From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeff Layton Subject: Re: [PATCH v1 11/11] locks: give the blocked_hash its own spinlock Date: Tue, 4 Jun 2013 10:56:56 -0400 Message-ID: <20130604105656.18663efa@corrin.poochiereds.net> 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> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: "Stefan (metze) Metzmacher" , viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn@public.gmane.org, matthew-Ztpu424NOJ8@public.gmane.org, bfields-uC3wQj2KruNg9hUCZPvPmw@public.gmane.org, linux-cifs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-nfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, cluster-devel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org, sage-4GqslpFJ+cxBDgjK7y7TUQ@public.gmane.org, samba-technical-w/Ol4Ecudpl8XjKLYN78aQ@public.gmane.org, Trond.Myklebust-HgOvQuBEEgTQT0dZR+AlfA@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-afs-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org, dhowells-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org, smfrench-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org, linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, ceph-devel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org, swhiteho-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org To: Christoph Hellwig Return-path: In-Reply-To: <20130604144640.GA7730-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org> Sender: linux-cifs-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-ID: 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