(sorry for the delay in my replies) On Mon, Oct 04, 2021 at 12:18:24PM -0400, Theodore Ts'o wrote: > On Mon, Oct 04, 2021 at 01:17:02PM +0100, Luis Henriques wrote: > > > > Ok, I may have narrowed it a bit more. The disks being used in my testing > > were zram-based (I know, I should have mentioned it before :-/ ). If I use > > file-based disks the test passes and I see no crashes in fio. > > What was the last kernel version where it didn't crash for you? 5.14? No, this is not a regression. I tried to go as far as 5.0 and I still get the exact same behaviour. Also, I've tried fio 3.24 and it still crashes. So, this definitely looks like a zram issue. I've added the maintainers to the CC list in case they have any ideas. > And maybe we need to have a test which explicitly uses zram, since I > suspect many/most of the fs developers who are running fstests aren't > using zram.... > > - Ted Cheers, -- Luís