(SOLVED) Ryzen 5900X MCE: Hardware Error - Should I be concerned?

[jfoxwoosh]

I have been consistently getting this hardware error.

Quote

Jul 31 09:10:44 kernel: mce: [Hardware Error]: Machine check events logged

Jul 31 09:10:44 kernel: [Hardware Error]: Corrected error, no action required.

Jul 31 09:10:44 kernel: [Hardware Error]: CPU:1 (19:21:0) MC15_STATUS[-|CE|-|-|PCC|-|UECC|-|-|-]: 0x820b64a7c7c748ee

Jul 31 09:10:44 kernel: [Hardware Error]: IPID: 0x0000000000000000

Jul 31 09:10:44 kernel: [Hardware Error]: Microprocessor 5 Unit Ext. Error Code: 7, Instruction Cache Bank B ECC or parity error.

Jul 31 09:10:44 kernel: [Hardware Error]: cache level: L2, tx: RESV

 

Some googling of this, seems to point to early Ryzen CPU defect. However, I haven't found any other report like this online for 3rd gen Ryzen (5900X). Should this error be of concern and perhaps required a warranty service with AMD?

 

My system diagnostics is attached.

diagnostics-20220731-1416.zip

Edited November 15, 2022 by jfoxwu

[JorgeB]

If the error has been consistent I would try to get a replacement.

[jfoxwoosh]

I have identified the cause of the MCE error message. I need to set "typical idle current" in bios for the CPU as described in this post by JorgeB. Thanks!

I remember having this set correctly when the server was built initially, however, after some MB bios updates later, I forgot to change it back when all bios settings got reset.

 

It has been 30+ days now, and the server hasn't given any error message like before.

Edited November 16, 2022 by jfoxwu
typo