> There is also the fact that raw io for databases IS faster. Whatever type
> filesystem you design, doesn't matter since we know which blocks to write
[...]
> did a cool job;)... but I would like to hear solutions to the above, if
> raw dev ain't the way to go technology-wise... if you cannot give a
> solution, then what keeps you from implementing raw dev as a short term
> solution (2.3) ?
Well from Linus' comments it sounds like raw devices won't be appearing in
2.3, or indeed, ever.
However, it would seem
1) Raw devices can be implemented in a technically clean manner
2) There is "big customer" demand for this feature, i.e. serious database
applications
3) RedHat are paying for code development of this feature
Based on 1) 2) and 3), I predict that raw devices will be standard on any
"serious" linux distribution by the way of a vendor added kernel patch. It
doesn't really matter if the patches aren't in the "official" kernel tree.
Chris
-
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/