Linux Device Mapper development
 help / color / mirror / Atom feed
From: Mike Snitzer <snitzer@redhat.com>
To: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, dm-devel@redhat.com,
	Mikulas Patocka <mpatocka@redhat.com>
Subject: [PATCH v2 0/6] per-cpu in_flight counters for bio-based drivers
Date: Fri, 30 Nov 2018 17:22:20 -0500	[thread overview]
Message-ID: <20181130222226.77216-1-snitzer@redhat.com> (raw)
In-Reply-To: <20181128004211.368810060@debian.vm>

Hi,

This v2 the product of more thorough review and testing (on my part)
of Mikulas' original patchset.

Not seeing a major performance win in general but no loss either.  DM
devices do see a huge boost in IOPS thanks to being able to eliminate
the inefficient md->pending IO accounting that it was doing, see:
https://www.redhat.com/archives/dm-devel/2018-November/msg00415.html

Happy to iterate on this patchset further as needed, all
review/suggestions are very much appreciated.

Thanks,
Mike

Mike Snitzer (1):
  dm rq: leverage blk_mq_queue_busy() to check for outstanding IO

Mikulas Patocka (5):
  dm: dont rewrite dm_disk(md)->part0.in_flight
  block: delete part_round_stats and switch to less precise counting
  block: switch to per-cpu in-flight counters
  block: return just one value from part_in_flight
  dm: remove the pending IO accounting

 block/bio.c               | 28 ++++++++++++++++----
 block/blk-core.c          | 67 +++++------------------------------------------
 block/blk-merge.c         |  3 +--
 block/blk-mq.c            | 12 ++++-----
 block/blk-mq.h            |  3 +--
 block/genhd.c             | 59 +++++++++++++++++++++++------------------
 block/partition-generic.c | 10 +++----
 drivers/md/dm-core.h      |  2 --
 drivers/md/dm-rq.c        |  9 +++----
 drivers/md/dm.c           | 36 +++++++++++--------------
 include/linux/genhd.h     | 13 +++++----
 11 files changed, 98 insertions(+), 144 deletions(-)

-- 
2.15.0

  parent reply	other threads:[~2018-11-30 22:22 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-11-28  0:42 [PATCH 0/3] per-cpu in_flight counters for bio-based drivers Mikulas Patocka
2018-11-30 14:43 ` Mike Snitzer
2018-11-30 15:50   ` Mike Snitzer
2018-11-30 19:57     ` Mike Snitzer
2018-11-30 22:22 ` Mike Snitzer [this message]
2018-11-30 22:22   ` [PATCH v2 1/6] dm: dont rewrite dm_disk(md)->part0.in_flight Mike Snitzer
2018-11-30 22:22   ` [PATCH v2 2/6] dm rq: leverage blk_mq_queue_busy() to check for outstanding IO Mike Snitzer
2018-11-30 22:22   ` [PATCH v2 3/6] block: delete part_round_stats and switch to less precise counting Mike Snitzer
2018-11-30 22:22   ` [PATCH v2 4/6] block: switch to per-cpu in-flight counters Mike Snitzer
2018-12-05 17:30     ` Jens Axboe
2018-12-05 17:49       ` Mike Snitzer
2018-12-05 17:54         ` Jens Axboe
2018-12-05 18:03           ` Mike Snitzer
2018-12-05 18:04             ` Jens Axboe
2018-12-05 18:18               ` Mike Snitzer
2018-12-05 18:35                 ` Jens Axboe
2018-11-30 22:22   ` [PATCH v2 5/6] block: return just one value from part_in_flight Mike Snitzer
2018-11-30 22:22   ` [PATCH v2 6/6] dm: remove the pending IO accounting Mike Snitzer

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=20181130222226.77216-1-snitzer@redhat.com \
    --to=snitzer@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=dm-devel@redhat.com \
    --cc=linux-block@vger.kernel.org \
    --cc=mpatocka@redhat.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox