On Wed, Dec 20, 2017 at 04:57:28PM -0800, Linus Torvalds wrote: > On Wed, Dec 20, 2017 at 2:45 PM, NeilBrown <neilb@xxxxxxxx> wrote: > > > > We could just leave the code unchanged, but apart from that being > > potentially confusing, the (unfair) bit-spin-lock which protects > > s_anon can become a bottle neck when lots of disconnected dentries are > > being created. > > > > So this patch renames s_anon to s_roots, and stops storing > > disconnected dentries on the list. Only dentries obtained with > > d_obtain_root() are now stored on this list. There are many fewer of > > these (only NFS and NILFS2 use the call, and only during filesystem > > mount) so contention on the bit-lock will not be a problem. > > Thanks, Neil. This is much nicer than the magical special case patch > for s_anon bitlock. > > Al, I'm going to assume I'll get this through your vfs tree (with > whatever edits from the comments people made). *nod* I've got sidetracked digging through the Lustre mess with dcache (revalidation stuff, again), will finish once I get some sleep. In any case, I like that variant; it's definitely going to be applied.
