pci express error counters, whats normal whats a problem?

[JeffPuserid]

I am hoping that someone could take pity on us mere mortals and help us in understanding PCI Error counters, specifically what is potentially problematic and what is normal, I have two gaming PC's in the house, one is mine and the other is my grandson's, both have AMD cpu's (5700X3d and 9800X3d) and Nvidia Gpu's (3070 and 4090) Having upgraded to HWInfo 8.28 I am sudenly aware of this new metric and both of our Pc's show 100's of 'Recovery Counts' , hoping this is normal. One of them had 7 Bad TLP and 7 Naks sent errors. I would love to know, for the sake of my restfull sleep, Is my gaming world about to come crashing down around our ear's and cost me another small fortune, or Is it even a problem and if it is, is there anything we can do about it. Your help and advice would be greatly appreciated.

 

[Martin]

Unfortunately NVIDIA doesn't provide further details about these counter.
"Recovery Count" should be normal as long as the numbers aren't increasing rapidly. I have seen this on all GPUs tested so far.
Problematic should be "Fatal Error Count" and perhaps "Lane Errors".

 

[JeffPuserid]

Unfortunately NVIDIA doesn't provide further details about these counter.
"Recovery Count" should be normal as long as the numbers aren't increasing rapidly. I have seen this on all GPUs tested so far.
Problematic should be "Fatal Error Count" and perhaps "Lane Errors".

Thank you for your quick reply, I shall sleep easier now.

 

[Martin]

The "Recovery Count" counts the number of changes from L0 to Recovery. It triggers for example during a change in speed, width, or other possible reasons that usually don't mean a PCIe error occured.
The other counters however might indicate a problem on PCIe interface.