On Tue, Apr 10, 2007 at 03:33:04PM -0700, Bill Stouder-Studenmund wrote:
> [...]
> 
> The bigger problem with trying to fix this with queuing is that we still
> haven't fixed the issue. Queuing says, "Complete this before startintg
> that." As long as "completing" an operation doesn't necessarily imply
> writing it to disk (which i the whole point of the cache), we have a
> problem. What we need is a form of FUA (Force Unit Access) support; we
> need to know that a given operation has been committed to disk (or to a
> BBU).

My point was that AFAIK, there's no FUA for ATA command set other than
dissabling or flushing the whole cache. I don't remember the details but I
think that the NCQ command set (NCQ interface, really) offers something
better in this area. If you don't want queuing just use the same tag
for all commands :)

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