On Mon, Jun 02, 2025 at 09:57:07AM +0200, Peter Zijlstra wrote:
On Sat, May 31, 2025 at 06:51:50AM -0700, Kees Cook wrote:
It's not for you, then. :) I can't operate ftrace, but I use kunit almost daily. Ignoring WARNs makes this much nicer, and especially for CIs.
I'm thinking you are more than capable of ignoring WARNs too. This leaves the CI thing.
So all this is really about telling CIs which WARNs are to be ignored, and which are not? Surely the easiest way to achieve that is by printing more/better identifying information instead of suppressing things?
You might also want to test that the warn is indeed emitted, and it not being emitted result in a test failure.
And I can see a future where we would fail a test that would trigger an unexpected WARN.
Doing either, or none, would be pretty terrible UX for !CI users too. How on earth would you know if the hundreds of WARN you got from the tests output are legitimate or not, and if you introduced new ones you're supposed to fix?
Maxime