From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752826AbdJ3KDD (ORCPT ); Mon, 30 Oct 2017 06:03:03 -0400 Received: from bombadil.infradead.org ([65.50.211.133]:41387 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751460AbdJ3KDB (ORCPT ); Mon, 30 Oct 2017 06:03:01 -0400 Date: Mon, 30 Oct 2017 11:02:58 +0100 From: Peter Zijlstra To: Fengguang Wu Cc: Andi Kleen , Linux Kernel Mailing List , Linus Torvalds , Ingo Molnar , Stephane Eranian , Kan Liang Subject: Re: Linux 4.14-rc6: WARNING: CPU: 9 PID: 5377 at arch/x86/events/intel/core.c:2228 intel_pmu_handle_irq+0x4a8/0x4c0 Message-ID: <20171030100258.q4elbl6kgz477b6u@hirez.programming.kicks-ass.net> References: <20171029225155.qcum5i75awrt5tzm@wfg-t540p.sh.intel.com> <20171030062736.tv4el5mkwg6tkeup@wfg-t540p.sh.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20171030062736.tv4el5mkwg6tkeup@wfg-t540p.sh.intel.com> User-Agent: NeoMutt/20170609 (1.8.3) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Oct 30, 2017 at 07:27:36AM +0100, Fengguang Wu wrote: > [ 189.480568] perf: interrupt took too long (5132 > 4982), lowering kernel.perf_event_max_sample_rate to 38000 > [ 189.690660] perf: interrupt took too long (6582 > 6415), lowering kernel.perf_event_max_sample_rate to 30000 > [ 189.901706] perf: interrupt took too long (8268 > 8227), lowering kernel.perf_event_max_sample_rate to 24000 > [ 272.841032] perfevents: irq loop stuck! > [ 272.841038] ------------[ cut here ]------------ > [ 272.841046] WARNING: CPU: 9 PID: 5377 at arch/x86/events/intel/core.c:2228 intel_pmu_handle_irq+0x4a8/0x4c0 So I've not seen this in a fair while; is this new in 4.14? > [ 272.841083] CPU: 9 PID: 5377 Comm: usemem Not tainted 4.14.0-rc6 #1 At least you've got the right kernel this time... :-) > [ 272.841084] Hardware name: Intel Corporation S2600WTT/S2600WTT, BIOS GRRFSDP1.86B.0271.R00.1510301446 10/30/2015 That's a dual socket board for Xeon E5v3, which translates to HSW-EP if google is any good today. That's not a machine I have. Can you see this on other hardware too, like say IVB-EP ?