I've heard a few times that every extra [number1] milliseconds it takes to process a web request and return a response will lose you [number2] percent of users. Is this just "conventional wisdom," or have there been actual studies on the subject? And has there been found to be a lower bound to this phenomenon, like "[number3] milliseconds is fast enough, improving further than that won't hold any more users"?
You should read Jakob Nielsen thoughts on this topic.
0.1 second is about the limit for having the user feel that the system is reacting instantaneously, meaning that no special feedback is necessary except to display the result.
1.0 second is about the limit for the user's flow of thought to stay uninterrupted, even though the user will notice the delay. Normally, no special feedback is necessary during delays of more than 0.1 but less than 1.0 second, but the user does lose the feeling of operating directly on the data.
10 seconds is about the limit for keeping the user's attention focused on the dialogue. For longer delays, users will want to perform other tasks while waiting for the computer to finish, so they should be given feedback indicating when the computer expects to be done. Feedback during the delay is especially important if the response time is likely to be highly variable, since users will then not know what to expect.