On Thu, Jun 09, 2022 at 08:22:09PM +0100, Matthew Wilcox wrote: > It's not really that. This is more about per-IO overhead, so you'd want > to do a lot of 1-byte writes to maximise your chance of seeing a > difference. Here's an earlier thread on ->read_iter vs ->read performance costs: https://lore.kernel.org/linux-fsdevel/20210107151125.GB5270@xxxxxxxxxxxxxxxxxxxx/
