Re: Problems with merlot* AMD Opteron 6376 systems (Was Re: stable trees

[Ian Campbell <ian.campbell@citrix.com>]

On Fri, 2015-06-26 at 15:36 -0400, Boris Ostrovsky wrote:
> On 06/26/2015 10:52 AM, Jan Beulich wrote:
> >>>> On 26.06.15 at 16:34, <ian.campbell@citrix.com> wrote:
> >> I did this using rdmsr from mst-tools instead, running on a native
> >> kernel gave:
> >>
> >> # for i in $(seq 0 31) ;do rdmsr -p $i MSR_K8_TOP_MEM2; done
> >> 0
> >> [...]
> >> 0
> 
> Is MSR_K8_TOP_MEM2 defined somewhere in the shell?

There is no $ there, so it wouldn't make any difference...

I had foolishly assumed that rdmsr would either know the names of the
MSRs or it would complain about a string it didn't understand which
wasn't a number.

Instead it just reads some random register which happens to be
strtoul("MSR_K8_TOP_MEM2"), how helpful.

> Just to make sure, could you use explicit address, i.e.
> 
>      for i in $(seq 0 31) ;do rdmsr -p $i 0xc001001d; done
> 
> (and if they are still all zeroes, can you read 0xc0010010 (SYSCFG) as 
> well?)

I'll try this next week.

Ian.