From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeff Layton Date: Tue, 4 Jun 2013 10:56:56 -0400 Subject: [Cluster-devel] [PATCH v1 11/11] locks: give the blocked_hash its own spinlock In-Reply-To: <20130604144640.GA7730@infradead.org> References: <1370056054-25449-1-git-send-email-jlayton@redhat.com> <1370056054-25449-12-git-send-email-jlayton@redhat.com> <51ADF789.70906@samba.org> <20130604144640.GA7730@infradead.org> Message-ID: <20130604105656.18663efa@corrin.poochiereds.net> List-Id: To: cluster-devel.redhat.com MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit On Tue, 4 Jun 2013 07:46:40 -0700 Christoph Hellwig wrote: > Having RCU for modification mostly workloads never is a good idea, so > I don't think it makes sense to mention it here. > > If you care about the overhead it's worth trying to use per-cpu lists, > though. > Yeah, I looked at those too in an earlier set and it did help some. Moving to a hashtable for the blocked_list really seemed to help the most there, but percpu lists with lglocks or something might help a lot on the file_lock_list. -- Jeff Layton