Kernel opps'es and lock-up under heavy TCP/IP traffic - Squeeze AMD64

[Angus Hedger <demidevil@gmail.com>]

Hey there.

I have been finding when I am doing anything network intensive (for example bit-torrent) I have been getting alarmingly regular kernel oops's, also on one occasion the system has locked up around the time one of these oops's occurred.

One of the submitted kernel oopses: http://www.kerneloops.org/submitresult.php?number=1763715

I also have the following in my syslog on each start-up, and I feel it might be related.

Feb  2 22:48:33 veyka kernel: [   12.229668] shpchp: Standard Hot Plug PCI Controller Driver version: 0.4

Feb  2 22:48:33 veyka kernel: [   12.257320] ACPI: I/O resource nForce2_smbus [0x1c00-0x1c3f] conflicts with ACPI region SM00 [0x1c00-0x1c05]

Feb  2 22:48:33 veyka kernel: [   12.257428] ACPI: If an ACPI driver is available for this device, you should use it instead of the native driver

Feb  2 22:48:33 veyka kernel: [   12.257431] nForce2_smbus 0000:00:0a.1: Error probing SMB1.

Feb  2 22:48:33 veyka kernel: [   12.257539] i2c i2c-0: nForce2 SMBus adapter at 0x1c80

Feb  2 22:48:33 veyka kernel: [   12.662694] ACPI: PCI Interrupt Link [AAZA] enabled at IRQ 22

Feb  2 22:48:33 veyka kernel: [   12.662699] HDA Intel 0000:00:10.1: PCI INT B -> Link[AAZA] -> GSI 22 (level, low) -> IRQ 22

Feb  2 22:48:33 veyka kernel: [   12.662761] HDA Intel 0000:00:10.1: setting latency timer to 64

Some more info about my system:

angus@veyka:~$ uname -r

2.6.32-trunk-amd64

It is a fully updated Squeeze install.

I did not have this problem under the older 2.6.30-2-amd64 kernel.

I would be very great-full if anyone could shed some light on my problem, I can provide more logs and information if needed.

Regards,

Angus