Re: [RFC 2/2] block: add a fast path for seg split of large bio

[Pavel Begunkov <asml.silence@gmail.com>]

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@gmail.com>
> ---
>  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