On Mon, 2004-01-26 at 20:27, Alan Cox wrote:
On Mon, Jan 26, 2004 at 07:21:58PM +0100, Ronny Buchmann wrote:
> > The file system may still do smart stuff like merging requests. Also only
> It's usually used for reading from block devices (disks).
Issue a few reads and the kernel will begin readahead, it will also merge
the read and readahead into one I/O at times.
> > with floppies because the 'real' blocksize of a hard disk is now
> > 8-32K
> Does the kernel do read-ahead in the block layer or in vfs?
Some of the file systems (especially xfs) do quite smart readahead tricks,
others use the basic facilities of the block layer and others still like
jffs and nfs don't use the block layer but their own ways of handling
Is DMA going to be enabled in FC2?