From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from zeniv.linux.org.uk ([195.92.253.2]:33894 "EHLO ZenIV.linux.org.uk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750757AbdLUFkK (ORCPT ); Thu, 21 Dec 2017 00:40:10 -0500 Date: Thu, 21 Dec 2017 05:40:00 +0000 From: Al Viro To: Linus Torvalds Cc: NeilBrown , "J. Bruce Fields" , Trond Myklebust , Anna Schumaker , linux-fsdevel , Linux Kernel Mailing List , Linux NFS Mailing List Subject: Re: [PATCH/RFC] VFS: don't keep disconnected dentries on d_anon Message-ID: <20171221054000.GX21978@ZenIV.linux.org.uk> References: <87y3lxj9wr.fsf@notabene.neil.brown.name> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: Sender: linux-fsdevel-owner@vger.kernel.org List-ID: On Wed, Dec 20, 2017 at 04:57:28PM -0800, Linus Torvalds wrote: > On Wed, Dec 20, 2017 at 2:45 PM, NeilBrown 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.