From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751472AbdJSGWS (ORCPT ); Thu, 19 Oct 2017 02:22:18 -0400 Received: from mail-wm0-f51.google.com ([74.125.82.51]:48551 "EHLO mail-wm0-f51.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750985AbdJSGWR (ORCPT ); Thu, 19 Oct 2017 02:22:17 -0400 X-Google-Smtp-Source: ABhQp+RgkWH8oEBITtmuJ6Uzazf2bdV5BnDbmITGkRUnYXd20I/ASNpftOVPWfYJ6r56w0bWAPUahA== Date: Thu, 19 Oct 2017 08:22:12 +0200 From: Ingo Molnar To: Byungchul Park Cc: peterz@infradead.org, tglx@linutronix.de, linux-kernel@vger.kernel.org, linux-mm@kvack.org, kernel-team@lge.com, Linus Torvalds Subject: Re: [PATCH 1/2] lockdep: Introduce CROSSRELEASE_STACK_TRACE and make it not unwind as default Message-ID: <20171019062212.n55vzg4khtds3mqk@gmail.com> References: <1508318006-2090-1-git-send-email-byungchul.park@lge.com> <20171018100944.g2mc6yorhtm5piom@gmail.com> <20171019043240.GA3310@X58A-UD3R> <20171019055730.mlpoz333ekflacs2@gmail.com> <20171019061112.GB3310@X58A-UD3R> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20171019061112.GB3310@X58A-UD3R> User-Agent: NeoMutt/20170113 (1.7.2) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org * Byungchul Park wrote: > On Thu, Oct 19, 2017 at 07:57:30AM +0200, Ingo Molnar wrote: > > > > * Byungchul Park wrote: > > > > > On Wed, Oct 18, 2017 at 12:09:44PM +0200, Ingo Molnar wrote: > > > > BTW., have you attempted limiting the depth of the stack traces? I suspect more > > > > than 2-4 are rarely required to disambiguate the calling context. > > > > > > I did it for you. Let me show you the result. > > > > > > 1. No lockdep: 2.756558155 seconds time elapsed ( +- 0.09% ) > > > 2. Lockdep: 2.968710420 seconds time elapsed ( +- 0.12% ) > > > 3. Lockdep + Crossrelease 5 entries: 3.153839636 seconds time elapsed ( +- 0.31% ) > > > 4. Lockdep + Crossrelease 3 entries: 3.137205534 seconds time elapsed ( +- 0.87% ) > > > 5. Lockdep + Crossrelease + This patch: 2.963669551 seconds time elapsed ( +- 0.11% ) > > > > I think the lockdep + crossrelease + full-stack numbers are missing? > > Ah, the last version of crossrelease merged into vanilla, records 5 > entries, since I thought it overloads too much if full stack is used, > and 5 entries are enough. Don't you think so? Ok, fair enough, I missed that limitation! > > That's very reasonable and we can keep the single-entry cross-release feature > > enabled by default as part of CONFIG_PROVE_LOCKING=y - assuming all the crashes > > BTW, is there any crash by cross-release I don't know? Of course, I know > cases of false positives, but I don't about crash. There's no current crash regression that I know of - I'm just outlining the conditions of getting all this re-enabled in the next merge window. Instead of sending two series, could you please send a series that includes both these fixing + re-enabling patches, plus the false positive fixes? In particular I think the cross-release re-enabling should be done as the last patch, so that any future bisections of new false positives won't be made more difficult by re-introducing the old false positives near the end of the bisection. Thanks, Ingo