On Wed, 28 Jul 1999 23:07:17 +0200 (MET DST), wtenhave@sybase.com (Wim
Ten Have) said:
> I like to make a small comment or perhaps suggestions to the
> raw IO changes which I hope make it into the Linux stable
> (production) kernels a.s.a.p.
> Your kernel API does only allow 512 byte memory aligned user space
> buffers ... this for technical reasons. Performing in kernel memory
> copies are left out by you because of performance I guess.
As far as I know that is also standard practice on other Unix raw
devices. Do existing applications using raw IO on other Unixen really
use unaligned buffers? I know that Oracle was able to run with the
Linux raw devices without problems.
> I.e. now you return an EINVAL (errno 22) whenever the user buffer
> address is *not* 512 bytes aligned. Such cripples for example a
> simple 'dd if=/dev/raw1 of=....'
dd on Linux is at fault, I believe: on Solaris at least, dd uses aligned
buffers. On Linux, you can use "lmdd" from lmbench which aligns buffers
correctly.
> Since you already perform a check to detect the misalignment to
> return EINVAL you may decide to invoke a kernel internal memcopy
> instead. This to a kernel private buffer and correcting the
> alignment.
But then the IO isn't strictly raw!
--Stephen
-
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/