Experienced twice, diagnostics are from the most recent occurrence. I recently upgraded the CPU on this server.

 

Nov  7 08:40:53 UnraidServer kernel: mce: [Hardware Error]: Machine check events logged
Nov  7 08:40:53 UnraidServer kernel: [Hardware Error]: Deferred error, no action required.
Nov  7 08:40:53 UnraidServer kernel: [Hardware Error]: CPU:1 (19:21:2) MC27_STATUS[Over|-|-|-|PCC|-|Deferred|Poison|-]: 0xc35b9aeb5bdf8948
Nov  7 08:40:53 UnraidServer kernel: [Hardware Error]: IPID: 0x0000000000000000
Nov  7 08:40:53 UnraidServer kernel: [Hardware Error]: Bank 27 is reserved.
Nov  7 08:40:53 UnraidServer kernel: [Hardware Error]: cache level: RESV, tx: GEN

Nov 29 16:07:02 UnraidServer  emhttpd: read SMART /dev/sdw
Nov 29 16:07:02 UnraidServer  emhttpd: read SMART /dev/sdp
Nov 29 16:09:47 UnraidServer kernel: mce: [Hardware Error]: Machine check events logged
Nov 29 16:09:47 UnraidServer kernel: [Hardware Error]: Corrected error, no action required.
Nov 29 16:09:47 UnraidServer kernel: [Hardware Error]: CPU:1 (19:21:2) MC27_STATUS[-|CE|-|-|-|-|-|-|-]: 0x80000001ae5b9163
Nov 29 16:09:47 UnraidServer kernel: [Hardware Error]: IPID: 0x0000000000000000
Nov 29 16:09:47 UnraidServer kernel: [Hardware Error]: Bank 27 is reserved.
Nov 29 16:09:47 UnraidServer kernel: [Hardware Error]: cache level: L3/GEN, tx: INSN
Nov 29 16:27:17 UnraidServer  emhttpd: spinning down /dev/sdw
Nov 29 16:27:17 UnraidServer  emhttpd: spinning down /dev/sdp

 

unraidserver-diagnostics-20221130-1145.zip

This is very similar to what I had before. See here.

What solved it for me was to change the cpu idle current setting in the bios.

33 minutes ago, jfoxwu said:

This is very similar to what I had before. See here.

What solved it for me was to change the cpu idle current setting in the bios.

 

Thanks, I changed that in my bios and I'll update the thread if no further MCE happen.

No luck, had another MCE today:

Dec 10 09:59:27 UnraidServer kernel: vfio-pci 0000:08:00.0: vfio_ecap_init: hiding ecap 0x26@0x410
Dec 10 09:59:27 UnraidServer kernel: vfio-pci 0000:08:00.0: vfio_ecap_init: hiding ecap 0x27@0x440
Dec 10 13:19:10 UnraidServer kernel: mce: [Hardware Error]: Machine check events logged
Dec 10 13:19:10 UnraidServer kernel: [Hardware Error]: Corrected error, no action required.
Dec 10 13:19:10 UnraidServer kernel: [Hardware Error]: CPU:1 (19:21:2) MC8_STATUS[-|CE|-|-|-|-|-|-|-]: 0x80000001b23bd063
Dec 10 13:19:10 UnraidServer kernel: [Hardware Error]: IPID: 0x0000000000000000
Dec 10 13:19:10 UnraidServer kernel: [Hardware Error]: Bank 8 is reserved.
Dec 10 13:19:10 UnraidServer kernel: [Hardware Error]: cache level: L3/GEN, tx: INSN
Dec 10 13:40:14 UnraidServer  emhttpd: spinning down /dev/sdm
Dec 10 17:55:39 UnraidServer  emhttpd: spinning down /dev/sdd

 

Can anyone help figure out what's happening?

One suggestion found via Google would be to run the memory at it's stock speed (2133) instead of underclocking it to 1866.  Look in the BIOS for various settings.

On 12/11/2022 at 4:07 AM, Squid said:

One suggestion found via Google would be to run the memory at it's stock speed (2133) instead of underclocking it to 1866.  Look in the BIOS for various settings.

 

Does it say in the diagnostics somewhere that my memory is being underclocked? When I check System Profiler it says all the memory is 2666 MT/s, which matches the purchased sticks.