Re: [PATCH 6/9] clockpro-clockpro.patch

[Peter Zijlstra <a.p.zijlstra@chello.nl>]

On Sat, 2005-12-31 at 00:24 -0500, Rik van Riel wrote:
> > > > Why do you use only two clock hands and not three (HandHot, HandCold and 
> > > > HandTest) as in the original paper?
> > > 
> > > Because the non-resident pages cannot be in the clock.
> > > This is both because of space overhead, and because the
> > > non-resident list cannot be per zone.
> > 
> > I see - that is a fundamental change from the original CLOCK-Pro
> > algorithm, right? 
> > 
> > Do you have a clear idea about the consequences of not having           
> > non-resident pages in the clock? 
> 
> The consequence is that we could falsely consider a non-resident
> page to be active, or not to be active.  However, this can only
> happen if we let the scan rate in each of the memory zones get
> way too much out of whack (which is bad regardless).

Yes, the uncertainty of position causes a time uncertainty wrt.
terminating the test period (heisenberg anyone?). So individual pages
can be terminated either too soon or too late, however statistics make
it come out even in the end.

-- 
Peter Zijlstra <a.p.zijlstra@chello.nl>

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>