lpfc: system freezing if FC connection is broken under load

From: Bodo Stroesser (bstroesser_at_fujitsu-siemens.com)
Date: 08/02/05

  • Next message: Lukas Hejtmanek: "Re: 2.6.13-rc5 - ACPI regression" 
    Date:	Tue, 02 Aug 2005 21:33:27 +0200
To: linux-kernel@vger.kernel.org

    Hi,

    my dual Xeon machine freezes, if connection between
    FC switch and tape drives is broken while writing to tapes.

    There is one SCSI target with 16 tape LUNs connected to my
    FC controller via FC switch. I can reproduce the problem by
    starting "dd if=/dev/zero of=/dev/st[0-7] bs=256K" on the
    first 8 LUNs. Then I unplug the connection between switch and
    tapes.

    It doesn't matter if using LP9802 or one channel of LP9402DC.
    The problem happens immediately after cfg_nodev_tmo has
    run out. If nodev_tmo is changed, time from breaking connection
    to machine freezing changes accordingly.

    After the problem happened, even NMIs no longer are handled.
    I added nmi_watchdog=1 to cmdline and added some simple code
    to nmi handler, that writes the nmi counter directly to video ram.
    In case of error, nmi no longer counts (but I have no idea, how
    this can happen, maybe there is some HW bug).

    What could I do to analyze the problem?

    Please CC me, I'm not on the list.

    Regards
            Bodo
    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

  • Next message: Lukas Hejtmanek: "Re: 2.6.13-rc5 - ACPI regression"

    Relevant Pages

    • Re: lpfc: system freezing if FC connection is broken under load
      ... > my dual Xeon machine freezes, if connection between ... > FC switch and tape drives is broken while writing to tapes. ... lpfc, after nodev_tmo expired. ...
      (Linux-Kernel)
    • Please help me identify conductor
      ... and is as thin as, clear tape, but with two conductors buried in it. ... The other end becomes a switch. ... I can also find how to prep the ends to make the connection at ...
      (sci.electronics.repair)
    • Re: Help with long term network problem
      ... Using a CNET network switch connected to a CNet Wireless G router Model ... Having the chart listing all of the computers is a great start. ... /all" shows only an Intel 2200BG WiFi connection - no Ethernet is apparent. ...
      (microsoft.public.windowsxp.network_web)
    • [patch 60/60] tape message cleanup
      ... struct irb *irb, int no) ... cu detected incorrect block-id sequence on tape. ... CU will switch to ... return ret; ...
      (Linux-Kernel)
    • [patch/s390 46/46] tape message cleanup
      ... struct irb *irb, int no) ... cu detected incorrect block-id sequence on tape. ... CU will switch to ... return ret; ...
      (Linux-Kernel)