public inbox for linux-block@vger.kernel.org
 help / color / mirror / Atom feed
From: Ming Lei <ming.lei@redhat.com>
To: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, Christoph Hellwig <hch@lst.de>,
	Ed Tsai <ed.tsai@mediatek.com>, Ming Lei <ming.lei@redhat.com>
Subject: [PATCH V2 0/2] block: try to make aligned bio in case of big chunk IO
Date: Thu,  9 Nov 2023 16:28:19 +0800	[thread overview]
Message-ID: <20231109082827.2276696-1-ming.lei@redhat.com> (raw)

Hello,

The 1st adds check to avoid to call into iov_iter_revert() with zero
'unroll'.

The 2nd patch improves big chunk sequential IO performance by aligning
bio with max io size.

V2:
	- add patch 1/2
	- add 'max_size' hint to iov_iter_extract_pages() so that bio/iov
	  iter revert can be minimized, as suggested by Christoph

BTW, the check on 'bio->bi_bdev' isn't removed because there are more
such patterns(P2PDMA, block size check) in __bio_iov_iter_get_pages(),
and we need to audit that bio->bi_bdev is really non-NULL first, so it
shouldn't be part of this patchset

Ming Lei (2):
  block: don't call into iov_iter_revert if nothing is left
  block: try to make aligned bio in case of big chunk IO

 block/bio.c            | 126 +++++++++++++++++++++++++++++++++++++++--
 include/linux/blkdev.h |   5 ++
 2 files changed, 125 insertions(+), 6 deletions(-)

-- 
2.41.0


             reply	other threads:[~2023-11-09  8:28 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-11-09  8:28 Ming Lei [this message]
2023-11-09  8:28 ` [PATCH V2 1/2] block: don't call into iov_iter_revert if nothing is left Ming Lei
2023-11-09 14:35   ` Christoph Hellwig
2023-11-09  8:28 ` [PATCH V2 2/2] block: try to make aligned bio in case of big chunk IO Ming Lei
2023-11-09 14:39   ` Christoph Hellwig
2023-11-09 19:30   ` kernel test robot

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=20231109082827.2276696-1-ming.lei@redhat.com \
    --to=ming.lei@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=ed.tsai@mediatek.com \
    --cc=hch@lst.de \
    --cc=linux-block@vger.kernel.org \
    /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