On 00:52 Fri 31 Aug , Christoph Lameter wrote:
> On Fri, 31 Aug 2007, Jens Axboe wrote:
>
> > They have nothing to do with each other, you are mixing things up. It
> > has nothing to do with the device being able to dma into that memory or
> > not, we have fine existing infrastructure to handle that. But different
> > hardware have different characteristics on what a single segment is. You
> > can say "a single segment cannot cross a 32kb boundary". So from the
> > example above, your single 64k page may need to be split into two
> > segments. Or it could have a maximum segment size of 32k, in which case
> > it would have to be split as well.
> >
> > Do you see what I mean now?
>
> Ok. So another solution maybe to limit the blocksizes that can be used
> with a device?
IMHO It is not good because after fs was created with big blksize it's image
cant be used on other devices.
We may just rewrite submit_bh simular to drivers/md/dm-io.c:do_region
with following pseudocode:
remaning = super_page_size();
while (remaining) {
init_bio(bio);
/*Try and add as many pages as possible*/
while (remaining) {
dp->get_page(dp, &page, &len, &offset);
len = min(len,
to_bytes(remaining));
if(!bio_add_page(bio, page, len, offset))
break;
offset = 0;
remaining -= to_sector(len);
dp->next_page(dp);
}
atomic_inc(&io->count);
submit_bio(rw, bio);
}
> > > How do we split that up today? We could add processing to submit_bio
> > > to check for the boundary and create two bios.
> >
> > But we do not split them up today - see what I wrote! Today we impose
> > the restriction that a device must be able to handle a single "normal"
> > page, and if it can't do that, it has to split it up itself.
> >
> > But yes, you would have to create some out-of-line function to use
> > bio_split() until you have chopped things down enough. It's not a good
> > thing for performance naturally, but if we consider this a "just make it
> > work" fallback, I don't think it's too bad. You want to make a note of
> > that it is happening though, so people realize that it is happening.
>
> Hmmmm.. We could keep the existing scheme too and check that device
> drivers split things up if they are too large? Isnt it possible today
> to create a huge bio of 2M for huge pages and send it to a device?
-
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
