Machine check events

[MvL]

Hi,

 

I have found machine check events on my server. Fix common problems has warned me for three times now so I guess it's time to find out what the problem is. Can someone help to solve the issue? I have my thoughts what the issue is. I have attached my diagnostic file to this post. 

 

 

rackserver-diagnostics-20190518-0936.zip

[MvL]

I see this in the syslog:

 

Quote

May 17 22:35:46 RackServer kernel: mce: [Hardware Error]: Machine check events logged
May 17 22:35:46 RackServer kernel: EDAC sbridge MC0: HANDLING MCE MEMORY ERROR
May 17 22:35:46 RackServer kernel: EDAC sbridge MC0: CPU 0: Machine Check Event: 0 Bank 13: 8c000049000800c0
May 17 22:35:46 RackServer kernel: EDAC sbridge MC0: TSC ab5c2e16c9629 
May 17 22:35:46 RackServer kernel: EDAC sbridge MC0: ADDR a58102000 
May 17 22:35:46 RackServer kernel: EDAC sbridge MC0: MISC 90000008000928c 
May 17 22:35:46 RackServer kernel: EDAC sbridge MC0: PROCESSOR 0:306f2 TIME 1558125346 SOCKET 0 APIC 0
May 17 22:35:46 RackServer kernel: EDAC MC0: 1 CE memory scrubbing error on CPU_SrcID#0_Ha#0_Chan#1_DIMM#0 (channel:1 slot:0 page:0xa58102 offset:0x0 grain:32 syndrome:0x0 -  area:DRAM err_code:0008:00c0 socket:0 ha:0 channel_mask:2 rank:0)

 

Are this memory error's? I've checked my bios but I can't find anything related to this..

[JorgeB]

Are this memory error's?

Yes, at least that's what it looks like.

 

 

[MvL]

Thank you for the reply.

 

The weirdest part is I don't see errors in my bios log files. Any idea how to diagnostic this further?

[MvL]

Investigating!

 

I have found the memtest86 what you see in the options during booting of unRAID. It's running at the moment. I'll keep you informed.

[JorgeB]

memtest86 won't detect ECC errors, passmark memtest might in some cases.

[MvL]

So this is ecc error? Googling Passmark memtest. 

[JorgeB]

13 minutes ago, MvL said:

So this is ecc error?

Looks like a corrected error, board's system event log might also have some more info.

[MvL]

Appreciate your guidance.

 

I've checked the event log via IPMI and there are no events. The latest event was on 2019-5-2.

 

I have put Passmark memtest on usb stick and it is now running.

[JorgeB]

If no errors on memtest best bet is to remove one or more dimms at a time and see if the log errors go away.

[MvL]

Okay. 

 

The log of unRAID is reporting Chan#1_DIMM#0. I'm guessing this is DIMM A2? So the first DIMM position (A) on the motherboard then the second slot of DIMM A thus DIMM A2? I'm guessing there is also a channel 0. So channel 0 --> slot 1, channel 1 --> slot 2.

[MvL]

The Passmark memtest detected ECC error's. I'm trying to figure out which module is defect..