Re: [PATCH] x86 idle: repair large-server 50-watt idle-powerregression

[Peter Zijlstra]

On Thu, Dec 19, 2013 at 11:22:01AM -0800, H. Peter Anvin wrote:
> On 12/19/2013 10:19 AM, Ingo Molnar wrote:
> > 
> > ( It would also be nice to know whether MONITOR loads that cacheline 
> >   into the CPUs cache, and in what state it loads it. )
> > 
> 
> I would assume that is implementation-dependent.  However, one plausible
> implementation is to load the cache line into the cache in shared state
> and monitor for evictions.

I suppose the monitor part is the important part because certain C
states drop all cache, presumably including the cacheline we're actually
monitoring.


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/