Hello, looks like we are seeing some MCE (machine check events) error here. Things to consider: Can you boot the OS? The error comes up with after which device is plugged? The system restarted again you said- is there some logs from the OS left?
The error comes up with after which device is plugged?
The error happens only when I am running applications in parallel and I use more than 6 cores (the server restarts after a few minutes of program execution).
Then I decided to do the test with the ePSA tool and every time the memory test is reached the server restarted (first it showed the error that appears in the images).
The system restarted again you said- is there some logs from the OS left?
Hi now it sounds like one of the memories has an issue, and we need to figure out which one that is- Run ePsa memory test with only one memory plugged and repeat.
DELL-Young E
Moderator
•
5.4K Posts
0
January 10th, 2023 20:00
Hello, looks like we are seeing some MCE (machine check events) error here.
Things to consider:
Can you boot the OS?
The error comes up with after which device is plugged?
The system restarted again you said- is there some logs from the OS left?
Could you also try this?
https://dell.to/3GExs9Q
saruiz
3 Posts
0
January 15th, 2023 20:00
Hello
Can you boot the OS?
Yes
The error comes up with after which device is plugged?
The error happens only when I am running applications in parallel and I use more than 6 cores (the server restarts after a few minutes of program execution).
Then I decided to do the test with the ePSA tool and every time the memory test is reached the server restarted (first it showed the error that appears in the images).
The system restarted again you said- is there some logs from the OS left?
the operating system does not show any errors
Could you also try this?
Attached are the SEL and Lifecycler Log reports
SEL : https://www.dropbox.com/s/kyc0ngmld2as78o/sel.csv?dl=0
Lifecycler : https://www.dropbox.com/s/vkur6l095xarfb6/DXSYLR2-log.xml.gz?dl=0
DELL-Young E
Moderator
•
5.4K Posts
0
January 15th, 2023 21:00
Hi now it sounds like one of the memories has an issue, and we need to figure out which one that is- Run ePsa memory test with only one memory plugged and repeat.