July 31, 20223 yr 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, 20223 yr by jfoxwu
August 1, 20223 yr Community Expert If the error has been consistent I would try to get a replacement.
November 15, 20223 yr Author Solution 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, 20223 yr by jfoxwu typo
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.