NVIDIA PCI Express Error Counters

[rabithole1234]

In the release notes, it says:

• Added monitoring of NVIDIA PCI Express Error Counters.

but I don't see this anywhere. Where is the option to monitor this?

 

[Martin]

This is available on Kepler and later models and looks like this:

 

[rabithole1234]

This is available on Kepler and later models and looks like this:

View attachment 12805

Weird, I'm not seeing the dropdown for "Total GPU Power (normalized)

 

[Martin]

Please attach the HWiNFO Debug File for analysis. It's quite possible that 50 series work different.

 

[asder00]

Please attach the HWiNFO Debug File for analysis. It's quite possible that 50 series work different.

Hello Martin, I have the same issue can't see the new error counters, 5090 FE

 

[Martin]

Looks like the 50 series require adjustment here. Will need to look into that...

 

[rabithole1234]

Not sure if you still need my debug file, but here it is:

 

[bomzhik]

Could you please explane me what does it mean "Recovery Count"? And why the value of it rises a little by little?

 

[Martin]

Support for 50 series will be added in the next (Beta) build.

 

[Martin]

Could you please explane me what does it mean "Recovery Count"? And why the value of it rises a little by little?

Post in thread 'pci express error counters, whats normal whats a problem?'

Monday at 10:16 AM

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".

• Martin

• 

 

[bomzhik]

Thank you for your quick reply, Martin, I shall sleep easier now as well as JeffPuserid.

 

[Martin]

Support for 50 series was added in v8.29-5775 Beta.

 

[sicklown]

Doing some testing with my 4090, it seems that Recovery Count is tied to power management as it increases every time power states increase or decrease, probably due to the PCI-E link needing to be reset as it changes link speeds. It also seems that Bad TLP Count and NAKs Sent are tied together as they always match, but I haven't been able to see any events that match. Hopefully more documentations will be forth coming.

 

[Martin]

Sorry, I posted this in the other thread, so copying here too:
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.