On Fri, Dec 13, 2024 at 03:32:24PM +0100, Christoph Hellwig wrote: > On Thu, Dec 12, 2024 at 09:51:45PM +0800, kernel test robot wrote: > > > > > > Hello, > > > > kernel test robot noticed a 49.6% regression of stress-ng.aiol.ops_per_sec on: > > This sounds like there is some other I/O path that still reorders, > which got messed up. What storage driver is this using? The repro > material talks about an ata disk, but I'm still curious if it's ahci > or some other driver, or a SAS HBA? Do you have the information on what hardware is used for this test?
