From mboxrd@z Thu Jan 1 00:00:00 1970 From: Al Viro Subject: Re: [PATCH v4 1/1] dcache: Translating dentry into pathname without taking rename_lock Date: Tue, 10 Sep 2013 01:57:54 +0100 Message-ID: <20130910005754.GV13318@ZenIV.linux.org.uk> References: <20130909182111.GQ13318@ZenIV.linux.org.uk> <20130910004020.29299.qmail@science.horizon.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: torvalds@linux-foundation.org, aswin@hp.com, john@stoffel.org, linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org, scott.norton@hp.com, Waiman.Long@hp.com To: George Spelvin Return-path: Content-Disposition: inline In-Reply-To: <20130910004020.29299.qmail@science.horizon.com> Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-fsdevel.vger.kernel.org On Mon, Sep 09, 2013 at 08:40:20PM -0400, George Spelvin wrote: > I'm really wondering about only trying once before taking the write lock. > Yes, using the lsbit is a cute hack, but are we using it for its cuteness > rather than its effectiveness? > > Renames happen occasionally. If that causes all the current pathname > translations to fall back to the write lock, that is fairly heavy. > Worse, all of those translations will (unnecessarily) bump the write > seqcount, triggering *other* translations to fail back to the write-lock > path. _What_ "pathname translations"? Pathname resolution doesn't fall back to seq_writelock() at all.