Messages in this thread | | | From | Daniel Phillips <> | Subject | Re: Note describing poor dcache utilization under high memory pressure | Date | Tue, 29 Jan 2002 11:27:36 +0100 |
| |
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/
| |