From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756797AbYIDVkW (ORCPT ); Thu, 4 Sep 2008 17:40:22 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754598AbYIDVkG (ORCPT ); Thu, 4 Sep 2008 17:40:06 -0400 Received: from mx2.mail.elte.hu ([157.181.151.9]:33751 "EHLO mx2.mail.elte.hu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754559AbYIDVkF (ORCPT ); Thu, 4 Sep 2008 17:40:05 -0400 Date: Thu, 4 Sep 2008 23:39:45 +0200 From: Ingo Molnar To: Linus Torvalds Cc: Alan Cox , Thomas Gleixner , LKML , Alok Kataria , Arjan van de Veen , "H. Peter Anvin" , Peter Zijlstra Subject: Re: [RFC patch 0/4] TSC calibration improvements Message-ID: <20080904213945.GA18347@elte.hu> References: <20080904190728.59634020@lxorguk.ukuu.org.uk> <20080904204305.GA29065@elte.hu> <20080904205236.GA3864@elte.hu> <20080904212130.GA12406@elte.hu> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.18 (2008-05-17) X-ELTE-VirusStatus: clean X-ELTE-SpamScore: -1.5 X-ELTE-SpamLevel: X-ELTE-SpamCheck: no X-ELTE-SpamVersion: ELTE 2.0 X-ELTE-SpamCheck-Details: score=-1.5 required=5.9 tests=BAYES_00 autolearn=no SpamAssassin version=3.2.3 -1.5 BAYES_00 BODY: Bayesian spam probability is 0 to 1% [score: 0.0000] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org * Linus Torvalds wrote: > On Thu, 4 Sep 2008, Linus Torvalds wrote: > > > > Face it, if somebody tries to make QUICK_PIT_MS be so large as to > > that be an issue, then the whole point of the function goes away. > > Btw, the same is true of adding any random "sanity checking". The > point of that thing was to simply only work when the PIT works as > advertized, and fail immediately if it doesn't. Even *if* you were to > pick a big calibration delay *and* if you happened to have a PIT that > is broken and doesn't wrap correctly, the design of the thing would > mean that it would then fail the calibration already. > > Exactly because it would _see_ that it's not wrapping. yeah - pit_expect_msb() would return after 50,000 iterations with a failure. So i was wondering whether for such PITs we _want_ the slow and complicated case to run. Probably not, because the PIT could quite likely still be counting very precisely as long as no wraparound was involved. Ingo