On Mon, Aug 25, 2025 at 06:37:05PM -0600, Keith Busch wrote: > On Mon, Aug 25, 2025 at 09:47:44AM +0200, Christoph Hellwig wrote: > > Also with this we should be able to drop the iov_iter_alignment check > > for always COW inodes in xfs_file_dio_write. If you don't feel like > > doing that yourself I can add it to my todo list. > > I'm unsure about the commit that introduced that behavior, so I think > you should remove it if you know its okay. :) Yeah. > Specifically, we have this in the comments and commit message: > > check the alignment of each individual iovec segment, as they could > end up with different I/Os due to the way bio_iov_iter_get_pages works > > bio_iov_iter_get_pages() might submit the segments as separate IO's > anyway for other reasons. I am not sure why the alignment conditions are > handled specifically here. I'll take another look. Basically what this wants to prevent is bio_iov_iter_get_pages creating bios not aligned to file system block size.
