From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751730Ab2AQCrj (ORCPT ); Mon, 16 Jan 2012 21:47:39 -0500 Received: from mail-yx0-f174.google.com ([209.85.213.174]:39993 "EHLO mail-yx0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751624Ab2AQCrg convert rfc822-to-8bit (ORCPT ); Mon, 16 Jan 2012 21:47:36 -0500 MIME-Version: 1.0 In-Reply-To: <1326744932.16150.9.camel@sbsiddha-desk.sc.intel.com> References: <1326744932.16150.9.camel@sbsiddha-desk.sc.intel.com> Date: Mon, 16 Jan 2012 18:47:36 -0800 X-Google-Sender-Auth: AcO7lmvotPWJI4EyHIH2KkrcvVU Message-ID: Subject: Re: [patch] x86, tsc: fix SMI induced variation in quick_pit_calibrate() From: Yinghai Lu To: Suresh Siddha Cc: Linus Torvalds , Ingo Molnar , Thomas Gleixner , "H. Peter Anvin" , linux-kernel , asit.k.mallick@intel.com Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Jan 16, 2012 at 12:15 PM, Suresh Siddha wrote: > Linus, We are seeing NTP failures on a big cluster as a result of big > variation in calibrated TSC values. Our debug showed that it is indeed > because of the SMI and its effect on quick pit calibration. Appended > patch helps fix it. It ran over the weekend boot tests with out any > failures. > > >  [ As far as the SMI source is concerned, this is a periodic SMI that gets >    disabled after ACPI is enabled by the OS. But the TSC calibration happens >    before the ACPI is enabled. ] > Hi, Suresh Do you know what is SMI doing at that time ? with USB legacy emulating? I have some patches that will do USB hand off early. Wonder if that would help. please check those patches at git://git.kernel.org/pub/scm/linux/kernel/git/yinghai/linux-yinghai.git usb_smi_disable_early Thanks Yinghai Lu