From andy@sees.bangor.ac.uk Tue Sep 7 02:03:58 1999 Return-Path: Received: from saturn.sees.bangor.ac.uk (saturn.sees.bangor.ac.uk [147.143.102.11]) by hub.freebsd.org (Postfix) with ESMTP id 6127F14F7B for ; Tue, 7 Sep 1999 02:03:56 -0700 (PDT) (envelope-from andy@sees.bangor.ac.uk) Received: from idris.sees.bangor.ac.uk (idris.sees.bangor.ac.uk [147.143.9.79]) by saturn.sees.bangor.ac.uk (8.8.8/8.8.8) with ESMTP id KAA00826 for ; Tue, 7 Sep 1999 10:03:47 +0100 (BST) Received: by idris.sees.bangor.ac.uk (8.9.3) id KAA01987; Tue, 7 Sep 1999 10:02:12 +0100 (BST) Message-Id: <199909070902.KAA01987@idris.sees.bangor.ac.uk> Date: Tue, 7 Sep 1999 10:02:12 +0100 (BST) From: Dr A W G Duller Reply-To: andy@sees.bangor.ac.uk To: FreeBSD-gnats-submit@freebsd.org Subject: "Timedout SCB handled by another timeout" on dual processor X-Send-Pr-Version: 3.2 >Number: 13612 >Category: kern >Synopsis: "Timedout SCB handled by another timeout" on dual processor >Confidential: no >Severity: serious >Priority: high >Responsible: gibbs >State: closed >Quarter: >Keywords: >Date-Required: >Class: sw-bug >Submitter-Id: current-users >Arrival-Date: Tue Sep 7 02:10:01 PDT 1999 >Closed-Date: Sat Feb 24 12:03:14 PST 2001 >Last-Modified: Sat Feb 24 12:04:09 PST 2001 >Originator: Dr A W G Duller >Release: FreeBSD 3.2-RELEASE i386 >Organization: University of Wales, Bangor, UK >Environment: Extract from /var/log/message Sep 2 13:50:19 idris /kernel: meteor0: ioctl: tsleep error -1 Sep 2 13:50:31 idris last message repeated 2 times Sep 2 13:52:36 idris /kernel: Timedout SCB handled by another timeout Sep 2 13:54:37 idris /kernel: Timedout SCB handled by another timeout Sep 2 13:56:36 idris /kernel: Timedout SCB handled by another timeout Sep 2 13:56:36 idris /kernel: meteor0: ioctl: tsleep error -1 Sep 2 13:58:36 idris /kernel: Timedout SCB handled by another timeout Sep 2 14:19:33 idris /kernel: Copyright (c) 1992-1999 FreeBSD Inc. Sep 2 14:19:33 idris /kernel: Copyright (c) 1982, 1986, 1989, 1991, 1993 Sep 2 14:19:33 idris /kernel: The Regents of the University of California. All rights reserved. Sep 2 14:19:33 idris /kernel: FreeBSD 3.2-RELEASE #5: Mon Jul 12 09:41:57 BST 1999 Sep 2 14:19:33 idris /kernel: andy@idris.sees.bangor.ac.uk:/usr/src/sys/compile/IDRIS Sep 2 14:19:33 idris /kernel: Timecounter "i8254" frequency 1193182 Hz Sep 2 14:19:33 idris /kernel: CPU: Pentium III (686-class CPU) Sep 2 14:19:33 idris /kernel: Origin = "GenuineIntel" Id = 0x673 Stepping=3 Sep 2 14:19:33 idris /kernel: Features=0x387fbff,MMX,,> Sep 2 14:19:33 idris /kernel: real memory = 536870912 (524288K bytes) Sep 2 14:19:34 idris /kernel: avail memory = 520024064 (507836K bytes) Sep 2 14:19:34 idris /kernel: Programming 24 pins in IOAPIC #0 Sep 2 14:19:34 idris /kernel: FreeBSD/SMP: Multiprocessor motherboard Sep 2 14:19:34 idris /kernel: cpu0 (BSP): apic id: 1, version: 0x00040011, at 0xfee00000 Sep 2 14:19:34 idris /kernel: cpu1 (AP): apic id: 0, version: 0x00040011, at 0xfee00000 Sep 2 14:19:34 idris /kernel: io0 (APIC): apic id: 2, version: 0x00170011, at 0xfec00000 Sep 2 14:19:34 idris /kernel: Preloaded elf kernel "kernel" at 0xc02bf000. Sep 2 14:19:34 idris /kernel: Probing for devices on PCI bus 0: Sep 2 14:19:34 idris /kernel: chip0: rev 0x00 on pci0.0.0 Sep 2 14:19:34 idris /kernel: chip1: rev 0x00 on pci0.1.0 Sep 2 14:19:34 idris /kernel: ahc0: rev 0x00 int a irq 11 on pci0.12.0 Sep 2 14:19:34 idris /kernel: ahc0: aic7896/97 Wide Channel A, SCSI Id=7, 16/255 SCBs Sep 2 14:19:34 idris /kernel: ahc1: rev 0x00 int a irq 11 on pci0.12.1 Sep 2 14:19:34 idris /kernel: ahc1: aic7896/97 Wide Channel B, SCSI Id=7, 16/255 SCBs Sep 2 14:19:34 idris /kernel: meteor0: rev 0x00 int a irq 11 on pci0.13.0 Sep 2 14:19:34 idris /kernel: meteor0: rev 0x1 Sep 2 14:19:34 idris /kernel: fxp0: rev 0x08 int a irq 10 on pci0.14.0 Sep 2 14:19:34 idris /kernel: fxp0: Ethernet address 00:a0:c9:ac:a5:98 Sep 2 14:19:34 idris /kernel: adv0: rev 0x03 int a irq 5 on pci0.16.0 Sep 2 14:19:34 idris /kernel: adv0: AdvanSys Ultra SCSI Host Adapter, SCSI ID 7, queue depth 240 Sep 2 14:19:34 idris /kernel: chip2: rev 0x02 on pci0.18.0 Sep 2 14:19:34 idris /kernel: chip3: rev 0x02 on pci0.18.3 Sep 2 14:19:34 idris /kernel: vga0: rev 0x23 on pci0.20.0 Sep 2 14:19:34 idris /kernel: Probing for devices on PCI bus 1: Sep 2 14:19:34 idris /kernel: chip4: rev 0x06 on pci1.15.0 Sep 2 14:19:34 idris /kernel: Probing for devices on PCI bus 2: Sep 2 14:19:34 idris /kernel: vga1: rev 0x01 int a irq 11 on pci2.4.0 Sep 2 14:19:34 idris /kernel: Probing for PnP devices: Sep 2 14:19:34 idris /kernel: Probing for devices on the ISA bus: Sep 2 14:19:34 idris /kernel: sc0 on isa Sep 2 14:19:34 idris /kernel: sc0: VGA color <16 virtual consoles, flags=0x0> Sep 2 14:19:34 idris /kernel: atkbdc0 at 0x60-0x6f on motherboard Sep 2 14:19:34 idris /kernel: atkbd0 irq 1 on isa Sep 2 14:19:34 idris /kernel: psm0 irq 12 on isa Sep 2 14:19:34 idris /kernel: psm0: model Generic PS/2 mouse, device ID 0 Sep 2 14:19:34 idris /kernel: sio0 at 0x3f8-0x3ff irq 4 flags 0x10 on isa Sep 2 14:19:34 idris /kernel: sio0: type 16550A Sep 2 14:19:34 idris /kernel: sio1 at 0x2f8-0x2ff irq 3 on isa Sep 2 14:19:34 idris /kernel: sio1: type 16550A Sep 2 14:19:34 idris /kernel: fdc0 at 0x3f0-0x3f7 irq 6 drq 2 on isa Sep 2 14:19:34 idris /kernel: fdc0: FIFO enabled, 8 bytes threshold Sep 2 14:19:34 idris /kernel: fd0: 1.44MB 3.5in Sep 2 14:19:34 idris /kernel: ppc0 at 0x378 irq 7 flags 0x40 on isa Sep 2 14:19:34 idris /kernel: ppc0: Generic chipset (NIBBLE-only) in COMPATIBLE mode Sep 2 14:19:34 idris /kernel: lpt0: on ppbus 0 Sep 2 14:19:34 idris /kernel: lpt0: Interrupt-driven port Sep 2 14:19:34 idris /kernel: ppi0: on ppbus 0 Sep 2 14:19:34 idris /kernel: plip0: on ppbus 0 Sep 2 14:19:34 idris /kernel: lpt0: on ppbus 0 Sep 2 14:19:34 idris /kernel: lpt0: Interrupt-driven port Sep 2 14:19:34 idris /kernel: adv0 not found at 0x330 Sep 2 14:19:34 idris /kernel: vga0 at 0x3b0-0x3df maddr 0xa0000 msize 131072 on isa Sep 2 14:19:34 idris /kernel: npx0 on motherboard Sep 2 14:19:34 idris /kernel: npx0: INT 16 interface Sep 2 14:19:34 idris /kernel: APIC_IO: Testing 8254 interrupt delivery Sep 2 14:19:34 idris /kernel: APIC_IO: routing 8254 via pin 2 Sep 2 14:19:34 idris /kernel: Waiting 15 seconds for SCSI devices to settle Sep 2 14:19:34 idris /kernel: SMP: AP CPU #1 Launched! Sep 2 14:19:35 idris /kernel: changing root device to da0s2a Sep 2 14:19:35 idris /kernel: cd0 at adv0 bus 0 target 0 lun 0 Sep 2 14:19:35 idris /kernel: cd0: Removable CD-ROM SCSI-2 device Sep 2 14:19:35 idris /kernel: cd0: 10.000MB/s transfers (10.000MHz, offset 15) Sep 2 14:19:35 idris /kernel: cd0: Attempt to query device size failed: NOT READY, Medium not present Sep 2 14:19:35 idris /kernel: da1 at ahc0 bus 0 target 1 lun 0 Sep 2 14:19:35 idris /kernel: da1: Fixed Direct Access SCSI-2 device Sep 2 14:19:35 idris /kernel: da1: 80.000MB/s transfers (40.000MHz, offset 15, 16bit), Tagged Queueing Enabled Sep 2 14:19:35 idris /kernel: da1: 8715MB (17850000 512 byte sectors: 255H 63S/T 1111C) Sep 2 14:19:35 idris /kernel: da0 at ahc0 bus 0 target 0 lun 0 Sep 2 14:19:35 idris /kernel: da0: Fixed Direct Access SCSI-2 device Sep 2 14:19:35 idris /kernel: da0: 80.000MB/s transfers (40.000MHz, offset 15, 16bit), Tagged Queueing Enabled Sep 2 14:19:35 idris /kernel: da0: 8715MB (17850000 512 byte sectors: 255H 63S/T 1111C) >Description: Under heavily loaded conditions (copying a 180Mb file at the same time as image grabbing and processing using the Matrox Meteor card the error message: "Timedout SCB handled by another timeout" appears and all operations are performed extremely slowly (several minutes to perform an ls). The only cure seems to be a reboot. >How-To-Repeat: It appears hard to duplicate when required but has happened twice, both times the Matrox Meteor was in use and the "/kernel: meteor0: ioctl: tsleep error -1" appeared a few minutes before. >Fix: None known. >Release-Note: >Audit-Trail: Responsible-Changed-From-To: freebsd-bugs->gibbs Responsible-Changed-By: ken Responsible-Changed-When: Tue Sep 7 23:07:58 PDT 1999 Responsible-Changed-Why: Justin's driver. State-Changed-From-To: open->closed State-Changed-By: gibbs State-Changed-When: Sat Feb 24 12:03:14 PST 2001 State-Changed-Why: These types of problems indicate that ineterrupt delivery is broken. My guess is that the SMP issue that caused this problem has been fixed in a later release. If that is not the case, please reopen a PR. http://www.freebsd.org/cgi/query-pr.cgi?pr=13612 >Unformatted: