture is that a single Appliance can get 70+% offload on a network, and three appliances clustered together can get 90+% offload, while consuming approximately 500 watts of power, using 4U of rack space, and serving 14Gbps per appliance. The downside of this architecture is that it requires significant bandwidth to fill; in some ISPs cases significantly more than they consume at peak viewing time. This is why our solution may not work well for some small ISPs and we instead suggest peering, which has 100% offload. We've put a lot of effort into localizing our peering infrastructure worldwide. As you can see from this map (sorry for the image), we're in 49 locations around the world with the significant bulk of them in the US (blue pins = 1 location, red pins = >1 location in a metro) - more detailed version at http://goo.gl/eDHpHU and in our PeeringDB record ( http://as2906.peeringdb.com) : We constantly re-evaluate the best places to deliver our traffic from and this year alone (2014) have added 14 POP's and still have at least 4 more to go. We continue to make large capital expenditures and invest human capital in making our streaming technology more efficient to ensure a lower cost of delivery for our partner ISPs and consistent quality for our mutual customers. I'm happy to answer any questions or address concerns, and as always you can reach out to (peering)@(netfilx).com -Dave Temkin Director, Network Architecture & Strategy On Fri, Jul 11, 2014 at 5:27 AM, Dave Bell <me@geordish.org> wrote:
Would it be right if Netflix comes to You and says we see you've got a lot of our customers hooked up to your backbone so to serve better service we'd like to connect to your network directly.
Yes. As an eyeball network operator I pay my transit provider to get the packets my customers want to me. Content providers pay their transit providers to get their packets to my customers. If there is a way we can cut out the transit provider, why wouldn't we?
And Netflix goes: well how about you build the link to us bearing all the costs and you gonna charge us nothing for the transport you provide, deal?
This isn't exactly how it goes though. Netflix are able to peer at around 25 locations in the US. The chances of a large ISP not having at least one common point are pretty slim.
So then it goes down to an interconnect cost across a building. I'm in the UK, and I know the price that we pay is not very much at all. I wouldn't be surprised if Netflix were willing to split the cost of this link.
Then we are down to port costs. These days a 10G port costs very little indeed. And of course the larger you are, the more buying clout you have, the less it costs. Combined with the fact that you are taking traffic off your transit connection, therefore paying a smaller bill, it is very likely that this will work out in a profit situation.
c) You could not give a damn about your customers as they have nowhere else to go anyways and use this advantage to force Netflix to become your customer (well paying customer as they would need big pipes).
This appears to be what Comcast, Verizon etc are doing. Instead of paying to receive the packets from their transit provider, they want to be paid to receive them instead. I wonder just how much the recent price increase from Netflix was to help fund the extortion they are being subjected to?
Dave
