From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754619AbZC3Pyf (ORCPT ); Mon, 30 Mar 2009 11:54:35 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751686AbZC3Py0 (ORCPT ); Mon, 30 Mar 2009 11:54:26 -0400 Received: from gir.skynet.ie ([193.1.99.77]:42052 "EHLO gir.skynet.ie" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751929AbZC3PyZ (ORCPT ); Mon, 30 Mar 2009 11:54:25 -0400 Date: Mon, 30 Mar 2009 16:54:19 +0100 From: Mel Gorman To: Pekka Enberg Cc: David Rientjes , Christoph Lameter , Nick Piggin , Martin Bligh , linux-kernel@vger.kernel.org Subject: Re: [patch 1/3] slub: add per-cache slab thrash ratio Message-ID: <20090330155419.GC27169@csn.ul.ie> References: <1238397091.26742.35.camel@penberg-laptop> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-15 Content-Disposition: inline In-Reply-To: <1238397091.26742.35.camel@penberg-laptop> User-Agent: Mutt/1.5.17+20080114 (2008-01-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Mar 30, 2009 at 10:11:31AM +0300, Pekka Enberg wrote: > On Sun, 2009-03-29 at 22:43 -0700, David Rientjes wrote: > > The slab_thrash_ratio for each cache do not have non-zero defaults > > (yet?). > > If we're going to merge this code, I think it would be better to put a > non-zero default there; otherwise we won't be able to hit potential > performance regressions or bugs. Furthermore, the optimization is not > very useful on large scale if people need to enable it themselves. > > Maybe stick 20 there and run tbench, sysbench, et al to see if it makes > a difference? I'm cc'ing Mel in case he has some suggestions how to test > it. > netperf and tbench will both pound the sl*b allocator far more than sysbench will in my opinion although I don't have figures on-hand to back that up. In the case of netperf, it might be particular obvious if the client is on one CPU and the server on another because I believe that means all allocs happen on one CPU and all frees on another. I have a vague concern that such a tunable needs to exist at all though and wonder what workloads it can hurt when set to 20 for example versus any other value. -- Mel Gorman Part-time Phd Student Linux Technology Center University of Limerick IBM Dublin Software Lab