You can now perform content discovery at 100k requests per second with h3fuzz on http/3 hosts (fork of ffuf with http/3 support). Tool here: Research post here:

100k/s? My god, are you trying to melt servers? 😅

Haha. I talk about the practical limitations of this in the blog, but from experience, the best infra to handle this scale has been Google Cloud CDN. For example, Uber hosts happily respond without dying.

@zseano You might be sending 100k requests, but you’re only getting a fraction of the actual responses back. This is as reliable as a 1950 Yugo with 2 million miles on it

@zseano You're welcome to run the harness included in the repo locally to check my work. When running this tool on my dedicated server, going after Google Cloud CDN infra, I am easily able to get over 60-70k RPS.

Will do, and again, I don’t doubt you can send 100k request, the problem is handling the massive amount of responses and handshakes. You WILL drop packets and accuracy will be impacted, but I will definitely try it when I get home. I’ve been doing this for a very long time but I’m hopping I’m wrong because this will make my job easier.

That's tesla roadster speed.

Amazing

51k on screen and the title says 100k

Feeling sad for Servers 😭

Awesome

@zseano Unless this is distributed it’s probably smoke and mirrors, the hardware itself can’t handle this amount of traffic on a single computer.

what about this????