Re: Note describing poor dcache utilization under high memory pressure

From: Daniel Phillips (phillips@bonn-fries.net)
Date: Tue Jan 29 2002 - 05:27:36 EST


On January 29, 2002 10:20 am, Momchil Velikov wrote:
> >>>>> "Daniel" == Daniel Phillips <phillips@bonn-fries.net> writes:
>
> Daniel> On January 29, 2002 09:39 am, Momchil Velikov wrote:
> >> >>>>> "Oliver" == Oliver Xymoron <oxymoron@waste.org> writes:
> Oliver> you can't actually _share_ the page tables without marking the pages
> Oliver> themselves readonly.
> >>
> >> Of course, ptes are made COW, just like now. Which brings up the
> >> question how much speedup we'll gain with a code that touches every
> >> single pte anyway ?
>
> Daniel> It's only touching the ptes on tables that are actually used, so if a parent
> Daniel> with a massive amount of mapped memory forks a child that only instantiates
> Daniel> a small portion of it (common situation) then the saving is pretty big.
>
> Umm, all the ptes af the parent ought to be made COW, no ?

My explanation above is borked, please see my reply to wli. In short, each
page table of the parent is already either shared - in which case the CoW
ptes are already marked RO - or it was instantiated by the parent, in which
case the work of marking its pte's RO is insignificant, and is certainly not
more than the cost incurred by the current method.

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



This archive was generated by hypermail 2b29 : Thu Jan 31 2002 - 21:00:58 EST