Re: [PATCH] io_uring: Use io_schedule* in cqring wait

[Jens Axboe]

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