> just a quick edit right after posting—I never really see Cloudflare in use directly by the top sites. They do exist, but it’s pretty rare, and even if you don’t believe me, I can always tell when a site uses Cloudflare due to its phantom latencies.

Are you saying you can feel that a website is using cloudflare because they have 5ms elevated latency?

▲

computably 3 hours ago | parent [-]

I assume they're referring to some amplification of that latency that makes it easily observable. e.g. multiple round trips on a user interaction

▲

echoangle 3 hours ago | parent [-]

Even if you have a button you click that changes color when the result return, I can’t really believe it. 5ms isn’t a lot, even with a two way journey it means that the effect you’re looking for is delayed by a single frame of your display (assuming 60hz).

	▲	epolanski an hour ago \| parent [-]
		It's not about one query but multiple ones, sometimes chained where it definitely makes a difference.