On 05/01/2021 19:43, Pavel Begunkov wrote:
> blk_bio_segment_split() is very heavy, but the current fast path covers
> only one-segment under PAGE_SIZE bios. Add another one by estimating an
> upper bound of sectors a bio can contain.
>
> One restricting factor here is queue_max_segment_size(), which it
> compare against full iter size to not dig into bvecs. By default it's
> 64KB, and so for requests under 64KB, but for those falling under the
> conditions it's much faster.
>
> Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
> ---
> block/blk-merge.c | 29 +++++++++++++++++++++++++----
> 1 file changed, 25 insertions(+), 4 deletions(-)
>
[...]
>
> - return __blk_bio_segment_split(q, bio, bs, nr_segs);
> + q_max_sectors = get_max_io_size(q, bio);
> + if (!queue_virt_boundary(q) && bio_segs < queue_max_segments(q) &&
> + bio->bi_iter.bi_size <= queue_max_segment_size(q)) {
I think I miss a seg_boundary_mask check here. Any insights how to skip it?
Or why it's 2^31-1 by default, but not say ((unsigned long)-1)?
--
Pavel Begunkov
