It has been my understanding that Windows loads their "kernel" into
the top portion of memory. Using the top of memory for a file cache
only wouldn't explain the performance hit that c't saw by itself
(uncached memory is still faster then a PCI burst transfer).
> Probably it would be a good idea to use memory above 64MB on
> Triton FX/VX/TX boards (and some others) as _fast_ swap space.
> (Eg allocate the memory as ram disk and than use it as swap device)
> Where in memory are ramdisks located?
Either way would faster for certain applications. As a user machine,
fast-swap would be an excellent idea, but for a server, using that RAM
as a pure cache would be a better idea. The fast-swap would probably
be easier though.
> However, I think this is still broken (as is the idea to use more
> than 64MB in these machines).
Using more then 64MB is useful in these machines, depending on the
applications and the data you deal with. For example, editing large
image files (80 MB bitmaps come to mind) sees a huge benefit, even on
these machines.
=====================================================================
// Chris Giard (a.k.a. Slyglif Cain) | I find my life is a lot
// EMAIL: slyglif@magerealm.com | easier the lower I keep
// URL: http://www.primenet.com/~slyglif | everyone's expectations.
// ICQ: 4481627 | --Calvin 1992
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.altern.org/andrebalsa/doc/lkml-faq.html