Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755950AbYGXNmj (ORCPT ); Thu, 24 Jul 2008 09:42:39 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752713AbYGXNmb (ORCPT ); Thu, 24 Jul 2008 09:42:31 -0400 Received: from dgate10.fujitsu-siemens.com ([80.70.172.49]:48131 "EHLO dgate10.fujitsu-siemens.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751643AbYGXNmb (ORCPT ); Thu, 24 Jul 2008 09:42:31 -0400 DomainKey-Signature: s=s768; d=fujitsu-siemens.com; c=nofws; q=dns; h=X-SBRSScore:X-IronPort-AV:Received:X-IronPort-AV: Received:Received:Message-ID:Date:From:Organization: User-Agent:MIME-Version:To:CC:Subject:References: In-Reply-To:Content-Type:Content-Transfer-Encoding; b=OUUv0gjUjnUSz3kVuV3gmVosjrHQpk4IqeYokC+PMZIYfLx1gDzbBqGI pMK4SSUp4HBsGwNFAZFmROi9QbUhtyrvwaZAiivXOEzKMfoijcznW2OzU FbhYGTABP7JLGNy; X-SBRSScore: None X-IronPort-AV: E=Sophos;i="4.31,245,1215381600"; d="scan'208";a="23408036" X-IronPort-AV: E=Sophos;i="4.31,245,1215381600"; d="scan'208";a="36319246" Message-ID: <488886C8.3020904@fujitsu-siemens.com> Date: Thu, 24 Jul 2008 15:42:32 +0200 From: Martin Wilck Organization: Fujitsu Siemens Computers User-Agent: Thunderbird 2.0.0.15pre (X11/20080508) MIME-Version: 1.0 To: "H. Peter Anvin" CC: Thomas Gleixner , "linux-kernel@vger.kernel.org" , "Wichert, Gerhard" Subject: Re: [PATCH] x86 (64): make calibrate_APIC_clock() SMI-safe References: <48885DDC.9010003@fujitsu-siemens.com> <48888444.1020305@zytor.com> In-Reply-To: <48888444.1020305@zytor.com> Content-Type: text/plain; charset=ISO-8859-15; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1305 Lines: 40 H. Peter Anvin wrote: > The other thing we may want to consider is doing multiple runs of the > calibration loop. I suspect we'd get a more accurate result running, > say, 9 loops of the 1/9 the current duration and looking either for the > best result or the median (NOT the mean.) > > -hpa We considered that. However I think if you know what result to expect (here: TICK_COUNT + a few cycles) it is both easier and safer to compare against the expected value than to do statistics. SMI protection is all about outliers (thus, the median is a good suggestion but I'd say it would be over-enigineered). Martin PS: I am sorry for the stupid, misleading typo (SMi -> smp) in the mail subject. -- Martin Wilck PRIMERGY System Software Engineer FSC IP ESP DEV 6 Fujitsu Siemens Computers GmbH Heinz-Nixdorf-Ring 1 33106 Paderborn Germany Tel: ++49 5251 8 15113 Fax: ++49 5251 8 20209 Email: mailto:martin.wilck@fujitsu-siemens.com Internet: http://www.fujitsu-siemens.com Company Details: http://www.fujitsu-siemens.com/imprint.html -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/