I am about to convert a Windows Server 2019 to Unraid. The this kernel panic appear during startup.

 

I tested 3 different USB sticks in 3 different USB ports 

 

When running memtest this comes up. It it a small error, big error? And likely to cause the panic? Note that the server is running Windows Server 2019 on daily basis. Any thought will be appreciated. 

 

 

 

32 minutes ago, frodr said:

When running memtest this comes up. It it a small error, big error? And likely to cause the panic? Note that the server is running Windows Server 2019 on daily basis. Any thought will be appreciated. 

Any error can be fatal.

You must suspect any file that touches a system with bad RAM, as it's practically impossible to know whether or not it has been silently corrupted.

The only acceptable number of errors in memtest is zero.

You shouldn't even attempt to use a computer with any RAM problems. Everything goes through RAM, the OS and other code, your data, everything.

13 hours ago, frodr said:

Windows Server 2019 on daily basis

And probably bluescreening or having weird crashes etc

5 hours ago, Squid said:

And probably bluescreening or having weird crashes etc

That's the best case scenario. If windows appears to run flawlessly with bad RAM, it's likely that there is file corruption happening silently in the background.

 

It's much better for the system to halt at the first sign of trouble than to run like nothing is wrong while mangling your data. I'm convinced 99% of the reports of silent bit rot on otherwise healthy hard drives is caused by bad system RAM.

Thanks for advice. The same error occur with all mem config tested, leading me suspect the mainboard. New mainboard is ordered. 

51 minutes ago, frodr said:

Thanks for advice. The same error occur with all mem config tested, leading me suspect the mainboard. New mainboard is ordered. 

The memory controller is most probably in the CPU, not directly on the MB.

Might be a MB problem, but it is not guaranteed.

I have another Xeon processor that I will try. That could make things a bit clearer.

Same error with another cpu. Then I removed all pice cards, no error. 

Then I tested pcie cards, one at the time. And the devil is a Mellanox 40Gbe card.