High Performance at Massive Scale: Lessons Learned at Facebook

In some ways that might be an advantage. More people are going through the growing pains associated with tens of millions of people using their site and request-per-second and data size problems, and making trade-offs for that providing service at that scale.

Jumping to Facebook's current architecture and taking on the trade-offs taken there (assuming you even have a problem where those trade-offs make sense at massive scale) is probably not the right thing to do when you are much smaller (in terms of requests/traffic/load, servers, and employees).

I'd love to see a 2013 update on some of these numbers.

I don't think it is the same talk, he talks about the tagging platform which is a new feature.

Or maybe the slides are just that old? :-)

The Guardian (citing a May 2012 Nielsen.com [2]) reported that Facebook is #1 (by a wide margin - almost 3x the closest competitor) as measured by the time users spend on the site.

[1] http://www.guardian.co.uk/news/datablog/2012/jun/22/website-...

[2] https://docs.google.com/spreadsheet/pub?key=0AuZLaKQQs5xpdGd...

#1 was Google, which includes Search, Gmail (found at mail.google.com), Google Docs (found at docs.google.com), etc.