On Sun, Apr 08, 2007 at 12:10:28AM +0100, Andrew Doran wrote:
> >> If we get a journalling implementation that's something it can take care
> >> of, whether it's PATA (flush the cache) or SCSI, where it can force
> >> access
> >> to the disc.
> >
> > Flushing the entire cache is unnecessary and will kill performance.
> 
> Unless things have changed recently, PATA gives you no other option.

and some SATA, I think only SATA NCQ has a reasonable alternative.

-- 
Manuel Bouyer <bouyer@antioche.eu.org>
     NetBSD: 26 ans d'experience feront toujours la difference
--