On Thu, Oct 14, 2021 at 12:34:55PM -0600, Jens Axboe wrote: > This generates a lot better code for me, and bumps performance from > 7650K IOPS to 7750K IOPS. Looking at profiles for the run and running > perf diff, it confirms that we're now sending a lot less time there: > > 6.38% -2.80% [kernel.vmlinux] [k] blkdev_direct_IO > > Taking it from the 2nd most cycle consumer to only the 9th most at > 3.35% of the CPU time. Kinda weird that the overhead is so big. That being said for more than a single flag I prefer the bit ops anyway, this code just "evolved". Reviewed-by: Christoph Hellwig <hch@xxxxxx>
