ATA flush cache on sync()
R. B. Riddick
arne_woerner at yahoo.com
Sat Sep 2 09:43:19 UTC 2006
--- hardware at ee.ccny.cuny.edu wrote:
> When the sync() system call is called on an ATA drive with a UFS 2
> filesystem, is the "FLUSH CACHE" ATA command sent to the drive?
>
As far as I know, when sync() return u cannot even be sure, that the in-kernel
buffers are flushed already...
And the "FLUSH CACHE" ATA command (or BIO_FLUSH since gjournal) is disputed,
since it might break (in FBSD not implemented) concepts like TCQ(?) (tagged
command queuing) or so...
But I think there should be a FLUSH CACHE command from time to time, so that
there cannot be an arbitrary gap...
-Arne
__________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
http://mail.yahoo.com
More information about the freebsd-fs
mailing list