Re: [PATCH] jbd2: enforce power-of-two default revoke hash size at compile time

[Theodore Tso]

On Thu, Apr 16, 2026 at 12:16:05PM +0200, Jan Kara wrote:
> 
> Yes, I know. But there is already a runtime assertion in
> jbd2_journal_init_revoke() making sure the passed value is a power of two
> which is verifying also other callers that aren't using
> JOURNAL_REVOKE_DEFAULT_HASH value. I don't see a value in the *additional*
> BUILD_BUG_ON when we already have that runtime check.

... and if a developer doesn't run regression tests before bothering
the list with a patch... that's not a developer we want to cater to.

Milos, my recommended to workflow is to use kvm-xfstests[1], and just do:

% install-kconfig
% kbuild
% kvm-xfstests smoke

[1] https://github.com/tytso/xfstests-bld/blob/master/Documentation/kvm-quickstart.md

For a successful run, "kvm-xfstests smoke" will run take 15-20
minutes.  In the case of screwing up the default power-of-two default
revoke hash size, "kvm-xfstests smoke" will report a failure in less
than a minute.

						- Ted