Re: [PATCH] PAGE_SIZE IO for RAW (RAW VARY)
Jens Axboe (axboe@suse.de)
Thu, 10 Jan 2002 08:12:52 +0100
On Wed, Jan 09 2002, Benjamin LaHaise wrote:
> On Wed, Jan 09, 2002 at 10:12:11AM -0800, Badari Pulavarty wrote:
> > why ? could you explain ? I am not expecting that user buffer be aligned
> > to PAGE_SIZE.
>
> Okay, that part I misread from the message, but that leaves the question of
> "does it work?" Iirc, Jeff Merkey tested variable sized ios with nwfs, but
> found that triggered bugs in the low level drivers, some of which assume that
> all buffer heads within a request have the same block size. Given that
> concern, I really don't think this is a safe 2.4 patch.
I don't think that point was ever proven, and Jeff never showed any
information as to what was broken. I'm reluctant to allow differently
sized buffers heads in the _same_ request for 2.4 just to be cautios,
but that's a two-liner (or so) in the elevator to stop that from
happening.
--
Jens Axboe
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/