On Wed, Apr 24, 2019 at 1:56 AM Zygo Blaxell <ce3g8...@umail.furryterror.org> wrote: > > 132096 is 129 * 1024, which is not a multiple of 4K. There will be a CoW > operation in cases where one 4K block from each pwrite is written twice > in separate transactions (or with fsync between).
Yes, the writes have odd sizes. This is unfortunate, but it's due to gocryptfs' encryption overhead. > fallocate is only going to behave the way posix_fallocate specifies on > files with datacow turned off. I see. Thank you! Jakob
