On Mon, 01 Nov 1999 15:24:16 -0700, "Jeff V. Merkey"
<jmerkey@timpanogas.com> said:
> There is also a very clean layer between disks and cache, unlike
> Linux, which is quite frankly a big, nasty ***MESS*** between the disk
> drivers and the buffer cache.
Sure it is. This is why, if you want a clean abstraction, you shouldn't
use the buffer cache --- the buffer cache is not _meant_ to map cleanly
to data, it is meant to map cleanly to specific disk blocks. The page
cache is Linux's logical cache, and the buffer cache is its physical
one. Don't blame the buffer cache for not doing what is better done in
the page cache.
> There's no obvious method of supporting async callbacks (which will
> increase file system performance by several hundred percent).
Sure there is --- as I wrote before, read buffer.c:brw_page(), which
performs IO with async callbacks, bypassing the buffer cache entirely.
--Stephen
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/