Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751115AbWJQPSM (ORCPT ); Tue, 17 Oct 2006 11:18:12 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751006AbWJQPSL (ORCPT ); Tue, 17 Oct 2006 11:18:11 -0400 Received: from mta11.adelphia.net ([68.168.78.205]:15808 "EHLO mta11.adelphia.net") by vger.kernel.org with ESMTP id S1751115AbWJQPSK (ORCPT ); Tue, 17 Oct 2006 11:18:10 -0400 Message-ID: <4534F41A.1030504@Adelphia.net> Date: Tue, 17 Oct 2006 11:17:46 -0400 From: Dyson User-Agent: Thunderbird 1.5.0.7 (X11/20060911) MIME-Version: 1.0 To: linux-kernel@vger.kernel.org CC: Dyson Shultz Subject: Re: Still broken sata (VIA) on Asus A8V (kernel 2.6.14+) with irqbalance Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 20831 Lines: 362 (REG, Still broken sata (VIA) on Asus A8V (kernel 2.6.14+) with irqbalance) Ok, a little late, Heikki Orsila, can you send dmesg from working kernel and /proc/interrupts too ? and if you have a dmesg from a not working kernel can you send too ? Vladimir B. Savkin , have you try the patch if so , please send the results Thanks, On Sun, 2006-07-30 at 13:48 +0300, Heikki Orsila wrote: > On Sat, Jul 29, 2006 at 05:08:09AM +0100, Sergio Monteiro Basto wrote: > > cat DMESG | grep -i fixup > > PCI: VIA IRQ fixup for 0000:00:0f.1, from 255 to 0 > > PCI: VIA IRQ fixup for 0000:00:10.0, from 11 to 3 > > PCI: VIA IRQ fixup for 0000:00:10.1, from 11 to 3 > > PCI: VIA IRQ fixup for 0000:00:10.2, from 10 to 3 > > > > with IO-APIC working , you could try patches to not "VIA IRQ quirk > > fixup", but could not be the main problem. > > > > I have a very experimental patch > > http://lkml.org/lkml/2006/7/28/99 > > > > > > Which you can just apply and make bzImage, install and reboot , don't > > need to recompile all over again. > > Applied, tried and it worked! I couldn't reproduce the error in 30 > minutes of stress testing. With a buggy kernel it only took a matter of > minutes to reproduce it. Thank you for your effort. > > Heikki Orsila ------------- I was getting these sata messages after about 8 to 10 hours of uptime and the computer would freeze at least twice a day repeatedly for a week. Oct 16 05:36:17 O1600 kernel: ata1: command 0x35 timeout, stat 0x50 host_stat 0x4 Oct 16 05:36:47 O1600 kernel: ata1: command 0xea timeout, stat 0x50 host_stat 0x0 I tried kernel 2.6.19-rc2 and I would get this message instead with the computer freezing. Oct 15 00:04:36 O1600 kernel: APIC error on CPU0: 00(08) I put in the patch mentioned below to get rid of the VIA IRQ fixup for a VIA K8T800 SMP machine and the computer hasn't froze yet after 19 hours. The motherboard is a MSI K8T Master2-FAR with two Opteron 242s. Here is the IRQ fixup messages pre patch running kernel 2.6.16.21-0.25-custom (SuSE 10.1): <6>PCI: VIA IRQ fixup for 0000:00:0f.1, from 255 to 9 <6>VP_IDE: VIA vt8237 (rev 00) IDE UDMA133 controller on pci0000:00:0f.1 <6>PCI: VIA IRQ fixup for 0000:00:10.0, from 10 to 1 <6>PCI: VIA IRQ fixup for 0000:00:10.1, from 10 to 1 <6>PCI: VIA IRQ fixup for 0000:00:10.2, from 11 to 1 Post patch I don't have any VIA fixup messages. The lspci and interrupts look the same before and after the patch. eth0 and nvidia weren't irq balancing pre or post the patch - I'm not sure why. Here is my interrupts: -post patch CPU0 CPU1 0: 32807264 32848573 IO-APIC-edge timer 1: 1701 1693 IO-APIC-edge i8042 7: 0 2 IO-APIC-edge parport0 8: 0 0 IO-APIC-edge rtc 9: 0 1 IO-APIC-level acpi 12: 212960 207505 IO-APIC-edge i8042 14: 558126 566095 IO-APIC-edge ide0 15: 295527 293224 IO-APIC-edge ide1 169: 267097 277613 IO-APIC-level libata 177: 9915860 10 IO-APIC-level eth0, nvidia 185: 0 0 IO-APIC-level uhci_hcd:usb1, uhci_hcd:usb2, uhci_hcd:usb3, ehci_hcd:usb4 193: 30462 29909 IO-APIC-level EMU10K1 201: 0 3 IO-APIC-level ohci1394 209: 0 0 IO-APIC-level cx88[0] NMI: 64698 64682 LOC: 65647942 65646061 ERR: 0 MIS: 0 Here is my lspci -vvv post patch 00:00.0 Host bridge: VIA Technologies, Inc. VT8385 [K8T800 AGP] Host Bridge (rev 01) Subsystem: Micro-Star International Co., Ltd. Unknown device 1300 Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- Status: Cap+ 66MHz+ UDF- FastB2B- ParErr- DEVSEL=medium >TAbort- SERR- TAbort- SERR- TAbort- Reset- FastB2B- Capabilities: [80] Power Management version 2 Flags: PMEClk- DSI- D1+ D2- AuxCurrent=0mA PME(D0-,D1-,D2-,D3hot-,D3cold-) Status: D0 PME-Enable- DSel=0 DScale=0 PME- 00:06.0 Multimedia audio controller: Creative Labs SB Audigy (rev 03) Subsystem: Creative Labs SB0090 Audigy Player Control: I/O+ Mem- BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- Status: Cap+ 66MHz- UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR- TAbort- SERR-