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

[Peter Zijlstra]

On Sat, 2005-12-31 at 20:40 -0200, Marcelo Tosatti wrote:
> On Fri, Dec 30, 2005 at 11:43:34PM +0100, Peter Zijlstra wrote:
> > 
> > From: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
> 
> Peter,
> 
> I tried your "scan-shared.c" proggy which loops over 140M of a file
> using mmap (on a 128MB box). The number of loops was configured to "5".
> 
> The amount of major/minor pagefaults was exactly the same between
> vanilla and clockpro, isnt the clockpro algorithm supposed to be
> superior than LRU in such "sequential scan of MEMSIZE+1" cases?

yes it should, hmm, have to look at that then.

What should happen is that nr_cold_target should drop to the bare
minimum, which effectivly pins all hot pages and only rotates the few
cold pages.

> Oh well, to be sincere, I still haven't understood what makes CLOCK-Pro
> use inter reference distance instead of recency, given that its a simple
> CLOCK using reference bits (but with three clocks instead of one).
> 
> But thats probably just my ignorance, need to study more.

The reuse distance is in PG_test. Please see the clockpro-documentation
patch, which should explain this. If its still not clear after that let
me know, I'll be more verbose then.

-- 
Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>

-
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/