From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753254AbZHSVq5 (ORCPT ); Wed, 19 Aug 2009 17:46:57 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753198AbZHSVq4 (ORCPT ); Wed, 19 Aug 2009 17:46:56 -0400 Received: from mail-ew0-f207.google.com ([209.85.219.207]:45445 "EHLO mail-ew0-f207.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753193AbZHSVq4 convert rfc822-to-8bit (ORCPT ); Wed, 19 Aug 2009 17:46:56 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=j5icfcKCTE96kUdYNJU+YcpFj9lgzm3Q9kbIKKO1tCFzEGqJv66lzc2di5LLeb+iFG Quv8pm1Pk0m+HCjHy8yvp1O/Nrcj/vEXvN+/D/4q4/9s+sb+Hb23954etUzOJYkUJ1W6 FAKgE21JHqjcHlaA9OElWBtsHCIFPwtlKoCIk= MIME-Version: 1.0 In-Reply-To: References: <4A80C2F8.2040208@gmail.com> <4A835760.2050803@gmail.com> Date: Wed, 19 Aug 2009 18:46:56 -0300 Message-ID: Subject: Re: Flooded by do_IRQ: 0.91 No irq handler for vector From: Luis Fernando Planella Gonzalez To: "Eric W. Biederman" Cc: Robert Hancock , linux-kernel@vger.kernel.org Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org I have changed my distro to sidux, so it won't be an easy task to return to 2.6.24.... Anyway, I do use the 64bit kernel. But I've downloaded the 32 bit version (sidux 2009.02 with the 2.6.30.1 kernel), and the very same error occurs. I've just used the live cd, and it does happen. Something that changed from 2.6.28 to 2.6.30 is that it no longer happens the 0.99 message. All complaints are about 0.91... One more thing: Deleting /usr/sbin/irqbalance changed nothing, which is no surprise, as I had already tested the noirqbalance kernel option.... I'm pasting here something I had previously replied personally to Robert Hancock, and may be useful: Well, as I've installed sidux, it has upgraded the kernel to 2.6.30.5, but the error is the same. I've also tried: * noapic: the message changes to do_IRQ: 0.55 No irq handler for vector (irq -1), but then the X server fails to start * noacpi: have no effect on the error message. Thanks a lot. -- Luis Fernando Planella Gonzalez 2009/8/19 Eric W. Biederman : > Robert Hancock writes: > >> On 08/11/2009 04:28 PM, Luis Fernando Planella Gonzalez wrote: >>> I'm really concerned that all those interrupts might slow down the >>> computer somehow... >>> Here is an attached syslog part after a reboot. >>> Sometimes, the ratelimit says that thousands of callbacks were suppressed. >>> Is there a way to make this message be displayed only once? >>> >>> In arch/x86/kernel/irq.c, the line 213 is: >>> irq = __get_cpu_var(vector_irq)[vector]; >>> >>> In my case, the returned irq is -1. Doesn't it makes sense to not log >>> the "No irq handler for vector" message when irq<  0? >>> >>> Or even a deeper answer: Why, in my case, the resulting irq is -1? >> >> Not logging would just cover up the problem, the issue in your case is that >> something seems to be asserting a ton of interrupts on an IRQ line that no >> driver has claimed.. > > It is slightly worse.  We are seeing interrupts asserted and we don't > know which IRQ line they belong to.  This should never happen. > > You say it is first 0.99 and 0.91 so it is moving. > > Luis are you running a 64bit kernel?  I think you would have to be > for your symptoms to go all of the way back to 2.6.24. > > My primary suspect is that something the irq migration code is not > working properly on your computer.  Could you disable > /usr/sbin/irqbalance (possibly just by deleting it) and tell me if > that fixes your symptoms? > > If not we have a very nasty bug in how your ioapics are being programmed. > > Eric >