From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andrew Vasquez Subject: Re: Recurring qla2xxx crashes (maybe APIC related) Date: Tue, 29 Apr 2008 14:16:55 -0700 Message-ID: <20080429211655.GA72811@plap4.qlogic.org> References: <4811ACAC.7060808@linpro.no> <20080425155018.GG8849@plap4> <48120F8B.7060005@linpro.no> <20080425171821.GK8849@plap4> <4815709C.3060502@linpro.no> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from avexch1.qlogic.com ([198.70.193.115]:6419 "EHLO avexch1.qlogic.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751078AbYD2VQ4 (ORCPT ); Tue, 29 Apr 2008 17:16:56 -0400 Content-Disposition: inline In-Reply-To: <4815709C.3060502@linpro.no> Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: Tore Anderson Cc: Linux SCSI Mailing List On Mon, 28 Apr 2008, Tore Anderson wrote: > * Andrew Vasquez > > > Hmm, MSI is enabled: > > Indeed - seems to be the default behaviour. > > > could you try disabling MSI via 'pci=nomsi' (I believe), we've dealt > > with a large number of problem reports where customers reported 'odd' > > behaviours (no interrupt routining) with several motherboard > > chipsets. At least it could be another useful datapoint... > > The system has now been up for 58 hours straight with MSI disabled per > your suggestion. This is almost a new record, usually it has crashed > once per day or more. I won't open the champagne before a week more has > passed, but this looks _very_ promising! That's good news... > Thank you very much for your help in tracking this down! Be sure to let > me know if you want any more information and I'll see what I can do. > The system isn't yet back in full production, so I have a small window > of opportunity to reproduce the problem, test patches, and so on. In general, most MSI/MSI-X machine/chipset quirks (global/bus-level disabling) are handled by the PCI layer. I'd be curious to see if any of the 30+ updates to drivers/pci/quirk.c since 2.6.22 have addressed this issue via DECLARE_PCI_FIXUP_FINAL()??? Could you send the output of 'lspci -vvx'?