Your server has detected hardware errors

[Rubene]

I bought a new machine to run unRAID on. After booting I got this message: 'Your server has detected hardware errors'. The array seems to run fine (although it is still a small array without parity disk. Explored unRAID on old hardware. Since it's a good fit to replace my Synology I bought new hardware and going to purchase a license).

 

This is in the syslog:

Jan  9 21:21:03 Tower kernel: smpboot: CPU0: Intel(R) Core(TM) i3-8100 CPU @ 3.60GHz (family: 0x6, model: 0x9e, stepping: 0xb)
Jan  9 21:21:03 Tower kernel: mce: [Hardware Error]: Machine check events logged
Jan  9 21:21:03 Tower kernel: mce: [Hardware Error]: CPU 0: Machine Check: 0 Bank 8: ae00000000801136
Jan  9 21:21:03 Tower kernel: mce: [Hardware Error]: TSC 0 ADDR 8b445140 MISC 43040000086
Jan  9 21:21:03 Tower kernel: mce: [Hardware Error]: PROCESSOR 0:906eb TIME 1578601246 SOCKET 0 APIC 0 microcode ca
Jan  9 21:21:03 Tower kernel: mce: [Hardware Error]: Machine check events logged
Jan  9 21:21:03 Tower kernel: mce: [Hardware Error]: CPU 0: Machine Check: 0 Bank 9: ae00000000801136
Jan  9 21:21:03 Tower kernel: mce: [Hardware Error]: TSC 0 ADDR 8b445100 MISC 43040000086
Jan  9 21:21:03 Tower kernel: mce: [Hardware Error]: PROCESSOR 0:906eb TIME 1578601246 SOCKET 0 APIC 0 microcode ca

To be sure it's not the RAM, I ran memtest. After 4 hours it completed and did not find any issues.

 

+---------------------------------------------+-----------------+--------+
|                    Test                     | # Tests Passed  | Errors |
+---------------------------------------------+-----------------+--------+
| Test 0 [Address test, walking ones, 1 CPU]  | 4/4 (100%)      |      0 |
| Test 1 [Address test, own address, 1 CPU]   | 4/4 (100%)      |      0 |
| Test 2 [Address test, own address]          | 4/4 (100%)      |      0 |
| Test 3 [Moving inversions, ones & zeroes]   | 4/4 (100%)      |      0 |
| Test 4 [Moving inversions, 8-bit pattern]   | 4/4 (100%)      |      0 |
| Test 5 [Moving inversions, random pattern]  | 4/4 (100%)      |      0 |
| Test 6 [Block move, 64-byte blocks]         | 4/4 (100%)      |      0 |
| Test 7 [Moving inversions, 32-bit pattern]  | 4/4 (100%)      |      0 |
| Test 8 [Random number sequence]             | 4/4 (100%)      |      0 |
| Test 9 [Modulo 20, ones & zeros]            | 4/4 (100%)      |      0 |
| Test 10 [Bit fade test, 2 patterns, 1 CPU]  | 4/4 (100%)      |      0 |
| Test 13 [Hammer test]                       | 4/4 (100%)      |      0 |
+---------------------------------------------+-----------------+--------+

If I understood correctly, this might happen very early in the boot process during initialization. Doesn't seem something to worry about but I would like to be sure.

Thanks!

 

tower-diagnostics-20200109-2056.zip

[Rubene]

Yesterday it happened again:

 

Jan 10 21:08:29 Tower kernel: smpboot: CPU0: Intel(R) Core(TM) i3-8100 CPU @ 3.60GHz (family: 0x6, model: 0x9e, stepping: 0xb)
Jan 10 21:08:29 Tower kernel: mce: [Hardware Error]: Machine check events logged
Jan 10 21:08:29 Tower kernel: mce: [Hardware Error]: CPU 0: Machine Check: 0 Bank 8: ae00000000801136
Jan 10 21:08:29 Tower kernel: mce: [Hardware Error]: TSC 0 ADDR 8b445140 MISC 47040000086 
Jan 10 21:08:29 Tower kernel: mce: [Hardware Error]: PROCESSOR 0:906eb TIME 1578686893 SOCKET 0 APIC 0 microcode ca
Jan 10 21:08:29 Tower kernel: mce: [Hardware Error]: Machine check events logged
Jan 10 21:08:29 Tower kernel: mce: [Hardware Error]: CPU 0: Machine Check: 0 Bank 9: ae00000000801136
Jan 10 21:08:29 Tower kernel: mce: [Hardware Error]: TSC 0 ADDR 8b445100 MISC 43040000086 
Jan 10 21:08:29 Tower kernel: mce: [Hardware Error]: PROCESSOR 0:906eb TIME 1578686893 SOCKET 0 APIC 0 microcode ca

Any idea what this could be? Since it happened twice now.

[Rubene]

The hardware errors actually happens every time during boot, except one time. Did around 20 - 30 reboots I guess.

I checked the mcelog (/dev/mcelog) but its empty. I also did a second memtest: no errors. Apart from the notifications, the machine & array seems to be running fine.

 

But I also had some issues with my new flash drive during some boots. Looked like it couldn't read some files. But these got solved when I moved the flash drive to a USB 3.0 port instead of a 2.0 which it was in before. Could that make sense?

 

Could anyone please have a look at these hardware errors? The hardware is brand new, I want to avoid any problems with it.

 

 

[Squid]

The mce happens during initialization of the CPU.  Happens on certain hardware combinations due to flux in the vortex / the house is built using pyramids instead of A-Frames / Gremlins  (IE: no particular reason for it, and nothing to worry about at all)

[Rubene]

Thanks for your reply!

Glad to hear that it is nothing to worry about.

Is this something unraid specific?

[itimpi]

5 minutes ago, Rubene said:

Is this something unraid specific?

I think it will occur on any Linux based system using the same kernel level as is being used by the Unraid release.