AMD EPYC "DPC Containment event" Errors

[Stewge]

Hi,

Just updated one of our nodes last night to the latest Kernel 4.15.18-16-pve (for the SACK patches) and I started getting a massive amount of log spam to /var/log/messages and dmesg.
The message is:

Jun 24 22:56:00 orthrus4 kernel: [  233.086556] dpc 0000:30:03.1:pcie010: DPC containment event, status:0x1f00 source:0x0000

There's approximately 50/second.

So far I've managed to silence it by adding "pcie_aspm=off" to the /etc/default/grub boot parameters but I'm unsure of what other effects that will have.

This didn't occur on the older 4.15.18-9-pve kernel.

 

[Stoiko Ivanov]

any chance there is a newer BIOS/firmware for your system (and all its components) ? - This might help in situations like this.

Additionally I found the following links which might help:
https://community.amd.com/thread/219564
https://devtalk.nvidia.com/default/...cie-bus-error-with-two-nvidia-cards-on-linux/
https://askubuntu.com/questions/949254/new-system-with-pcie-errors-need-help-debugging

I hope this helps!