[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: Support for Multiple Page Sizes
From: |
Espen Skoglund |
Subject: |
Re: Support for Multiple Page Sizes |
Date: |
Thu, 9 Aug 2007 17:25:43 +0200 |
[Neal H Walfield]
> Why Multiple Page Sizes
> -----------------------
> In Jochen's paper in which he describes guarded page tables he
> discusses fitting objects into the minimum number of pages possible.
> But is the common usage pattern to really access all bits of an
> object? Today we don't swap tasks; we page them. The justification
> is that only bits and pieces are used and the cost of the additional
> faults, memory and TLBs is generally less than the cost of paging
> the object as a whole.
> An exception to this observation is a rendered image. In this case,
> the image is often either completely or wholly displayed on the
> screen (think web browser); the entirety of the object is used at
> once.
The main reason for wanting multiple page sizes is mostly to lower the
TLB footprint. [2] gives a good summary of what the performance
advantages are and talks about various strategies for demoting and
promoting pages/superpages.
eSk
> [1] Page Table Structures For Fine-Grain Virtual Memory by Jochen
> Liedtke (1994).
> http://citeseer.ist.psu.edu/liedtke94page.html
[2] Practical, Transparent Operating System Support for Superpages,
Juan Navarro, Sitaram Iyer, Peter Druschel, Alan Cox (2002)
http://citeseer.ist.psu.edu/579979.html