On Wed, 16 Oct 2024 at 11:56, Jingbo Xu <jefflexu@xxxxxxxxxxxxxxxxx> wrote: > FYI The posix sync(2) says, "The writing, although scheduled, is not > necessarily complete upon return from sync()." [1] > > Thus hopefully it won't break the posix semantics of sync(2) down if we > skip the waiting on the writeback of fuse pages. Since this has been the case for fuse since day one and no one complained, this is not a worry. Thanks, Miklos
