Linux Device Mapper development
 help / color / mirror / Atom feed
From: Mike Snitzer <snitzer@redhat.com>
To: dm-devel@redhat.com
Subject: [PATCH v2 0/9] dm: changes staged in linux-next for 5.1 so far
Date: Wed, 20 Feb 2019 16:44:27 -0500	[thread overview]
Message-ID: <20190220214436.38476-1-snitzer@redhat.com> (raw)

This v2 eliminates the dm-mpath local cache for per-bio-data and
switches to allocating the target required per-bio-data as part of the
'struct dm_noclone' allocation -- special thanks to Mikulas for his
ideas and patch (#6) that went into this v2.

Test results show a slight improvement for bio-based dm-multipath (but
not the kind of win dm-linear gets from switching to noclone):

   linear: raw=6087MB/s clone=4241MB/s noclone=5148MB/s
   mpath:  raw=6087MB/s clone=3331MB/s noclone=3420MB/s

More work is needed to improve DM multipath performance (story of my
life)... but at least this shifts the focus away from DM core and back
to the dm-multipath target code.

Mike Snitzer (6):
  dm: update dm_process_bio() to split bio if in ->make_request_fn()
  dm: eliminate 'split_discard_bios' flag from DM target interface
  dm: improve noclone bio support
  dm: improve noclone_endio() to support multipath target
  dm mpath: enable noclone support for bio-based
  dm: remove unused _rq_tio_cache and _rq_cache

Mikulas Patocka (3):
  dm: refactor start_io_acct and end_io_acct
  dm: implement noclone optimization for bio-based
  dm: add per-bio-data support to noclone bio

 drivers/md/dm-cache-target.c  |   1 -
 drivers/md/dm-linear.c        |   3 +-
 drivers/md/dm-mpath.c         |  13 +-
 drivers/md/dm-raid.c          |  14 +-
 drivers/md/dm-rq.c            |  16 ++
 drivers/md/dm-rq.h            |  16 --
 drivers/md/dm-stripe.c        |   3 +-
 drivers/md/dm-table.c         |  11 ++
 drivers/md/dm-thin.c          |   1 -
 drivers/md/dm-zero.c          |   1 +
 drivers/md/dm-zoned-target.c  |   1 -
 drivers/md/dm.c               | 406 ++++++++++++++++++++++++++++--------------
 drivers/md/dm.h               |   1 +
 include/linux/device-mapper.h |   9 +-
 include/uapi/linux/dm-ioctl.h |   4 +-
 15 files changed, 330 insertions(+), 170 deletions(-)

-- 
2.15.0

             reply	other threads:[~2019-02-20 21:44 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-02-20 21:44 Mike Snitzer [this message]
2019-02-20 21:44 ` [PATCH v2 1/9] dm: update dm_process_bio() to split bio if in ->make_request_fn() Mike Snitzer
2019-02-20 21:44 ` [PATCH v2 2/9] dm: eliminate 'split_discard_bios' flag from DM target interface Mike Snitzer
2019-02-21  4:36   ` Mike Snitzer
2019-02-20 21:44 ` [PATCH v2 3/9] dm: refactor start_io_acct and end_io_acct Mike Snitzer
2019-02-20 21:44 ` [PATCH v2 4/9] dm: implement noclone optimization for bio-based Mike Snitzer
2019-02-20 21:44 ` [PATCH v2 5/9] dm: improve noclone bio support Mike Snitzer
2019-02-22 10:59   ` Mikulas Patocka
2019-02-22 15:22     ` Mike Snitzer
2019-02-22 16:56       ` Mike Snitzer
2019-02-20 21:44 ` [PATCH v2 6/9] dm: add per-bio-data support to noclone bio Mike Snitzer
2019-02-20 21:44 ` [PATCH v2 7/9] dm: improve noclone_endio() to support multipath target Mike Snitzer
2019-02-20 21:44 ` [PATCH v2 8/9] dm mpath: enable noclone support for bio-based Mike Snitzer
2019-02-20 21:44 ` [PATCH v2 9/9] dm: remove unused _rq_tio_cache and _rq_cache 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=20190220214436.38476-1-snitzer@redhat.com \
    --to=snitzer@redhat.com \
    --cc=dm-devel@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