Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1422947AbXEDX7S (ORCPT ); Fri, 4 May 2007 19:59:18 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1161609AbXEDX7S (ORCPT ); Fri, 4 May 2007 19:59:18 -0400 Received: from netops-testserver-3-out.sgi.com ([192.48.171.28]:50357 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1161597AbXEDX7R (ORCPT ); Fri, 4 May 2007 19:59:17 -0400 Date: Fri, 4 May 2007 16:59:15 -0700 (PDT) From: Christoph Lameter X-X-Sender: clameter@schroedinger.engr.sgi.com To: Tim Chen cc: "Chen, Tim C" , "Siddha, Suresh B" , "Zhang, Yanmin" , "Wang, Peter Xihong" , Arjan van de Ven , linux-kernel@vger.kernel.org, linux-mm@kvack.org Subject: RE: Regression with SLUB on Netperf and Volanomark In-Reply-To: <1178318609.23795.214.camel@localhost.localdomain> Message-ID: References: <9D2C22909C6E774EBFB8B5583AE5291C02786032@fmsmsx414.amr.corp.intel.com> <1178298897.23795.195.camel@localhost.localdomain> <1178318609.23795.214.camel@localhost.localdomain> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1275 Lines: 31 On Fri, 4 May 2007, Tim Chen wrote: > On Fri, 2007-05-04 at 11:27 -0700, Christoph Lameter wrote: > > > > > Not sure where to go here. Increasing the per cpu slab size may hold off > > the issue up to a certain cpu cache size. For that we would need to > > identify which slabs create the performance issue. > > > > One easy way to check that this is indeed the case: Enable fake NUMA. You > > will then have separate queues for each processor since they are on > > different "nodes". Create two fake nodes. Run one thread in each node and > > see if this fixes it. > > I tried with fake NUMA (boot with numa=fake=2) and use > > numactl --physcpubind=1 --membind=0 ./netserver > numactl --physcpubind=2 --membind=1 ./netperf -t TCP_STREAM -l 60 -H > 127.0.0.1 -i 5,5 -I 99,5 -- -s 57344 -S 57344 -m 4096 > > to run the tests. The results are about the same as the non-NUMA case, > with slab about 5% better than slub. Hmmmm... both tests were run in the same context? NUMA has additional overhead in other areas. - 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/