On 10/15/24 6:01 PM, Miklos Szeredi wrote: > On Mon, 14 Oct 2024 at 20:23, Joanne Koong <joannelkoong@xxxxxxxxx> wrote: > >> This change sets AS_NO_WRITEBACK_RECLAIM on the inode mapping so that >> FUSE folios are not reclaimed and waited on while in writeback, and >> removes the temporary folio + extra copying and the internal rb tree. > > What about sync(2)? 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. [1] https://pubs.opengroup.org/onlinepubs/9699919799/functions/sync.html -- Thanks, Jingbo
