From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753330AbZBWGQb (ORCPT ); Mon, 23 Feb 2009 01:16:31 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752257AbZBWGQH (ORCPT ); Mon, 23 Feb 2009 01:16:07 -0500 Received: from one.firstfloor.org ([213.235.205.2]:59420 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752170AbZBWGQG (ORCPT ); Mon, 23 Feb 2009 01:16:06 -0500 Date: Mon, 23 Feb 2009 07:34:07 +0100 From: Andi Kleen To: David Miller Cc: andi@firstfloor.org, linux-kernel@vger.kernel.org Subject: Re: x86's nmi_hz wrt. oprofile's nmi_timer_int.c Message-ID: <20090223063406.GS26292@one.firstfloor.org> References: <873ae6wgd6.fsf@basil.nowhere.org> <20090222.201152.169082487.davem@davemloft.net> <20090223045159.GR26292@one.firstfloor.org> <20090222.215906.240407314.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20090222.215906.240407314.davem@davemloft.net> User-Agent: Mutt/1.4.2.1i Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > Look at the fallback logic, the pure NMI profiler can fail for > a number of reasons, not just because the watchdog is in > I/O APIC mode. I assume you mean nmi_init? It doesn't check for the watchdog at all, just if it knows the CPU and if it can profile All the reasons it fails on (unknown CPU, no APIC) will imply that the lapic based watchdog won't run either, because it relies on the same perfctr hardware. The only case where it could fall into this path is in IO-APIC nmi watchdog mode (and unknown CPU) and then again the IO-APIC watchdog doesn't do the multiple frequencies thing, it always runs with HZ. Admittedly the logic is quite obscure. -Andi -- ak@linux.intel.com -- Speaking for myself only.