From: Greg Banks Subject: Re: [PATCH 4/8] knfsd: repcache: split hash index Date: Mon, 16 Oct 2006 21:06:49 +1000 Message-ID: <20061016110649.GF8568@sgi.com> References: <1160566044.8530.13.camel@hole.melbourne.sgi.com> <17714.59304.768727.298610@cse.unsw.edu.au> <20061016095121.GB8568@sgi.com> <17715.23970.155314.297331@cse.unsw.edu.au> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Cc: Linux NFS Mailing List Return-path: Received: from sc8-sf-mx1-b.sourceforge.net ([10.3.1.91] helo=mail.sourceforge.net) by sc8-sf-list2-new.sourceforge.net with esmtp (Exim 4.43) id 1GZQJ5-0002PQ-R0 for nfs@lists.sourceforge.net; Mon, 16 Oct 2006 04:06:55 -0700 Received: from omx2-ext.sgi.com ([192.48.171.19] helo=omx2.sgi.com) by mail.sourceforge.net with esmtp (Exim 4.44) id 1GZQJ6-0001Zq-K1 for nfs@lists.sourceforge.net; Mon, 16 Oct 2006 04:06:56 -0700 To: Neil Brown In-Reply-To: <17715.23970.155314.297331@cse.unsw.edu.au> List-Id: "Discussion of NFS under Linux development, interoperability, and testing." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: nfs-bounces@lists.sourceforge.net Errors-To: nfs-bounces@lists.sourceforge.net On Mon, Oct 16, 2006 at 08:23:30PM +1000, Neil Brown wrote: > On Monday October 16, gnb@sgi.com wrote: > > > > Let's look at the maths. If we were to limit cache_buckets[] to a > > single page, I calculate that would give us 186 entries on ia64, 46 > > on x86_64, and 68 on i386 (fewer if various spinlock-related config > > options are enabled). That's too low on x86_64 but fine on the other > > platforms. With a single order-1 allocation we could cover most > > bases. > > I had thought that ____cacheline_aligned_in_smp would have padded it > more making few entries per page, but that probably isn't important. Ooops, you're right. That makes the numbers 128 on ia64, 42 on x86_64, and 64 on i386. > > Alternatively, we could allocate the buckets separately and make > > cache_buckets[] an array of pointers to buckets. Then we could do a > > single (say) 128*sizeof(svc_cache_bucket*) allocation plus (say) 128 * > > sizeof(svc_cache_bucket) allocations, all of which would be order 0. > > Now we've effectively got a 3-level fat tree keyed on hash value. > > > > The more I think about it, the more I like this idea. > > > > Me too. Righto, new patches probably tomorrow. Greg. -- Greg Banks, R&D Software Engineer, SGI Australian Software Group. I don't speak for SGI. ------------------------------------------------------------------------- Using Tomcat but need to do more? Need to support web services, security? Get stuff done quickly with pre-integrated technology to make your job easier Download IBM WebSphere Application Server v.1.0.1 based on Apache Geronimo http://sel.as-us.falkag.net/sel?cmd=lnk&kid=120709&bid=263057&dat=121642 _______________________________________________ NFS maillist - NFS@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/nfs