Non Recoverable, SEL:CPU 1 machine check detected.

G.Bakalarski at icm.edu.pl G.Bakalarski at icm.edu.pl
Mon Mar 12 10:41:13 CDT 2012


Dear All

the following error randomly appears on LCDs of our servers
during reboot:

Non Recoverable, SEL:CPU 1 machine check detected.

We noted at least 10 such events.
The server works then more or less correctly, but I dont feel
comfortable with this (orange blinking LCD). This does not happen every reboot,
nor periodically . Just after next reboot it appeared.

There are some variants of this message - mainly CPU numer changes.
Within error log it says that a sensor caused non  recovarable
assertion .....

When I clear event log during boot (CTRL-E), then make hardware test
- no errors are detected ... And all look fine - until next Nth reboot
(N from 1 to 10)

It happened on at least 5 new R815 server (BIOS 1.5.2)  ...
We are running Debian Linux on our servers ..

Any hints ???


GB




More information about the Linux-PowerEdge mailing list