From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753526AbYIBGbj (ORCPT ); Tue, 2 Sep 2008 02:31:39 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752420AbYIBGba (ORCPT ); Tue, 2 Sep 2008 02:31:30 -0400 Received: from one.firstfloor.org ([213.235.205.2]:54654 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752316AbYIBGb3 (ORCPT ); Tue, 2 Sep 2008 02:31:29 -0400 To: "CHADHA,VINEET" Cc: nickpiggin@yahoo.com.au, linux-kernel@vger.kernel.org Subject: Re: TLB evaluation for Linux From: Andi Kleen References: <1942732773.182121220328723728.JavaMail.osg@osgjas04.cns.ufl.edu> Date: Tue, 02 Sep 2008 08:31:28 +0200 In-Reply-To: <1942732773.182121220328723728.JavaMail.osg@osgjas04.cns.ufl.edu> (VINEET CHADHA's message of "Tue, 2 Sep 2008 00:12:03 -0400 (EDT)") Message-ID: <87od37vz27.fsf@basil.nowhere.org> User-Agent: Gnus/5.1008 (Gnus v5.10.8) Emacs/21.3 (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 "CHADHA,VINEET" writes: > Hi, > > I have been working to evaluate TLB performance for Linux O/S and > virtualized workloads(such as Xen) in a Full system > simulator(e.g. simics). While my evaluation is in nascent stage, I do > notice that most of the IPIs in multi-core environments cause complete > TLB Flush. > > I want to evaluate cost of TLB shootdown including re-population > vs. each entry shootdown (invlpg). While a similar study has been done > in other kernels (e.g. L4 kernel), I am not aware if it has been done > for Linux O/S. > > Are there hooks or patches to test or evaluate TLB > performance. Specifically, I would like to know where to make changes > in Linux kernel to support each entry shootdown. Linux doesn't use a threshold to distingush between range flush and full flush in certain situations, but always does the full flush. That is something that might be possible to be improved, but it was so far always unclear how much it helps (it depends on the particular TLB size, cost of TLB refill etc.) -Andi -- ak@linux.intel.com