Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754447AbXEDEhW (ORCPT ); Fri, 4 May 2007 00:37:22 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1767679AbXEDEhW (ORCPT ); Fri, 4 May 2007 00:37:22 -0400 Received: from smtp1.linux-foundation.org ([65.172.181.25]:56113 "EHLO smtp1.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1767678AbXEDEhV (ORCPT ); Fri, 4 May 2007 00:37:21 -0400 Date: Thu, 3 May 2007 21:37:17 -0700 From: Andrew Morton To: Christoph Lameter Cc: linux-kernel@vger.kernel.org Subject: Re: Remove constructor from buffer_head Message-Id: <20070503213717.37be3e56.akpm@linux-foundation.org> In-Reply-To: References: <20070503202111.667c9b14.akpm@linux-foundation.org> X-Mailer: Sylpheed version 2.2.7 (GTK+ 2.8.17; x86_64-unknown-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1783 Lines: 45 On Thu, 3 May 2007 20:34:48 -0700 (PDT) Christoph Lameter wrote: > On Thu, 3 May 2007, Andrew Morton wrote: > > > On Thu, 3 May 2007 20:08:41 -0700 (PDT) Christoph Lameter wrote: > > > > > Performance tests show a slight improvements in netperf (not a > > > strong case for a performance improvement but removing the > > > constructor has definitely no negative impact so why keep > > > this around?). > > > > > > TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to localhost (127.0.0.1) port 0 AF_INET > > > Recv Send Send > > > Socket Socket Message Elapsed > > > Size Size Size Time Throughput > > > bytes bytes bytes secs. 10^6bits/sec > > > > > > Before: > > > 87380 16384 16384 10.01 6026.04 > > > 87380 16384 16384 10.01 5992.17 > > > 87380 16384 16384 10.01 6071.23 > > > > > > After: > > > 87380 16384 16384 10.01 6090.20 > > > 87380 16384 16384 10.01 6078.3 > > > 87380 16384 16384 10.00 6013.52 > > > > How could a filesystem change affect networking performance? > > > > The change looks nice, but I'd microbenchmark it with a write-to-ext2-on-ramdisk > > or something like that. > > Hmmmm.. I was told in another thread that this is the most frequently used > slab for this benchmark That would be hair-raising ;) I suspect confusion with sk_buff. buffer_heads do get used quite a bit though. A good microbenchmark would be to sit in a tight loop extending and truncating an ext2 file - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/