On Mon, 2022-08-08 at 09:16 -0700, Dave Hansen wrote:
> On 8/8/22 04:03, Ingo Molnar wrote:
> > > Again, I don't believe this is too much overhead but I don't want
> > > people 
> > > to say it was not discussed.
> > Is it necessary to do this, what are the alternatives, can this
> > overhead be 
> > avoided?
> 
> I'm thinking that the whole racy smp_processor_id() thing wasn't so
> bad
> in the first place.
> 

FWIW, just grabbing the CPU number in show_signal_msg()
appears to be good enough for our use. 

It will typically show >90% of the errors happening on the
CPU core that went bad, which is more than enough to diagnose 
that a server has a hardware issue and should probably have
the CPU repaired.

-- 
All Rights Reversed.