On Thu, May 28 2009, Artem Bityutskiy wrote:Jens Axboe wrote:That would be great, I would have no problem integrating such a feature.Hi Al, Christoph,
It definitely makes sense.
unless you have objections against the whole idea, I wonder if
it would be possible to make the patches which wrap sb->s_dirt
usage go via VFS tree first, and then I'd continue the timer
optimization work separately. IMO, wrapping s_dirt makes sense
in general. I mean, patches 01-17 from this series.
That makese sense, those are totally separate from the actual
functionality.