On Sat, Jul 13, 2002 at 05:57:59PM +0100, David Laight wrote:

 > No - that does something (horribly) different - since it tends destroy
 > any possible optimistations.
 > I was thinking of something that would ensure (say) that an inode
 > update (to delete a file) before the allocation map bits are
 > changed.
 > Maybe the second write could just be scheduled when the first finishes
 > from the biodone() code.

That is, more or less, how the kernel works *now*.

-- 
        -- Jason R. Thorpe <thorpej@wasabisystems.com>