On Thu, Jul 04 2002, Andre Hedrick wrote:
> 1) 8K writes and 64K (or larger) reads.
I've heard this before, but noone seems to have tested it yet. You know,
this is a couple of lines of change in ll_rw_blk.c and blkdev.h to
support this. Any reason you haven't done that, benched, and submitted
something to that effect? I'll even walk you through the 2.5 changes
needed to do this:
blkdev.h:
unsigned short max_sectors;
change to
unsigned short max_sectors[2];
ll_rw_blk.c:
ll_back_merge_fn()
if (req->nr_sectors + bio_sectors(bio) > q->max_sectors) {
change to
if (req->nr_sectors + bio_sectors(bio) > q->max_sectors[rq_data_dir[req]) {
Ditto for ll_front_merge_fn() and ll_merge_requests_fn(). The line in
attempt_merge() can be killed.
generic_make_request()
BUG_ON(bio_sectors(bio) > q->max_sectors);
change to
BUG_ON(bio_sectors(bio) > q->max_sectors[bio_data_dir(bio)];
And do the trivial thing to blk_queue_max_sectors() as well. Now all you
need to do is change ide-probe.c to set the values you want.
> 2) ONE maybe TWO passes on elevator operations.
Explain.
> Since this is falling on deaf ears in general, oh well.
How so?
-- 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/
This archive was generated by hypermail 2b29 : Sun Jul 07 2002 - 22:00:14 EST