Messages in this thread | | | Subject | Re: [PATCH] block: switch to atomic_t for request references | From | Jens Axboe <> | Date | Mon, 6 Dec 2021 09:31:24 -0700 |
| |
On 12/5/21 11:53 PM, Christoph Hellwig wrote: > On Fri, Dec 03, 2021 at 08:35:40AM -0700, Jens Axboe wrote: >> refcount_t is not as expensive as it used to be, but it's still more >> expensive than the io_uring method of using atomic_t and just checking >> for potential over/underflow. >> >> This borrows that same implementation, which in turn is based on the >> mm implementation from Linus. > > If refcount_t isn't good enough for a normal kernel fast path we have > a problem. Can we discuss that with the maintainers instead of coming > up with our home grown schemes again?
I think what needs to happen next here is that the code is put into a separate header so that the vm, io_uring, and block can all use it. refcount_t is better than it used to be, but there's a difference between fast path and tens of millions of inc/decs per second.
-- Jens Axboe
| |