On 2020-05-13 13:10, Bill Woodcock wrote:
On 2020-05-13 11:00, Mark Delany wrote:
On 13May20, Denys Fedoryshchenko allegedly wrote:
What about introducing some cache offloading, like CDN doing? (Google, Facebook, Netflix, Akamai, etc) Maybe some opensource communities can help as well Surely someone has already thought thru the idea of a community CDN? Perhaps along the lines of pool.ntp.org? What became of that discussion?
Yes, Jeff Ubois and I have been discussing it with Brewster.
There was significant effort put into this some eighteen or twenty years ago, backed mostly by the New Zealand government… Called the “Internet Capacity Development Group.” It had a NOC and racks full of servers in a bunch of datacenters, mostly around the Pacific Rim, but in Amsterdam and Frankfurt as well, I think. PCH put quite a lot of effort into supporting it, because it’s a win for ISPs and IXPs to have community caches with local or valuable content that they can peer with. There’s also a much higher hit-rate (and thus efficiency) to caching things the community actually cares about, rather than whatever random thing a startup is paying Akamai or Cloudflare or whatever to push, which may never get viewed at all. It ran well enough for about ten years, but over the long term it was just too complex a project to survive at scale on community support alone. It was trending toward more and more of the hard costs being met by PCH’s donors, and less and less by the donors who were supporting the content publishers, which was the goal.
The newer conversation is centered around using DAFs to support it on behalf of non-profit content like the Archive, Wikipedia, etc., and that conversation seems to be gaining some traction. Unfortunately because there are now a smaller number of really wealthy people who need places to shove all their extra money. Not how I’d have liked to get here. I think this is a simple equation.
1) The minimum cost of implementation and technical support efforts I think earlier this was the main problem, 10 years ago there was no such level of software automation as it is available today. 2) Win for operators. Before it was more trivial by running squid and trivial cache, now, with HTTPS it is not possible. 3) Proud badge of non-profit projects supporter and charity activities. (Whether it is possible to write off tax/etc as donations - depends on the laws of your country)