Live data from Hacker News

An Uber-like CDN

medium.com

81–86 of 86 posts

Re: An Uber-like CDN

#81
post #59
post #51

Earlier quoted context omitted.

1. None of the issues I listed affect traditional CDNs though. 3. Why would the people running a peer have cheaper access to servers and bandwidth than a company specializing in that business? Everything about this business should have huge economies of scale (buying hardware, system administration, transit/peering). The only situation where I can see a distributed model winning out is if the entity running the peer…

It's a matter of locale. Having an entrepreneur in South Africa or Tibet hear about the money making opportunity, setting up a peer, and then paying them for it is better than flying there for a month to set up a business presence and figuring out all the local everythings. Akamai et al has already done this, and charge money commensurate with having done that. This group seems to be banking on someone in Kathmandu h…

But the majority of the valuable traffic will be coming from popular places. Wouldn't a CDN node in Tibet be a microoptimization after you've got datacenters in Virginia, SF, and Amsterdam?

Re: An Uber-like CDN

#82

It seems a little odd to use GitHub as the CDN for your JavaScript library. Like what if this got really popular, what’s to stop GutHub for shutting it down for abusing their hosting? If I were a customer for a CDN, I would feel more comfortable if they owned their own domain and could control how (and if!) their JavaScript is available to customers. Anyways, other than that it’s a fun concept. I like the P2P nature…

That's insane. This JS has to be loaded before they can start any of the actual requests. It should be on the most performant host possible.

Re: An Uber-like CDN

#83

What stops a peer from, say, injecting malicious JavaScript into pages? Or going rogue and serving porn for every request for a JPEG? What if they only do it for every 1000th request? You could send a hash of the file to the client from the coordination server and check it. If the hash isn't valid, you can re-request the file from another peer. But I don't think you can trust the client to report abuse: a malicious c…

> Since the requested file comes from an untrusted source, the next step is to verify the integrity of the file. The script calculates the hash sum and compares it to the digest from the JSON reply. If the sums match, the script displays the downloaded file to the User.

And if they don't? Or if the client says they don't?

Re: An Uber-like CDN

#84

Earlier quoted context omitted.

> That's why the _Peer_ sets the price for his service. But that breaks the economics of this, no? If you're in the US and charge $6/TB and I'm in Germany and charge $100/TB, why would traffic ever go to my server? If your US server gets overloaded, am I now making $100/TB? How does the network ensure that this is both fair and competitive? Moreover, how can a customer know that they're not going to get a surprise bi…

If someone wants to serve traffic from a peer in Germany, then they will pay you. What they are paying for with a global CDN is ultimately location.

That's the point though: not every peer can have all content, it's not a data center with a massive cache. So what's stopping me from using FUSE to make it seem like I've got petabytes of storage and throw the data in S3? Now, I never evict anything from the cache. My node is going to be far more likely to be the closest node to any given user. And so I jack up my price.

There's many variables, but the important ones for choosing a peer are cost and latency/distance. What conditions do you have for choosing far-but-cheap versus near-but-pricey? You can't simply choose peers randomly or round robin because I could just set my prices through the roof and pick up a massive paycheck.

Re: An Uber-like CDN

#85

Earlier quoted context omitted.

If someone wants to serve traffic from a peer in Germany, then they will pay you. What they are paying for with a global CDN is ultimately location.

That's the point though: not every peer can have all content, it's not a data center with a massive cache. So what's stopping me from using FUSE to make it seem like I've got petabytes of storage and throw the data in S3? Now, I never evict anything from the cache. My node is going to be far more likely to be the closest node to any given user. And so I jack up my price. There's many variables, but the important ones…

I'm not sure I understand your thinking, here. You will set a higher price than others and win bids relative to them, somehow?

In markets, generally, providers are not chosen randomly or round-robin; they are chosen based on the balance of cost and what is offered.

Re: An Uber-like CDN

#86
post #49

Travis built RedSwoosh ( https://en.m.wikipedia.org/wiki/Red_Swoosh ) and then went on to build Uber. Now someone saw Uber and claims it inspired them to rebuild RedSwoosh. ¯\_(ツ)_/¯

>The Red Swoosh peercasting tool is a _browser_extension_ that caches data, reflecting and sharing files delivered through the "Swoosh network" I don't know how it works in details, but it looks like you need to install a browser plugin to enable the p2p network here. Our solution works transparently for the end user.

The extension simply rewrites the URLs and there's a way to "swoosh" your links which works transparent for the end user: https://web.archive.org/web/20050111015750/http://redswoosh....
Post reply on HN