On 7/24/23 11:24?AM, Andres Freund wrote: > Hi, > > On 2023-07-24 09:16:56 -0700, Andres Freund wrote: >> Building a kernel to test with the patch applied, will reboot into it once the >> call I am on has finished. Unfortunately the performance difference didn't >> reproduce nicely in VM... > > Performance is good with the patch applied. Results are slightly better even, > but I think that's likely just noise. Could be - it's avoiding a few function calls and the flush, but would probably have to be a pretty targeted test setup to find that for storage IO. Thanks for testing! -- Jens Axboe
