Messages in this thread | | | Date | Wed, 9 Apr 2014 21:14:54 +0200 | From | Borislav Petkov <> | Subject | Re: [PATCH 3/3] ie31200_edac: Add driver |
| |
On Wed, Apr 09, 2014 at 02:57:19PM -0400, Jason Baron wrote: > Right, so maybe the fact that its a desktop chipset means that it > behaves differently and doesn't raise MCEs on memory errors. We have a > bunch of these processors and we haven't yet seen an MCE raised on a > memory error.
This can't be - an uncorrectable error will have to generate a machine check exception if consumed - there's no other option.
Can you do
rdmsr 0x179 rdmsr 0x17b
and paste the results here?
> The reason I went with ie31200 is that afaiu the memory controller hub > is integrated into the cpu. Another alternative might be ie312xx?
Yeah, if Tony doesn't come up with something more official about that MCH.
-- Regards/Gruss, Boris.
Sent from a fat crate under my desk. Formatting is fine. --
| |