2016-02-22 1:26 GMT-08:00 Tim Starling tstarling@wikimedia.org:
I don't think it is plausible, given the data collected at:
https://meta.wikimedia.org/wiki/Research:HHVM_newcomer_engagement_experiment
25,000 new users were put into an HHVM bucket, so the whole site was twice as fast for them. Then they were tracked for a week. There was no improvement in engagement or productivity.
I'm sure the performance improvements we did in 2004-2005 had a big impact, especially initial batch of 9 Tampa servers in February 2004. There must be a scale effect: going from 20s to 10s is much more important than going from 2s to 1s.
I'm familiar with that research. I suggested at the time (see talk) to specifically also evaluate impact on existing users. My reasoning was that a new editor faces many barriers and high cognitive load, and as you say, performance improvements at the level realized here are probably not going to be the thing that helps you in making those first edits. But if you're a power user who, say, performs a ton of category edits with low cognitive load, reducing the amount of time spent waiting ought to increase productivity.
Erik