I made a few tests with lab js in one of the sites I've developed and got a reduction of 200ms in the page load time. The total time spent now after backend processing is around 1.5 seconds.
I was wandering if its worth the trouble. Is 200ms a huge gain? A ridiculous one? I know that page load times affect page ranking, but 200ms will make such a big difference?
Quoting Milliseconds are Money: How Much Performance Matters in the Cloud:
5) The Proof That Milliseconds Matter …
The big guys in the cloud industry have really dug deep and proved that those milliseconds matter:
For every 100ms increase in load time of Amazon.com decreased sales by 1% (Kohavi and Longbotham 2007).
Google discovered that a change from loading a 10-result page in 0.4 seconds to a 30-result page loading in 0.9 seconds decreased traffic and ad revenues by 20% (Linden 2006).
Google Search found that a 400 millisecond delay resulted in a -0.59% change in searches/user. What’s more, even after the delay was removed, these users still had -0.21% fewer searches, indicating that a slower user experience affects long term behavior.
Another study by Google found that an extra 500ms in loading time resulted in 20% drop in traffic.
Yahoo also found that a 400ms slower page would see 5-9% more people leave before the page finished loading.
I think this answers your question.
An absolute 200ms gain is not a huge gain IMHO.
But... If you spend several days optimizing and each day you manage to gain 200ms, it will become significant.
What you should ask yourself is: when I open my page, do I feel like clicking away or not? As if you were a clicking-away caffeinated monkey I mean.
If you feel like staying, then don't optimize. If you feel you saw too many microseconds of empty-white-page before the page loaded, then continue optimizing.
来源：https://stackoverflow.com/questions/14510499/is-a-200ms-decrease-in-page-load-time-significant