All of lore.kernel.org
 help / color / mirror / Atom feed
From: Changheun Lee <nanich.lee@samsung.com>
To: Johannes.Thumshirn@wdc.com, asml.silence@gmail.com,
	axboe@kernel.dk, damien.lemoal@wdc.com,
	linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
	ming.lei@redhat.com, osandov@fb.com, patchwork-bot@kernel.org,
	tj@kernel.org, tom.leiming@gmail.com
Cc: jisoo2146.oh@samsung.com, junho89.kim@samsung.com,
	mj0123.lee@samsung.com, seunghwan.hyun@samsung.com,
	sookwan7.kim@samsung.com, woosung2.lee@samsung.com,
	yt0928.kim@samsung.com, Changheun Lee <nanich.lee@samsung.com>
Subject: [PATCH v3 1/2] bio: limit bio max size
Date: Tue, 26 Jan 2021 10:32:34 +0900	[thread overview]
Message-ID: <20210126013235.28711-1-nanich.lee@samsung.com> (raw)
In-Reply-To: CGME20210126014805epcas1p2c4fc40f01c9c89b0a94ff6cac5408347@epcas1p2.samsung.com

bio size can grow up to 4GB when muli-page bvec is enabled.
but sometimes it would lead to inefficient behaviors.
in case of large chunk direct I/O, - 32MB chunk read in user space -
all pages for 32MB would be merged to a bio structure if the pages
physical addresses are contiguous. it makes some delay to submit
until merge complete. bio max size should be limited to a proper size.

When 32MB chunk read with direct I/O option is coming from userspace,
kernel behavior is below now. it's timeline.

 | bio merge for 32MB. total 8,192 pages are merged.
 | total elapsed time is over 2ms.
 |------------------ ... ----------------------->|
                                                 | 8,192 pages merged a bio.
                                                 | at this time, first bio submit is done.
                                                 | 1 bio is split to 32 read request and issue.
                                                 |--------------->
                                                  |--------------->
                                                   |--------------->
                                                              ......
                                                                   |--------------->
                                                                    |--------------->|
                          total 19ms elapsed to complete 32MB read done from device. |

If bio max size is limited with 1MB, behavior is changed below.

 | bio merge for 1MB. 256 pages are merged for each bio.
 | total 32 bio will be made.
 | total elapsed time is over 2ms. it's same.
 | but, first bio submit timing is fast. about 100us.
 |--->|--->|--->|---> ... -->|--->|--->|--->|--->|
      | 256 pages merged a bio.
      | at this time, first bio submit is done.
      | and 1 read request is issued for 1 bio.
      |--------------->
           |--------------->
                |--------------->
                                      ......
                                                 |--------------->
                                                  |--------------->|
        total 17ms elapsed to complete 32MB read done from device. |

As a result, read request issue timing is faster if bio max size is limited.
Current kernel behavior with multipage bvec, super large bio can be created.
And it lead to delay first I/O request issue.

Signed-off-by: Changheun Lee <nanich.lee@samsung.com>
---
 block/bio.c            | 17 ++++++++++++++++-
 include/linux/bio.h    |  4 +++-
 include/linux/blkdev.h |  3 +++
 3 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 1f2cc1fbe283..ec0281889045 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -287,6 +287,21 @@ void bio_init(struct bio *bio, struct bio_vec *table,
 }
 EXPORT_SYMBOL(bio_init);
 
+unsigned int bio_max_size(struct bio *bio)
+{
+	struct request_queue *q;
+
+	if (!bio->bi_disk)
+		return UINT_MAX;
+
+	q = bio->bi_disk->queue;
+	if (!blk_queue_limit_bio_size(q))
+		return UINT_MAX;
+
+	return blk_queue_get_max_sectors(q, bio_op(bio)) << SECTOR_SHIFT;
+}
+EXPORT_SYMBOL(bio_max_size);
+
 /**
  * bio_reset - reinitialize a bio
  * @bio:	bio to reset
@@ -877,7 +892,7 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page,
 		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 
 		if (page_is_mergeable(bv, page, len, off, same_page)) {
-			if (bio->bi_iter.bi_size > UINT_MAX - len) {
+			if (bio->bi_iter.bi_size > bio_max_size(bio) - len) {
 				*same_page = false;
 				return false;
 			}
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 1edda614f7ce..cdb134ca7bf5 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -100,6 +100,8 @@ static inline void *bio_data(struct bio *bio)
 	return NULL;
 }
 
+extern unsigned int bio_max_size(struct bio *);
+
 /**
  * bio_full - check if the bio is full
  * @bio:	bio to check
@@ -113,7 +115,7 @@ static inline bool bio_full(struct bio *bio, unsigned len)
 	if (bio->bi_vcnt >= bio->bi_max_vecs)
 		return true;
 
-	if (bio->bi_iter.bi_size > UINT_MAX - len)
+	if (bio->bi_iter.bi_size > bio_max_size(bio) - len)
 		return true;
 
 	return false;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index f94ee3089e01..3aeab9e7e97b 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -621,6 +621,7 @@ struct request_queue {
 #define QUEUE_FLAG_RQ_ALLOC_TIME 27	/* record rq->alloc_time_ns */
 #define QUEUE_FLAG_HCTX_ACTIVE	28	/* at least one blk-mq hctx is active */
 #define QUEUE_FLAG_NOWAIT       29	/* device supports NOWAIT */
+#define QUEUE_FLAG_LIMIT_BIO_SIZE 30	/* limit bio size */
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_SAME_COMP) |		\
@@ -667,6 +668,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_fua(q)	test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags)
 #define blk_queue_registered(q)	test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags)
 #define blk_queue_nowait(q)	test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags)
+#define blk_queue_limit_bio_size(q)	\
+	test_bit(QUEUE_FLAG_LIMIT_BIO_SIZE, &(q)->queue_flags)
 
 extern void blk_set_pm_only(struct request_queue *q);
 extern void blk_clear_pm_only(struct request_queue *q);
-- 
2.28.0


       reply	other threads:[~2021-01-26 19:49 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CGME20210126014805epcas1p2c4fc40f01c9c89b0a94ff6cac5408347@epcas1p2.samsung.com>
2021-01-26  1:32 ` Changheun Lee [this message]
     [not found]   ` <CGME20210126014807epcas1p1a7274e9ba472286df03aac8e627b4633@epcas1p1.samsung.com>
2021-01-26  1:32     ` [PATCH v3 2/2] bio: add limit_bio_size sysfs Changheun Lee
2021-01-26  3:57   ` [PATCH v3 1/2] bio: limit bio max size Ming Lei
2021-01-26  4:06     ` Damien Le Moal
2021-01-26  6:07       ` Ming Lei
2021-01-26  6:26         ` Damien Le Moal
2021-01-26 11:54           ` Ming Lei
     [not found]             ` <CGME20210127005900epcas1p2456b0f3321b404995445b8654468c30e@epcas1p2.samsung.com>
2021-01-27  0:43               ` Changheun Lee
2021-01-26 15:05     ` Christoph Hellwig
     [not found] <CGME20210126093706epcas1p150e9b57a678f8724fa8ab9eddcec8a42@epcas1p1.samsung.com>
2021-01-26  9:21 ` Changheun Lee
2021-01-26 10:28   ` Damien Le Moal
     [not found]     ` <CGME20210127003642epcas1p4f167d553fc79ef5029a928550adbebea@epcas1p4.samsung.com>
2021-01-27  0:21       ` Changheun Lee
2021-01-27  1:03         ` Damien Le Moal
     [not found]           ` <CGME20210127053827epcas1p1e0cda00cdbfdacd5a3ede69c788d6710@epcas1p1.samsung.com>
2021-01-27  5:22             ` Changheun Lee

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210126013235.28711-1-nanich.lee@samsung.com \
    --to=nanich.lee@samsung.com \
    --cc=Johannes.Thumshirn@wdc.com \
    --cc=asml.silence@gmail.com \
    --cc=axboe@kernel.dk \
    --cc=damien.lemoal@wdc.com \
    --cc=jisoo2146.oh@samsung.com \
    --cc=junho89.kim@samsung.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=ming.lei@redhat.com \
    --cc=mj0123.lee@samsung.com \
    --cc=osandov@fb.com \
    --cc=patchwork-bot@kernel.org \
    --cc=seunghwan.hyun@samsung.com \
    --cc=sookwan7.kim@samsung.com \
    --cc=tj@kernel.org \
    --cc=tom.leiming@gmail.com \
    --cc=woosung2.lee@samsung.com \
    --cc=yt0928.kim@samsung.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.