Re: [PATCH] cache large files in the page cache

[Linus Torvalds <torvalds@transmeta.com>]

On 30 May 1999, Eric W. Biederman wrote:
> 
> LT> Indeed. An dI would suggest that the shift be limited to at most 9 anyway:
> LT> right now I applied the part that disallows non-page-aligned offsets, but
> LT> I think that we may in the future allow anonymous mappings again at finer
> LT> granularity (somebody made a really good argument about wine for this).
> 
> I'd love to hear the argument.   Something that would negate the disadvantage
> of ntuple buffering, and the need for reverse page maps, and isn't portable.

Wine.

Mapping windows binaries in a Linux address space.

Portability is a non-issue: this would only work on a 386, and only on
Linux anyway (MAYBE on other architectures Wine supports, but that's their
problem). 

Windows binaries are _not_ nicely aligned like the Linux ones. They are
often 512-byte aligned.

Yes, we can read them in. That is slow as hell, and doesn't allow sharing. 
Bad. 

> Well, currectly supporting non-aligned mappings needs more than just a
> few extra bits.  The code to update all mappings on write, and the
> ability to ensure that a given byte is only faulted in for a single
> offset at a time.   (Admittedly if everything is a read mapping you
> can be a smidge more lax).

We would not guarantee write coherency for anything but the page-aligned
case. 

		Linus

--
To unsubscribe, send a message with 'unsubscribe linux-mm my@address'
in the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://humbolt.geo.uu.nl/Linux-MM/