Re: [PATCH -v3] x86, MCE: Drop the default decoding notifier

[Borislav Petkov <bp@amd64.org>]

On Thu, Apr 14, 2011 at 11:33:18AM -0400, Russ Anderson wrote:
> On Thu, Apr 14, 2011 at 05:16:21PM +0200, Borislav Petkov wrote:
> > On Thu, Apr 14, 2011 at 11:04:43AM -0400, Prarit Bhargava wrote:
> > > On 04/14/2011 11:00 AM, Borislav Petkov wrote:
> > > > On Wed, Apr 13, 2011 at 01:37:05PM -0400, Borislav Petkov wrote:
> > > >   
> > > >> In the worst case, we will report 32 CEs before panicking. For that case
> > > >> we either do printk_once as Tony suggested or we ratelimit it. I'll
> > > >> update the patch.
> > > >>     
> > > > Ok, how about the following, I ratelimit the printk to the default of 10
> > > > messages per 5 seconds. I've also got the hardware MCE injection patches
> > > > ready and will do some testing with them.
> > > >   
> > > 
> > > See my previous email ;)  I think just putting in a printk_once after
> > > the CE call to print_mce() in mce_panic() might be better?  At least
> > > that way we get the --ascii message for *EVERY* UC which IMO would be
> > > nice...
> > 
> > Are you sure? printk_once() is, as its name says, a one-time thing and
> > it is implemented that way - a static bool counter which is once set and
> > that's it. I.e., the "--ascii" message will be printed only once for the
> > system's lifetime.
> > 
> > The ratelimit-ed thing dumps it a strict number of times. In the end,
> > I don't have a strong opinion on how many times we issue it - I'm fine
> > with it either way.
> > 
> > Maybe some other opinions. Tony?
> 
> In general I think you and Prarit are headed in the right direction.
> 
> As for when to throttle messages, differing people will have
> different opinions as to the right number.  For example, some
> sites may want the threshold low because once they see a CE they
> will schedule to replace the DIMM.  Manufacturing sometimes 
> wants to see all the CEs to know how good/bad the DIMM is.
> 
> My suggestion is to pick a default value and have a /sys (or
> other) way of changing the value.  That way if someone has 
> a need to change the value they can.  In real life someone 
> will have a legitimate need to change the value.
> 
> Is the thresholding on a per DIMM, per Socket, or per system
> basis?  SGI tends to have large systems with lots of DIMMs.
> Per DIMM or per Socket thresholds tend to scale better.

Nah, we're talking about the decoding hint only

	"Run the above through 'mcelog --ascii'"

and that issuing it makes no sense when no correctable errors info is on
dmesg.

The CEs don't get reported in this case, I think on Intel you have to
run mcelog. On AMD, you generally use the amd64_edac driver and collect
all CEs info which gets decoded to chip selects on the node and then you
can do thresholding.

What you're talking above is not yet fully ... hm.. implemented yet :).

-- 
Regards/Gruss,
Boris.

Advanced Micro Devices GmbH
Einsteinring 24, 85609 Dornach
General Managers: Alberto Bozzo, Andrew Bowd
Registration: Dornach, Gemeinde Aschheim, Landkreis Muenchen
Registergericht Muenchen, HRB Nr. 43632