RE: SMP forcing crash/reboot in 4.9-STABLE

guy_at_device.dyndns.org
Date: 12/18/03

  • Next message: Sapo: "ahc0: Dumping Card State in Message-in phase, at SEQADDR 0x1ae"
    Date: Thu, 18 Dec 2003 16:24:14 +0100 (CET)
    To: Adam Maloney <adam@whee.org>
    
    

    On 18-Dec-2003 Adam Maloney wrote:
    > We have a 4-way P3/500 Xeon system running FreeBSD. We had been running
    > 4.8-STABLE for a number of months with SMP enabled and no issues. Around
    > 25-November we moved to 4.9-STABLE. The system ran without SMP enabled
    > until Tuesday, when we enabled SMP and APIC_IO, rebuilt the kernel, and
    > rebooted. Then about every 30 minutes the system would reboot. We moved
    > back to single-processor (using the source updated on 25-Nov) and it has
    > worked since.
    >
    > So we synced source last night and tried enabling SMP again this morning.
    > We are still seeing the same problem. We have switched back to a non-SMP
    > kernel (from last night's sync) and are running fine.
    >
    > Has anyone else seen this? Any ideas where to look? There is nothing in
    > messages or dmesg about the crash, and I haven't been able to catch it at
    > the console to see if there's a message there.

    This may be related to my problem, though the symptom is different.

    Since the same time (around the end of november) i tried many times to
    build a SMP-enabled 4.9-STABLE kernel for my bi-athlon machine. It always
    hangs (no error msg, total iresponsiveness) at the end of the kernel boot
    (just before mounting filesystems).

    I then reverted my cvs tree to use -RELEASE, and all is fine.

    I did not yet try a non-SMP kernel. I'll do that asap.

    --
            Guy
    _______________________________________________
    freebsd-stable@freebsd.org mailing list
    http://lists.freebsd.org/mailman/listinfo/freebsd-stable
    To unsubscribe, send any mail to "freebsd-stable-unsubscribe@freebsd.org"
    

  • Next message: Sapo: "ahc0: Dumping Card State in Message-in phase, at SEQADDR 0x1ae"

    Relevant Pages

    • 2.6.12-rc5-mm2 bug report
      ... stable smp machine has gone a little less stable after I installed some more ... Reiser4 demanded the use of -mm branch of kernel. ... Jun 4 19:32:26 router vmunix: PREEMPT SMP ... # Performance-monitoring counters support ...
      (Linux-Kernel)
    • Re: [GIT PATCH] ACPI patches for 2.6.25-rc0 (#2)
      ... ACPI: add newline to printk ... SMP ... Kernel panic - not syncing: ... # Infrared-port device drivers ...
      (Linux-Kernel)
    • Re: [FreeBSD 5.3 STABLE/RC2] SMP crashes
      ... While compiling ATLAS library and working with some other applications, ... With SMP disabled, the box was now stable for over 7 days, also under heavy load. ... > I was in good luck taking the panic kernel report. ... > resetting SCSI bus! ...
      (comp.unix.bsd.freebsd.misc)
    • Re: panic: sorele
      ... I only have squid in my machine and although I have 1 cpu. ... I didnt try to compile kernel without SMP but I will try ... # To include support for VESA video modes ...
      (freebsd-current)
    • Re: PREEMPT_RT and I-PIPE: the numbers, take 3
      ... >> benchmark a UP kernel on a UP system. ... PREEMPT_RT is quite similar to the SMP kernel (it ... For someone working on making PREEMPT_RT better, comparing to ... worst-case irq latencies were roughly comparable. ...
      (Linux-Kernel)