> For 2.3 I should have a generic facility for having writeable pages
> in the page cache. This nearly eliminates the need for a buffer
> cache, though it isn't on my immediate hit list. I'm putting the
> finishing touches on a pgflush kernel daemon now.
>
> With a LVM and similiar you also need to much around with where
> filesystems get their blocks from, and the caching thereof.
>
> Depending on how a LVM is implemented it might be worthwhile to
> coordinate our efforts.
Indeed. I would be interested in any white papers or other documents
describing how your architecture works, what interface it will present
to filesystems, etc.
LFS's require the ability to change a buffer's "physical association"
i.e., when a buffer is dirtied it must (a) not be written back to its
original location and (b) eventually be assigned a new block location.
I would imagine the LVM layer would require a similar capability for
the physical volume removal case at least. How well would your
interface cope with this?
Adam
-- You crucify all honesty \\Adam D. Bradley artdodge@cs.bu.edu No signs you see do you believe \\Boston University Computer Science And all your words just twist and turn\\ Grad Student and Linux Hacker Reviving just to crash and burn \\ <>< ---------> Why can't you listen as love screams everywhere? <--------
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu