I recently built a new server (2x Xeon 6318T on an Asus WS C621E Sage with 128GB Ram).  Unraid boots and seems to be functioning. However, after a few hours or sometimes 1 day, I get the following error before Unraid hangs.

 

kernel:NMI: PCI system error (SERR) for reason a0 on CPU 0

kernel:Dazed and confused, but trying to continue

 

I have not installed the GPUs at the moment;  Still using the onboard video while I burn in motherboard, NICs and Asus Hyper M.2 X16 card (4x NVMe storage).

 

Has anyone come across this kernel panic and know how to resolve it?  I doubt it's caused by the onboard video. I'll pull the Intel X540-T2 10Gb NIC out and see if that helps - the problem started when I added that card.

13 hours ago, zanzu said:

kernel:Dazed and confused, but trying to continue

 

That's a very unusual and somewhat humorous error message. Did you try a web search? It crops up several times over nearly 20 years and appears to be related to spurious PCIe interrupts. More information would be needed to investigate further. You could try unplugging all cards and seeing if it goes away, then re-installing them until you find the problem one.

Thanks for the suggestion.  I've stripped the server of all PCIe cards and am testing each component.  Since the error happens within 2 days, it will take me a week or so to completely check each card. 

I realized I haven't updated this post.   Long story short, the problem with all my hardware issues was related to a faulty cable connecting the power supply to the motherboard.