On Tue, Aug 26, 2025 at 10:57:28AM -0600, Keith Busch wrote: > Not sure what to say about this patch right now, but it triggered > a thought: if I can successfully get filesystem and block layers to > tolerate the hardware's minimum alignments, how is user space to know > it's allowed to send IO aligned to it? The existing statx dio fields > just refer to address alignments, but lengths are still assumed to be > block sized. Length as in total transfer length? Nothing in the block layer or storage interface will allow you to do sub-sector transfers, so this just won't work. Length as in segment length? If we can support that we'll need a new limit for that.
