block: avoid blk_bio_segment_split for small I/O operations

__blk_queue_split() adds significant overhead for small I/O operations.
Add a shortcut to avoid it for cases where we know we never need to
split.

Based on a patch from Ming Lei.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Christoph Hellwig 2019-11-04 10:05:43 -08:00 committed by Jens Axboe
parent d2c9be89f8
commit fa53228721
1 changed files with 15 additions and 1 deletions

View File

@ -293,7 +293,7 @@ split:
void __blk_queue_split(struct request_queue *q, struct bio **bio,
unsigned int *nr_segs)
{
struct bio *split;
struct bio *split = NULL;
switch (bio_op(*bio)) {
case REQ_OP_DISCARD:
@ -309,6 +309,20 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio,
nr_segs);
break;
default:
/*
* All drivers must accept single-segments bios that are <=
* PAGE_SIZE. This is a quick and dirty check that relies on
* the fact that bi_io_vec[0] is always valid if a bio has data.
* The check might lead to occasional false negatives when bios
* are cloned, but compared to the performance impact of cloned
* bios themselves the loop below doesn't matter anyway.
*/
if (!q->limits.chunk_sectors &&
(*bio)->bi_vcnt == 1 &&
(*bio)->bi_io_vec[0].bv_len <= PAGE_SIZE) {
*nr_segs = 1;
break;
}
split = blk_bio_segment_split(q, *bio, &q->bio_split, nr_segs);
break;
}