Re: [patch 2/3] only allow nonlinear vmas for ram backed filesystems

[William Lee Irwin III]

On Sat, 2007-03-24 at 23:09 +0100, Miklos Szeredi wrote:
>>> Dirty page accounting/limiting doesn't work for nonlinear mappings, so
>>> for non-ram backed filesystems emulate with linear mappings.  This
>>> retains ABI compatibility with previous kernels at minimal code cost.
>>> All known users of nonlinear mappings actually use tmpfs, so this
>>> shouldn't have any negative effect.

On Sun, Mar 25, 2007 at 02:12:32PM +0200, Peter Zijlstra wrote:

On Sun, Mar 25, 2007 at 10:51:27AM -0500, Matt Mackall wrote:
> They do? I thought the whole point of nonlinear mappings was for
> mapping files bigger than the address space (eg. databases). Is Oracle
> instead using this to map >3G files on a tmpfs??

It's used for > 3GB files on tmpfs and also ramfs, sometimes
substantially larger than 3GB.

It's not used for the database proper. It's used for the buffer pool,
which is the in-core destination and source of direct I/O, the on-disk
source and destination of the I/O being the database.


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