strange mcelog mesage / still in rc7.git10

Don Zickus dzickus at redhat.com
Fri Jul 22 13:14:07 UTC 2011


On Thu, Jul 21, 2011 at 11:36:17PM -0400, Genes MailLists wrote:
> 
> 
> 
>  Still have same error in latest kernel build:
> 
> rc7.git10
> 
> 
> Jul 21 23:30:28 lap3 mcelog[937]: HARDWARE ERROR. This is *NOT* a
> software problem!
> Jul 21 23:30:28 lap3 mcelog[937]: Please contact your hardware vendor
> Jul 21 23:30:28 lap3 mcelog[937]: MCE 15
> Jul 21 23:30:28 lap3 mcelog[937]: CPU 7 THERMAL EVENT TSC 7f14a833e3
> Jul 21 23:30:28 lap3 mcelog[937]: TIME 1311305428 Thu Jul 21 23:30:28 2011
> Jul 21 23:30:28 lap3 mcelog[937]: Processor 7 below trip temperature.
> Throttling disabled
> Jul 21 23:30:28 lap3 mcelog[937]: STATUS c000000088230800 MCGSTATUS 0
> Jul 21 23:30:28 lap3 mcelog[937]: MCGCAP c09 APICID 7 SOCKETID 0
> Jul 21 23:30:28 lap3 mcelog[937]: CPUID Vendor Intel Family 6 Model 42
> Jul 21 23:31:36 lap3 pulseaudio[2281]: ratelimit.c: 16 events suppressed

If you are running a Sandy Bridge laptop, there is probably a BIOS update
that might fix this.  I don't think Sandy Bridge processors have been
released to the general public yet.

We were chasing broken MCEs in Nehalem that reported bad memory all the
time.  Various kernel hacks worked around it until a BIOS fix came along.

I wouldn't be surprised if this is just another broken MCE, especially if
the laptop doesn't feel hot.

Cheers,
Don


More information about the kernel mailing list