On Wed, 6 Mar 2002, Peter Pentchev wrote:
> On Wed, Mar 06, 2002 at 12:12:44PM -0500, Zhihui Zhang wrote:
> >
> >
> > On Wed, 6 Mar 2002, Peter Edwards wrote:
> >
> > > Zhihui Zhang wrote:
> > >
> > > <snip>
> > >
> > > > ... I also do not read anything during the partial block write,
> > > > and I think the disk controller should not do that either.
> > >
> > > If you do a partial block write, surely at some point the block must be read
> > > in order to preserve that segment of data you are _not_ overwriting?
> >
> > First off, I am not writing through any file system. I access the raw
> > device directly. Secondly, the bytes written are always a multiple of 512
> > bytes. If one sector is the I/O unit of a disk controller, why should it
> > read anything to prevent overwritten?
>
> I think Peter was referring to the (more common IMHO) case when one sector
> was not quite the I/O unit of the disk controller, especially WRT caching.
> That is, the disk controller does not actually do a physical disk write
> for each and every sector, but only in larger blocks.
This makes sense. So you are saying that the read-modify-write cycle
actually happens within the disk controller? If so, I would love to know
the unit of the disk controller I/O to avoid it!
-Zhihui
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message
