From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754174Ab0CXCQR (ORCPT ); Tue, 23 Mar 2010 22:16:17 -0400 Received: from one.firstfloor.org ([213.235.205.2]:40038 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754064Ab0CXCQQ (ORCPT ); Tue, 23 Mar 2010 22:16:16 -0400 To: holt@sgi.com Cc: Ingo Molnar , "H. Peter Anvin" , Thomas Gleixner , Venkatesh Pallipadi , Suresh Siddha , Linux Kernel Mailing List , x86@kernel.org, Rafael Wysocki Subject: Re: [patch 0/2] x86,pat: Reduce contention on the memtype_lock -V4 From: Andi Kleen References: <20100324003608.811051277@gulag1.americas.sgi.com> Date: Wed, 24 Mar 2010 03:16:14 +0100 In-Reply-To: <20100324003608.811051277@gulag1.americas.sgi.com> (holt@sgi.com's message of "Tue, 23 Mar 2010 19:36:08 -0500") Message-ID: <87wrx2for5.fsf@basil.nowhere.org> User-Agent: Gnus/5.1008 (Gnus v5.10.8) Emacs/22.3 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org holt@sgi.com writes: > Tracking memtype on x86 uses a single global spin_lock for either reading > or changing the memory type. This includes changes made to page flags > which is perfectly parallel. > > Part one of the patchset makes the page-based tracking use cmpxchg > without a need for a lock. > > Part two of the patchset converts the spin_lock into a read/write lock. I'm curious: in what workloads did you see contention? For any scalability patches it would be always good to have a description of the workload. -Andi -- ak@linux.intel.com -- Speaking for myself only.