On 15 Mar 2016, Raimund Steger uttered the following: > On Tue, 15 Mar 2016 14:10:19 +0000 > Nick Alcock <nick.alcock@xxxxxxxxxx> wrote: > >> On 15 Mar 2016, Raimund Steger outgrape: >> >> > On Sun, 13 Mar 2016 13:40:41 -0700 >> > Behdad Esfahbod <behdad@xxxxxxxxxx> wrote: >> >> [...] >> >> There are four usecases we need to consider: >> >> >> >> - Normal Linux / other Unix-like. We can assume high-precision >> >> timestamps are available and take care of stuff, >> >> >> >> - Linux / Unix-like system with network file system. Any issues there >> >> with your proposed patch? >> > >> > NFSv3 spec has nanoseconds, but I think server support is optional. >> > I'll do some research what kind of support currently is out there. The >> > implementations I'm using here seem to support it. Even if not, there >> > might be little choice, as the stat penalty is most severe with NFS >> > and 2.11 behavior is more acceptable IMHO. >> >> Really? I was seeing multiple second startup penalties caused by all >> those stats before I patched fontconfig to stop doing them. Any given > > But on 2.11, really? I mean last stable? If I truss Yes. The problem is that it still has to stat() everything to see if it's a directory, for recursion :( it wasn't using dirent.d_type... -- NULL && (void) _______________________________________________ Fontconfig mailing list Fontconfig@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/fontconfig
