Peer2Peer s*cks, here’s why
Peer2Peer (P2P) is sometimes proposed as an alternative for distributed content delivery. Some CDN’s are built upon P2P technology. P2P vendors, researchers and CDN’s claim that P2P lowers costs. It does. For the content owner. But it raises costs for the network owners. Significantly.
Basically the concept of P2P is that every client can redistribute content to other clients. As a content provider you don’t need to buy servers or traffic. Your audience distributes your content ‘for free’. Ingest the content into the network and let it flow. It is also hard to trace where content is hosted and ingested from. That is why P2P is so popular for (illegal) file sharing services.
To use P2P you need a P2P client. When you search for content, your client will lookup which other clients already have the content, and will start downloading chunks from each client. When all chunks are downloaded, your P2P client stitches them to a file. The more popular the file, the more clients have it, the faster you can download.
1) The first problem here is that P2P is geo unaware. If your client can download chunks from Australia, Brazil, USA and Germany, it will do so. So P2P does exactly the opposite of what a CDN does: it generates more global traffic, even more than with regular hosting from a central server. Some P2P developers have made their technology geo aware. This means that the P2P client will only download chunks from within the same IP range, ISP or country. That helps a lot. But this also brings down the number of peers. You may not find that asset at all. Or the download could be really slow.
2) The second problem is that P2P generates a lot of overhead traffic. P2P clients are constantly seeking for peers with assets. There is also a lot of download overhead communication between peers.
3) The third problem is that P2P generates a lot of upload traffic. Most P2P clients are active and are uploading chunks to other peers, even if the user is not actively using the P2P application. This can saturate their link and can dramatically decrease the performance of other services that the user does want to use at that moment. This upload traffic has to flow over the ISP’s networks. The ISP’s are paying for this traffic.
4) The fourth problem:perhaps the biggest misconception about P2P is that traffic between peers is always distributed 1-on-1. Many DSL broadband providers have one big star based network for the entire country. All traffic flows through a central DSLAM. So even if you share content via P2P with your direct neighbour, who is connected to the same ISP, via the same dispatch, all your neighbours traffic has to be uploaded to the central DSLAM and then back to you through hundreds,thousands miles of fiber. That is two times the traffic compared to a central download server that is directly connected to the DSLAM. It doubles the transmission costs. All paid for by the ISP. This is horribly, horribly inefficient.
I’m not sure about other countries, but in the Netherlands there is a law that forces ISP’s to tap Internet traffic. So even with a highly decentralized network, with local metro rings etc, the ISP may be forced to push all traffic through a central hub. Rendering 1-on-1 P2P file sharing impossible and doubling the network load. (A CDN is also distributed, but it is a controlled environment, with trusted content partners and it centrally logs all actions).
Yes, the content owners save money. Because the ISP’s pay for all the traffic.
P2P is not cheaper. It moves costs to another part of the value chain.
Actually, If you look at P2P from a macro-economic perspective, the overall costs could be 2 times higher with P2P than with regular downloading from a central server. Because of all the overhead communication.
The entire value chain has no benefit from P2P: it makes things much worse.
Many ISP’s struggle with P2P traffic. It has an uncontrolled, unpredictable and destructive nature. ISP’s don’t like CDN’s with P2P or Peer assisted services. It may cost these CDN’s their peering agreements eventually.
Five percent of the subscribers cause over 60% of the network traffic, because they are heavy P2P users.
How fair is that towards the other 95% of the subscribers who have to share just 40% of the network resources? In the Netherlands, you pay €20 flat-fee per month for 20Mbps broadband. If ISP’s could charge heavy P2P users for actual usage, these users would end up paying €300 per month. The price for all the other users could go down to €5 per month. Thanks but no thanks, P2P distributors!
————-
P.S. I did get a lot of response on this article. Cheering responses from ISP’s and angry responses from P2P sharing fanboys.
The thing that really annoys me is that the European Union gives millions euros to academic P2P research labs. The researchers make a lot of claims in terms of scalability and costs savings. But there has never been good academic research towards the true efficiency of P2P compared to downloading or CDN delivery. Those labs are payed by the taxes that we all pay. That my company pays as well. And with that money and their claims, the researchers confuse our market.
I really look forward to an honest objective, academic research paper that explains the true efficiency of P2P compared to downloads, streaming and CDN’s. There simply are no facts to have a good discussion. If such a document is published, or if new P2P technologies rise that overcome the issues that I described above, I’m happy to change my thoughts. I’m not a P2P basher. I just don’t like claims that aren’t true. And I don’t like waste of tax payers’ money. If you have further insights, please share these with me, I love a good and positive discussion!
No comments yet.