From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932189AbXCLWAy (ORCPT ); Mon, 12 Mar 2007 18:00:54 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S932713AbXCLWAy (ORCPT ); Mon, 12 Mar 2007 18:00:54 -0400 Received: from ozlabs.org ([203.10.76.45]:35647 "EHLO ozlabs.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932189AbXCLWAx (ORCPT ); Mon, 12 Mar 2007 18:00:53 -0400 Date: Mon, 12 Mar 2007 17:00:42 -0500 From: Anton Blanchard To: Nick Piggin Cc: Rik van Riel , Lorenzo Allegrucci , linux-kernel@vger.kernel.org, Ingo Molnar , Suparna Bhattacharya , Jens Axboe Subject: Re: SMP performance degradation with sysbench Message-ID: <20070312220042.GA807@kryten> References: <1172425476.5489.11.camel@odyssey.lan> <45E21FEC.9060605@redhat.com> <45E2E244.8040009@yahoo.com.au> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <45E2E244.8040009@yahoo.com.au> User-Agent: Mutt/1.5.12-2006-07-14 Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Hi Nick, > Anyway, I'll keep experimenting. If anyone from MySQL wants to help look > at this, send me a mail (eg. especially with the sched_setscheduler issue, > you might be able to do something better). I took a look at this today and figured Id document it: http://ozlabs.org/~anton/linux/sysbench/ Bottom line: it looks like issues in the glibc malloc library, replacing it with the google malloc library fixes the negative scaling: # apt-get install libgoogle-perftools0 # LD_PRELOAD=/usr/lib/libtcmalloc.so /usr/sbin/mysqld Anton