From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752701AbZBAHav (ORCPT ); Sun, 1 Feb 2009 02:30:51 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751333AbZBAHan (ORCPT ); Sun, 1 Feb 2009 02:30:43 -0500 Received: from mga12.intel.com ([143.182.124.36]:23021 "EHLO azsmga102.ch.intel.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751281AbZBAHam (ORCPT ); Sun, 1 Feb 2009 02:30:42 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.37,359,1231142400"; d="scan'208";a="105813539" Subject: hackbench [pthread mode] regression with 2.6.29-rc3 From: "Zhang, Yanmin" To: Peter Zijlstra Cc: LKML Content-Type: text/plain; charset=UTF-8 Date: Sun, 01 Feb 2009 15:30:26 +0800 Message-Id: <1233473426.2604.13.camel@ymzhang> Mime-Version: 1.0 X-Mailer: Evolution 2.22.1 (2.22.1-2.fc9) Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Comparing with 2.6.29-rc2's result, hackbench [pthread mode] result is increased about 50%~100% with 2.6.29-rc3 on my 4 qual-core process tigerton machine and 4 qual-core Montvale Itanium mahchine. The smaller result, the better performance.  Command to run hackbench: #./hackbench 100 thread 2000 Bisect located below patch. commit 490dea45d00f01847ebebd007685d564aaf2cd98 Author: Peter Zijlstra Date: Mon Nov 24 17:06:57 2008 +0100 itimers: remove the per-cpu-ish-ness Either we bounce once cacheline per cpu per tick, yielding n^2 bounces or we just bounce a single.. Also, using per-cpu allocations for the thread-groups complicates the per-cpu allocator in that its currently aimed to be a fixed sized allocator and the only possible extention to that would be vmap based, which is seriously constrained on 32 bit archs. After above patch is reverted, hackbench result is restored. yanmin