public inbox for [email protected]
 help / color / mirror / Atom feed
From: Pavel Begunkov <[email protected]>
To: Jens Axboe <[email protected]>
Cc: Alexander Viro <[email protected]>,
	[email protected], [email protected],
	[email protected], [email protected],
	Matthew Wilcox <[email protected]>
Subject: [PATCH 2/2] block: no-copy bvec for direct IO
Date: Wed,  9 Dec 2020 02:19:52 +0000	[thread overview]
Message-ID: <51905c4fcb222e14a1d5cb676364c1b4f177f582.1607477897.git.asml.silence@gmail.com> (raw)
In-Reply-To: <[email protected]>

The block layer spends quite a while in blkdev_direct_IO() to copy and
initialise bio's bvec. However, if we've already got a bvec in the input
iterator it might be reused in some cases, i.e. when new
ITER_BVEC_FLAG_FIXED flag is set. Simple tests show considerable
performance boost, and it also reduces memory footprint.

Suggested-by: Matthew Wilcox <[email protected]>
[BIO_WORKINGSET] Suggested-by: Johannes Weiner <[email protected]>
Signed-off-by: Pavel Begunkov <[email protected]>
---
 fs/block_dev.c | 30 +++++++++++++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index d699f3af1a09..aee5d2e4f324 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -349,6 +349,28 @@ static void blkdev_bio_end_io(struct bio *bio)
 	}
 }
 
+static int bio_iov_fixed_bvec_get_pages(struct bio *bio, struct iov_iter *iter)
+{
+	bio->bi_vcnt = iter->nr_segs;
+	bio->bi_max_vecs = iter->nr_segs;
+	bio->bi_io_vec = (struct bio_vec *)iter->bvec;
+	bio->bi_iter.bi_bvec_done = iter->iov_offset;
+	bio->bi_iter.bi_size = iter->count;
+
+	/*
+	 * In practice groups of pages tend to be accessed/reclaimed/refaulted
+	 * together. To not go over bvec for those who didn't set BIO_WORKINGSET
+	 * approximate it by looking at the first page and inducing it to the
+	 * whole bio
+	 */
+	if (unlikely(PageWorkingset(iter->bvec->bv_page)))
+		bio_set_flag(bio, BIO_WORKINGSET);
+	bio_set_flag(bio, BIO_NO_PAGE_REF);
+
+	iter->count = 0;
+	return 0;
+}
+
 static ssize_t
 __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_vecs)
 {
@@ -368,6 +390,8 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_vecs)
 	    (bdev_logical_block_size(bdev) - 1))
 		return -EINVAL;
 
+	if (iov_iter_bvec_fixed(iter))
+		nr_vecs = 0;
 	bio = bio_alloc_bioset(GFP_KERNEL, nr_vecs, &blkdev_dio_pool);
 
 	dio = container_of(bio, struct blkdev_dio, bio);
@@ -398,7 +422,11 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_vecs)
 		bio->bi_end_io = blkdev_bio_end_io;
 		bio->bi_ioprio = iocb->ki_ioprio;
 
-		ret = bio_iov_iter_get_pages(bio, iter);
+		if (iov_iter_is_bvec(iter) && iov_iter_bvec_fixed(iter))
+			ret = bio_iov_fixed_bvec_get_pages(bio, iter);
+		else
+			ret = bio_iov_iter_get_pages(bio, iter);
+
 		if (unlikely(ret)) {
 			bio->bi_status = BLK_STS_IOERR;
 			bio_endio(bio);
-- 
2.24.0


  parent reply	other threads:[~2020-12-09  2:24 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-12-09  2:19 [RFC 0/2] nocopy bvec for direct IO Pavel Begunkov
2020-12-09  2:19 ` [PATCH 1/2] iov: introduce ITER_BVEC_FLAG_FIXED Pavel Begunkov
2020-12-09  8:36   ` Christoph Hellwig
2020-12-09  9:06     ` Christoph Hellwig
2020-12-09 11:54       ` Pavel Begunkov
2020-12-09 13:07     ` Al Viro
2020-12-09 13:37       ` Pavel Begunkov
2020-12-09 17:55         ` Christoph Hellwig
2020-12-09 18:24           ` Matthew Wilcox
2020-12-13 22:09             ` Pavel Begunkov
2020-12-09  2:19 ` Pavel Begunkov [this message]
2020-12-09  8:40   ` [PATCH 2/2] block: no-copy bvec for direct IO Christoph Hellwig
2020-12-09 12:01     ` Pavel Begunkov
2020-12-09 12:05       ` Christoph Hellwig
2020-12-09 12:03         ` Pavel Begunkov
2020-12-11 14:06     ` Johannes Weiner
2020-12-11 14:20       ` Pavel Begunkov
2020-12-11 15:38         ` Johannes Weiner
2020-12-11 15:47           ` Pavel Begunkov
2020-12-11 16:13             ` Johannes Weiner
2020-12-09 21:13   ` David Laight
2020-12-09  6:50 ` [RFC 0/2] nocopy " Christoph Hellwig
2020-12-09 11:54   ` Pavel Begunkov
2020-12-09 16:53 ` Jens Axboe
2020-12-13 22:03   ` Pavel Begunkov
2020-12-09 17:06 ` Al Viro

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=51905c4fcb222e14a1d5cb676364c1b4f177f582.1607477897.git.asml.silence@gmail.com \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox