From: Liu Bo <bo.li.liu@oracle.com>
To: linux-btrfs@vger.kernel.org
Subject: [RFC PATCH v5 0/5] Online data deduplication
Date: Wed, 31 Jul 2013 23:37:40 +0800 [thread overview]
Message-ID: <1375285066-14173-1-git-send-email-bo.li.liu@oracle.com> (raw)
Data deduplication is a specialized data compression technique for eliminating
duplicate copies of repeating data.[1]
This patch set is also related to "Content based storage" in project ideas[2].
PATCH 1 is a hang fix with deduplication on, but it's also useful without
dedup in practice use.
PATCH 2 and 3 are targetting delayed refs' scalability problems, which are
uncovered by the dedup feature.
PATCH 4 is a speed-up improvement, which is about dedup and quota.
PATCH 5 is full of real things, all details about implementation of dedup.
Plus, there is also a btrfs-progs patch which helps to enable/disable dedup
feature.
TODO:
* a bit-to-bit comparison callback.
All comments are welcome!
[1]: http://en.wikipedia.org/wiki/Data_deduplication
[2]: https://btrfs.wiki.kernel.org/index.php/Project_ideas#Content_based_storage
v4->v5:
- go back to one dedup key with a special backref for dedup tree because
the disk format understands backref well.
- fix a fsync hang with dedup enabled.
- rebase onto the latest btrfs.
Liu Bo (5):
Btrfs: skip merge part for delayed data refs
Btrfs: improve the delayed refs process in rm case
Btrfs: introduce a head ref rbtree
Btrfs: disable qgroups accounting when quata_enable is 0
Btrfs: online data deduplication
fs/btrfs/backref.c | 9 +
fs/btrfs/ctree.h | 59 ++++
fs/btrfs/delayed-ref.c | 141 +++++++----
fs/btrfs/delayed-ref.h | 8 +
fs/btrfs/disk-io.c | 30 ++
fs/btrfs/extent-tree.c | 196 ++++++++++++--
fs/btrfs/extent_io.c | 29 ++-
fs/btrfs/extent_io.h | 16 ++
fs/btrfs/file-item.c | 217 +++++++++++++++
fs/btrfs/inode.c | 637 ++++++++++++++++++++++++++++++++++++++------
fs/btrfs/ioctl.c | 93 +++++++
fs/btrfs/ordered-data.c | 36 ++-
fs/btrfs/ordered-data.h | 11 +-
fs/btrfs/qgroup.c | 6 +
fs/btrfs/relocation.c | 3 +
fs/btrfs/super.c | 27 ++-
fs/btrfs/transaction.c | 4 +-
include/uapi/linux/btrfs.h | 5 +
18 files changed, 1356 insertions(+), 171 deletions(-)
--
1.7.7
next reply other threads:[~2013-07-31 15:38 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-07-31 15:37 Liu Bo [this message]
2013-07-31 15:37 ` [RFC PATCH v5 1/5] Btrfs: skip merge part for delayed data refs Liu Bo
2013-07-31 15:37 ` [RFC PATCH v5 2/5] Btrfs: improve the delayed refs process in rm case Liu Bo
2013-07-31 16:45 ` Stefan Behrens
2013-07-31 15:37 ` [RFC PATCH v5 3/5] Btrfs: introduce a head ref rbtree Liu Bo
2013-07-31 21:19 ` Zach Brown
2013-07-31 15:37 ` [RFC PATCH v5 4/5] Btrfs: disable qgroups accounting when quota is off Liu Bo
2013-08-05 12:34 ` Jan Schmidt
2013-08-05 14:18 ` Liu Bo
2013-08-05 15:10 ` Jan Schmidt
2013-08-06 2:25 ` Liu Bo
2013-07-31 15:37 ` [RFC PATCH v5 5/5] Btrfs: online data deduplication Liu Bo
2013-07-31 22:50 ` Zach Brown
2013-08-01 10:14 ` Liu Bo
2013-08-01 18:35 ` Zach Brown
2013-07-31 15:37 ` [PATCH] Btrfs-progs: add dedup subcommand Liu Bo
2013-07-31 16:30 ` Stefan Behrens
2013-08-01 10:17 ` Liu Bo
2013-08-01 22:01 ` Mark Fasheh
2013-08-02 2:29 ` Liu Bo
2013-07-31 21:20 ` [RFC PATCH v5 0/5] Online data deduplication Josef Bacik
2013-08-01 10:16 ` Liu Bo
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=1375285066-14173-1-git-send-email-bo.li.liu@oracle.com \
--to=bo.li.liu@oracle.com \
--cc=linux-btrfs@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;
as well as URLs for NNTP newsgroup(s).