On Tue, Oct 28, 2025 at 11:06:05PM +0100, Daniel Stenberg wrote: D> > This may actually help our case! D> > I'm going to give a try to unmodified 8.16.0. D> D> It could be worth exploring more exactly what we're talking about. I mean D> what measurements to do and how to tell what's "good" and what's "bad" in D> this context.
The microbenchmark David used is desribed in his email: https://www.mail-archive.com/[email protected]/msg02593.html The regression was discovered by a huge A/B test of a system overall, that involves many machines, many hours and a ton of traffic. What I'm going to do now is to re-run this A/B test with 8.16.0, to avoid relying on year old data. -- Gleb Smirnoff -- Unsubscribe: https://lists.haxx.se/mailman/listinfo/curl-library Etiquette: https://curl.se/mail/etiquette.html
